{"meta":{"query_hash":"f27e7d734805","filters":{"topic":"Evaluation and Performance Assessment"},"cohort_total":2407,"direct_labels_cover":84,"predictions_cover":2407,"exported":2407,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/f27e7d734805","api":"https://metacan.xera.ac/api/v1/cohort?topic=Evaluation+and+Performance+Assessment"},"results":[{"id":"W101835194","doi":"","title":"REALITIES AND CHALLENGES OF EDUCATIONAL REFORM IN THE PROVINCE OF QUÉBEC: EXPLORATORY RESEARCH ON TEACHING SCIENCE AND TECHNOLOGY / RÉALITÉS ET DÉFIS DE LA RÉFORME SCOLAIRE QUÉBÉCOISE : UNE ÉTUDE EXPLORATOIRE DE L’ENSEIGNEMENT DE LA SCIENCE ...","year":2007,"lang":"fr","type":"article","venue":"McGill Journal of Education / Revue des sciences de l'éducation de McGill","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Montréal; Université du Québec à Trois-Rivières; Université du Québec à Montréal","funders":"","keywords":"Humanities; Political science; Sociology; Exploratory research; Library science; Pedagogy; Art; Social science; Computer science","score_opus":0.3200341529283524,"score_gpt":0.5210237462951633,"score_spread":0.20098959336681094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W101835194","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8949975,0.004396087,0.00011576079,0.078369655,0.0003732127,0.00035054423,0.000014112001,0.000006668694,0.021376474],"genre_scores_gemma":[0.9825728,0.005386768,0.010926213,0.00078927196,0.00009230742,0.00005473205,5.967919e-7,0.000013071408,0.0001642594],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9922213,0.002441016,0.0013582138,0.00058640435,0.0025450736,0.0008480168],"domain_scores_gemma":[0.9902961,0.0047729495,0.0011963998,0.000495628,0.0028821935,0.00035668924],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch","sts"],"category_scores_codex":[0.1318926,0.00023665468,0.00035967378,0.0032776946,0.0025463165,0.0002997273,0.001750735,0.00018629798,0.000027971579],"category_scores_gemma":[0.013603298,0.00018930904,0.000060901384,0.0044431803,0.012146963,0.0024379739,0.00019765468,0.00087503606,0.0000021631179],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00007867512,0.0013828673,0.01527582,0.00033688228,0.000012293228,0.0000056928484,0.10536471,0.00071473274,0.0045680613,0.7637187,0.00027301066,0.10826852],"study_design_scores_gemma":[0.000514999,0.001501199,0.20878722,0.0024775073,0.000041723986,0.0015125792,0.5695494,0.0014436584,0.009399888,0.19006355,0.014356681,0.00035164197],"about_ca_topic_score_codex":0.005753096,"about_ca_topic_score_gemma":0.016256724,"teacher_disagreement_score":0.5736552,"about_ca_system_score_codex":0.008774281,"about_ca_system_score_gemma":0.041171834,"threshold_uncertainty_score":0.99875224},"labels":[],"label_agreement":null},{"id":"W1051780262","doi":"10.46743/2160-3715/2015.2237","title":"Assessing the FACTS: A Mnemonic for Teaching and Learning the Rapid Assessment of Rigor in Qualitative Research Studies","year":2015,"lang":"en","type":"article","venue":"The Qualitative Report","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Royal University","funders":"University of Calgary","keywords":"Mnemonic; Qualitative research; Critical appraisal; Rigour; Psychology; Pedagogy; Educational research; Reading (process); Mathematics education; Engineering ethics; Sociology; Epistemology; Medicine; Social science","score_opus":0.8660095880391695,"score_gpt":0.7902869173486363,"score_spread":0.07572267069053318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1051780262","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9535309,0.0011171977,0.008134435,0.024443554,0.00020172818,0.0012268065,0.000004505028,0.000014298347,0.011326559],"genre_scores_gemma":[0.99355274,0.000051983472,0.0038782407,0.00015654793,0.00005077278,0.00027574913,0.00000377277,0.000012007053,0.0020181965],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9441521,0.048564095,0.0019445774,0.00059004093,0.004265557,0.00048358543],"domain_scores_gemma":[0.894265,0.10109623,0.0012182276,0.00070785946,0.0026439466,0.00006872564],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.40499797,0.00016805643,0.00046242942,0.00023322117,0.0014137267,0.00033891416,0.00060461205,0.000045854038,0.000023799972],"category_scores_gemma":[0.08294493,0.000066706125,0.000101290774,0.000795332,0.0013635742,0.0006410058,0.00030224433,0.0011497346,0.0000057484053],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041750965,0.000054918448,0.0015602559,0.000020086003,0.00010776875,0.0000033667495,0.96352154,0.00055967836,0.00010968913,0.016489316,0.0014609431,0.016070673],"study_design_scores_gemma":[0.00041819873,0.0003373961,0.008863425,0.00007116504,0.00001721113,0.0000132486075,0.8958447,0.005924584,0.000045314217,0.08252316,0.0058503705,0.00009124058],"about_ca_topic_score_codex":0.00030285734,"about_ca_topic_score_gemma":0.00014146816,"teacher_disagreement_score":0.32205305,"about_ca_system_score_codex":0.00022521257,"about_ca_system_score_gemma":0.0009457633,"threshold_uncertainty_score":0.9998863},"labels":[],"label_agreement":null},{"id":"W107040214","doi":"","title":"International Perspectives in Participatory Research and Evaluation","year":2005,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Participatory action research; General partnership; Citizen journalism; Context (archaeology); Sociology; Certificate; Political science; Public relations; Pedagogy; Geography","score_opus":0.8462773535762547,"score_gpt":0.7068909936246691,"score_spread":0.13938635995158555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W107040214","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8065683,0.000099711884,0.00008374617,0.012698669,0.000070926224,0.00012791212,4.2889198e-7,0.0000061854244,0.18034407],"genre_scores_gemma":[0.99601936,0.000048825324,0.0006787866,0.0001088513,0.000096554184,0.00003814109,8.415408e-7,0.000001809518,0.0030068276],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9965898,0.00034006836,0.0002633973,0.0002380214,0.0024425848,0.00012613808],"domain_scores_gemma":[0.9983837,0.0004869236,0.000032442193,0.00015871637,0.0008951343,0.000043099015],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.019506834,0.00003637454,0.00005835662,0.00040701596,0.000066703724,0.00014837933,0.00018585565,0.000023759527,0.012723641],"category_scores_gemma":[0.0012768526,0.000026146667,0.000010864421,0.0003718995,0.00008362855,0.0005234271,0.0000674854,0.00010087735,0.00045190935],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044506993,0.0002773961,0.3290477,7.241911e-7,0.000007935089,5.775815e-7,0.017137583,0.0016336454,0.00039546588,0.060990185,0.009813723,0.58065057],"study_design_scores_gemma":[0.00060007017,0.000050670074,0.55639946,0.0000043422656,0.0000011153078,0.0000011074004,0.021784358,0.3491077,0.00023769034,0.018938292,0.05281621,0.000058966878],"about_ca_topic_score_codex":0.000020956715,"about_ca_topic_score_gemma":0.000568676,"teacher_disagreement_score":0.5805916,"about_ca_system_score_codex":0.00014910987,"about_ca_system_score_gemma":0.00012682752,"threshold_uncertainty_score":0.98817885},"labels":[],"label_agreement":null},{"id":"W110059870","doi":"","title":"The use and misuse of members' statements","year":2009,"lang":"en","type":"article","venue":"Canadian parliamentary review","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Business; Accounting","score_opus":0.30988822255951576,"score_gpt":0.5050923129635176,"score_spread":0.19520409040400188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W110059870","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4896088,0.32843864,0.0000808944,0.1601089,0.0011550637,0.003947568,0.0003107018,0.00003191301,0.016317533],"genre_scores_gemma":[0.5693794,0.3440157,0.00084741425,0.08155332,0.0000532851,0.000034318236,0.000041985517,0.000011951282,0.004062674],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982797,0.00017815336,0.0005675074,0.00017537734,0.00060048583,0.00019878095],"domain_scores_gemma":[0.9986767,0.00026752122,0.00018024181,0.0004361689,0.00016172617,0.0002776379],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0021882192,0.00008675407,0.00020171508,0.000072330324,0.00017372082,0.00013161305,0.00030581924,0.000015767837,0.0015576804],"category_scores_gemma":[0.00032201465,0.00005092192,0.00004923555,0.00029574294,0.00006109698,0.00048575146,0.000015176382,0.000057486104,0.00007744236],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004901786,0.000012331544,0.015765661,0.00005042071,0.000020849491,0.0000039763013,0.00013318605,0.000008359478,0.000008780974,0.00060426997,0.4017399,0.5816474],"study_design_scores_gemma":[0.00013444466,0.00005298622,0.01928988,0.00028137743,0.000021501366,0.0000027917288,0.00016028658,0.000159386,0.000011533329,0.0005691781,0.979249,0.000067618974],"about_ca_topic_score_codex":0.010791208,"about_ca_topic_score_gemma":0.1061967,"teacher_disagreement_score":0.58157974,"about_ca_system_score_codex":0.00007875671,"about_ca_system_score_gemma":0.00031815452,"threshold_uncertainty_score":0.999355},"labels":[],"label_agreement":null},{"id":"W11542012","doi":"10.1139/e85-209","title":"Disaster Resistant Communities Initiative: Assessment Of The Pilot Phase - Year 3","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Earth Sciences","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"Federal Emergency Management Agency","keywords":"General partnership; Program evaluation; Impact assessment; Public relations; Political science; Environmental planning; Environmental resource management; Engineering; Geography; Public administration","score_opus":0.4214026578139658,"score_gpt":0.4794232770345788,"score_spread":0.05802061922061302,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W11542012","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9417146,0.00019001648,0.00012420594,0.0036853817,0.00066285237,0.0000872536,0.00003755504,0.0000013198774,0.053496804],"genre_scores_gemma":[0.9979767,0.000019411344,0.00071622804,0.000529826,0.00005121962,7.885349e-7,2.2911587e-7,0.0000025026504,0.0007030517],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9971052,0.00042809683,0.00066284847,0.0000880292,0.0014981941,0.0002176623],"domain_scores_gemma":[0.9978341,0.00048058853,0.0006118566,0.00028615497,0.00054700667,0.00024030288],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0049115825,0.000078682,0.00019407136,0.00038590745,0.00055963936,0.00029565903,0.0012084948,0.000019157049,0.00726345],"category_scores_gemma":[0.00043702833,0.000042391322,0.00009203504,0.00088408805,0.00095831254,0.0006351805,0.000033333057,0.00019000676,0.000024233685],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004042052,0.0003225907,0.9087098,0.00001487271,0.00006709902,0.000022830136,0.024143126,0.0031227246,0.0008735666,0.026119174,0.019380301,0.017183486],"study_design_scores_gemma":[0.0019306008,0.0032571785,0.81728023,0.00023610765,0.00003179115,0.0000473069,0.045976836,0.0129610235,0.00040271177,0.0059363027,0.11167917,0.00026073493],"about_ca_topic_score_codex":0.00055870775,"about_ca_topic_score_gemma":0.05220498,"teacher_disagreement_score":0.092298865,"about_ca_system_score_codex":0.000014068719,"about_ca_system_score_gemma":0.0016158826,"threshold_uncertainty_score":0.99364406},"labels":[],"label_agreement":null},{"id":"W119338607","doi":"10.18584/iipj.2013.4.2.1","title":"Evaluation of Aboriginal Programs: What Place is Given to Participation and Cultural Sensitivity?","year":2013,"lang":"en","type":"article","venue":"International Indigenous Policy Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université Laval","funders":"Social Sciences and Humanities Research Council of Canada; Aboriginal Affairs and Northern Development Canada; Indigenous and Northern Affairs Canada","keywords":"Technocracy; Cultural sensitivity; Citizen journalism; Autonomy; Participatory evaluation; Indigenous; Commission; Quality (philosophy); Sociology; Political science; Public administration; Psychology; Epistemology; Politics; Law","score_opus":0.19111011153958266,"score_gpt":0.5498375507491303,"score_spread":0.35872743920954764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W119338607","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9809114,0.00008000909,0.000539071,0.015665144,0.00046761538,0.00047827483,0.000009705394,0.000008933167,0.0018398928],"genre_scores_gemma":[0.9969276,0.00014924277,0.0007488346,0.0009292743,0.0006404821,0.000044837256,0.000007476682,0.00000722293,0.0005450334],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9942519,0.00047265398,0.0007049151,0.00022596493,0.0040872996,0.00025725501],"domain_scores_gemma":[0.99313295,0.0002681469,0.0004952119,0.00016778285,0.005714337,0.00022158721],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007127945,0.00012864111,0.00018206144,0.0005662136,0.00022511638,0.0014120849,0.00028800612,0.000056221,0.0013685894],"category_scores_gemma":[0.0011712228,0.000094686606,0.00007415829,0.00040803177,0.000066707886,0.0027207234,0.00004907046,0.00016187636,0.00032643706],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038001384,0.0001466517,0.03396719,0.0000026472214,0.000121956924,0.0000022278714,0.046382323,0.0028079147,0.0017737697,0.00072920806,0.0026353176,0.9113928],"study_design_scores_gemma":[0.0028807025,0.0010159855,0.72833204,0.00026976655,0.00016367562,0.00058901,0.02281118,0.12764035,0.005382829,0.04460425,0.06567902,0.0006311562],"about_ca_topic_score_codex":0.0006178942,"about_ca_topic_score_gemma":0.00023202613,"teacher_disagreement_score":0.91076165,"about_ca_system_score_codex":0.00039145388,"about_ca_system_score_gemma":0.0009822485,"threshold_uncertainty_score":0.99962455},"labels":[],"label_agreement":null},{"id":"W119659682","doi":"","title":"Place-Based Decision-Making: The Role of the Federal Government - Results from a Critical Conversation","year":2010,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Conversation; Corporate governance; Government (linguistics); Perspective (graphical); Political science; Public relations; Public administration; Sociology; Management; Computer science; Economics","score_opus":0.027618893438517787,"score_gpt":0.3821389632007782,"score_spread":0.3545200697622604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W119659682","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96668994,0.00019115656,0.009178165,0.020121763,0.0010720189,0.00018833586,0.000033487973,0.000008205265,0.0025169216],"genre_scores_gemma":[0.9987442,0.000027023932,0.0003813098,0.00040891083,0.0002669975,0.000004015763,0.0000010215052,0.0000069558746,0.00015954925],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99487066,0.0003394677,0.0007248336,0.00022812242,0.0031455436,0.00069139496],"domain_scores_gemma":[0.9939629,0.0046124067,0.00047082113,0.0005575043,0.00033908244,0.00005731499],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010825229,0.00011377082,0.00015105175,0.000041875766,0.0005101615,0.0002657368,0.0009775863,0.00007614506,0.0005551469],"category_scores_gemma":[0.006937217,0.000054099284,0.00016870523,0.00026871846,0.00015976626,0.00023999155,0.00007997456,0.0015319559,0.000054089593],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028102368,0.0003529624,0.06382817,0.0000016810384,0.00015602582,0.0000016924707,0.0035112326,0.004316276,0.007564803,0.25865832,0.0036502194,0.6551484],"study_design_scores_gemma":[0.0015881392,0.00020459353,0.034682747,0.00003414311,0.000031934844,0.000031906296,0.009936606,0.06324389,0.001576802,0.87264156,0.015891599,0.00013607417],"about_ca_topic_score_codex":0.000046535577,"about_ca_topic_score_gemma":0.0021100964,"teacher_disagreement_score":0.6550123,"about_ca_system_score_codex":0.00038351901,"about_ca_system_score_gemma":0.003140061,"threshold_uncertainty_score":0.8304998},"labels":[],"label_agreement":null},{"id":"W120546875","doi":"10.26522/brocked.v18i1.114","title":"Trends in Canadian faculties of education: An overview of graduate programs, curricular offerings, exit requirements, and modes of delivery.","year":2008,"lang":"en","type":"article","venue":"Brock Education Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Curriculum; Modalities; Medical education; Graduate students; Psychology; Graduate education; Sociology; Higher education; Pedagogy; Library science; Political science; Computer science; Medicine","score_opus":0.4649202859866278,"score_gpt":0.5111193604400197,"score_spread":0.046199074453391886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W120546875","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99597293,0.0023651246,0.000023698956,0.00042615287,0.0002508272,0.000110765504,0.0000061619658,0.0000022058437,0.00084213103],"genre_scores_gemma":[0.9951864,0.002298651,0.0017349176,0.00006570957,0.00006358043,0.000011525165,0.00001919741,0.0000052015753,0.0006148429],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9977056,0.00016494776,0.0009025625,0.000161682,0.00090452144,0.00016070543],"domain_scores_gemma":[0.9976233,0.000032407497,0.0006273926,0.00021597095,0.0012297629,0.00027115957],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00087882276,0.00010069888,0.00025208603,0.0013207907,0.00011570809,0.00004142539,0.00027242242,0.000039700142,0.0004235527],"category_scores_gemma":[0.00017066617,0.000081591155,0.00006311993,0.0010486773,0.00008282122,0.00069127395,0.000020941266,0.000101334466,0.000002104289],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015450636,0.00048883114,0.5421669,0.000039428196,0.000016721247,3.2378924e-7,0.0037367186,0.00023217437,0.00051827857,0.00071801513,0.005643546,0.44642362],"study_design_scores_gemma":[0.00033954452,0.00020638647,0.973914,0.0002495857,0.0000179147,0.00009133977,0.010508785,0.0007880194,0.00078549085,0.002016052,0.0109543055,0.00012855425],"about_ca_topic_score_codex":0.014463445,"about_ca_topic_score_gemma":0.012348749,"teacher_disagreement_score":0.44629505,"about_ca_system_score_codex":0.00008882912,"about_ca_system_score_gemma":0.0033791445,"threshold_uncertainty_score":0.99209934},"labels":[],"label_agreement":null},{"id":"W122890052","doi":"","title":"Participation and stewardship: Sustainability in two Canadian environmental programmes","year":2008,"lang":"en","type":"book-chapter","venue":"Research Repository (Kingston University London)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Stewardship (theology); Environmental stewardship; Sustainability; Environmental planning; Environmental resource management; Business; Environmental ethics; Political science; Geography; Environmental science; Ecology; Law","score_opus":0.11955065441899067,"score_gpt":0.42767999663875483,"score_spread":0.3081293422197642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W122890052","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5354576,0.00045027523,0.000011391953,0.00130139,0.00017803152,0.001481198,0.000032634292,0.000034915,0.46105254],"genre_scores_gemma":[0.7200436,0.000273772,0.000029342977,0.000019712232,0.000047780133,0.0000035333433,0.000019745557,0.000013301253,0.27954924],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99472076,0.0006299811,0.00046004582,0.000845755,0.002714859,0.00062857516],"domain_scores_gemma":[0.9974416,0.0006037712,0.00020665655,0.0006681213,0.0005377675,0.00054209743],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038862857,0.00023522625,0.0003602569,0.0016375147,0.0009050112,0.0002208387,0.0005898341,0.00022453655,0.00031650497],"category_scores_gemma":[0.00032102686,0.00023934165,0.00010989041,0.0002637029,0.0008509104,0.0005599318,0.0003026927,0.0008923047,0.00009751514],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011288638,0.00048684643,0.6037681,0.00018774603,0.0001853207,0.0054439264,0.012890871,0.0005709147,0.00013566727,0.07377957,0.013043318,0.28837883],"study_design_scores_gemma":[0.00094521546,0.00025687454,0.12317803,0.000072959025,0.000018871131,0.00002706055,0.0021058447,0.0010688892,0.00008196682,0.0028808117,0.86896944,0.00039401458],"about_ca_topic_score_codex":0.030952502,"about_ca_topic_score_gemma":0.1198961,"teacher_disagreement_score":0.85592616,"about_ca_system_score_codex":0.0040038484,"about_ca_system_score_gemma":0.002494153,"threshold_uncertainty_score":0.9998196},"labels":[],"label_agreement":null},{"id":"W129581792","doi":"10.7202/1086394ar","title":"Vers une réconciliation des théories et de la pratique de l’évaluation, perspectives d’avenir","year":2006,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Canadian Institutes of Health Research; U.S. Public Health Service","keywords":"Humanities; Political science; Philosophy","score_opus":0.0812542158922439,"score_gpt":0.4763211380666037,"score_spread":0.3950669221743598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W129581792","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6958203,0.0015963382,0.15829647,0.076841846,0.0015801518,0.0010261678,0.000043191973,0.00013770755,0.064657845],"genre_scores_gemma":[0.95196927,0.0012155415,0.021386573,0.00092899136,0.00061174226,0.0002479304,0.00033986894,0.0000479883,0.0232521],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.96987164,0.024665235,0.001330122,0.0008423632,0.0027053587,0.0005852577],"domain_scores_gemma":[0.98985964,0.005788033,0.0008763726,0.00061709946,0.0027132984,0.00014555696],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09524943,0.00042447113,0.00039080303,0.0005353403,0.0006452515,0.0009888142,0.00042104736,0.00049704354,0.0025257803],"category_scores_gemma":[0.011315543,0.00043225478,0.00017775818,0.0017277926,0.00046963693,0.0027589905,0.000054226075,0.000557254,0.00040600487],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00007439514,0.000732334,0.06898948,0.00007482279,0.00007900545,0.0000018455102,0.50482106,0.09441226,0.0039629326,0.2655244,0.019012103,0.042315356],"study_design_scores_gemma":[0.0009899123,0.00016730603,0.71104586,0.00012681444,0.00015936873,0.000026286447,0.029781213,0.045642354,0.0012081253,0.17106816,0.03939057,0.00039401656],"about_ca_topic_score_codex":0.004449431,"about_ca_topic_score_gemma":0.0067832903,"teacher_disagreement_score":0.6420564,"about_ca_system_score_codex":0.005413699,"about_ca_system_score_gemma":0.023974635,"threshold_uncertainty_score":0.9998129},"labels":[],"label_agreement":null},{"id":"W131813906","doi":"10.2139/ssrn.2260028","title":"The 'Lumpiness' Thesis Revisited: The Venues of Policy Work and the Distribution of Analytical Techniques in Canada","year":2013,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Toronto Metropolitan University; Simon Fraser University","funders":"","keywords":"Work (physics); Distribution (mathematics); Econometrics; Economics; Computer science; Data science; Engineering; Mathematics; Mechanical engineering","score_opus":0.028739056950519894,"score_gpt":0.37653548523272573,"score_spread":0.34779642828220586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W131813906","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95178753,0.0019088555,0.00035475063,0.045302533,0.00003473221,0.0002205804,0.000003906157,0.0000016389006,0.0003854654],"genre_scores_gemma":[0.9963444,0.0033350554,0.0000042559377,0.00009746807,0.00007293908,0.000009705435,7.2168194e-7,0.0000024666124,0.00013301967],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9977466,0.000444814,0.0005089977,0.00008051841,0.0007726619,0.00044644502],"domain_scores_gemma":[0.9977251,0.0013865342,0.000344166,0.00024949317,0.00027068003,0.000024022345],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009537177,0.00006320091,0.00016476776,0.000051782223,0.00019474293,0.00008153316,0.0005054472,0.000021448575,0.000024792584],"category_scores_gemma":[0.0015939442,0.000023440503,0.000052851243,0.0006803891,0.00020660771,0.00011309458,0.00004780483,0.00048296142,0.0000014967793],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012273468,0.000016393244,0.13983579,0.0000032782646,0.00006565084,2.0811655e-7,0.00040647207,0.000056603294,0.000015067437,0.26962528,0.0019246979,0.5879278],"study_design_scores_gemma":[0.0005686791,0.00009607275,0.5353945,0.000058847032,0.00003370533,0.000031425392,0.008990825,0.0031546059,0.00015102708,0.43931514,0.012107648,0.00009757191],"about_ca_topic_score_codex":0.090313114,"about_ca_topic_score_gemma":0.21798876,"teacher_disagreement_score":0.58783025,"about_ca_system_score_codex":0.00044550502,"about_ca_system_score_gemma":0.004118333,"threshold_uncertainty_score":0.91574454},"labels":[],"label_agreement":null},{"id":"W13854993","doi":"","title":"Reforming Ontario Teachers (1990-2010): The Role of the College of Teachers","year":2014,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Pedagogy; Mathematics education; Public relations; Political science; Medical education; Psychology; Medicine","score_opus":0.08532558238122047,"score_gpt":0.3839283513867004,"score_spread":0.29860276900547994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W13854993","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8304994,0.000017892558,0.00013367349,0.0019334316,0.00025757236,0.00018871954,0.000003873015,0.0000075920093,0.16695784],"genre_scores_gemma":[0.9575729,0.0000016139446,0.00037191325,0.00029700337,0.00002432657,0.0000066033044,4.133412e-7,0.000004224131,0.04172102],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973924,0.00027859694,0.0005723988,0.00017019625,0.0014403573,0.00014600666],"domain_scores_gemma":[0.9981042,0.0005162781,0.0003421628,0.00080669497,0.00019159634,0.000039027265],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0066479812,0.00008811436,0.00018685756,0.00006761545,0.0001649192,0.000020606985,0.0009650672,0.00005284776,0.0021020907],"category_scores_gemma":[0.0005066894,0.000034778768,0.00013321446,0.00038521137,0.00016569688,0.0001899552,0.0001412164,0.00017963498,0.0000632331],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002488439,0.00012195542,0.7795546,0.000002845883,0.000048402406,6.590707e-8,0.04043704,0.00074803125,0.0049425843,0.028116275,0.017103674,0.12889962],"study_design_scores_gemma":[0.00052469125,0.000117540876,0.3577086,0.000019954005,0.00002570758,0.0000024850908,0.035173077,0.0074735815,0.017706478,0.017152002,0.5639669,0.0001290297],"about_ca_topic_score_codex":0.0070436727,"about_ca_topic_score_gemma":0.055963147,"teacher_disagreement_score":0.5468632,"about_ca_system_score_codex":0.00008909813,"about_ca_system_score_gemma":0.0003346759,"threshold_uncertainty_score":0.9995685},"labels":[],"label_agreement":null},{"id":"W13968874","doi":"","title":"Challenges in monitoring and evaluation : an opportunity to institutionalize M&E systems","year":2010,"lang":"it","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Session (web analytics); Accountability; Transparency (behavior); Government (linguistics); Political science; Civil society; Public administration; Public relations; Politics; Business","score_opus":0.6072076411236819,"score_gpt":0.5489962455002827,"score_spread":0.058211395623399165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W13968874","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91864616,0.0007372617,0.000095153286,0.004497212,0.0039450256,0.00088796555,0.0000063360017,0.000025487063,0.07115938],"genre_scores_gemma":[0.99710816,0.00078967906,0.0006539621,0.00010006206,0.00037748239,0.00011154495,0.0000059229837,0.0000076155607,0.0008455986],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99516857,0.0005633818,0.000769227,0.00065388426,0.0025615052,0.00028345396],"domain_scores_gemma":[0.99728596,0.00035335866,0.00016674434,0.0006291057,0.0008889501,0.00067589735],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.018655913,0.00019120378,0.00027359353,0.00051366474,0.00022332439,0.0004821484,0.0003694116,0.00017505138,0.0028104256],"category_scores_gemma":[0.002176393,0.00015694476,0.000028459703,0.00046911548,0.000075164404,0.0013583846,0.00012836583,0.00032930015,0.00024796306],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047004447,0.0003204913,0.085746534,0.000031803916,0.000015162322,0.000004195716,0.0060770023,0.0056942124,0.0020525423,0.06866579,0.00020048015,0.8311448],"study_design_scores_gemma":[0.0010660882,0.00028128608,0.74597436,0.00015530795,0.000026688187,0.000020271918,0.015594012,0.19652829,0.00020286067,0.0021111574,0.037636388,0.0004033086],"about_ca_topic_score_codex":0.0003679857,"about_ca_topic_score_gemma":0.002103552,"teacher_disagreement_score":0.83074147,"about_ca_system_score_codex":0.0001424501,"about_ca_system_score_gemma":0.0015656026,"threshold_uncertainty_score":0.9981011},"labels":[],"label_agreement":null},{"id":"W14092155","doi":"10.3138/cjpe.018.003","title":"Balancing Ethical Principles in Evaluation: A Case Study","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Neglect; Engineering ethics; Politics; Indigenous; Ethical decision; Ethical issues; Ethical code; Political science; Public relations; Psychology; Sociology; Law; Engineering","score_opus":0.5803079388152322,"score_gpt":0.5911604505217036,"score_spread":0.01085251170647139,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W14092155","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99082863,0.00026528197,0.0002958871,0.0011297342,0.0008278991,0.0023476207,0.0000013253033,0.000005645399,0.0042979666],"genre_scores_gemma":[0.99745315,0.0000015923196,0.0020038434,0.00021198692,0.00009186349,0.00016894589,0.0000019350937,0.000009543282,0.000057150704],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98916966,0.0041672713,0.0016099624,0.0003083575,0.0043962253,0.0003485209],"domain_scores_gemma":[0.99345493,0.00048630557,0.0007016309,0.0003905687,0.0044822665,0.00048428244],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.097543,0.00014661787,0.0003072087,0.0011273955,0.0002483656,0.00044979778,0.00032838952,0.00015148488,0.0035729127],"category_scores_gemma":[0.017930117,0.00011646579,0.00010265616,0.0014756593,0.000070716254,0.00049347273,0.000010358769,0.00062361796,0.00005050762],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012396595,0.00018604836,0.50701976,0.0000033768574,0.000029899433,0.00057777885,0.009866308,0.021048248,0.00000548264,0.0007365697,0.0004000125,0.46011415],"study_design_scores_gemma":[0.008355482,0.0022806372,0.42706475,0.00012296515,0.00034881776,0.005566809,0.090087235,0.41918325,0.000048138867,0.0109780105,0.03544289,0.00052102853],"about_ca_topic_score_codex":0.0011661276,"about_ca_topic_score_gemma":0.17299503,"teacher_disagreement_score":0.45959312,"about_ca_system_score_codex":0.0010264902,"about_ca_system_score_gemma":0.013871942,"threshold_uncertainty_score":0.99733794},"labels":[],"label_agreement":null},{"id":"W1440351073","doi":"","title":"L'évolution des pratiques évaluatives dans les programmes du primaire au Québec depuis 1960","year":2011,"lang":"fr","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Humanities; Art","score_opus":0.2542721208472743,"score_gpt":0.4499875406310343,"score_spread":0.19571541978376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1440351073","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7825596,0.0021367485,0.04181104,0.0058380803,0.0009207729,0.00080454914,0.000011257626,0.00016361164,0.16575433],"genre_scores_gemma":[0.92549324,0.00059520866,0.038105097,0.00025600966,0.0002990376,0.0001490611,0.000010812684,0.000024557512,0.035066966],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.994776,0.0011326554,0.0010843438,0.0006957775,0.0016415085,0.000669718],"domain_scores_gemma":[0.9968441,0.00068424235,0.00045527905,0.0005856673,0.0011457889,0.00028491757],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0052236253,0.0003892923,0.0004015494,0.000247654,0.0011049042,0.00032454717,0.0006854658,0.00023522468,0.013489368],"category_scores_gemma":[0.0015866782,0.00028657823,0.00022939601,0.00077179447,0.0017111831,0.0019455694,0.00018456511,0.00024820637,0.0010563022],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032070366,0.00036883025,0.5025785,0.000027636459,0.000039792947,0.0000028233317,0.063408054,0.000020311805,0.00008689355,0.017361687,0.0008797491,0.41519365],"study_design_scores_gemma":[0.0005144362,0.00086940394,0.8799361,0.000140261,0.00009685377,0.000027095104,0.043932684,0.01624499,0.005044585,0.009672938,0.04307407,0.00044656827],"about_ca_topic_score_codex":0.2782461,"about_ca_topic_score_gemma":0.71423864,"teacher_disagreement_score":0.43599257,"about_ca_system_score_codex":0.0011207175,"about_ca_system_score_gemma":0.0069135167,"threshold_uncertainty_score":0.99995863},"labels":[],"label_agreement":null},{"id":"W146365109","doi":"","title":"COACHING, A FIELD FOR PROFESSIONAL SUPERVISORS?","year":2007,"lang":"en","type":"article","venue":"University of Zagreb University Computing Centre (SRCE)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Coaching; Field (mathematics); Psychology; Professional development; Croatian; Applied psychology; Medical education; Pedagogy; Psychotherapist; Medicine","score_opus":0.06728279226268935,"score_gpt":0.37420490912559895,"score_spread":0.3069221168629096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W146365109","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86511636,0.000009044949,0.12744093,0.0014864184,0.00043608833,0.00026386968,0.000019804702,0.000050373714,0.0051771123],"genre_scores_gemma":[0.97877914,0.0000059031836,0.0077295704,0.00017624331,0.000053542306,3.2774942e-12,0.00001756558,0.0000049411215,0.013233073],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9979678,0.00016941194,0.0002621569,0.0003969884,0.00086263847,0.00034101802],"domain_scores_gemma":[0.9965914,0.0019526958,0.0003292283,0.0003249999,0.0006367947,0.00016486378],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0025415586,0.0001395701,0.0002675498,0.0003898509,0.00064825796,0.000027871809,0.0008476902,0.00012444005,0.0010330543],"category_scores_gemma":[0.00027477858,0.00014696423,0.00022169398,0.00051337795,0.00011101279,0.00032239995,0.00034423426,0.0001799757,0.00006410218],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002675075,0.0011844571,0.08269605,0.00013506222,0.00029521406,0.0001497862,0.5927013,0.004051963,0.0011533097,0.042716347,0.100159876,0.17208153],"study_design_scores_gemma":[0.0030655807,0.0002378265,0.03294377,0.00010639048,0.000073765994,0.0000058421433,0.8442722,0.05241478,0.00049904827,0.0005625406,0.065420344,0.00039793027],"about_ca_topic_score_codex":0.0001921839,"about_ca_topic_score_gemma":0.0005618153,"teacher_disagreement_score":0.25157085,"about_ca_system_score_codex":0.00013575624,"about_ca_system_score_gemma":0.00022115232,"threshold_uncertainty_score":0.99988014},"labels":[],"label_agreement":null},{"id":"W1484338393","doi":"10.21225/d5rk5p","title":"A Comparison of Two Methods of Needs Assessment: Implications for Continuing Professional Education","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of University Continuing Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Needs assessment; Continuing education; Medical education; Continuing professional development; Identification (biology); Needs analysis; Professional development; Information needs; Psychology; Professional association; Special needs; Medicine; Continuing medical education; Public relations; Sociology; Political science; Computer science; Mathematics education","score_opus":0.17171229579044345,"score_gpt":0.5280368584892412,"score_spread":0.35632456269879775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1484338393","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9454329,0.00046388485,0.040611967,0.0041842563,0.0020715413,0.0004064131,0.000031673346,0.0000041361063,0.006793254],"genre_scores_gemma":[0.9538431,0.000010558048,0.042188153,0.00005111877,0.00010063758,0.0000017692955,0.000009801443,0.0000057861266,0.0037890703],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99814445,0.00042021586,0.0008041374,0.00013034693,0.0003439754,0.00015688622],"domain_scores_gemma":[0.99350953,0.000920436,0.0017028736,0.00025208155,0.0033582747,0.0002568206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032883477,0.000091824804,0.00034790213,0.0013633942,0.00015244943,0.00005414419,0.0005080996,0.000062515275,0.00040013064],"category_scores_gemma":[0.0010737701,0.00008968329,0.00015604994,0.0008812092,0.00009648423,0.0005711832,0.000015160558,0.0001553903,0.0000020220057],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017604187,0.0002516293,0.27902967,0.00002175273,0.000029562756,7.198251e-8,0.014260163,0.00017084162,0.0032258688,0.025850438,0.015021236,0.6621212],"study_design_scores_gemma":[0.0021648179,0.00044694202,0.60112435,0.00093146134,0.0003294326,0.000026892561,0.15037394,0.008995549,0.002309777,0.011491608,0.22140749,0.00039772337],"about_ca_topic_score_codex":0.0003667239,"about_ca_topic_score_gemma":0.0010781863,"teacher_disagreement_score":0.66172343,"about_ca_system_score_codex":0.00028624543,"about_ca_system_score_gemma":0.0032299769,"threshold_uncertainty_score":0.57298404},"labels":[],"label_agreement":null},{"id":"W1484543936","doi":"10.1177/160940690200100101","title":"Influence of the Research Frame on Qualitatively Derived Health Science Knowledge","year":2002,"lang":"en","type":"article","venue":"International Journal of Qualitative Methods","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":156,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Qualitative research; Field (mathematics); Orientation (vector space); Frame (networking); Epistemology; Process (computing); Body of knowledge; Psychology; Sociology; Knowledge management; Computer science; Social science; Mathematics","score_opus":0.94641623802093,"score_gpt":0.8155280055453412,"score_spread":0.13088823247558878,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1484543936","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9400995,0.00040198478,0.026247555,0.025137074,0.0010919783,0.00019819317,0.000015561825,0.000004217569,0.0068039843],"genre_scores_gemma":[0.9357807,0.00006275168,0.06252913,0.00076995575,0.00009837679,0.0000050130393,1.4533414e-7,0.000006247881,0.00074768334],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9729568,0.016572222,0.0020079832,0.00032343564,0.007826641,0.00031291778],"domain_scores_gemma":[0.9634341,0.01936312,0.002007929,0.0004026165,0.014621317,0.00017092185],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.15601629,0.00012286477,0.0003737625,0.0012810286,0.00032465998,0.00016922533,0.0030450006,0.00004017407,0.0004656022],"category_scores_gemma":[0.047523487,0.00006929951,0.00019102998,0.002275639,0.0016757502,0.0008100135,0.00027570847,0.00063628284,0.00008864516],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002251896,0.0007489899,0.002317326,0.000014674321,0.0001534983,0.000002562144,0.56388587,0.0064619216,0.028970702,0.17268485,0.005317539,0.21921688],"study_design_scores_gemma":[0.0025077888,0.0028557093,0.28473768,0.00094023225,0.000014095256,0.000056394612,0.16705777,0.009994461,0.071324445,0.42072114,0.039385308,0.00040500207],"about_ca_topic_score_codex":0.000027372824,"about_ca_topic_score_gemma":0.000008576645,"teacher_disagreement_score":0.39682811,"about_ca_system_score_codex":0.00044221833,"about_ca_system_score_gemma":0.0011163438,"threshold_uncertainty_score":0.96049964},"labels":[],"label_agreement":null},{"id":"W1485638814","doi":"10.7202/051319ar","title":"Harrisson, Michael I., and Arie Shirom, Organizational Diagnosis and Assessment: Bridging Theory and Practice","year":2000,"lang":"en","type":"article","venue":"Relations industrielles","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Bridging (networking); Sociology; Computer science; Computer security","score_opus":0.10192246389478749,"score_gpt":0.4268065319817227,"score_spread":0.3248840680869352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1485638814","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94387746,0.0014426492,0.0036519128,0.022873253,0.0000892752,0.0003053303,0.00003949507,0.000038809645,0.027681818],"genre_scores_gemma":[0.9886984,0.0018638622,0.0030879679,0.0006761735,0.00007918428,0.000021819778,0.000023825158,0.000011731428,0.005536984],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9978877,0.0005141771,0.00042341236,0.00036753924,0.00065936125,0.0001478378],"domain_scores_gemma":[0.99363035,0.005613526,0.00016832177,0.00021763223,0.0002444799,0.00012571772],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003843832,0.00012921687,0.00015327873,0.00018078357,0.00064782286,0.00043769716,0.0001140556,0.00014573973,0.0049556037],"category_scores_gemma":[0.0040167375,0.00010901585,0.000015919413,0.0006018189,0.0001910224,0.0009982747,0.00007475921,0.00030053634,0.00007359476],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036554266,0.00010309872,0.41449475,0.0000018036106,0.00005916039,0.00000382973,0.0034805187,0.00045849534,0.000031052055,0.064073704,0.009478714,0.50777835],"study_design_scores_gemma":[0.0010704441,0.00009693304,0.5879958,0.000056711084,0.00012976103,0.00011980142,0.009003629,0.015184855,0.00008215239,0.03148322,0.3543997,0.00037695107],"about_ca_topic_score_codex":0.00001881215,"about_ca_topic_score_gemma":0.000009138823,"teacher_disagreement_score":0.50740135,"about_ca_system_score_codex":0.000030724615,"about_ca_system_score_gemma":0.00024547667,"threshold_uncertainty_score":0.995954},"labels":[],"label_agreement":null},{"id":"W1486190448","doi":"10.1111/medu.12091","title":"Rethinking programme evaluation in health professions education: beyond ‘did it work?’","year":2013,"lang":"en","type":"article","venue":"Medical Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":217,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Holland Bloorview Kids Rehabilitation Hospital; The Wilson Centre; London Health Sciences Centre; Centre Hospitalier Universitaire Sainte-Justine; SickKids Foundation; University of Toronto","funders":"","keywords":"Parallels; Context (archaeology); Engineering ethics; Curriculum; Field (mathematics); Process (computing); Work (physics); Health professions; Sociology; Program evaluation; Medical education; Management science; Health care; Psychology; Pedagogy; Political science; Medicine; Computer science; Engineering","score_opus":0.23449198114469882,"score_gpt":0.5649593503657884,"score_spread":0.33046736922108955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1486190448","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32645208,0.0008345829,0.0008498525,0.6307736,0.0055437195,0.0030721338,6.404841e-7,0.000063535044,0.03240988],"genre_scores_gemma":[0.9565141,0.00006178032,0.0035748684,0.030613799,0.00043962675,0.0018663682,0.00011398457,0.000012797873,0.0068026753],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9917692,0.0012354866,0.001319934,0.0005079057,0.004767813,0.00039963733],"domain_scores_gemma":[0.9966258,0.00055027456,0.00049946224,0.00059350894,0.0013427244,0.0003882717],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.019713202,0.00014929233,0.00024619215,0.0004800796,0.00027404208,0.00026669493,0.00056138297,0.00017311501,0.027775377],"category_scores_gemma":[0.013279266,0.00011158622,0.00005725619,0.0018745811,0.00009005772,0.0007750383,0.00007520419,0.00046270184,0.0014847076],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000033581832,0.000600027,0.027350988,0.000012465831,0.000002066635,3.81092e-8,0.006203607,0.000013973506,0.0000017407823,0.0017504151,0.1787212,0.78534013],"study_design_scores_gemma":[0.000949665,0.0001507055,0.406803,0.0010116324,0.000012693103,0.000009404574,0.022745062,0.026681274,0.000013048379,0.2428915,0.29835606,0.00037594448],"about_ca_topic_score_codex":0.0005847532,"about_ca_topic_score_gemma":0.0006480052,"teacher_disagreement_score":0.78496414,"about_ca_system_score_codex":0.00056104985,"about_ca_system_score_gemma":0.024479685,"threshold_uncertainty_score":0.99929273},"labels":[],"label_agreement":null},{"id":"W1488090947","doi":"","title":"Models of Inservice Professional Development: An Exploration of Effective Practices","year":2005,"lang":"en","type":"article","venue":"Society for Information Technology & Teacher Education International Conference","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Professional development; Engineering ethics; Pedagogy; Mathematics education; Psychology; Engineering","score_opus":0.22444119753093406,"score_gpt":0.5120948215540253,"score_spread":0.28765362402309125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1488090947","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70811665,0.000071188995,0.25682893,0.016714467,0.0016209265,0.0017561696,0.00006148053,0.00013375445,0.014696433],"genre_scores_gemma":[0.94937927,0.00002325137,0.048234504,0.00038514065,0.000072161296,0.0006064703,0.00028734404,0.000005760025,0.0010060809],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99732584,0.000068735986,0.0011831775,0.00021877809,0.0010707878,0.00013271203],"domain_scores_gemma":[0.991906,0.00021825699,0.002504888,0.0003280359,0.004996784,0.000046049507],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002430838,0.00013922158,0.00020750563,0.00051059126,0.00015441419,0.0000871716,0.000824611,0.0002145751,0.00044176515],"category_scores_gemma":[0.00087170175,0.00012169193,0.000119359116,0.00058805535,0.00013290315,0.011891608,0.000094705734,0.00019556128,0.000044519846],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009706051,0.0008083757,0.0052647386,0.000055285927,0.00009963907,3.7209287e-9,0.03515957,0.0015456867,0.0009828487,0.3127033,0.0026588498,0.64062464],"study_design_scores_gemma":[0.0021086645,0.00037301748,0.01529499,0.00019431619,0.0000630023,0.000004882321,0.15141064,0.35489422,0.0369092,0.18776537,0.25042972,0.00055198104],"about_ca_topic_score_codex":0.000015734377,"about_ca_topic_score_gemma":0.000033144395,"teacher_disagreement_score":0.64007264,"about_ca_system_score_codex":0.00016399488,"about_ca_system_score_gemma":0.0016150221,"threshold_uncertainty_score":0.8621129},"labels":[],"label_agreement":null},{"id":"W1488273786","doi":"10.56645/jmde.v1i1.148","title":"The State of Evaluation in Canada","year":2004,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Health Canada; Government of Canada; Industry Canada; Australian Government; Transport Canada","keywords":"State (computer science); Political science; Evaluation methods; Public administration; Library science; Regional science; Sociology; Computer science; Engineering; Reliability engineering","score_opus":0.15798301331153608,"score_gpt":0.4877877855008924,"score_spread":0.32980477218935633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1488273786","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99346966,0.0005740071,0.00059981004,0.0034773343,0.0009200249,0.0004627712,0.0000035350574,0.0000011134022,0.00049176643],"genre_scores_gemma":[0.9992451,0.00009568643,0.00051277026,0.000024864023,0.000056404988,0.000013518684,0.0000026432103,0.0000053357526,0.000043660562],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9887437,0.001031384,0.0019584526,0.00016402524,0.0079189325,0.00018349795],"domain_scores_gemma":[0.9928364,0.0010755212,0.0017413489,0.0003298453,0.0039459,0.00007096136],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.044391565,0.00010269275,0.00025046995,0.00029674705,0.00015824266,0.00005591445,0.00041850033,0.000025784575,0.00019528622],"category_scores_gemma":[0.0035611242,0.0000598346,0.000089715184,0.0007500778,0.000051188596,0.00060753524,0.00006206142,0.00019792166,0.000010736458],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013684393,0.00005556459,0.023529323,0.0000025194056,0.00001433397,0.0000025244233,0.0018086142,0.73361224,0.00064578844,0.000051794075,0.0001707677,0.23996969],"study_design_scores_gemma":[0.0024622611,0.00017276163,0.6508724,0.00005782896,0.000035870682,0.000015903834,0.0032391162,0.28862464,0.0012293236,0.053102173,0.000114827315,0.00007289255],"about_ca_topic_score_codex":0.028572258,"about_ca_topic_score_gemma":0.6946353,"teacher_disagreement_score":0.666063,"about_ca_system_score_codex":0.0019138462,"about_ca_system_score_gemma":0.013888982,"threshold_uncertainty_score":0.99170136},"labels":[],"label_agreement":null},{"id":"W1489492151","doi":"10.7202/1013125ar","title":"Les déterminants de l’utilisation des recherches en éducation : le cas des conseillers pédagogiques au Québec","year":2012,"lang":"fr","type":"article","venue":"McGill Journal of Education / Revue des sciences de l éducation de McGill","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"École Nationale d'Administration Publique","funders":"","keywords":"Political science; Humanities; Philosophy","score_opus":0.7968597598974836,"score_gpt":0.6003725567790945,"score_spread":0.19648720311838908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1489492151","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9432604,0.0043569966,0.0046091774,0.015439999,0.005421386,0.00037433373,0.00003868769,0.000035851415,0.026463198],"genre_scores_gemma":[0.9236613,0.0028483847,0.057792105,0.0009636809,0.0008849013,0.000059504044,0.000009189791,0.000038600047,0.013742335],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9908335,0.0043473477,0.0019506968,0.0005405183,0.0011403143,0.0011876157],"domain_scores_gemma":[0.9901756,0.0033268654,0.0021847459,0.00050843076,0.0029205133,0.000883817],"candidate_categories":["metaresearch","metaepi_narrow","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.033572793,0.0004501027,0.00054469774,0.0011885423,0.0041854186,0.00041811145,0.0012451679,0.00036773848,0.00090044836],"category_scores_gemma":[0.015860125,0.00042635656,0.0003250642,0.001919615,0.002652443,0.0051896977,0.00009792411,0.00062739325,0.00012466438],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00008808047,0.0021294549,0.23905933,0.0003862426,0.00008320628,0.0000032888856,0.21248202,0.004029272,0.001611529,0.01630352,0.0045750523,0.519249],"study_design_scores_gemma":[0.0005919685,0.00076420157,0.5347291,0.0015004802,0.00027575172,0.003672185,0.2022191,0.0055917464,0.0111554265,0.047159962,0.19150366,0.0008363735],"about_ca_topic_score_codex":0.04709133,"about_ca_topic_score_gemma":0.039342493,"teacher_disagreement_score":0.51841265,"about_ca_system_score_codex":0.027959146,"about_ca_system_score_gemma":0.02785967,"threshold_uncertainty_score":0.9998188},"labels":[],"label_agreement":null},{"id":"W1490602178","doi":"10.3138/cjpe.0028.005","title":"A Professional Grounding and History of the Development and Formal Use of Evaluator Competencies","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Professionalization; Viewpoints; Credentialing; Engineering ethics; Value (mathematics); Professional association; Field (mathematics); Foundation (evidence); Professional development; Psychology; Political science; Sociology; Pedagogy; Public relations; Engineering; Computer science; Social science; Law","score_opus":0.39851549563026134,"score_gpt":0.4680725057001939,"score_spread":0.06955701006993253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1490602178","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9972078,0.00047347244,0.00041240518,0.00037208907,0.00077779446,0.00046345955,0.0000015523182,0.0000013902713,0.0002900378],"genre_scores_gemma":[0.9914935,0.000003557874,0.008165202,0.00006982547,0.00003314269,0.000015593778,0.0000012932861,0.00000389175,0.00021397306],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9966415,0.0005461826,0.0008401165,0.00010627956,0.0017187638,0.00014714221],"domain_scores_gemma":[0.9966117,0.000375993,0.000935033,0.00014882977,0.0017438403,0.00018458746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014703625,0.0000784705,0.00020210067,0.00031699255,0.00014275951,0.000060899743,0.00020123128,0.000045147535,0.00018360106],"category_scores_gemma":[0.002625795,0.000047842113,0.000049443366,0.00020185641,0.00022244331,0.00064530846,0.000030935662,0.00011306833,9.573965e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021211858,0.000027878763,0.17504327,0.000023525643,0.000023388937,1.5964446e-7,0.007321842,0.00016179019,0.00027992052,0.0016933694,0.00090998213,0.81449366],"study_design_scores_gemma":[0.0007983416,0.00027414647,0.8656971,0.00017030787,0.000064901484,0.000022093473,0.0015822303,0.04331083,0.00021403203,0.0017634028,0.08601237,0.00009024481],"about_ca_topic_score_codex":0.00014166378,"about_ca_topic_score_gemma":0.0052625253,"teacher_disagreement_score":0.8144034,"about_ca_system_score_codex":0.00034348806,"about_ca_system_score_gemma":0.006019714,"threshold_uncertainty_score":0.99961525},"labels":[],"label_agreement":null},{"id":"W1492600101","doi":"10.2139/ssrn.1546251","title":"Re-Visiting Meltsner: Policy Advice Systems and the Multi-Dimensional Nature of Professional Policy Analysis","year":2009,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Advice (programming); Policy analysis; Political science; Public relations; Public administration; Computer science","score_opus":0.03252770513279875,"score_gpt":0.451167510539205,"score_spread":0.4186398054064063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1492600101","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8434268,0.012965899,0.0043842574,0.13296928,0.0005618214,0.00065325183,0.000021864702,0.000051041952,0.004965741],"genre_scores_gemma":[0.99273455,0.0005856979,0.0001865361,0.0012913358,0.00066531595,0.000003867621,0.0000044994276,0.000006802633,0.0045213783],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9945953,0.0008446189,0.00097653246,0.00030341843,0.0022007267,0.0010794201],"domain_scores_gemma":[0.99705446,0.0008226207,0.0008980455,0.0003582794,0.0007444024,0.00012219162],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017316336,0.00017977861,0.0004771276,0.0010483682,0.00056976965,0.00018748367,0.0006082672,0.000147318,0.0000646061],"category_scores_gemma":[0.0017076024,0.00009399926,0.0002691222,0.0025232146,0.00012600205,0.00037797866,0.000078461766,0.0018621004,0.000012116955],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00056772406,0.00018792851,0.014090173,0.000007164885,0.0010188401,0.0000025257652,0.0019577355,0.0151355965,0.0003324627,0.9168779,0.0007356356,0.049086295],"study_design_scores_gemma":[0.009220502,0.00062268565,0.11587091,0.00013538147,0.00066994224,0.0004719696,0.0309868,0.3865069,0.000103334976,0.44984373,0.0049547744,0.0006131025],"about_ca_topic_score_codex":0.00030856187,"about_ca_topic_score_gemma":0.00064519455,"teacher_disagreement_score":0.4670342,"about_ca_system_score_codex":0.00040704064,"about_ca_system_score_gemma":0.005241469,"threshold_uncertainty_score":0.92981404},"labels":[],"label_agreement":null},{"id":"W1493131192","doi":"10.22329/il.v25i3.1136","title":"Limits of Truth: Exploring Epistemological Approaches to Argumentation","year":2005,"lang":"en","type":"article","venue":"Informal Logic","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Argumentation theory; Epistemology; Argument (complex analysis); Value (mathematics); Philosophy; Cognition; Sociology; Psychology; Computer science","score_opus":0.828222202449797,"score_gpt":0.49034824065344995,"score_spread":0.3378739617963471,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1493131192","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.900753,0.000027795895,0.012967766,0.0016068856,0.00028590587,0.00022776882,0.0000036478548,0.000034070184,0.08409315],"genre_scores_gemma":[0.9912814,0.000011890979,0.0072200918,0.0007164051,0.00008954302,0.000054035736,0.0000059616505,0.0000027934605,0.0006178777],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9978382,0.000064918095,0.00073851924,0.00017998356,0.0009778903,0.00020050995],"domain_scores_gemma":[0.9988965,0.00041472263,0.00021109311,0.0002539557,0.0001240072,0.000099732366],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002325299,0.00009880687,0.00019044359,0.00022019536,0.00007996634,0.00007987775,0.00036923174,0.00004836012,0.0009523176],"category_scores_gemma":[0.00068714237,0.000064704596,0.00007304915,0.0004493256,0.000040099098,0.0010767266,0.00007833812,0.0000807085,0.00090253586],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013434012,0.0001413319,0.02138654,0.000009781508,0.000013891603,0.0000011953301,0.002857071,0.14166161,0.0002085163,0.12252866,0.0005273981,0.7105297],"study_design_scores_gemma":[0.0017350803,0.0016718851,0.7158831,0.000038374154,0.000024219136,0.00002985303,0.006532367,0.15119635,0.021153681,0.007908993,0.093164325,0.0006618167],"about_ca_topic_score_codex":0.0000024883884,"about_ca_topic_score_gemma":0.000007409739,"teacher_disagreement_score":0.70986784,"about_ca_system_score_codex":0.000035949524,"about_ca_system_score_gemma":0.000044105767,"threshold_uncertainty_score":0.99996096},"labels":[],"label_agreement":null},{"id":"W1493783673","doi":"10.4000/ries.4351","title":"Les résultats des élèves asiatiques dans les enquêtes internationales","year":2015,"lang":"fr","type":"article","venue":"Revue internationale d éducation de Sèvres","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Humanities; Philosophy","score_opus":0.36501126710811865,"score_gpt":0.5055535060290076,"score_spread":0.14054223892088896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1493783673","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81073284,0.0096067805,0.034847658,0.028276375,0.0042222273,0.00047390035,0.00020304564,0.00013008175,0.11150711],"genre_scores_gemma":[0.8381178,0.0022599837,0.01266333,0.0003575113,0.0013442066,0.00016921136,0.00019450212,0.000043171585,0.14485033],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99481094,0.0008796813,0.0013305926,0.00071600423,0.0017988827,0.00046392926],"domain_scores_gemma":[0.99263453,0.002118799,0.0008106655,0.00052629673,0.0035172056,0.00039247822],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0040202257,0.000396175,0.00037814493,0.0006794658,0.00039458717,0.0008183735,0.0013074031,0.00025866783,0.00609967],"category_scores_gemma":[0.008182733,0.0003926237,0.0002463578,0.0006426553,0.0005804165,0.0017107778,0.00020025783,0.0003787327,0.0010940784],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007421284,0.00073846965,0.34376985,0.00011921489,0.00020370925,0.00001120873,0.07496887,0.0072848164,0.00040992151,0.13238214,0.024993116,0.4150445],"study_design_scores_gemma":[0.00084591954,0.00021478902,0.3579507,0.0007986644,0.00007459811,0.00018697744,0.030434541,0.05339834,0.0028384542,0.096653245,0.4560057,0.00059810124],"about_ca_topic_score_codex":0.004040673,"about_ca_topic_score_gemma":0.009083978,"teacher_disagreement_score":0.43101257,"about_ca_system_score_codex":0.0023651272,"about_ca_system_score_gemma":0.0018906007,"threshold_uncertainty_score":0.99985254},"labels":[],"label_agreement":null},{"id":"W1494699756","doi":"","title":"ARTICLE 6: METAEVALUATION: EVALUATING THE EVALUATION OF THE PARIS DECLARATION","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Declaration; Strengths and weaknesses; Evaluation methods; Quality (philosophy); Commission; Political science; Psychology; Computer science; Engineering; Law; Social psychology; Reliability engineering","score_opus":0.7038098888130093,"score_gpt":0.5979079630601261,"score_spread":0.10590192575288326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1494699756","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9825568,0.0026360922,0.000995877,0.0050094486,0.0023398488,0.0028121485,0.000005006285,0.000006866466,0.003637875],"genre_scores_gemma":[0.99733824,0.000007731987,0.0016363292,0.00023993038,0.00046109874,0.0002093993,0.000005783524,0.00001315698,0.0000883145],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.97850215,0.0062176166,0.0019308786,0.00022039509,0.01267289,0.0004560923],"domain_scores_gemma":[0.97983736,0.0008476868,0.0022332226,0.0007934531,0.015951522,0.0003367521],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.17275204,0.00017655084,0.00029406222,0.00039082018,0.00067151035,0.00034356827,0.00086531555,0.00011200776,0.0038565958],"category_scores_gemma":[0.023309542,0.00009501661,0.00029602705,0.0018127494,0.00022402736,0.0014707368,0.000036765592,0.00033204517,0.000079874],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021557238,0.00008615927,0.08393175,0.0000038323724,0.00007338699,6.993813e-8,0.0042101704,0.030742887,0.00062218314,0.0011302126,0.0027772547,0.87640053],"study_design_scores_gemma":[0.0012810957,0.0003334343,0.5114548,0.00004366725,0.001016052,0.000030471761,0.0025939445,0.46123654,0.0018211835,0.01312138,0.00692505,0.00014234812],"about_ca_topic_score_codex":0.00031294007,"about_ca_topic_score_gemma":0.004348504,"teacher_disagreement_score":0.8762582,"about_ca_system_score_codex":0.0008936226,"about_ca_system_score_gemma":0.009686183,"threshold_uncertainty_score":0.99705404},"labels":[],"label_agreement":null},{"id":"W1496927098","doi":"","title":"Barbier, J. C., & Hawkins, P. (Eds.). (2012). Evaluation Cultures: Sense-making in Complex Times","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sense (electronics); Psychology; Chemistry; Physical chemistry","score_opus":0.32864005862634,"score_gpt":0.529181536959155,"score_spread":0.20054147833281505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1496927098","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.914903,0.008910811,0.0015984819,0.014815374,0.0029088103,0.009682803,0.000021180613,0.000051038347,0.04710854],"genre_scores_gemma":[0.9939196,0.000040220028,0.0046179937,0.0005782025,0.0002643181,0.00021824153,0.00004736465,0.0000170257,0.0002970487],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9915931,0.0015893616,0.0016300856,0.0003466024,0.004336669,0.0005041455],"domain_scores_gemma":[0.99121916,0.00031459957,0.0010649067,0.00043042013,0.0064892694,0.00048164793],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.024165379,0.0002210271,0.00038885177,0.0013459219,0.00030302702,0.00094940653,0.000518145,0.00015177,0.030361231],"category_scores_gemma":[0.0044165393,0.0001717881,0.0001661787,0.0012811847,0.000118183714,0.0019855385,0.000021396174,0.00036428872,0.00066091947],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009964975,0.000054719938,0.011434986,0.000004850131,0.000024608727,0.000005259016,0.0015215726,0.006644245,0.00014191386,0.00026641885,0.04408773,0.9358037],"study_design_scores_gemma":[0.0019968052,0.00036515563,0.34669542,0.00012593446,0.000116869436,0.0000881908,0.0024428787,0.46290538,0.00004815057,0.027714426,0.1571759,0.00032488737],"about_ca_topic_score_codex":0.0015049927,"about_ca_topic_score_gemma":0.040194746,"teacher_disagreement_score":0.93547887,"about_ca_system_score_codex":0.00083022326,"about_ca_system_score_gemma":0.0054051992,"threshold_uncertainty_score":0.9773192},"labels":[],"label_agreement":null},{"id":"W1497778884","doi":"10.5539/res.v7n7p407","title":"Self-Evaluation as a Factor of Quality Assurance in Education","year":2015,"lang":"en","type":"article","venue":"Review of European Studies","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Work (physics); Psychology; Quality (philosophy); Atmosphere (unit); Self evaluation; Precondition; Sample (material); Quality assurance; Empirical research; Medical education; Institution; Pedagogy; Sociology; Applied psychology; Medicine; Computer science; Engineering; Social science","score_opus":0.591741891693703,"score_gpt":0.6280412653403656,"score_spread":0.03629937364666269,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1497778884","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3898264,0.43358642,0.00004079973,0.0029405877,0.00066483475,0.0010276986,0.000008736735,0.000018310866,0.17188622],"genre_scores_gemma":[0.88952905,0.10794101,0.0013840649,0.00064335816,0.00005100428,0.000023093338,0.0000038686408,0.0000063363996,0.0004181852],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99414,0.0025292253,0.0012554707,0.00020581158,0.0017895985,0.00007984468],"domain_scores_gemma":[0.99550205,0.0005174247,0.0008147685,0.00038700507,0.0027415454,0.00003720996],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.024255995,0.000086379216,0.00045681515,0.000115707226,0.000021162607,0.000010609319,0.00025584304,0.0000092984055,0.00012011846],"category_scores_gemma":[0.015550091,0.00005762595,0.00007230817,0.00060300255,0.00004840903,0.00025087342,0.000082723534,0.000048479724,0.00023986997],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003182073,0.0007460636,0.094692454,0.007254372,0.00012535814,6.635467e-7,0.014367549,0.000055247245,0.00012676595,0.0054071015,0.04121923,0.8359734],"study_design_scores_gemma":[0.000904946,0.0002452829,0.7527399,0.008145646,0.00008904515,0.0000022404981,0.009476807,0.00020009272,0.00020364857,0.003719499,0.22402115,0.00025171612],"about_ca_topic_score_codex":0.000009385062,"about_ca_topic_score_gemma":0.00001630722,"teacher_disagreement_score":0.8357217,"about_ca_system_score_codex":0.00007530106,"about_ca_system_score_gemma":0.0005769549,"threshold_uncertainty_score":0.99274236},"labels":[],"label_agreement":null},{"id":"W1498958831","doi":"10.1177/160940691301200122","title":"Bridging Conceptions of Quality in Moments of Qualitative Research","year":2013,"lang":"en","type":"article","venue":"International Journal of Qualitative Methods","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":75,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Bridging (networking); Qualitative research; Diversity (politics); Management science; Quality (philosophy); Sociology; Qualitative analysis; Computer science; Epistemology; Engineering ethics; Social science; Engineering","score_opus":0.9541240624199693,"score_gpt":0.8419877740146262,"score_spread":0.11213628840534307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1498958831","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.752726,0.00014772672,0.23688824,0.0056967814,0.00060873874,0.00021099574,0.00003840494,0.0000022345098,0.0036808231],"genre_scores_gemma":[0.86265177,0.0000355912,0.13651893,0.00011643087,0.000072204544,0.000014591619,0.0000026632906,0.0000063025504,0.00058155175],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.94871247,0.040716525,0.0040138457,0.00026999594,0.0060334364,0.00025373325],"domain_scores_gemma":[0.95277345,0.029540475,0.002685036,0.0002675554,0.014621291,0.00011220265],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.16770148,0.00012050205,0.0006218225,0.0016475114,0.000050007173,0.000079518344,0.0011306854,0.000062365914,0.0022335819],"category_scores_gemma":[0.032440104,0.00008957398,0.0002330299,0.001104058,0.0006033597,0.0010563754,0.00015821871,0.00045053678,0.000042599266],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034653454,0.0006866745,0.010026034,0.000027552294,0.00036530697,0.000003348432,0.68037665,0.0010006501,0.05146104,0.08565649,0.0023275004,0.16772223],"study_design_scores_gemma":[0.0017976055,0.00045471868,0.09049452,0.00024030604,0.0000088786655,0.000006154255,0.4693349,0.0023656804,0.016292667,0.41798308,0.00086954376,0.00015193076],"about_ca_topic_score_codex":0.0005207028,"about_ca_topic_score_gemma":0.000033187618,"teacher_disagreement_score":0.3323266,"about_ca_system_score_codex":0.00023966213,"about_ca_system_score_gemma":0.00047349697,"threshold_uncertainty_score":0.9986785},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"evaluation","study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W1498966462","doi":"","title":"Issue #9 - April 7, 2004","year":2004,"lang":"en","type":"article","venue":"Pro Tem","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Dream; Art; Art history; Banquet; Performance art; Cartography; Humanities; Geography","score_opus":0.21518543695717304,"score_gpt":0.4995966653775885,"score_spread":0.28441122842041544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1498966462","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4890599,0.0010322691,0.026187267,0.055438183,0.0033369896,0.0010911492,0.000012972074,0.00032210466,0.42351916],"genre_scores_gemma":[0.9765085,0.000009793687,0.0029305408,0.0012715157,0.00018264206,0.000021725124,0.000001975822,0.000005510937,0.019067788],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99814415,0.00004092419,0.0003038285,0.00022434248,0.0011326352,0.00015414634],"domain_scores_gemma":[0.99921155,0.000082902036,0.0000898559,0.0003588568,0.00018499825,0.000071843235],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0018506268,0.00006897468,0.00010751283,0.000094664145,0.00010647546,0.00014023481,0.0003429095,0.000035375557,0.0043495744],"category_scores_gemma":[0.00034328934,0.00004640224,0.000044023425,0.00039425763,0.00003099848,0.00029852896,0.0000482831,0.000075150565,0.0126668345],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058936803,0.000433193,0.055183634,0.000022598624,0.000032950673,0.00001630522,0.006257194,0.010257985,0.0019335087,0.046041913,0.16265611,0.7171057],"study_design_scores_gemma":[0.00072737946,0.00008997748,0.019004902,0.000014277119,0.000004604253,0.0000060465427,0.0006120999,0.0009934743,0.0048650797,0.058008723,0.91552293,0.00015047737],"about_ca_topic_score_codex":0.000019376466,"about_ca_topic_score_gemma":0.000027618098,"teacher_disagreement_score":0.75286686,"about_ca_system_score_codex":0.000058574406,"about_ca_system_score_gemma":0.00023069092,"threshold_uncertainty_score":0.9965606},"labels":[],"label_agreement":null},{"id":"W1499796364","doi":"","title":"Benchmarking 10 Major Canadian Universities at the Divisional Level: A Powerful Tool for Strategic Decision Making","year":2010,"lang":"en","type":"article","venue":"Planning for higher education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Benchmarking; Higher education; Ranking (information retrieval); Political science; China; Strategic planning; Internationalization; Public relations; Management; Sociology; Marketing; Business; Economics; Computer science","score_opus":0.18310191546486337,"score_gpt":0.47827438631146485,"score_spread":0.2951724708466015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1499796364","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97910506,0.000084867555,0.0018790241,0.0034731512,0.0050330977,0.0005932942,0.00014109597,0.000019639032,0.009670769],"genre_scores_gemma":[0.95548624,5.6685855e-7,0.008270365,0.0006707292,0.0005370404,0.00006512792,0.0001682608,0.000013421977,0.03478822],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981958,0.000045806763,0.00036014724,0.00035489284,0.0007320327,0.00031129067],"domain_scores_gemma":[0.9963556,0.0023744418,0.00022650871,0.00036102792,0.00057740835,0.00010499383],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0023341768,0.00014097226,0.00013386947,0.00031815987,0.0010525587,0.0004149646,0.00048013456,0.000101045116,0.0077417647],"category_scores_gemma":[0.00020557233,0.00009864118,0.000102171354,0.00029532213,0.000056760608,0.0003878672,0.000050213243,0.00013570016,0.00014322948],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00066691986,0.00018024915,0.09698028,0.00004436008,0.00008554933,0.0000015826796,0.0066884337,0.006137178,0.0010945501,0.1352323,0.62030226,0.13258632],"study_design_scores_gemma":[0.00044186122,0.000098282864,0.23226026,0.00007536406,0.00003274992,0.0000066906214,0.002821881,0.007881655,0.00004684655,0.035325944,0.72075605,0.00025241563],"about_ca_topic_score_codex":0.00067703205,"about_ca_topic_score_gemma":0.009448872,"teacher_disagreement_score":0.13527998,"about_ca_system_score_codex":0.00028987028,"about_ca_system_score_gemma":0.0020456528,"threshold_uncertainty_score":0.9931653},"labels":[],"label_agreement":null},{"id":"W1500339204","doi":"10.1787/9789264023666-14-fr","title":"La réflexion prospective: Sa pratique et son potentiel","year":2006,"lang":"fr","type":"paratext","venue":"˜L'œécole de demain","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Humanities; Art; Political science","score_opus":0.049890296818828735,"score_gpt":0.4369353245068849,"score_spread":0.38704502768805615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1500339204","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05484028,0.002177523,0.12261995,0.010366579,0.004079622,0.0028667331,0.0004478698,0.00013507104,0.8024664],"genre_scores_gemma":[0.31804663,0.0005940797,0.0074919085,0.00518688,0.0009244919,0.00057434925,0.00047998235,0.0001045025,0.6665972],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98847663,0.0041035786,0.0018235344,0.0014795684,0.0029029378,0.001213765],"domain_scores_gemma":[0.99437034,0.0018976888,0.0012272261,0.0011485408,0.0009455172,0.0004106721],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.014684843,0.0008344629,0.0010718808,0.0006604967,0.0005902387,0.0013673472,0.0012260472,0.0014449407,0.018208401],"category_scores_gemma":[0.0008433993,0.00075133087,0.0004903006,0.0014421045,0.00037125498,0.00091799867,0.0003197136,0.0017613379,0.02398525],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030279593,0.0012771781,0.02528839,0.0003021266,0.0001915999,0.00015168567,0.0028412894,0.040320475,0.0008539825,0.11833207,0.7381866,0.071951784],"study_design_scores_gemma":[0.0014985821,0.0004336373,0.11035,0.00048304594,0.000113595044,0.00012204069,0.0010111785,0.055057462,0.0005626037,0.025687652,0.8036847,0.0009954779],"about_ca_topic_score_codex":0.00084710325,"about_ca_topic_score_gemma":0.0028648856,"teacher_disagreement_score":0.26320636,"about_ca_system_score_codex":0.0015891514,"about_ca_system_score_gemma":0.007212644,"threshold_uncertainty_score":0.9998514},"labels":[],"label_agreement":null},{"id":"W150102863","doi":"","title":"Changing through Clusters: Vermont's Policy Clusters","year":2003,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Population; Commission; Legislature; State (computer science); Criminology; Psychiatry; Law; Political science; Psychology; Sociology; Demography","score_opus":0.20629142290531488,"score_gpt":0.49408321163140134,"score_spread":0.28779178872608646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W150102863","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06052844,0.000055969333,0.06446318,0.0073784413,0.0007870856,0.00025438803,0.0000022307674,0.00008311775,0.86644715],"genre_scores_gemma":[0.9536778,0.000023788973,0.0044459943,0.00898594,0.0001321054,0.000013623926,0.0000020878094,0.000009482584,0.03270922],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99725723,0.0002153297,0.0004470681,0.00033395734,0.0013649425,0.00038149746],"domain_scores_gemma":[0.99874806,0.00033890014,0.00012887608,0.00051004137,0.00018087098,0.00009325724],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002995957,0.00012712993,0.00017580234,0.00037124514,0.00024084005,0.00025819335,0.00037333078,0.00005557924,0.0051751365],"category_scores_gemma":[0.0008738538,0.00008721909,0.00009697764,0.0013794991,0.000050045965,0.00081539573,0.00007669534,0.00008859175,0.001963767],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007686194,0.00029405596,0.019719144,0.000020731808,0.00009145971,0.000015191483,0.0355616,0.008780225,0.00035204942,0.6235516,0.12374054,0.18779653],"study_design_scores_gemma":[0.0020722793,0.00018725973,0.00479398,0.000026964086,0.00001768362,0.000033388395,0.0327599,0.03470626,0.002582076,0.059542462,0.86267304,0.00060472416],"about_ca_topic_score_codex":0.000051516337,"about_ca_topic_score_gemma":0.00007259705,"teacher_disagreement_score":0.8931493,"about_ca_system_score_codex":0.000097245764,"about_ca_system_score_gemma":0.0002591004,"threshold_uncertainty_score":0.99881333},"labels":[],"label_agreement":null},{"id":"W1501592175","doi":"10.56645/jmde.v11i24.422","title":"Utilization Focused Developmental Evaluation: Learning Through Practice","year":2015,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Mastercard Foundation","keywords":"Data collection; Context (archaeology); Curriculum; Intervention (counseling); Sample (material); Citizen journalism; Participatory evaluation; Process (computing); Knowledge management; Computer science; Psychology; Process management; Medical education; Management science; Pedagogy; Sociology; Engineering; Medicine","score_opus":0.6300483308941991,"score_gpt":0.5906089619140568,"score_spread":0.03943936898014233,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1501592175","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8673399,0.0015700263,0.061353836,0.009704444,0.0032551503,0.0014204931,0.0000028501347,0.0000400949,0.055313177],"genre_scores_gemma":[0.9605368,0.0000604638,0.038320918,0.00013723026,0.00042331225,0.000030746243,0.00002969428,0.000017886676,0.00044299796],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9819041,0.0036068102,0.0019463428,0.0003551281,0.011948775,0.00023883351],"domain_scores_gemma":[0.9803132,0.0014017653,0.0025037923,0.00027994602,0.015298688,0.00020264788],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.075059645,0.0002055334,0.00035850206,0.00044660753,0.00036933014,0.00029247507,0.0005054672,0.00012143738,0.001525129],"category_scores_gemma":[0.034551606,0.00015416335,0.000148876,0.0011618643,0.00006678399,0.0048248954,0.00014797553,0.00038484286,0.00039196835],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00093501055,0.00061230385,0.024847297,0.0000069446087,0.00012887242,0.000011437022,0.048307434,0.35581607,0.0005688733,0.00040976255,0.009918499,0.5584375],"study_design_scores_gemma":[0.007250878,0.0010750075,0.037174463,0.0000788917,0.00038540465,0.00029711713,0.072895885,0.8296646,0.00081063487,0.020958483,0.029083325,0.00032535242],"about_ca_topic_score_codex":0.000008477923,"about_ca_topic_score_gemma":0.000019922036,"teacher_disagreement_score":0.55811214,"about_ca_system_score_codex":0.0012594844,"about_ca_system_score_gemma":0.004821962,"threshold_uncertainty_score":0.9993876},"labels":[],"label_agreement":null},{"id":"W1502535914","doi":"","title":"A Place of Transition: Directors’ Experiences of Providing Counseling and Advising to Distance Students","year":2005,"lang":"en","type":"article","venue":"International journal of e-learning & distance education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"MacEwan University","funders":"","keywords":"Distance education; Sociology; Humanities; Library science; Thematic analysis; Political science; Psychology; Qualitative research; Pedagogy; Art; Social science; Computer science","score_opus":0.04353161825189057,"score_gpt":0.4623236652620743,"score_spread":0.41879204701018374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1502535914","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9466851,0.00064178795,0.049617767,0.0015254457,0.0010208562,0.00010054541,0.0000027028743,0.0000046692844,0.0004011756],"genre_scores_gemma":[0.9951799,0.000100965524,0.0039395997,0.00010928842,0.0003021722,0.000008101444,0.0000024448489,0.0000064333685,0.0003510988],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.996281,0.00014937377,0.0010309999,0.00018346774,0.00225258,0.00010252222],"domain_scores_gemma":[0.9962831,0.00042214373,0.0011793323,0.0001065086,0.0019228498,0.00008606347],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002546231,0.000098964076,0.00023352363,0.00033802039,0.000084628286,0.00016784838,0.0005381295,0.000029694176,0.00019746416],"category_scores_gemma":[0.0010946912,0.00008272214,0.00007267582,0.00033331668,0.00006853219,0.0008755651,0.000028181646,0.00014198439,0.0000036704273],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011744435,0.0010915681,0.17325099,0.000059766553,0.00016888104,0.000003038708,0.508682,0.057115003,0.009886729,0.0054651257,0.001544206,0.24155825],"study_design_scores_gemma":[0.00296651,0.0011764845,0.14143334,0.004197781,0.00011048524,0.0001251823,0.6336337,0.022488942,0.019823296,0.0018201319,0.1714381,0.0007860436],"about_ca_topic_score_codex":0.000007809828,"about_ca_topic_score_gemma":0.000020107807,"teacher_disagreement_score":0.24077222,"about_ca_system_score_codex":0.00015492001,"about_ca_system_score_gemma":0.0003966101,"threshold_uncertainty_score":0.3373311},"labels":[],"label_agreement":null},{"id":"W1505207325","doi":"10.1002/ev.20084","title":"Credible Judgment: Combining Truth, Beauty, and Justice","year":2014,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Beauty; Argumentation theory; Economic Justice; Process (computing); Variety (cybernetics); Psychology; Social psychology; Public relations; Computer science; Law; Epistemology; Political science","score_opus":0.26060324573329097,"score_gpt":0.5132600924299058,"score_spread":0.2526568466966148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1505207325","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47108805,0.00071911485,0.3404806,0.010098822,0.011750565,0.0027786626,0.000027558683,0.000332174,0.16272445],"genre_scores_gemma":[0.988413,0.000043686363,0.0063800495,0.00037147166,0.0005321868,0.00017906392,0.000039729774,0.000013870568,0.00402695],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970622,0.00029614975,0.00049408665,0.00040511513,0.0015341006,0.00020836607],"domain_scores_gemma":[0.99659854,0.0019337749,0.0002322284,0.00034438472,0.0007485913,0.00014248508],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010944479,0.00011803131,0.00017863416,0.00032158155,0.00060951966,0.00030623333,0.0001708434,0.000068133595,0.0010581542],"category_scores_gemma":[0.00657607,0.0001013275,0.00006794571,0.00056416105,0.000037413196,0.0005508513,0.000038724298,0.00008280047,0.00015879556],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047694608,0.00007613646,0.0021284295,0.000013802403,0.000024608134,2.421048e-8,0.0010367356,0.005211268,0.00046721907,0.040553324,0.027216794,0.923224],"study_design_scores_gemma":[0.002476879,0.0002445968,0.018574277,0.000018653769,0.00025292544,0.0000040269274,0.0006525713,0.6494474,0.00065611524,0.08997813,0.23752828,0.0001661949],"about_ca_topic_score_codex":0.000043993452,"about_ca_topic_score_gemma":0.00011397061,"teacher_disagreement_score":0.9230578,"about_ca_system_score_codex":0.00013231748,"about_ca_system_score_gemma":0.0002699592,"threshold_uncertainty_score":0.99985504},"labels":[],"label_agreement":null},{"id":"W1505733966","doi":"10.1108/qrj-11-2013-0069","title":"Policy archaeology: digging into special education policy in Ontario, 1965-1978","year":2015,"lang":"en","type":"article","venue":"Qualitative Research Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Emmanuel Bible College","funders":"","keywords":"Context (archaeology); Situated; Narrative; Originality; Metaphor; Sociology; Disability studies; Stakeholder; Interpretation (philosophy); Special education; Value (mathematics); Inclusion (mineral); Discourse analysis; Social science; Epistemology; Pedagogy; Linguistics; Archaeology; Law; History; Political science; Gender studies; Qualitative research","score_opus":0.5984695695505742,"score_gpt":0.6960827621453781,"score_spread":0.09761319259480394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1505733966","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7692556,0.00015781875,0.0014245327,0.07837441,0.0008696516,0.0004002507,0.0000035880635,0.000011915157,0.14950226],"genre_scores_gemma":[0.9682542,0.00006963339,0.004943052,0.0006915851,0.005814605,0.0000424604,0.000007368407,0.000012641241,0.020164438],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98451483,0.008031417,0.001083051,0.00039176087,0.0052142767,0.0007646399],"domain_scores_gemma":[0.9922346,0.0032135902,0.00033464754,0.00038785834,0.0030974708,0.0007318631],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.06891281,0.00015585957,0.00032784112,0.0045039034,0.0004030052,0.00049239484,0.0009758364,0.00009310859,0.0017447156],"category_scores_gemma":[0.030176021,0.00011770745,0.000098835786,0.002972423,0.00062871294,0.001132878,0.0003154848,0.0016626229,0.0009930221],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021008874,0.00019263437,0.045679826,0.000004021415,0.000017384322,0.000013784593,0.58003855,0.00013204354,0.000055033288,0.21408859,0.0198571,0.13971092],"study_design_scores_gemma":[0.00069034914,0.0003072235,0.033120357,0.000040195562,9.829124e-7,0.00003806743,0.14519563,0.0001299026,0.000025534544,0.66507185,0.1552684,0.00011151054],"about_ca_topic_score_codex":0.07269622,"about_ca_topic_score_gemma":0.16516453,"teacher_disagreement_score":0.45098326,"about_ca_system_score_codex":0.003416797,"about_ca_system_score_gemma":0.035493627,"threshold_uncertainty_score":0.9997848},"labels":[],"label_agreement":null},{"id":"W1506594705","doi":"10.3138/cjpe.0028.003","title":"Introduction to Professionalizing Evaluation: A Global Perspective on Evaluator Competencies","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Perspective (graphical); Psychology; Sociology; Pedagogy; Knowledge management; Computer science; Artificial intelligence","score_opus":0.26065355762357273,"score_gpt":0.5437613801430642,"score_spread":0.28310782251949146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1506594705","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82943976,0.00063550955,0.0062538562,0.11480531,0.009398197,0.006551008,0.000025088515,0.000050906612,0.032840375],"genre_scores_gemma":[0.99011713,0.000001619837,0.0060318424,0.001099587,0.0023049777,0.00023156502,0.000014960596,0.000012905387,0.00018541994],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9885592,0.0025102177,0.0011632051,0.00049473473,0.0068667596,0.00040591945],"domain_scores_gemma":[0.9822205,0.00034558133,0.0008504243,0.00053579477,0.015265293,0.0007824491],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.046336632,0.00021927194,0.0003650954,0.00085105485,0.00048745642,0.0005200027,0.0006269352,0.00010645261,0.0055493354],"category_scores_gemma":[0.022129538,0.00016803588,0.00018092348,0.0017106251,0.00010542567,0.0007015944,0.000024497795,0.0002757392,0.0005686378],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000098235614,0.00010424194,0.0065263347,0.0000039875863,0.000051114548,0.0000012874799,0.0022933409,0.025187591,0.00007105719,0.02251467,0.037663065,0.9054851],"study_design_scores_gemma":[0.0034216421,0.004145266,0.2093225,0.00021000231,0.00039618183,0.00010756963,0.01480557,0.29891855,0.00021001066,0.118458845,0.34941664,0.0005872393],"about_ca_topic_score_codex":0.00038356776,"about_ca_topic_score_gemma":0.010318208,"teacher_disagreement_score":0.9048978,"about_ca_system_score_codex":0.003893956,"about_ca_system_score_gemma":0.008777533,"threshold_uncertainty_score":0.9999299},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"grok","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W1506735731","doi":"10.22329/celt.v4i0.3267","title":"5. Strategies for Evaluating Undergraduate Degree Programs","year":2011,"lang":"en","type":"article","venue":"Collected Essays on Learning and Teaching","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Task (project management); Degree (music); Higher education; Degree program; Management science; Evaluation methods; Work (physics); Computer science; Program evaluation; Mathematics education; Psychology; Medical education; Engineering; Political science; Systems engineering","score_opus":0.39559990537809536,"score_gpt":0.4879763027374061,"score_spread":0.09237639735931075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1506735731","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6481081,0.000059955728,0.040235437,0.0004379818,0.00024761667,0.0005730877,0.0000014618713,0.00021697811,0.31011933],"genre_scores_gemma":[0.98088604,0.000006867431,0.011638659,0.0000832757,0.000050412986,0.00010001138,0.000009302995,0.00001936942,0.007206044],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99713945,0.0007420327,0.0004687624,0.00047134663,0.0008531251,0.00032528493],"domain_scores_gemma":[0.9977636,0.0013195277,0.00029107986,0.00021265585,0.00031021316,0.000102977356],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.006732405,0.000179609,0.00024826388,0.00026645773,0.0013765984,0.00060764316,0.00024716492,0.00007796537,0.00016492406],"category_scores_gemma":[0.00276735,0.00013431307,0.00007779371,0.0002911444,0.00006261679,0.0003607476,0.000056312965,0.00050711236,0.000040419287],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023480403,0.00016793939,0.029170347,0.000022942462,0.00005368211,0.000002120453,0.011616286,0.0010327109,0.00042850716,0.13284832,0.000896323,0.823526],"study_design_scores_gemma":[0.0042606303,0.00613413,0.035192035,0.00032716425,0.00011462185,0.000024161063,0.05743472,0.6145498,0.00025247945,0.25632378,0.024377981,0.001008464],"about_ca_topic_score_codex":0.00004616781,"about_ca_topic_score_gemma":0.00007965513,"teacher_disagreement_score":0.8225176,"about_ca_system_score_codex":0.000044243563,"about_ca_system_score_gemma":0.00028171996,"threshold_uncertainty_score":0.99992347},"labels":[],"label_agreement":null},{"id":"W1507117314","doi":"10.7202/1027404ar","title":"La politique québécoise d’évaluation des apprentissages et les pratiques évaluatives","year":2014,"lang":"fr","type":"article","venue":"Éducation et francophonie","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Political science; Humanities; Art","score_opus":0.1173704954732764,"score_gpt":0.4570104043246684,"score_spread":0.339639908851392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1507117314","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43990475,0.0053316257,0.1125312,0.06289746,0.0060287593,0.0010869971,0.000070353795,0.00020000833,0.37194887],"genre_scores_gemma":[0.93333703,0.0042836736,0.012039319,0.002335489,0.00048128696,0.00026339848,0.00012164946,0.000054481305,0.047083657],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9849356,0.010314821,0.0012802196,0.000866661,0.002067089,0.00053559954],"domain_scores_gemma":[0.99132496,0.005198369,0.0007878051,0.00087079575,0.001552894,0.00026516413],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.025173003,0.00047121194,0.0005185828,0.00048950623,0.00056550023,0.0008948199,0.00061289116,0.00044822757,0.01025795],"category_scores_gemma":[0.006459606,0.00043450738,0.00022981275,0.001050075,0.0007163538,0.0022725738,0.00011299857,0.0006653901,0.001592039],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030338228,0.0006122922,0.007910293,0.0001441038,0.000053385935,9.0619693e-7,0.09443115,0.002469133,0.00045424435,0.17797136,0.013753486,0.7021693],"study_design_scores_gemma":[0.0010094746,0.0003226891,0.3054471,0.00050371094,0.00007556388,0.000023972407,0.015799413,0.023599844,0.0017235469,0.12402209,0.52686626,0.0006063254],"about_ca_topic_score_codex":0.003662576,"about_ca_topic_score_gemma":0.012677215,"teacher_disagreement_score":0.701563,"about_ca_system_score_codex":0.00033788342,"about_ca_system_score_gemma":0.004075331,"threshold_uncertainty_score":0.9998107},"labels":[],"label_agreement":null},{"id":"W1508087803","doi":"10.55016/ojs/ajer.v54i1.55207","title":"Bridging the Research-Practice Gap: Research Translation and/or Research Transformation","year":2008,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Association for Research in Science Teaching; American Educational Research Association","keywords":"Bridging (networking); Transformation (genetics); Educational research; Psychology; Translation (biology); Mathematics education; Sociology; Computer science","score_opus":0.823437872868779,"score_gpt":0.677159060712461,"score_spread":0.146278812156318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1508087803","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47239968,0.0019170281,0.00009867228,0.36441877,0.00037831086,0.0009115137,0.000003987348,0.0000014462131,0.1598706],"genre_scores_gemma":[0.95598197,0.003858431,0.0005167311,0.00017195776,0.0011715618,0.00008492312,0.0000071368254,0.0000236623,0.038183626],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.95609075,0.017857209,0.001761515,0.00056107406,0.022419117,0.0013103131],"domain_scores_gemma":[0.7287785,0.24807532,0.00024925036,0.00067052525,0.021807207,0.0004191872],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.20352308,0.00015880186,0.0003096362,0.004011332,0.0052450956,0.0009935022,0.0020359503,0.00016243786,0.010903498],"category_scores_gemma":[0.17413205,0.000093899645,0.00012924329,0.0077675893,0.0023346883,0.0033572372,0.00021336458,0.0043519945,0.0016760753],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0047222176,0.001950377,0.015059287,0.00010354673,0.00017860258,0.000023723778,0.11093478,0.00056172424,0.003361193,0.13813812,0.5433824,0.18158405],"study_design_scores_gemma":[0.0017825644,0.0019578799,0.037812367,0.00030002338,0.000019060899,0.0016681233,0.054326784,0.009302875,0.00091622403,0.034812067,0.85681635,0.00028568614],"about_ca_topic_score_codex":0.0014509143,"about_ca_topic_score_gemma":0.0017570342,"teacher_disagreement_score":0.4835823,"about_ca_system_score_codex":0.0005621784,"about_ca_system_score_gemma":0.008550436,"threshold_uncertainty_score":0.9991012},"labels":[],"label_agreement":null},{"id":"W1512592001","doi":"","title":"A framework for demonstrating the value of human services","year":2012,"lang":"es","type":"article","venue":"Americanae (AECID Library)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Variety (cybernetics); Psychological intervention; Agency (philosophy); Value (mathematics); Work (physics); Public relations; Knowledge management; Psychology; Business; Medical education; Nursing; Medicine; Computer science; Political science; Sociology; Engineering","score_opus":0.08369528033706207,"score_gpt":0.4437884945063389,"score_spread":0.3600932141692768,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1512592001","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97128534,0.0014301899,0.0057704453,0.009948298,0.0007912379,0.0007594219,0.000079177036,0.0000581844,0.009877718],"genre_scores_gemma":[0.9642528,0.00014785917,0.029793771,0.0044687283,0.0006642207,0.00007751644,0.00002024597,0.00003813175,0.0005367054],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99631375,0.0004264281,0.0010510936,0.00038065366,0.0012216185,0.00060644484],"domain_scores_gemma":[0.9945436,0.0030212398,0.0011738818,0.0009020334,0.00013038938,0.00022882217],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0018209866,0.00028512414,0.0005136005,0.00019630964,0.0005784707,0.00023191907,0.0013611442,0.0001283494,0.0030526966],"category_scores_gemma":[0.0002590825,0.00018372177,0.00028703336,0.0013420193,0.00046199892,0.0022133049,0.0002553889,0.0002760769,0.00012741526],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021332691,0.00012384559,0.6795282,0.000057174133,0.00007175189,2.1609318e-7,0.0020113424,0.00006644614,0.0002383348,0.27906856,0.0027417939,0.036071006],"study_design_scores_gemma":[0.0003785234,0.0005690679,0.9243627,0.0002796629,0.00013506203,0.000002465027,0.011525518,0.007016267,0.0035426952,0.01993769,0.031831354,0.0004189635],"about_ca_topic_score_codex":0.001408174,"about_ca_topic_score_gemma":0.000006576857,"teacher_disagreement_score":0.25913087,"about_ca_system_score_codex":0.000019315035,"about_ca_system_score_gemma":0.00029626398,"threshold_uncertainty_score":0.99785864},"labels":[],"label_agreement":null},{"id":"W1514004023","doi":"10.3138/cjpe.025.006","title":"An Alternative to the Traditional Literature Review","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Alberta Health Services","funders":"","keywords":"Disk formatting; Process (computing); Information needs; Work (physics); Computer science; Process management; Outcome (game theory); Risk analysis (engineering); Knowledge management; Management science; Business; World Wide Web; Engineering; Economics","score_opus":0.4147867432021777,"score_gpt":0.5561090360664662,"score_spread":0.14132229286428855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1514004023","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6817788,0.017477175,0.0045924615,0.25378057,0.015407288,0.009382184,0.00020432363,0.000034293244,0.01734295],"genre_scores_gemma":[0.98912746,0.00015710876,0.0044206227,0.004960286,0.0010529949,0.00011789927,0.00003693544,0.000007559005,0.00011913254],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99621165,0.0005451065,0.00062965875,0.0001615148,0.0022777144,0.00017435678],"domain_scores_gemma":[0.99434376,0.00017877214,0.0004110885,0.00036366846,0.004126364,0.0005763293],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.019197132,0.00009187188,0.00015506925,0.00035304506,0.0002388567,0.0006036566,0.0007974832,0.000047794707,0.004248781],"category_scores_gemma":[0.0033017008,0.000052070296,0.000103408864,0.0009291824,0.000055400822,0.00077420275,0.0000052874607,0.0004082433,0.00013253636],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005488483,0.0000330403,0.0011698585,0.000006291658,0.000012499586,0.000005708258,0.0013640013,0.00065200066,0.00006444093,0.0026796716,0.034010712,0.9599963],"study_design_scores_gemma":[0.00053896604,0.00095202593,0.086873494,0.0006139081,0.000101839956,0.00030561793,0.00040949686,0.02981995,0.000085603504,0.02678906,0.853308,0.00020199682],"about_ca_topic_score_codex":0.000066651606,"about_ca_topic_score_gemma":0.019739572,"teacher_disagreement_score":0.9597943,"about_ca_system_score_codex":0.00009996898,"about_ca_system_score_gemma":0.002920967,"threshold_uncertainty_score":0.9981476},"labels":[],"label_agreement":null},{"id":"W1515606774","doi":"10.1002/9781118591444.app7","title":"Appendix G: About the Author","year":2001,"lang":"en","type":"other","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Citation; Appendix; Class (philosophy); Library science; Computer science; Artificial intelligence; Geology","score_opus":0.26709574592221647,"score_gpt":0.5280573401534066,"score_spread":0.2609615942311901,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1515606774","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000005668832,0.00033323967,0.0048830356,0.0042537353,0.0010227582,0.0002565929,0.000010781695,0.00009808518,0.9891361],"genre_scores_gemma":[0.00023330259,0.0001280394,0.00057129574,0.0016976623,0.00046405155,0.00001981181,0.000014688175,0.00007863527,0.9967925],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969918,0.00015876445,0.00037026964,0.00032334626,0.0019729738,0.00018280919],"domain_scores_gemma":[0.99837846,0.000285174,0.0002769867,0.0009225217,0.00007513922,0.00006173987],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0029449128,0.00015080487,0.00020811665,0.00024263545,0.000100379664,0.00028023822,0.001027365,0.00014532491,0.72278047],"category_scores_gemma":[0.00021947075,0.00006493533,0.0001036491,0.00045302275,0.00007166581,0.000055182227,0.000094854935,0.00016553169,0.09752927],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.892583e-7,0.000008452797,0.00060646934,8.496674e-7,0.000008538112,7.585246e-7,0.000045349523,0.000004298653,3.9304174e-7,0.0056576105,0.9303204,0.06334619],"study_design_scores_gemma":[0.0000915828,0.00001207137,0.0005582912,0.000014043216,0.0000071410955,0.0000030834722,0.00035127095,0.0005831464,0.0000024455544,0.0016243305,0.9966446,0.00010794813],"about_ca_topic_score_codex":0.00022542375,"about_ca_topic_score_gemma":0.001266301,"teacher_disagreement_score":0.6252512,"about_ca_system_score_codex":0.00001773185,"about_ca_system_score_gemma":0.00013961033,"threshold_uncertainty_score":0.9031734},"labels":[],"label_agreement":null},{"id":"W1515861994","doi":"10.21225/d5kp4s","title":"A Critical Appraisal Model of Program Evaluation in Adult Continuing Education","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of University Continuing Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Continuing education; Context (archaeology); Adult education; Process (computing); Medical education; Pedagogy; Articulation (sociology); Higher education; Critical appraisal; Psychology; Engineering ethics; Sociology; Political science; Computer science; Engineering; Medicine","score_opus":0.07498756545546002,"score_gpt":0.4305564587242842,"score_spread":0.3555688932688242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1515861994","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9870503,0.00010055536,0.00039524172,0.0014833973,0.0008262923,0.0003004426,0.0000054446355,0.0000042502356,0.009834068],"genre_scores_gemma":[0.9948611,0.000019124775,0.0038278974,0.00006701521,0.00009655445,0.000002601728,0.0000072806606,0.0000052616165,0.0011131592],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99782616,0.0004013893,0.0006082937,0.00017680199,0.0007946286,0.00019275001],"domain_scores_gemma":[0.99494475,0.0004557541,0.00039207964,0.0002055861,0.0037025108,0.00029932227],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036342805,0.000092095885,0.00021765333,0.0010010315,0.000073092466,0.00012057431,0.00038231298,0.000080104226,0.00082556333],"category_scores_gemma":[0.004267795,0.00009512567,0.000090497524,0.000690816,0.00010268193,0.001077068,0.0000065272006,0.00019249815,0.0000129413775],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037686517,0.00013256294,0.0152834505,0.000006067797,0.000003945241,7.973098e-7,0.0074713374,0.0027717508,0.0000822601,0.001883646,0.0013895613,0.97093695],"study_design_scores_gemma":[0.0035585773,0.0006187596,0.2941934,0.0022361374,0.00031537501,0.00008366356,0.16864204,0.4649818,0.0003430891,0.0093674585,0.05490275,0.00075694517],"about_ca_topic_score_codex":0.0012983186,"about_ca_topic_score_gemma":0.009550375,"teacher_disagreement_score":0.97018,"about_ca_system_score_codex":0.00041547508,"about_ca_system_score_gemma":0.0068568187,"threshold_uncertainty_score":0.9987734},"labels":[],"label_agreement":null},{"id":"W1517481237","doi":"","title":"Participatory action research and evaluation: creating change on the Yukon flats","year":2000,"lang":"en","type":"article","venue":"School for International Training Digital Collections (School for International Training)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Action (physics); Participatory action research; Citizen journalism; Climate change; Geography; Environmental resource management; Environmental planning; Political science; Sociology; Environmental science; Geology; Oceanography; Anthropology; Law","score_opus":0.8132413430627892,"score_gpt":0.59942367911456,"score_spread":0.2138176639482292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1517481237","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5358336,0.00008295745,0.0022481133,0.023475267,0.009416123,0.0053762677,0.0014666448,0.00024509116,0.42185593],"genre_scores_gemma":[0.9322532,0.00003500221,0.0008982396,0.0010163529,0.0033775335,0.0046565905,0.0003086169,0.00005116704,0.057403304],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99272054,0.00028994808,0.001249842,0.0010032246,0.004112262,0.0006241863],"domain_scores_gemma":[0.98751605,0.005429618,0.00038660972,0.00047372625,0.005841557,0.00035242125],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011689567,0.00034610738,0.00033336962,0.0011965343,0.0021394817,0.0031459047,0.0011134694,0.00017055756,0.009429987],"category_scores_gemma":[0.026606498,0.00027388378,0.00030807994,0.0012385623,0.00029005032,0.0022936822,0.000094224386,0.0005980022,0.00036532723],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0034686266,0.00093639176,0.007433276,0.000026490294,0.0012465178,0.0000037091302,0.015704019,0.0074905884,0.00017985323,0.068334796,0.19402549,0.70115024],"study_design_scores_gemma":[0.004178223,0.0014140707,0.0141308,0.00025030723,0.00006292745,0.000045882913,0.020430766,0.2445277,0.00019766933,0.12548923,0.588632,0.0006404277],"about_ca_topic_score_codex":0.00002126553,"about_ca_topic_score_gemma":0.000077684264,"teacher_disagreement_score":0.7005098,"about_ca_system_score_codex":0.0007654441,"about_ca_system_score_gemma":0.00084995735,"threshold_uncertainty_score":0.99997133},"labels":[],"label_agreement":null},{"id":"W1517551366","doi":"10.3138/cjpe.028.005","title":"Learning Circles for Advanced Professional Development in Evaluation","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Public Health Agency of Canada; Health Canada","funders":"","keywords":"Professional development; Context (archaeology); Process (computing); Quality (philosophy); Psychology; Professional learning community; Collaborative learning; Knowledge management; Medical education; Pedagogy; Computer science; Medicine","score_opus":0.36610878492078347,"score_gpt":0.5580433458244787,"score_spread":0.1919345609036952,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1517551366","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.991002,0.00029327843,0.0008963874,0.0018455794,0.0013112174,0.003793273,0.0000010278667,0.000006746619,0.0008504765],"genre_scores_gemma":[0.9862302,0.0000028199283,0.011879522,0.000103235296,0.00009854919,0.0012465403,0.00003083081,0.000010365897,0.00039792494],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9947668,0.00073370873,0.0012239476,0.0002278046,0.00272247,0.00032527602],"domain_scores_gemma":[0.9918566,0.0004033296,0.0007874163,0.00015325107,0.0064859483,0.0003134755],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02674914,0.00012008246,0.00022637114,0.00090876664,0.00027293336,0.00030257722,0.00033372745,0.0000856285,0.003300318],"category_scores_gemma":[0.007047738,0.00009623528,0.00008339116,0.0006366906,0.00004264221,0.0010634463,0.000010777642,0.00022766678,0.00010560339],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012406359,0.000040500996,0.028110398,0.000004534222,0.000009305485,3.2094002e-7,0.0017774027,0.013257513,0.00014000024,0.000067480316,0.0009935666,0.95558655],"study_design_scores_gemma":[0.003122929,0.0005185013,0.57187057,0.00015076082,0.000038829374,0.000009874915,0.00458243,0.34150413,0.00035628682,0.015344328,0.06227862,0.00022273372],"about_ca_topic_score_codex":0.00014051682,"about_ca_topic_score_gemma":0.010273616,"teacher_disagreement_score":0.9553638,"about_ca_system_score_codex":0.00084200915,"about_ca_system_score_gemma":0.010480989,"threshold_uncertainty_score":0.9976108},"labels":[],"label_agreement":null},{"id":"W1518519527","doi":"","title":"Developing a Metric for Evaluating Discussion Boards","year":2004,"lang":"en","type":"article","venue":"E-Learn: World Conference on E-Learning in Corporate, Government, Healthcare, and Higher Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Metric (unit); Metric system; Computer science; Mathematics; Operations management; Engineering","score_opus":0.35801699001939424,"score_gpt":0.4858802187922993,"score_spread":0.12786322877290507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1518519527","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6003296,0.0010657439,0.011266664,0.3093462,0.0069758394,0.00443707,0.000045819917,0.00031870118,0.066214405],"genre_scores_gemma":[0.9479689,0.00023394848,0.007428496,0.0021804636,0.00022653253,0.0003448336,0.000045844572,0.000035065437,0.04153594],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99409,0.00060971937,0.0011641956,0.0010130892,0.00255715,0.00056585023],"domain_scores_gemma":[0.9964763,0.00062219176,0.0014565533,0.00046000304,0.0007108376,0.0002741181],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.005308363,0.00035860308,0.0004982062,0.0006513028,0.0006787808,0.00057475036,0.00043336596,0.000148975,0.0006955989],"category_scores_gemma":[0.0010515115,0.0002659854,0.000086611406,0.0021008223,0.00008608068,0.00061805965,0.000110453155,0.00064567116,0.0001320468],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032886435,0.00033402618,0.11959533,0.00013695493,0.00002033738,0.0000014551537,0.0017184861,0.0017464621,0.00019542366,0.4756524,0.000988591,0.39928168],"study_design_scores_gemma":[0.0028654276,0.0014289606,0.68743616,0.001049318,0.000032438067,0.000005081988,0.0071911,0.004878742,0.00023984487,0.20058192,0.093400925,0.0008900954],"about_ca_topic_score_codex":0.000279717,"about_ca_topic_score_gemma":0.0008462815,"teacher_disagreement_score":0.5678408,"about_ca_system_score_codex":0.0014334528,"about_ca_system_score_gemma":0.0032226613,"threshold_uncertainty_score":0.99997926},"labels":[],"label_agreement":null},{"id":"W1520883134","doi":"","title":"Constructing Paradigm Change in Early Childhood Education: Rational and Cultural Influences on Policy Change","year":2011,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Veto; Underpinning; Positive economics; Politics; Public policy; Political science; Policy studies; Sociology; Political economy; Epistemology; Economics; Law","score_opus":0.1463253275193433,"score_gpt":0.4380230799957563,"score_spread":0.291697752476413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1520883134","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9890216,0.0008643785,0.000025919864,0.005035737,0.0002742354,0.000213943,0.0000021855967,0.000009445902,0.004552573],"genre_scores_gemma":[0.9965848,0.0010282716,0.00012346735,0.0009721528,0.0010727093,0.00004209374,0.0000025377035,0.0000058826845,0.00016810554],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99754727,0.00017851833,0.0004511692,0.00023636344,0.00077982974,0.0008068366],"domain_scores_gemma":[0.9992103,0.000100330675,0.0002968839,0.00013537357,0.00015820883,0.0000988987],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030379028,0.0001313486,0.00016265214,0.0004719908,0.00023759097,0.00019409542,0.00029532606,0.00005615808,0.00020986104],"category_scores_gemma":[0.0002628251,0.00009281937,0.00004726488,0.00055060664,0.000083161605,0.0013590846,0.000031804077,0.0007330595,0.000066843044],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015184172,0.00004726817,0.28776997,5.4484923e-7,0.000010770027,3.9319858e-7,0.0114095695,6.382154e-7,0.00000228713,0.3626095,0.0000081957905,0.33812568],"study_design_scores_gemma":[0.00040544034,0.00025792836,0.75155306,0.00002705758,0.000004258223,0.00021063945,0.009915982,0.000054298096,0.000013811977,0.23709509,0.000348884,0.00011355011],"about_ca_topic_score_codex":0.00054408977,"about_ca_topic_score_gemma":0.0020740791,"teacher_disagreement_score":0.4637831,"about_ca_system_score_codex":0.00041117432,"about_ca_system_score_gemma":0.0030177385,"threshold_uncertainty_score":0.5353339},"labels":[],"label_agreement":null},{"id":"W1523394866","doi":"10.1002/9781444325027.app3","title":"Appendix 3: Critical Appraisal","year":2010,"lang":"en","type":"other","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; University of Toronto","funders":"","keywords":"Critical appraisal; Appendix; Computer science; Geology; Medicine; Paleontology","score_opus":0.17333146054954035,"score_gpt":0.5623880453898987,"score_spread":0.3890565848403584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1523394866","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000054810016,0.000053535783,0.006822137,0.0019886463,0.0047910144,0.000101622994,0.000021936972,0.00014643779,0.9860692],"genre_scores_gemma":[0.00086708355,0.000011467017,0.0065475083,0.0005522284,0.0008284292,0.000012776653,0.000024128412,0.000113260176,0.9910431],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967921,0.000094992254,0.0003762685,0.00043342463,0.0020927282,0.00021053261],"domain_scores_gemma":[0.997054,0.0017712308,0.00012652605,0.00078535936,0.00012042283,0.00014249183],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0018579053,0.00016617043,0.00027370919,0.0003797423,0.000050250474,0.00024914206,0.0007110759,0.00034865268,0.7539479],"category_scores_gemma":[0.0035944209,0.00010399748,0.000099820296,0.00023176301,0.00013865657,0.00008746821,0.00010798393,0.00035624573,0.10649964],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011676842,0.00002233759,0.00020034167,0.000002695132,0.000004117207,0.0000013114837,0.00001736164,1.7110743e-7,0.000007887486,0.035798654,0.94079614,0.023147821],"study_design_scores_gemma":[0.00010376007,0.000018780967,0.0001185023,0.000009942988,0.000006240267,0.0000040242803,0.00008819459,0.00038562046,0.000013477946,0.0019623511,0.99713373,0.00015539097],"about_ca_topic_score_codex":0.000049806025,"about_ca_topic_score_gemma":0.0007595321,"teacher_disagreement_score":0.64744824,"about_ca_system_score_codex":0.0000069924695,"about_ca_system_score_gemma":0.0001864176,"threshold_uncertainty_score":0.89419603},"labels":[],"label_agreement":null},{"id":"W1524663891","doi":"","title":"Evaluation in a nutshell: a practical guide to the evaluation of health promotion programs","year":2013,"lang":"en","type":"book","venue":"ePrints Soton (University of Southampton)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":244,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Health promotion; Public relations; Promotion (chess); Accountability; Medical education; Computer science; Political science; Public health; Management science; Medicine; Engineering; Nursing","score_opus":0.3758254524828953,"score_gpt":0.49534675205837,"score_spread":0.1195212995754747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1524663891","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32592165,0.00037779845,0.047447667,0.04816596,0.0017392368,0.033927675,0.00011560099,0.000114045215,0.5421904],"genre_scores_gemma":[0.59616995,0.00010094013,0.009828543,0.00021624958,0.00015011776,0.00010070232,0.00032886662,0.000051643292,0.393053],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9854851,0.0027210603,0.0011741411,0.0007817469,0.009519723,0.00031825984],"domain_scores_gemma":[0.9916914,0.0003663488,0.0019074429,0.0011109525,0.0047874856,0.00013637745],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.059132814,0.00024560417,0.0006432126,0.00073208153,0.00019119019,0.000088982866,0.0009038294,0.00025381823,0.009877515],"category_scores_gemma":[0.0021859787,0.00020808882,0.00021694982,0.00073589094,0.00016710006,0.00069024134,0.00034167574,0.0004101628,0.0013586397],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006673646,0.00060642423,0.0029773996,0.000069404414,0.00009946992,8.1989344e-7,0.01626113,0.0023889893,0.000017234657,0.0018384627,0.033597674,0.94207627],"study_design_scores_gemma":[0.007316909,0.0020074742,0.14655735,0.002095594,0.00087660475,0.000013957051,0.043523204,0.31862646,0.000059299782,0.079265565,0.3984602,0.0011973653],"about_ca_topic_score_codex":0.0007937238,"about_ca_topic_score_gemma":0.0027209977,"teacher_disagreement_score":0.94087887,"about_ca_system_score_codex":0.0016345992,"about_ca_system_score_gemma":0.006782887,"threshold_uncertainty_score":0.9994189},"labels":[],"label_agreement":null},{"id":"W1527922208","doi":"10.1177/160940690800700104","title":"Expanding the Action Project Method to Encompass Comparative Analyses","year":2008,"lang":"en","type":"article","venue":"International Journal of Qualitative Methods","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Trinity Western University; Western University","funders":"","keywords":"Computer science; Qualitative comparative analysis; Action (physics); Management science; Set (abstract data type); Pragmatics; Action research; Qualitative research; Qualitative analysis; Sociology; Psychology; Mathematics education; Engineering; Linguistics; Social science","score_opus":0.973177451360447,"score_gpt":0.8415088220797372,"score_spread":0.13166862928070977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1527922208","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10048698,0.000084098836,0.88901836,0.0056321975,0.0012940704,0.00015796113,0.0000083323275,0.0000067962956,0.0033112087],"genre_scores_gemma":[0.42163405,0.000020997912,0.57641953,0.00075681304,0.0003297507,0.000012927236,0.0000012984434,0.000005022462,0.0008196146],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.98073524,0.014218093,0.0014437382,0.0002360917,0.0032061818,0.00016063842],"domain_scores_gemma":[0.97936296,0.0150799025,0.0013391174,0.00020192708,0.0039223703,0.0000937244],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.045291618,0.0001492274,0.00045066638,0.00091147353,0.00024504546,0.00018246594,0.0011707122,0.00003582575,0.0005173077],"category_scores_gemma":[0.0052097905,0.00007937074,0.00028907726,0.000976684,0.00012988552,0.00077554624,0.00010589209,0.00031009052,0.000060532642],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010083509,0.00029449706,0.0017565577,0.0000034698587,0.0012147453,0.00003133444,0.6424018,0.015987787,0.057726268,0.0069593526,0.035807125,0.23680869],"study_design_scores_gemma":[0.002086489,0.0011506982,0.03788087,0.00011380958,0.0001183093,0.00075348123,0.5226635,0.014359023,0.17393774,0.063470624,0.18292685,0.0005386153],"about_ca_topic_score_codex":0.00005132138,"about_ca_topic_score_gemma":0.000014552334,"teacher_disagreement_score":0.32114705,"about_ca_system_score_codex":0.00021095284,"about_ca_system_score_gemma":0.00041019917,"threshold_uncertainty_score":0.9830732},"labels":[],"label_agreement":null},{"id":"W153207139","doi":"10.18584/iipj.2013.4.3.2","title":"Policy Research: Good or Bad?","year":2013,"lang":"en","type":"article","venue":"International Indigenous Policy Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Western University","funders":"","keywords":"Indigenous; Process (computing); Public relations; Sight; Political science; Sociology; Computer science","score_opus":0.46241718618711397,"score_gpt":0.6198377549037174,"score_spread":0.15742056871660343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W153207139","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54813087,0.00006339546,0.0008922021,0.113981254,0.0016375759,0.0005872145,0.000043542314,0.000054436096,0.3346095],"genre_scores_gemma":[0.9150959,0.00021188153,0.0008216748,0.003243508,0.007659941,0.000038879305,0.0000057376833,0.000021701455,0.072900735],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9917733,0.0005655269,0.0010916793,0.0003262724,0.005479143,0.00076407136],"domain_scores_gemma":[0.9933005,0.0014833619,0.00045729298,0.000464968,0.0038055633,0.00048830267],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0077528628,0.00017694874,0.00022834935,0.0032528574,0.0009996475,0.002406709,0.0023258035,0.00011237764,0.022132905],"category_scores_gemma":[0.007675552,0.00011230089,0.00016652366,0.0017268539,0.00017538757,0.001477834,0.00027333573,0.0008119395,0.011034449],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017141964,0.0005363812,0.046426512,0.0000044120784,0.00029934084,0.00010406253,0.027054677,0.0008412196,0.0015274058,0.12643169,0.14917578,0.6474271],"study_design_scores_gemma":[0.0010618473,0.00043693822,0.105353706,0.000036265497,0.0000044972526,0.0015290553,0.0029389048,0.0014208771,0.0004604416,0.34912017,0.53734505,0.00029224867],"about_ca_topic_score_codex":0.0022880228,"about_ca_topic_score_gemma":0.00029520324,"teacher_disagreement_score":0.64713484,"about_ca_system_score_codex":0.0009044289,"about_ca_system_score_gemma":0.0053978115,"threshold_uncertainty_score":0.9986289},"labels":[],"label_agreement":null},{"id":"W1532511427","doi":"10.3917/spub.132.0137","title":"Une synthèse exploratoire du courtage en connaissance en santé publique","year":2013,"lang":"fr","type":"article","venue":"Santé Publique","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research","keywords":"Political science; Humanities; Philosophy","score_opus":0.05613395767954507,"score_gpt":0.3977485795791953,"score_spread":0.3416146218996502,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1532511427","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45286137,0.016416127,0.027391987,0.39591804,0.010317746,0.0034615311,0.0002966698,0.00052325916,0.09281326],"genre_scores_gemma":[0.9595199,0.0045840675,0.0020450894,0.010107863,0.0016997898,0.00067428616,0.00007448865,0.000093753704,0.02120075],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9888524,0.0031407513,0.0020797076,0.0014901758,0.00295076,0.0014862309],"domain_scores_gemma":[0.98937136,0.004167736,0.00089907827,0.001857133,0.0027838356,0.00092086266],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0112606445,0.0008226953,0.0010465616,0.0007637844,0.00066397316,0.0030599597,0.002487515,0.00083911803,0.044186573],"category_scores_gemma":[0.0066302167,0.000704221,0.00039236405,0.002821429,0.00076371006,0.0102264965,0.0006176024,0.0012537632,0.01023674],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000072531235,0.0007543193,0.038808394,0.00015459502,0.00017706006,0.000094081995,0.010513726,0.00044157272,0.00113301,0.1330099,0.5147151,0.30012572],"study_design_scores_gemma":[0.0013593392,0.0003604049,0.11934105,0.00042515752,0.000054014105,0.00010218989,0.009445498,0.029303763,0.001552705,0.039361347,0.79755294,0.0011416158],"about_ca_topic_score_codex":0.0025143258,"about_ca_topic_score_gemma":0.0016345028,"teacher_disagreement_score":0.50665855,"about_ca_system_score_codex":0.0005924342,"about_ca_system_score_gemma":0.0041383216,"threshold_uncertainty_score":0.99954087},"labels":[],"label_agreement":null},{"id":"W1533513017","doi":"10.18438/b8959p","title":"Web-Based Portal for Impact Evaluation Reveals Information Needs for Museums, Libraries and Archives","year":2007,"lang":"en","type":"article","venue":"Evidence Based Library and Information Practice","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Scale (ratio); World Wide Web; Computer science; Library science; Geography","score_opus":0.09066111590559417,"score_gpt":0.43531206096899056,"score_spread":0.3446509450633964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1533513017","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13815625,0.001095177,0.7384397,0.094403945,0.0008582568,0.006598185,0.00038238682,0.00030501926,0.01976108],"genre_scores_gemma":[0.92215997,0.00023811938,0.040513966,0.035797186,0.00013874687,0.00028229147,0.0006911635,0.00001194763,0.0001666079],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.996666,0.00030103244,0.0013767724,0.00017241969,0.0011786135,0.0003051568],"domain_scores_gemma":[0.9817555,0.016043754,0.0012562759,0.0003516398,0.0003770846,0.00021576672],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.009289343,0.00021897929,0.00024562326,0.0011015862,0.00052741653,0.0020364088,0.00028145412,0.00011840089,0.0004719513],"category_scores_gemma":[0.011975282,0.0001691067,0.000109087625,0.0008240237,0.0001133892,0.28861654,0.000061370934,0.0001467193,0.000021594966],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008499546,0.00011184112,0.017896466,0.0004446671,0.00006901802,4.282148e-7,0.004077421,0.007076733,0.0003309103,0.25109878,0.024745291,0.6856489],"study_design_scores_gemma":[0.0028363636,0.0007952802,0.056656875,0.00017413679,0.00009196381,0.0000115182365,0.0060287737,0.45376658,0.0014353185,0.0048024035,0.473078,0.00032277487],"about_ca_topic_score_codex":0.0000015060953,"about_ca_topic_score_gemma":1.2681045e-7,"teacher_disagreement_score":0.78400373,"about_ca_system_score_codex":0.000013924283,"about_ca_system_score_gemma":0.0011423787,"threshold_uncertainty_score":0.9989996},"labels":[],"label_agreement":null},{"id":"W1534140708","doi":"10.1002/ev.20088","title":"House With a View: Validity and Evaluative Argument","year":2014,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"123 Certification (Canada)","funders":"","keywords":"CLARITY; Argument (complex analysis); Style (visual arts); Epistemology; Narrative; Evaluation methods; Psychology; Computer science; Sociology; Linguistics; Philosophy; History","score_opus":0.24014051371560705,"score_gpt":0.5046303264375429,"score_spread":0.26448981272193584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1534140708","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6927229,0.00027866464,0.27715087,0.006789342,0.0012347682,0.0037945097,0.000017265203,0.00025929188,0.017752364],"genre_scores_gemma":[0.9857093,0.000054223678,0.009424304,0.0004004726,0.0002791543,0.00057547627,0.000021011261,0.000024837887,0.0035112035],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956893,0.0007325164,0.00048592233,0.0005260939,0.0023640727,0.00020209582],"domain_scores_gemma":[0.99627763,0.0013269075,0.00030108116,0.00045310974,0.0014917784,0.00014949881],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0147098405,0.00016303294,0.00023597265,0.0002837742,0.00047395576,0.00026132414,0.0001637112,0.000060291466,0.00096717395],"category_scores_gemma":[0.0033876372,0.00011447844,0.00006992483,0.0006268728,0.00006107021,0.00054571556,0.000031377695,0.00008689269,0.00016608277],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014236165,0.00012004933,0.008983283,0.0000074545474,0.000038331324,4.086496e-8,0.0016702731,0.003960565,0.00022085306,0.0024596564,0.018713046,0.9636841],"study_design_scores_gemma":[0.0048002857,0.0012163959,0.107372455,0.000036094545,0.00030533806,0.000008932052,0.00063070445,0.4839411,0.0013351155,0.064023845,0.33599976,0.00032999134],"about_ca_topic_score_codex":0.00005176118,"about_ca_topic_score_gemma":0.0005579006,"teacher_disagreement_score":0.9633541,"about_ca_system_score_codex":0.00016684395,"about_ca_system_score_gemma":0.00047155187,"threshold_uncertainty_score":0.99994606},"labels":[],"label_agreement":null},{"id":"W1534368883","doi":"10.56105/cjsae.v15i2.1914","title":"What's in a Definition? The Implications of Being Defined and Strategies for Change","year":2001,"lang":"fr","type":"article","venue":"Canadian Journal for the Study of Adult Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sociology; Epistemology; Environmental ethics; Political science; Philosophy","score_opus":0.2506974486554644,"score_gpt":0.47681304104847744,"score_spread":0.22611559239301304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1534368883","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.879359,0.003842939,0.000641789,0.11060823,0.002930352,0.0020750165,0.00003715515,0.0000010736449,0.00050441903],"genre_scores_gemma":[0.9963556,0.0015372701,0.00030428992,0.00055307074,0.00026110717,0.0004527901,0.0000060138404,0.0000075137687,0.00052235136],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99862677,0.00014501913,0.00062282215,0.00014247758,0.00024016324,0.00022276296],"domain_scores_gemma":[0.9965907,0.0012033451,0.00042666736,0.0002502998,0.0013921313,0.00013688499],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021406275,0.00009842634,0.00016489279,0.00031246844,0.00084541633,0.00045595123,0.00035964695,0.000043594857,0.00010686826],"category_scores_gemma":[0.00059337367,0.00006399711,0.000068467976,0.00053893577,0.00015721051,0.001037857,0.000009388776,0.00012472043,0.0000016179667],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000068524474,0.00045237553,0.0976166,0.000057149424,0.00008248833,2.2031885e-7,0.15894312,0.00030950637,0.00001531687,0.21157348,0.0034371212,0.5274441],"study_design_scores_gemma":[0.0007003271,0.00048301334,0.2865374,0.00018228077,0.00010057115,0.00003192482,0.52379745,0.0008253613,0.0000035292717,0.17576839,0.01149248,0.000077236924],"about_ca_topic_score_codex":0.014290986,"about_ca_topic_score_gemma":0.4215323,"teacher_disagreement_score":0.5273669,"about_ca_system_score_codex":0.00011518683,"about_ca_system_score_gemma":0.0035438125,"threshold_uncertainty_score":0.9922729},"labels":[],"label_agreement":null},{"id":"W1535533537","doi":"","title":"The Canada School of Public Service - Centre of Expertise in Communities of Practice","year":2008,"lang":"en","type":"article","venue":"E-Learn: World Conference on E-Learning in Corporate, Government, Healthcare, and Higher Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Public service; Service (business); Public relations; Business; Political science; Marketing","score_opus":0.2535245634571561,"score_gpt":0.40376916138761987,"score_spread":0.15024459793046374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1535533537","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9205086,0.0007467034,0.0000079293795,0.045748577,0.0005568642,0.00040943295,0.000014256517,0.0000090650865,0.031998567],"genre_scores_gemma":[0.9855676,0.0013248617,0.00014505135,0.0010882546,0.000029507657,0.000032261774,0.000013745646,0.000010988811,0.01178767],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9948776,0.0014871776,0.0011515502,0.00027040628,0.0019330911,0.00028017978],"domain_scores_gemma":[0.99466974,0.0014205087,0.0020779811,0.00050560996,0.0011749786,0.00015119778],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002765643,0.00017273045,0.0003780597,0.00021345464,0.00025225626,0.00007044532,0.00048074417,0.00006707254,0.00074625365],"category_scores_gemma":[0.0007868631,0.00013728606,0.000028920716,0.0012540715,0.0001683992,0.00046265003,0.000086784275,0.0005348418,0.000009064559],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002053281,0.00035856164,0.92997295,0.00008558986,0.00001484013,0.0000012662945,0.004806506,0.0002858302,0.00007129573,0.040602632,0.0023260121,0.021269202],"study_design_scores_gemma":[0.00054752704,0.000172376,0.9106834,0.0002951712,0.000005369693,0.0000026468801,0.045725238,0.0011675832,0.00010196481,0.0010567512,0.040085573,0.00015637625],"about_ca_topic_score_codex":0.21623175,"about_ca_topic_score_gemma":0.6574125,"teacher_disagreement_score":0.4411808,"about_ca_system_score_codex":0.000476423,"about_ca_system_score_gemma":0.00529907,"threshold_uncertainty_score":0.94003224},"labels":[],"label_agreement":null},{"id":"W1537940489","doi":"","title":"Integrating Evaluation: A Parting Thought","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Counselling and Psychotherapy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Temptation; Reading (process); Set (abstract data type); Field (mathematics); Sociology; Epistemology; Psychology; Computer science; Social psychology; Linguistics; Philosophy; Mathematics","score_opus":0.1807621228554837,"score_gpt":0.49093473033062723,"score_spread":0.3101726074751435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1537940489","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5536046,0.012542613,0.42572647,0.0019872661,0.0013940403,0.00011868732,0.0000018147064,0.000004364138,0.00462018],"genre_scores_gemma":[0.98795426,0.006553108,0.0026404231,0.0015700073,0.0006466325,0.0000012599578,6.881905e-7,0.00001153283,0.00062208343],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976063,0.00015654313,0.0008105483,0.000138159,0.001056417,0.00023207205],"domain_scores_gemma":[0.9971667,0.0005821279,0.0005005363,0.00016116539,0.0011979154,0.00039157685],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.024727836,0.0000921995,0.00017978916,0.00041546053,0.00026483592,0.00030916015,0.00023716774,0.00005357421,0.001277268],"category_scores_gemma":[0.000049010254,0.00006548456,0.000069976646,0.00045098102,0.00006118415,0.0002648116,7.6577564e-8,0.00020102685,0.000016636859],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005633408,0.000010433016,0.010248026,0.0000021350809,0.000031206695,0.000011532285,0.015950067,0.00060302136,0.00024076224,0.0077470364,0.0042490107,0.9608504],"study_design_scores_gemma":[0.00090853206,0.00018703492,0.0020892536,0.00009972691,0.00001747077,0.0001207807,0.0014685342,0.009558756,0.00022519383,0.22796282,0.75720406,0.00015782262],"about_ca_topic_score_codex":0.00006943534,"about_ca_topic_score_gemma":0.0136668235,"teacher_disagreement_score":0.9606926,"about_ca_system_score_codex":0.000023306518,"about_ca_system_score_gemma":0.00054967124,"threshold_uncertainty_score":0.9996357},"labels":[],"label_agreement":null},{"id":"W1538277815","doi":"","title":"The Application Of The Concept Of Continuous Development To The Cyprus Educational System, 9(7)","year":2005,"lang":"en","type":"article","venue":"International electronic journal for leadership in learning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sociology; Mathematics education; Psychology; Pedagogy; Epistemology; Philosophy","score_opus":0.1455352714130779,"score_gpt":0.44613219634620427,"score_spread":0.3005969249331264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1538277815","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43893033,0.002980841,0.16228579,0.38114333,0.0040252837,0.00239889,0.00001182669,0.000024034245,0.008199664],"genre_scores_gemma":[0.99488544,0.000009792321,0.00029244265,0.0002654213,0.0002603069,0.000069928836,0.000002754063,0.0000066879934,0.004207243],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970005,0.00027770095,0.0008892493,0.00014870321,0.001383738,0.00030010982],"domain_scores_gemma":[0.99639106,0.0017536258,0.00077523,0.00018006649,0.00086796586,0.00003206077],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007885198,0.00008448496,0.0001335556,0.00013484621,0.00040871926,0.000115116796,0.0012619296,0.00003529215,0.00006853642],"category_scores_gemma":[0.0018932722,0.000041879655,0.00011033051,0.00034364656,0.00008145735,0.00016709974,0.000050494033,0.0004535641,0.00003225528],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022493543,0.000112469184,0.02995686,0.000011743115,0.00014555019,7.987909e-8,0.013264959,0.26026013,0.0009350019,0.37233523,0.0021294665,0.32062358],"study_design_scores_gemma":[0.0010300837,0.0001651937,0.035209905,0.0001695594,0.000016778538,0.00008958638,0.03414987,0.04813968,0.0039963936,0.0043589245,0.87250906,0.00016494229],"about_ca_topic_score_codex":0.000010581118,"about_ca_topic_score_gemma":0.00032072436,"teacher_disagreement_score":0.8703796,"about_ca_system_score_codex":0.00056155975,"about_ca_system_score_gemma":0.0011039849,"threshold_uncertainty_score":0.31435794},"labels":[],"label_agreement":null},{"id":"W1539012291","doi":"","title":"Evidence-Based Policy Making: Some Observations of Recent Canadian Experience","year":2003,"lang":"en","type":"article","venue":"Social policy journal of New Zealand","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Political science; Evidence-based policy; Process (computing); Policy making; Set (abstract data type); Public administration; Public relations; Computer science","score_opus":0.5006318578145151,"score_gpt":0.5367263641032317,"score_spread":0.03609450628871658,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1539012291","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8432897,0.0002705759,0.00012275789,0.15106066,0.00047938872,0.00017508549,0.000017627692,0.0000064639225,0.004577781],"genre_scores_gemma":[0.99132806,0.00025589622,0.0006408371,0.00469293,0.0012952711,0.0000018769584,6.65021e-7,0.000008527502,0.0017759635],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9966524,0.00032583936,0.0010006739,0.00014142663,0.0015462834,0.00033338],"domain_scores_gemma":[0.99702436,0.00042484017,0.0009325036,0.00021158192,0.0010328124,0.00037391853],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002513457,0.00012044457,0.00031806808,0.0009689214,0.00025940317,0.0001398733,0.0005435526,0.00008522702,0.0008758698],"category_scores_gemma":[0.008727634,0.00009375427,0.00016329355,0.0017106808,0.00011110113,0.0007972284,0.000016327524,0.00018236387,0.000018751278],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024335846,0.00024793777,0.41135165,0.000019057989,0.0001194664,0.00002369745,0.053110193,0.0026394324,0.0050165853,0.16057599,0.24138536,0.12526727],"study_design_scores_gemma":[0.0011297298,0.0002247381,0.5292913,0.00010675002,0.000019663508,0.000020458843,0.0020580878,0.00009126412,0.00076307956,0.061381362,0.40472165,0.00019194915],"about_ca_topic_score_codex":0.018067455,"about_ca_topic_score_gemma":0.008332767,"teacher_disagreement_score":0.16333629,"about_ca_system_score_codex":0.00044664528,"about_ca_system_score_gemma":0.016576627,"threshold_uncertainty_score":0.9996223},"labels":[],"label_agreement":null},{"id":"W153920091","doi":"10.55016/ojs/ajer.v47i3.54876","title":"Formative Evaluation Following BEd Program Revisions: Background and Insights","year":2001,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Formative assessment; Psychology; Mathematics education; Pedagogy; Medical education; Medicine","score_opus":0.5452506328037124,"score_gpt":0.6462485285142908,"score_spread":0.10099789571057838,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W153920091","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9175659,0.0015165102,0.000014554095,0.015365024,0.00040783154,0.00044491043,3.9855638e-7,5.6199167e-7,0.06468434],"genre_scores_gemma":[0.99053603,0.00047397136,0.000927355,0.00015299978,0.00023349187,0.000051625964,0.00000779875,0.0000072029147,0.007609517],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9923805,0.0011441786,0.00097599305,0.00022548574,0.0050051003,0.00026875312],"domain_scores_gemma":[0.9682571,0.026685754,0.00041205075,0.00027537995,0.0041265883,0.00024307557],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.015758136,0.00010295659,0.00022765847,0.0008431059,0.0004828849,0.0005025399,0.0005063116,0.000059224712,0.019538175],"category_scores_gemma":[0.030526517,0.00006857841,0.000119983255,0.0014090374,0.00012046913,0.0018299808,0.0000925092,0.00036927348,0.0004752598],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000474341,0.0021289212,0.20108259,0.000034624863,0.00036227,0.0000038229164,0.026365187,0.0003275108,0.00064313755,0.050927088,0.10406756,0.61358297],"study_design_scores_gemma":[0.003012304,0.0017643365,0.3940968,0.00046453605,0.000113932816,0.000274361,0.025039384,0.01955153,0.00013418189,0.12602809,0.42913613,0.00038442394],"about_ca_topic_score_codex":0.000052583247,"about_ca_topic_score_gemma":0.00030347117,"teacher_disagreement_score":0.6131985,"about_ca_system_score_codex":0.00022544058,"about_ca_system_score_gemma":0.0019976664,"threshold_uncertainty_score":0.9813581},"labels":[],"label_agreement":null},{"id":"W15404402","doi":"","title":"An Integrated Approach to Neighbourhood Safety Through Planning Lessons from Saskatoon","year":2008,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Neighbourhood (mathematics); Local planning; Environmental planning; Comprehensive planning; Urban planning; Plan (archaeology); Inclusion (mineral); Process (computing); Enforcement; Strategic planning; Land-use planning; Business; Public relations; Political science; Geography; Land use; Sociology; Engineering; Computer science; Civil engineering; Marketing","score_opus":0.35762107649420594,"score_gpt":0.5035006798466767,"score_spread":0.14587960335247074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W15404402","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.340706,0.000026662898,0.38476375,0.00226905,0.00023653437,0.00021776641,0.000036812336,0.00011365968,0.27162975],"genre_scores_gemma":[0.9322901,0.000007516594,0.061207615,0.002658904,0.000102932565,0.000016862723,0.00008917287,0.000011405477,0.0036155374],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99679196,0.00025243973,0.00054072344,0.00060788705,0.0015263744,0.00028061276],"domain_scores_gemma":[0.9982843,0.0003418557,0.00012644663,0.0007559999,0.0002880915,0.00020330046],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0014653666,0.00017519326,0.00029063542,0.00014647965,0.00039647822,0.00021015939,0.0007429823,0.00008902975,0.0052231895],"category_scores_gemma":[0.00021890222,0.00011406345,0.00007222351,0.0009304362,0.00005744058,0.0010226112,0.00007806085,0.00018749025,0.0010927266],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00069050497,0.0021408598,0.25128216,0.000005232823,0.00015132764,0.000030287929,0.13436896,0.118287034,0.0030586768,0.04010196,0.21198636,0.23789665],"study_design_scores_gemma":[0.0013781481,0.00040375185,0.5507943,0.00002680238,0.000016902593,0.000022535256,0.033163432,0.15427932,0.0016210678,0.0057251006,0.25191796,0.0006506685],"about_ca_topic_score_codex":0.00047838295,"about_ca_topic_score_gemma":0.00015743998,"teacher_disagreement_score":0.591584,"about_ca_system_score_codex":0.000067076144,"about_ca_system_score_gemma":0.0002496002,"threshold_uncertainty_score":0.99968505},"labels":[],"label_agreement":null},{"id":"W1541185587","doi":"10.1002/ev.20112","title":"Credentialed Evaluator Designation Program, the Canadian Experience","year":2015,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Value (mathematics); Professional development; Service (business); Administration (probate law); Political science; Public relations; Management; Engineering ethics; Sociology; Pedagogy; Computer science; Engineering; Law; Business; Marketing; Economics","score_opus":0.4863368872817085,"score_gpt":0.5792195495990002,"score_spread":0.09288266231729175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1541185587","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5349118,0.0018904561,0.12974988,0.060768206,0.022911808,0.0323635,0.0000839934,0.0009676042,0.21635273],"genre_scores_gemma":[0.9850383,0.0000059336558,0.004685005,0.00037351664,0.0004518623,0.0022647902,0.000087539345,0.000015346437,0.007077704],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.994406,0.0006213262,0.00059874577,0.00043115177,0.0036381846,0.00030462866],"domain_scores_gemma":[0.9944095,0.0004991141,0.00026899442,0.00057216064,0.0038647642,0.00038546266],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016478546,0.00014391018,0.00014863165,0.00043730627,0.001097156,0.00081459805,0.0004925731,0.00009679403,0.0016292229],"category_scores_gemma":[0.008709146,0.000098911034,0.000116074436,0.0013864046,0.00007822403,0.00079630374,0.000025541329,0.00010440366,0.00036941134],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046479272,0.00007537816,0.002614932,0.0000011687065,0.000023279734,1.0811226e-7,0.0050582434,0.0065438366,0.00010340196,0.0024675087,0.10361656,0.8794491],"study_design_scores_gemma":[0.0016909133,0.0002075841,0.016783409,0.0000068080453,0.00009383341,0.0000053881417,0.00221719,0.4237547,0.00061258883,0.027050788,0.52739894,0.0001778751],"about_ca_topic_score_codex":0.014270325,"about_ca_topic_score_gemma":0.27331123,"teacher_disagreement_score":0.8792712,"about_ca_system_score_codex":0.0009569103,"about_ca_system_score_gemma":0.0060022413,"threshold_uncertainty_score":0.99964094},"labels":[],"label_agreement":null},{"id":"W1542966575","doi":"10.1023/a:1007837009747","title":"Measurement of S&amp;T Performance in the Government of Canada: From Outputs to Outcomes","year":2000,"lang":"en","type":"article","venue":"The Journal of Technology Transfer","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Ontario Stroke Network; Innovation, Science and Economic Development Canada","funders":"","keywords":"Incentive; Perspective (graphical); Process (computing); Organizational culture; Government (linguistics); Process management; Knowledge management; Performance management; Business; Public relations; Psychology; Operations management; Computer science; Marketing; Political science; Engineering; Economics","score_opus":0.10322156944387376,"score_gpt":0.36080917002969104,"score_spread":0.2575876005858173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1542966575","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9726,0.00021174463,0.0007533693,0.025066543,0.00010190254,0.00013448596,0.000009516067,0.0000019065207,0.001120525],"genre_scores_gemma":[0.999049,0.00013474179,0.00018669624,0.00048678595,0.000009847117,0.0000027681976,5.9081653e-8,0.000003038788,0.0001270307],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99501604,0.00016053351,0.0009596134,0.00008140902,0.0036357932,0.00014663048],"domain_scores_gemma":[0.9988845,0.00022926851,0.00014857372,0.00042717016,0.00028320518,0.00002725617],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006313257,0.00008911915,0.00031087614,0.00013006147,0.000050884904,0.0000069149814,0.0012332898,0.000050998347,0.00065431686],"category_scores_gemma":[0.0001945362,0.00003943616,0.00006597496,0.00052688445,0.000082076825,0.00008575363,0.000017360766,0.00023892062,0.0000061005776],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00087374565,0.0004696117,0.6294684,0.000014752923,0.00020625272,0.000004957377,0.00798285,0.010766708,0.012281653,0.0009035546,0.0037967374,0.3332308],"study_design_scores_gemma":[0.0008691723,0.00032513606,0.9484252,0.00008844744,0.00004919882,0.000012149445,0.0029435947,0.00010547812,0.021109246,0.0010391793,0.024949566,0.00008367879],"about_ca_topic_score_codex":0.0015522197,"about_ca_topic_score_gemma":0.05337988,"teacher_disagreement_score":0.3331471,"about_ca_system_score_codex":0.00012512997,"about_ca_system_score_gemma":0.00036895162,"threshold_uncertainty_score":0.9638935},"labels":[],"label_agreement":null},{"id":"W1542975043","doi":"10.4212/cjhp.v68i3.1450","title":"Move Over, Strategic Plan: Make Way for the Culture Plan!","year":2015,"lang":"en","type":"article","venue":"The Canadian Journal of Hospital Pharmacy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Plan (archaeology); Computer science; Process management; Business; Geography","score_opus":0.29844117861903385,"score_gpt":0.4638846169580957,"score_spread":0.16544343833906183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1542975043","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8812802,0.005158269,0.00041768397,0.067701966,0.009980473,0.0010729763,0.0002895552,0.0000125101515,0.03408637],"genre_scores_gemma":[0.9949989,0.000046069883,0.00007922151,0.0020079236,0.0007774419,0.0000068529635,0.0000035466032,0.000009217049,0.0020708474],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978139,0.00012333778,0.0005144916,0.00012203443,0.0011283702,0.0002978574],"domain_scores_gemma":[0.99750185,0.00042147114,0.0004320828,0.0002704462,0.0008044201,0.0005697474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004287091,0.00013071529,0.00018188295,0.0001156235,0.0004341923,0.00059005606,0.001252952,0.00003256265,0.0007382178],"category_scores_gemma":[0.00039267968,0.00005723681,0.00015437214,0.0002716514,0.0001291289,0.00036205185,0.000020725993,0.00034352008,0.000094651965],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024238226,0.000059404156,0.016551593,0.000005481336,0.00022360709,0.000075266806,0.018005442,0.006425118,0.000039662656,0.010846804,0.9147738,0.032751396],"study_design_scores_gemma":[0.0030647859,0.00068652874,0.008447621,0.000021961998,0.00009669798,0.00011521275,0.016792301,0.011292218,0.00020624873,0.057555523,0.90147084,0.00025004667],"about_ca_topic_score_codex":0.0017749503,"about_ca_topic_score_gemma":0.013123992,"teacher_disagreement_score":0.11371868,"about_ca_system_score_codex":0.00015453435,"about_ca_system_score_gemma":0.0024876038,"threshold_uncertainty_score":0.80829674},"labels":[],"label_agreement":null},{"id":"W1543074450","doi":"10.1002/ev.20076","title":"Framing the Capacity to Do and Use Evaluation","year":2014,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":96,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec en Outaouais; University of Ottawa","funders":"","keywords":"Framing (construction); Conceptualization; Situated; Construct (python library); Capacity building; Organizational change; Sociology; Management science; Knowledge management; Public relations; Computer science; Political science; Economics","score_opus":0.33725614035289037,"score_gpt":0.5217974321371192,"score_spread":0.1845412917842288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1543074450","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8407602,0.000105047366,0.14204979,0.0072794533,0.001531165,0.0027325596,0.000010104448,0.000055553242,0.0054761674],"genre_scores_gemma":[0.99182385,0.00000993597,0.005234292,0.0007115088,0.00034853845,0.00051332224,0.0000142671615,0.000011295844,0.0013329595],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9953135,0.0008927742,0.00049022416,0.00045211267,0.0026642405,0.00018712298],"domain_scores_gemma":[0.9946947,0.0024106472,0.00020944483,0.0005585527,0.0019984003,0.00012826748],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.026410995,0.00012614764,0.00015045555,0.00029568793,0.0007741525,0.00070068834,0.00021389604,0.00006843606,0.00078991486],"category_scores_gemma":[0.019065356,0.00008517937,0.00007428456,0.00080777606,0.00004072328,0.0007644431,0.000042597152,0.00009733968,0.0001531388],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002238382,0.000024922598,0.005238763,0.0000018992191,0.000013670584,3.4815855e-9,0.002191893,0.010581496,0.0004526603,0.004710428,0.012145513,0.96461636],"study_design_scores_gemma":[0.00086991186,0.0001158958,0.21413079,0.00001193432,0.00011588586,0.0000020620369,0.00040689702,0.55172205,0.00034424296,0.051301785,0.18085222,0.00012632723],"about_ca_topic_score_codex":0.00016511674,"about_ca_topic_score_gemma":0.0011327721,"teacher_disagreement_score":0.96449006,"about_ca_system_score_codex":0.00017750343,"about_ca_system_score_gemma":0.0002765738,"threshold_uncertainty_score":0.9891975},"labels":[],"label_agreement":null},{"id":"W1543938039","doi":"","title":"Les stages d’enseignement consécutifs en fin de formation initiale et le développement de compétences professionnelles : avantages et défis","year":2010,"lang":"fr","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université Sainte-Anne","funders":"","keywords":"Humanities; Political science; Art","score_opus":0.5068264997137086,"score_gpt":0.6479966913929225,"score_spread":0.14117019167921385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1543938039","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9049488,0.01139233,0.015658366,0.049362607,0.0033303935,0.0013683968,0.0002316884,0.000050052568,0.013657374],"genre_scores_gemma":[0.9505932,0.032644078,0.01196619,0.0023721757,0.00022940485,0.00014317325,0.000049743998,0.000041321382,0.001960725],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9904386,0.003340027,0.0021894919,0.00063540286,0.0026105752,0.0007859203],"domain_scores_gemma":[0.9925194,0.003144125,0.00211285,0.00068539236,0.001085739,0.00045253182],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.021539869,0.0005168768,0.0009128509,0.0010742157,0.0011162309,0.003623882,0.003573172,0.00031121334,0.04739512],"category_scores_gemma":[0.0017642883,0.00043311706,0.00025596938,0.0009836273,0.00047705567,0.005942037,0.0014613868,0.0012010395,0.00011314612],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033058,0.0016186323,0.43274236,0.00036736863,0.0002686193,0.00005015416,0.023136498,0.0020824927,0.0895616,0.008365393,0.19129877,0.25017753],"study_design_scores_gemma":[0.0017158043,0.0000806097,0.7511263,0.0015401238,0.00013272406,0.000059517846,0.01952852,0.0047825635,0.068667375,0.0496048,0.1019201,0.0008415631],"about_ca_topic_score_codex":0.002885675,"about_ca_topic_score_gemma":0.0041161086,"teacher_disagreement_score":0.31838393,"about_ca_system_score_codex":0.00034642266,"about_ca_system_score_gemma":0.0032618258,"threshold_uncertainty_score":0.99981207},"labels":[],"label_agreement":null},{"id":"W1544576951","doi":"","title":"A Review of the Literature on Case Study Research","year":2008,"lang":"en","type":"review","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":146,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Data science; Information retrieval","score_opus":0.8931945989899815,"score_gpt":0.7971990924816132,"score_spread":0.0959955065083683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1544576951","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013013117,0.9867095,0.0000017805385,0.00017004939,0.00091119076,0.0042002434,0.00011070925,0.000008794581,0.0065864157],"genre_scores_gemma":[0.00091767026,0.9962684,0.000020620746,0.00047461403,0.00023256926,0.0002573807,0.000009680725,0.000052197836,0.0017668643],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9761184,0.009994899,0.004183768,0.0010213223,0.00818668,0.00049492874],"domain_scores_gemma":[0.98288435,0.005686148,0.0042916695,0.0030376262,0.0038120195,0.0002881645],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.034494285,0.000609928,0.003809446,0.0026366785,0.0007936478,0.0022529983,0.01185976,0.00025561661,0.016987335],"category_scores_gemma":[0.007792914,0.00030701573,0.0012604778,0.011064341,0.00030023014,0.0016936219,0.0029466483,0.0023811169,0.0001486057],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001871954,0.0005807767,0.0022488455,0.008437269,0.00018791019,0.00039412585,0.0004263134,0.0000039444426,0.0000015160035,0.000019443132,0.27376613,0.713915],"study_design_scores_gemma":[0.00020231948,0.000042026215,0.0017328686,0.15143201,0.0001937118,0.0007816408,0.00024185741,0.0000030625479,0.000004304642,0.00044603035,0.8446277,0.00029250127],"about_ca_topic_score_codex":0.00023522986,"about_ca_topic_score_gemma":0.000058835045,"teacher_disagreement_score":0.7136225,"about_ca_system_score_codex":0.00024196092,"about_ca_system_score_gemma":0.0022469682,"threshold_uncertainty_score":0.9999382},"labels":[],"label_agreement":null},{"id":"W1544634347","doi":"10.56645/jmde.v3i4.95","title":"Review of Research Evaluation, Volumes 13(3), 14(1), and 14(2)","year":2006,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Psychology","score_opus":0.365610475907359,"score_gpt":0.5976328797105598,"score_spread":0.23202240380320077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1544634347","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9085251,0.0732238,0.00078922405,0.008825188,0.00091537106,0.0014887194,0.000010252284,0.00000898341,0.0062133335],"genre_scores_gemma":[0.9885162,0.0073126466,0.0028826906,0.000086221255,0.00042837506,0.000041122174,0.000021087184,0.000014373369,0.0006972747],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98090583,0.0035951212,0.0026480674,0.00036688612,0.012211114,0.00027295985],"domain_scores_gemma":[0.9750879,0.0017557396,0.0018820593,0.0005359554,0.020619156,0.00011923007],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14013585,0.00016385799,0.00053152815,0.00095284125,0.00031835792,0.00011450043,0.00053456123,0.00010118729,0.0021218376],"category_scores_gemma":[0.010996145,0.00011567008,0.00018756969,0.0014378459,0.00023403227,0.0011309827,0.00018231098,0.00036975666,0.000066011984],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044229554,0.0010932928,0.14044257,0.0013839846,0.000117679876,0.0000069961225,0.0029725202,0.017091079,0.0046982034,0.0006506827,0.18197703,0.64912367],"study_design_scores_gemma":[0.0037528367,0.0009793263,0.6121509,0.0049778433,0.00036641528,0.00010478521,0.0019356698,0.27889848,0.0009194429,0.08759868,0.008037434,0.0002781913],"about_ca_topic_score_codex":0.000023625302,"about_ca_topic_score_gemma":0.000089436304,"teacher_disagreement_score":0.6488455,"about_ca_system_score_codex":0.0002758199,"about_ca_system_score_gemma":0.0015603594,"threshold_uncertainty_score":0.9987904},"labels":[],"label_agreement":null},{"id":"W1546295638","doi":"","title":"Expanding the Practice-Based Taxonomy of Characteristics of TPACK","year":2010,"lang":"en","type":"article","venue":"Society for Information Technology & Teacher Education International Conference","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University","funders":"","keywords":"Taxonomy (biology); Computer science; Biology","score_opus":0.10736270825615853,"score_gpt":0.45475565747931895,"score_spread":0.34739294922316044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1546295638","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55947447,0.000026875647,0.33763593,0.057969708,0.0046864473,0.0019191467,0.00019670003,0.00011850633,0.03797223],"genre_scores_gemma":[0.97342837,0.000012123917,0.024912296,0.0006803258,0.00007539915,0.00035685606,0.00011034213,0.0000040775744,0.00042023207],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99794686,0.000031948803,0.0009905221,0.00013645658,0.00077731465,0.000116921256],"domain_scores_gemma":[0.99384546,0.00053997646,0.0016141597,0.00043926164,0.003531665,0.000029469182],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0026667023,0.00010667085,0.00017128846,0.00030115093,0.0001385532,0.000118102005,0.00095124496,0.00017436683,0.0009380329],"category_scores_gemma":[0.0032236376,0.000078272846,0.00018768973,0.00048087465,0.00033250984,0.0012571234,0.00006754887,0.00031660972,0.000030262716],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007756059,0.00043514787,0.053525254,0.000042217787,0.00012274165,9.796076e-9,0.00491338,0.00005237711,0.004608983,0.471822,0.01645912,0.4479412],"study_design_scores_gemma":[0.0010584972,0.00015545692,0.02041226,0.00005690533,0.00007060637,0.0000069923935,0.05754194,0.025273304,0.019264631,0.022094334,0.85378885,0.0002761898],"about_ca_topic_score_codex":0.000013086828,"about_ca_topic_score_gemma":0.0000051064544,"teacher_disagreement_score":0.83732975,"about_ca_system_score_codex":0.000056532885,"about_ca_system_score_gemma":0.001304212,"threshold_uncertainty_score":0.99997526},"labels":[],"label_agreement":null},{"id":"W1547906511","doi":"10.3138/cjpe.0028.008","title":"Evaluator Competencies: The South African Government Experience","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Presidency; Context (archaeology); Institution; Process (computing); Political science; Computer science; Geography","score_opus":0.27171115503889426,"score_gpt":0.4784742502509596,"score_spread":0.20676309521206532,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1547906511","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9661425,0.00034910833,0.005624685,0.0073208804,0.0020232867,0.0016000702,0.000011248182,0.000014439017,0.016913803],"genre_scores_gemma":[0.9968649,0.0000026102853,0.0019378857,0.0005800732,0.00028113765,0.000103872226,0.0000016988665,0.000008658168,0.0002191518],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99172586,0.0011307588,0.0009748143,0.00022737004,0.005608813,0.0003323861],"domain_scores_gemma":[0.99527,0.0005202429,0.00094287575,0.00052967126,0.0022402962,0.0004969074],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.026771361,0.00013883944,0.00023248456,0.0001869687,0.00045267472,0.0005932868,0.0009982089,0.000052178046,0.0030095556],"category_scores_gemma":[0.0072633186,0.00008091856,0.00015187215,0.00072213425,0.0002281765,0.00044975246,0.000023361525,0.00021417247,0.00014073601],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017611937,0.000031698695,0.032934353,0.0000021443684,0.000024215968,0.0000013948304,0.015806882,0.0039311163,0.000049003458,0.0016370735,0.002954001,0.9426105],"study_design_scores_gemma":[0.0011839968,0.0009564426,0.16144046,0.000045517332,0.00012216499,0.00004344007,0.03366141,0.29841024,0.00016538729,0.008112582,0.49559736,0.00026100254],"about_ca_topic_score_codex":0.0002065372,"about_ca_topic_score_gemma":0.005722884,"teacher_disagreement_score":0.9423495,"about_ca_system_score_codex":0.0005617798,"about_ca_system_score_gemma":0.0029617655,"threshold_uncertainty_score":0.99790186},"labels":[],"label_agreement":null},{"id":"W1547974196","doi":"10.1177/160940690400300105","title":"Practical Tips &amp; Techniques for Qualitative Researchers","year":2004,"lang":"en","type":"article","venue":"International Journal of Qualitative Methods","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Qualitative research; Feature (linguistics); Computer science; Data science; Management science; Engineering ethics; Sociology; Engineering; Social science","score_opus":0.9643934583022874,"score_gpt":0.8484411880269193,"score_spread":0.11595227027536814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1547974196","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0060047116,0.00007255344,0.9372919,0.05251815,0.0008507925,0.00023253102,0.00003466409,0.000012530244,0.0029821468],"genre_scores_gemma":[0.04534308,0.000039559836,0.9519307,0.00091823394,0.0003733858,0.0000325245,0.0000065724316,0.000013605547,0.0013423372],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98384595,0.009974658,0.0017609491,0.00028605017,0.0038878876,0.00024448358],"domain_scores_gemma":[0.96027327,0.028644668,0.0014578677,0.00022262333,0.009220659,0.00018094071],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12890272,0.00015071341,0.00039851785,0.0007769893,0.00011017615,0.0002806734,0.00093623815,0.00008647276,0.0006088963],"category_scores_gemma":[0.080155894,0.00010419193,0.00033455034,0.00044690867,0.0003060558,0.0011792339,0.000098917764,0.00043293394,0.00007063379],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016679919,0.0005088582,0.00006288094,0.000010832434,0.0006071756,0.00001608911,0.3724493,0.00020237824,0.0070188167,0.37341422,0.025701553,0.21833989],"study_design_scores_gemma":[0.001128669,0.00052396616,0.00011379934,0.000058561694,0.000017448765,0.00007075851,0.10362396,0.000100698795,0.010994258,0.67744756,0.2057805,0.0001398013],"about_ca_topic_score_codex":0.00002006424,"about_ca_topic_score_gemma":0.000019425948,"teacher_disagreement_score":0.30403334,"about_ca_system_score_codex":0.0004291449,"about_ca_system_score_gemma":0.0010936979,"threshold_uncertainty_score":0.92759234},"labels":[],"label_agreement":null},{"id":"W1548455965","doi":"10.1177/1035719x0700700105","title":"Contribution analysis","year":2007,"lang":"en","type":"article","venue":"Evaluation Journal of Australasia","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Advancing Health Outcomes","funders":"Australian Agency for International Development","keywords":"Outcome (game theory); Political science; Risk analysis (engineering); Process management; Computer science; Engineering; Business; Economics","score_opus":0.18382612084877567,"score_gpt":0.5447163949946406,"score_spread":0.36089027414586494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1548455965","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88567793,0.000083748455,0.10785539,0.0017899828,0.0006822624,0.00014835836,0.0000022347642,0.0000060986417,0.0037539708],"genre_scores_gemma":[0.99771845,0.000007661924,0.0014460967,0.00012391144,0.0002389525,9.997735e-7,0.0000063350985,0.0000031839502,0.00045440017],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9925101,0.00042316323,0.0016129245,0.00015651231,0.005086727,0.0002106083],"domain_scores_gemma":[0.9911426,0.00068796537,0.0013025143,0.0002613361,0.0064304126,0.00017519617],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.062236667,0.000093786424,0.00031066663,0.0012509817,0.00010511519,0.00015438136,0.00035927538,0.000069858725,0.00875173],"category_scores_gemma":[0.004824936,0.000065608605,0.00031883456,0.0024359268,0.00004326834,0.0007320279,0.000016091297,0.00018478069,0.00019188195],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031630194,0.00024153152,0.5999541,0.0000020064483,0.0009112599,0.000017125241,0.0013559841,0.052410845,0.0037652391,0.0042664153,0.013248406,0.32351074],"study_design_scores_gemma":[0.0011486746,0.00018881417,0.95637727,0.0000067776737,0.00069211086,0.000032198936,0.00079663587,0.020324362,0.0026472274,0.0078190975,0.0098742405,0.00009257317],"about_ca_topic_score_codex":0.0000017030579,"about_ca_topic_score_gemma":0.000031143973,"teacher_disagreement_score":0.35642314,"about_ca_system_score_codex":0.00019358945,"about_ca_system_score_gemma":0.00039080004,"threshold_uncertainty_score":0.9921544},"labels":[],"label_agreement":null},{"id":"W1549446091","doi":"","title":"Social Research Methods (review)","year":2007,"lang":"en","type":"article","venue":"Project Muse (Johns Hopkins University)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Objectivism; Sociology; Epistemology; Positivism; Social research; Critical realism (philosophy of perception); Strict constructionism; Qualitative research; Realism; Set (abstract data type); Phenomenology (philosophy); Social constructionism; Social science; Computer science","score_opus":0.3775916571919277,"score_gpt":0.5585262700840441,"score_spread":0.18093461289211638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1549446091","genre_codex":"other","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004806431,0.000023297818,0.016806835,0.001984413,0.000244524,0.0006058584,0.00000530366,0.00008022136,0.9754431],"genre_scores_gemma":[0.27693623,0.65431845,0.058511388,0.0038347016,0.0011006944,0.000012275476,0.00003872346,0.00007830418,0.005169215],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99433935,0.0017532663,0.00045047802,0.0005529136,0.002332144,0.0005718237],"domain_scores_gemma":[0.9960193,0.0018099649,0.0001932413,0.0005496228,0.0013010674,0.00012679932],"candidate_categories":["metaresearch","bibliometrics","insufficient_payload"],"consensus_categories":["bibliometrics"],"category_scores_codex":[0.029610634,0.00015425775,0.0003118384,0.015534547,0.00062243047,0.00009137969,0.0011643107,0.00011742877,0.0011687722],"category_scores_gemma":[0.0015283129,0.00013094957,0.0001867804,0.027346754,0.00018842448,0.0006071527,0.00039490464,0.0004584392,0.0006012721],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009625352,0.00014875311,0.0009243069,0.00004612181,0.000031392476,0.000054195625,0.0040086675,0.000002653052,0.000028355626,0.012583729,0.027741347,0.9543342],"study_design_scores_gemma":[0.00041348668,0.00008392848,0.0015608126,0.000042811844,0.000020432148,0.0000039326637,0.0018919096,0.00019702355,0.00034604306,0.000035726633,0.9952417,0.00016221342],"about_ca_topic_score_codex":0.0034811993,"about_ca_topic_score_gemma":0.004365074,"teacher_disagreement_score":0.9702739,"about_ca_system_score_codex":0.00031929693,"about_ca_system_score_gemma":0.00091200933,"threshold_uncertainty_score":0.9997443},"labels":[],"label_agreement":null},{"id":"W1556106592","doi":"10.15353/joci.v1i3.2027","title":"Editorial: Putting Our Work in Context","year":2005,"lang":"en","type":"editorial","venue":"The Journal of Community Informatics","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Work (physics); Context (archaeology); Engineering ethics; Sociology; Engineering; History; Mechanical engineering; Archaeology","score_opus":0.1392861425199959,"score_gpt":0.4742349474260947,"score_spread":0.3349488049060988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1556106592","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0073512318,0.0001289275,0.0003110306,0.0015219264,0.98827684,0.0001643519,0.00001542137,0.000008724632,0.0022215515],"genre_scores_gemma":[0.034179848,0.00046066707,0.0004061788,0.0003366443,0.9641566,0.0000017322923,0.000013289644,0.000015298601,0.0004297179],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98518956,0.0030302051,0.0042911647,0.000021510576,0.007136752,0.00033080767],"domain_scores_gemma":[0.9745334,0.0155458385,0.005271803,0.0012005634,0.0033287648,0.000119620985],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07367959,0.0002719924,0.00081862416,0.0006325315,0.0004815951,0.000539901,0.0045631886,0.00052638823,0.000080882695],"category_scores_gemma":[0.019535951,0.00015433904,0.00022111258,0.00088630745,0.000079060876,0.0013278084,0.0005083313,0.0070233247,0.0002431122],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001045338,0.0000547832,0.000038194652,0.0000147516985,0.000025885833,1.0391216e-7,0.067598924,0.0020052341,1.6804238e-7,0.0000048441525,0.89754146,0.03261111],"study_design_scores_gemma":[0.0007682809,0.00014914294,0.00007405812,0.00026261547,0.000038405804,0.0000048763354,0.16255523,0.0001832909,0.0000021691706,0.0007895985,0.8350528,0.000119540644],"about_ca_topic_score_codex":0.000060569666,"about_ca_topic_score_gemma":0.00031947996,"teacher_disagreement_score":0.0949563,"about_ca_system_score_codex":0.00033020508,"about_ca_system_score_gemma":0.0015706307,"threshold_uncertainty_score":0.9952675},"labels":[],"label_agreement":null},{"id":"W1557062321","doi":"10.1177/002205740518500310","title":"Current Trends in the Accreditation of K–12 schools: Cases in the United States, Australia, and Canada","year":2005,"lang":"en","type":"article","venue":"Journal of Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Accreditation; Current (fluid); Political science; Economic growth; Public administration; Engineering; Economics; Law","score_opus":0.27727292123096675,"score_gpt":0.5372473090552258,"score_spread":0.259974387824259,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1557062321","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9839377,0.00018045687,0.00001544813,0.015350068,0.0003605732,0.00005291497,0.0000030592726,2.65514e-7,0.00009953059],"genre_scores_gemma":[0.99916995,0.00011299312,0.00010368684,0.0003801771,0.00014866615,0.0000032726332,0.000012616825,0.0000010792495,0.00006758884],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9980801,0.00034225563,0.0005674026,0.000054918688,0.0008894442,0.00006591419],"domain_scores_gemma":[0.9984919,0.00062721525,0.0004427158,0.00011242349,0.00030040916,0.00002534906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039494997,0.000044301963,0.0000839514,0.00045923202,0.000034705856,0.00007395746,0.00023764116,0.000013789506,0.00014012454],"category_scores_gemma":[0.0005584357,0.000022236378,0.000018331773,0.0006679169,0.000015708889,0.0003652337,0.0000052399805,0.00017303754,0.0000011742652],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051474548,0.00043417246,0.38198173,0.0000074678305,0.0000063565603,0.0000018748882,0.015525051,0.007394985,0.000025110792,0.0006842029,0.23881286,0.35507473],"study_design_scores_gemma":[0.00022375592,0.00006826742,0.89637005,0.000034471544,0.000007550193,0.000029731524,0.027908903,0.0009532658,0.000015990783,0.0007176522,0.07364004,0.000030341866],"about_ca_topic_score_codex":0.05914331,"about_ca_topic_score_gemma":0.420423,"teacher_disagreement_score":0.5143883,"about_ca_system_score_codex":0.00011528031,"about_ca_system_score_gemma":0.0009213565,"threshold_uncertainty_score":0.9471219},"labels":[],"label_agreement":null},{"id":"W1557495874","doi":"10.7202/1021025ar","title":"L’impact des CAP sur le développement de la compétence des enseignants en évaluation des apprentissages","year":2013,"lang":"fr","type":"article","venue":"Éducation et francophonie","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec en Outaouais","funders":"","keywords":"Political science; Humanities; Valuation (finance); Art; Business","score_opus":0.20317633138891472,"score_gpt":0.4420780436471002,"score_spread":0.23890171225818546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1557495874","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9368085,0.004787494,0.045473676,0.0034105715,0.0018887775,0.0007525736,0.000026265121,0.0000649983,0.0067871124],"genre_scores_gemma":[0.94603926,0.00408395,0.034595422,0.00039328707,0.00019112215,0.0002589985,0.000050144234,0.000038663056,0.0143491775],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9932745,0.00276477,0.000993779,0.0006535417,0.0015577882,0.0007556284],"domain_scores_gemma":[0.99471533,0.002237959,0.00046052347,0.0006462257,0.0015817088,0.0003582277],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008947734,0.0004117517,0.00041182552,0.000360541,0.00092898635,0.0010593334,0.00065063837,0.00025126696,0.015554039],"category_scores_gemma":[0.0021467018,0.000366902,0.00020478302,0.0012452705,0.0011219013,0.002486562,0.00011867984,0.0003380921,0.0034194044],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017935334,0.00090616697,0.12997968,0.00011486238,0.00006831438,0.0000019377464,0.104985155,0.007876091,0.004650882,0.00018833713,0.02021556,0.73099506],"study_design_scores_gemma":[0.0010544243,0.00017900692,0.8903041,0.00037122564,0.000036995374,0.000037002137,0.010823629,0.0246167,0.002633858,0.06429209,0.0052510453,0.00039992752],"about_ca_topic_score_codex":0.0078076627,"about_ca_topic_score_gemma":0.0014074901,"teacher_disagreement_score":0.7603244,"about_ca_system_score_codex":0.0012112486,"about_ca_system_score_gemma":0.0050548664,"threshold_uncertainty_score":0.99997765},"labels":[],"label_agreement":null},{"id":"W1557717928","doi":"10.1002/ev.20082","title":"The Value in Validity","year":2014,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"123 Certification (Canada)","funders":"","keywords":"Beauty; Prioritization; Economic Justice; Value (mathematics); Sociology; Balance (ability); Management science; Psychology; Social psychology; Epistemology; Computer science; Political science; Law; Economics","score_opus":0.36226017726620263,"score_gpt":0.5450118219863205,"score_spread":0.18275164472011785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1557717928","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.58546084,0.0003399578,0.20470272,0.03869582,0.009478688,0.0041960557,0.0000124352055,0.00019033955,0.15692312],"genre_scores_gemma":[0.98942935,0.000033321325,0.0013984573,0.00027273785,0.00036547624,0.0003094481,0.000010885353,0.000008599464,0.008171696],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963982,0.0008966677,0.00054283754,0.0002901654,0.001685257,0.00018687545],"domain_scores_gemma":[0.994442,0.004180217,0.00019028345,0.00046460977,0.00066102564,0.000061897335],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02828205,0.00008381571,0.00011842549,0.00020031833,0.0005597453,0.0002651981,0.00029295534,0.000051581304,0.00044535272],"category_scores_gemma":[0.014001549,0.000054138935,0.000091714806,0.0007903934,0.00003311063,0.0003258729,0.000024279625,0.000086516244,0.00025154307],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032080417,0.000035452103,0.006722787,0.0000011017095,0.0000054412776,9.353223e-9,0.0004275869,0.014228228,0.00009164034,0.019376878,0.030175742,0.92890304],"study_design_scores_gemma":[0.0007418859,0.00006068935,0.05916897,0.0000038379326,0.000013991351,5.561759e-7,0.00013073008,0.41340658,0.00021539727,0.13486955,0.39132908,0.00005873568],"about_ca_topic_score_codex":0.00009400039,"about_ca_topic_score_gemma":0.0015647775,"teacher_disagreement_score":0.92884433,"about_ca_system_score_codex":0.0001737388,"about_ca_system_score_gemma":0.0003940238,"threshold_uncertainty_score":0.99430394},"labels":[],"label_agreement":null},{"id":"W1558175818","doi":"10.3138/cjpe.028.002","title":"The Reciprocal Relationship between Implementation Theory and Program Theory in Assisting Program Design and Decision-Making","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Reciprocal; Management science; Program Design Language; Interpretation (philosophy); Computer science; Decision theory; Focus (optics); Development theory; Theory of change; Epistemology; Sociology; Software engineering; Mathematics; Engineering; Economics; Programming language","score_opus":0.3607936961203019,"score_gpt":0.5650848166150938,"score_spread":0.20429112049479192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1558175818","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96794367,0.0012596272,0.023437733,0.001131988,0.00025981257,0.0056207874,0.0000021188175,0.000024262632,0.00031999705],"genre_scores_gemma":[0.94183874,0.000017200027,0.057206858,0.000057676603,0.00010569651,0.0007376913,0.000005750385,0.0000135016035,0.000016866154],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99348485,0.002894716,0.0013600474,0.00029796403,0.0015481613,0.0004142812],"domain_scores_gemma":[0.98637223,0.010697199,0.0008518075,0.00024632763,0.0014864744,0.00034596806],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05975969,0.00016686326,0.00024118922,0.00062708877,0.00076490256,0.0016661251,0.00034666003,0.000109843924,0.0002799919],"category_scores_gemma":[0.013369642,0.000109425106,0.00006258076,0.00087894505,0.00024967288,0.0011099634,0.000031270425,0.00036832117,0.000015184812],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025059111,0.000016614968,0.26071057,0.0000024842595,0.000011977442,9.963957e-7,0.00078048866,0.00013780763,0.0000010076087,0.002127491,0.00014888447,0.7360366],"study_design_scores_gemma":[0.00056228344,0.00049536175,0.6680868,0.000096124284,0.00005075847,0.000017947814,0.003913773,0.018236047,0.00000307402,0.30727673,0.0011572742,0.00010377932],"about_ca_topic_score_codex":0.00012298177,"about_ca_topic_score_gemma":0.0044204416,"teacher_disagreement_score":0.7359328,"about_ca_system_score_codex":0.00030245422,"about_ca_system_score_gemma":0.0018381677,"threshold_uncertainty_score":0.9993702},"labels":[],"label_agreement":null},{"id":"W1559496221","doi":"10.3138/cjpe.28.005","title":"Neutral Assessment of the National Research Council Canada Evaluation Function","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"École Nationale d'Administration Publique; National Research Council Canada","funders":"","keywords":"Treasury; Function (biology); Government (linguistics); Research council; Public administration; Political science; Public relations; Accounting; Business; Law","score_opus":0.7595030484590533,"score_gpt":0.59285100163704,"score_spread":0.1666520468220133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1559496221","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9370078,0.00029677153,0.00024367654,0.0106896795,0.0030869017,0.0038713065,0.000018075672,0.000004896038,0.044780903],"genre_scores_gemma":[0.9983985,0.0000029390426,0.0005531764,0.00030206272,0.0002454915,0.00024089821,0.0000055569167,0.000008468025,0.00024294779],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9661093,0.0024089257,0.0012826703,0.0002379479,0.029602014,0.0003591781],"domain_scores_gemma":[0.87890935,0.0005457408,0.00089047686,0.00029501642,0.11904572,0.0003137271],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12750128,0.000121477744,0.00021513164,0.00046222517,0.00047226792,0.0003812719,0.0007250073,0.00008507197,0.0058550206],"category_scores_gemma":[0.02127089,0.00007953943,0.00012580138,0.0015920843,0.00017448554,0.0008336924,0.000025307867,0.00044279706,0.00002738401],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000017301225,0.000108891785,0.050641254,0.000011827228,0.000090905676,5.8301924e-7,0.0007014079,0.051119145,0.00042746065,0.0033533713,0.3371784,0.55634946],"study_design_scores_gemma":[0.00084448856,0.000298619,0.6398241,0.00004153229,0.000069523536,0.000012139046,0.0011658731,0.2611075,0.0000868081,0.029097388,0.06735183,0.000100238125],"about_ca_topic_score_codex":0.27538505,"about_ca_topic_score_gemma":0.94555926,"teacher_disagreement_score":0.67017424,"about_ca_system_score_codex":0.013623818,"about_ca_system_score_gemma":0.22176318,"threshold_uncertainty_score":0.99505377},"labels":[],"label_agreement":null},{"id":"W1561406598","doi":"10.3968/j.css.1923669720120805.6353","title":"A Development of the Evaluation Model for Faculty Organizational Effectiveness in Public Universities","year":2012,"lang":"en","type":"article","venue":"Canadian social science","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Officer; Audit; Process (computing); Quality assurance; Quality (philosophy); Process management; Needs assessment; Medical education; Computer science; Management science; Operations management; Business; Engineering; Medicine; Political science; Accounting; External quality assessment","score_opus":0.3305595378121809,"score_gpt":0.48233336378113495,"score_spread":0.15177382596895406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1561406598","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.979729,0.000005284849,0.0046177865,0.00052134326,0.00022441772,0.00037353986,0.00002627548,0.0000025935187,0.014499761],"genre_scores_gemma":[0.9989276,7.2005406e-8,0.000799583,0.00010318351,0.000019857009,0.000018564013,0.0000053366425,0.0000017805297,0.00012403778],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99797153,0.00009736616,0.00018034811,0.00012906287,0.0013746324,0.0002470598],"domain_scores_gemma":[0.99856424,0.00010375254,0.00009367724,0.00008844047,0.0010324925,0.00011739564],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009873403,0.000043725922,0.0000703526,0.00024162486,0.00067315233,0.00006312238,0.00048966456,0.000029093246,0.00012627085],"category_scores_gemma":[0.0007304444,0.000031432923,0.000022094871,0.001757612,0.00020684295,0.0006586574,0.000043833526,0.00003333179,0.000006897363],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008153232,0.000054245596,0.5615591,0.000009295041,0.000006807901,2.7841304e-8,0.05766874,0.0017358644,0.0014413517,0.32717752,0.00043601255,0.049902886],"study_design_scores_gemma":[0.0003010867,0.0000032495454,0.8519047,0.000006070585,0.000003722221,1.5752842e-7,0.013050041,0.12741147,0.0005828232,0.0028531014,0.0037958492,0.000087761815],"about_ca_topic_score_codex":0.00018657288,"about_ca_topic_score_gemma":0.013610267,"teacher_disagreement_score":0.32432443,"about_ca_system_score_codex":0.0015576686,"about_ca_system_score_gemma":0.012248424,"threshold_uncertainty_score":0.9933512},"labels":[],"label_agreement":null},{"id":"W1564362335","doi":"","title":"An External Evaluation: A Case Study of a Design and Implementation Process","year":2008,"lang":"en","type":"article","venue":"SIT Digital Collections (SIT Graduate Institute)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Process (computing); Process management; Computer science; Business; Operations management; Risk analysis (engineering); Engineering; Programming language","score_opus":0.4104950060608888,"score_gpt":0.5245303794608792,"score_spread":0.11403537339999043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1564362335","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9755908,0.000019661928,0.019914027,0.00007745648,0.00025371902,0.0016577895,0.000015811434,0.000042592947,0.0024281102],"genre_scores_gemma":[0.9984187,0.0000061540695,0.00052539527,0.000029560317,0.000054056945,0.00023847906,0.000012216534,0.000009540731,0.0007058923],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99619895,0.0002662755,0.00079444825,0.00048242477,0.0020668553,0.00019103989],"domain_scores_gemma":[0.99739206,0.0001696844,0.0003150518,0.0003953789,0.0015816096,0.00014618773],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020380935,0.00017616406,0.0002497368,0.0006667129,0.0012375285,0.0005492253,0.00022839462,0.0000389403,0.00021835104],"category_scores_gemma":[0.0002620839,0.00014864161,0.00005125003,0.0023765557,0.0001512097,0.0032886595,0.000044472567,0.000112304464,0.00001969045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00073757995,0.007883428,0.26152351,0.00004685477,0.00038691764,0.0014985827,0.11531865,0.22799493,0.0005804282,0.0006585042,0.0064898985,0.3768807],"study_design_scores_gemma":[0.02122988,0.013684167,0.1402858,0.0000904463,0.00056820357,0.022031676,0.24936305,0.51890033,0.002571988,0.027081607,0.002289946,0.0019028938],"about_ca_topic_score_codex":0.00047251803,"about_ca_topic_score_gemma":0.0022149957,"teacher_disagreement_score":0.37497783,"about_ca_system_score_codex":0.00011255709,"about_ca_system_score_gemma":0.00083706825,"threshold_uncertainty_score":0.95181936},"labels":[],"label_agreement":null},{"id":"W1565934007","doi":"10.5206/cie-eci.v44i1.9267","title":"Diagnostic des conceptions en sciences susceptibles d’expliquer les différences de performances à une évaluation internationale entre le Québec et le Maroc","year":2015,"lang":"fr","type":"article","venue":"Comparative and International Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Montréal; Université du Québec à Montréal","funders":"","keywords":"Humanities; Political science; Explication; Sociology; Philosophy","score_opus":0.39088144254653556,"score_gpt":0.5425131484442631,"score_spread":0.15163170589772756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1565934007","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8585518,0.013959753,0.01017455,0.059516024,0.0025182571,0.00036779343,0.000048698865,0.00003176315,0.05483135],"genre_scores_gemma":[0.9386444,0.0027935035,0.005296593,0.00061665685,0.0004923485,0.00016541283,0.00013935374,0.0000097232105,0.051842026],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99648,0.00086104503,0.00069712556,0.0005349013,0.0011410582,0.00028588212],"domain_scores_gemma":[0.9948866,0.0022924726,0.0004378059,0.00016635109,0.0019968243,0.00021995083],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003426324,0.00027280452,0.00028351948,0.00045595775,0.0007312009,0.00078651,0.00063494674,0.00010902278,0.0014363161],"category_scores_gemma":[0.002182956,0.00024507215,0.00008878852,0.0006021497,0.0013490537,0.0029900658,0.00015150527,0.00024092683,0.00024751044],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007154565,0.0013926055,0.36956868,0.00003605202,0.00012421713,7.203896e-7,0.08878564,0.014429239,0.00028469152,0.25542384,0.048949454,0.2209333],"study_design_scores_gemma":[0.0012767015,0.0005327986,0.32472584,0.0005197743,0.000057759047,0.000054082673,0.20376256,0.12537721,0.00070228596,0.073394194,0.2690753,0.00052148383],"about_ca_topic_score_codex":0.023173742,"about_ca_topic_score_gemma":0.028240576,"teacher_disagreement_score":0.22041182,"about_ca_system_score_codex":0.0004839993,"about_ca_system_score_gemma":0.0102849845,"threshold_uncertainty_score":0.9994765},"labels":[],"label_agreement":null},{"id":"W1565979176","doi":"","title":"Evaluation par les nouveaux immigrants de leur vie au Canada","year":2010,"lang":"fr","type":"preprint","venue":"RePEc: Research Papers in Economics","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Humanities; Political science; Art","score_opus":0.14404034235383584,"score_gpt":0.458597340398251,"score_spread":0.31455699804441517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1565979176","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8084883,0.0002318168,0.000019374382,0.0040485812,0.0030127382,0.0013196745,0.0001233012,0.000014018388,0.18274216],"genre_scores_gemma":[0.9816882,0.00674818,0.0010262388,0.00032841624,0.00074207806,0.0004955109,0.00009345051,0.000057417594,0.008820536],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9868295,0.003180475,0.0020239367,0.0017206308,0.004505505,0.0017399052],"domain_scores_gemma":[0.9912745,0.0034227443,0.0006733769,0.002051515,0.0019408222,0.00063706376],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.053295642,0.00052661286,0.0008361738,0.0007296068,0.00097615574,0.00053774717,0.0022572356,0.0008556358,0.0062669874],"category_scores_gemma":[0.008283319,0.0005249708,0.00025359253,0.00048032677,0.0007009164,0.00040299437,0.00105948,0.003535355,0.00017983175],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.0000628968,0.00013659142,0.13379088,0.000045811004,0.0000720165,0.0000139279655,0.00090556894,0.05736041,0.0002445228,0.0005920162,0.00051052694,0.8062648],"study_design_scores_gemma":[0.0010196731,0.00010047179,0.2991202,0.00022042822,0.00003902972,0.0000172552,0.0032243924,0.38079926,0.00034913738,0.0037970378,0.31073403,0.0005790727],"about_ca_topic_score_codex":0.6345343,"about_ca_topic_score_gemma":0.9886815,"teacher_disagreement_score":0.80568576,"about_ca_system_score_codex":0.010766291,"about_ca_system_score_gemma":0.075598955,"threshold_uncertainty_score":0.99972016},"labels":[],"label_agreement":null},{"id":"W1567159340","doi":"10.1108/qae-09-2014-0046","title":"Self-regulation with rules","year":2015,"lang":"en","type":"article","venue":"Quality Assurance in Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Quality (philosophy); Benchmarking; Pooling; Jurisdiction; Accountability; Computer science; Accreditation; Quality assurance; Scope (computer science); Standardization; Work (physics); Autonomy; Process management; Business; Marketing; Political science; Law; Engineering","score_opus":0.25316117946801747,"score_gpt":0.538446493773278,"score_spread":0.28528531430526055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1567159340","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9576592,0.00011039744,0.0024349005,0.0052888193,0.000704992,0.0002679763,0.000002749087,0.000046488418,0.033484485],"genre_scores_gemma":[0.98522025,0.000009339842,0.012972716,0.00034128653,0.00012758195,0.000061959254,0.000022583861,0.0000056546974,0.0012386519],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9968841,0.00053571264,0.0005927792,0.00029979728,0.0015426268,0.00014495726],"domain_scores_gemma":[0.99786615,0.0004686976,0.00030726613,0.00044843575,0.00081396213,0.00009548487],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007451222,0.000094182295,0.00016689092,0.00020898732,0.00005801887,0.00016160459,0.0002532826,0.000052575935,0.00019831645],"category_scores_gemma":[0.0011156158,0.00006935918,0.000024242996,0.00073709927,0.000035592977,0.000923433,0.00001480214,0.00009123591,0.0005936531],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000076839686,0.0005287572,0.847904,0.000018187671,0.000006595525,1.6631668e-7,0.0077952933,0.0028425853,0.000041935255,0.02395643,0.0069401893,0.10988898],"study_design_scores_gemma":[0.00045235548,0.000049860857,0.89466023,0.000024913375,0.0000033330616,0.0000021700355,0.005352902,0.0037086664,0.0001111192,0.04041516,0.055079922,0.00013933641],"about_ca_topic_score_codex":0.00017893386,"about_ca_topic_score_gemma":0.0008908564,"teacher_disagreement_score":0.109749645,"about_ca_system_score_codex":0.00022234538,"about_ca_system_score_gemma":0.0016435597,"threshold_uncertainty_score":0.7630408},"labels":[],"label_agreement":null},{"id":"W1567314661","doi":"10.7202/1007733ar","title":"Le sens construit autour de la différenciation pédagogique dans le cadre d’une recherche-action-formation","year":2012,"lang":"fr","type":"article","venue":"Éducation et francophonie","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Commission Scolaire des Hautes Rivières; Université du Québec en Outaouais; Université du Québec à Trois-Rivières","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.21880465813844904,"score_gpt":0.4711848055050934,"score_spread":0.2523801473666444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1567314661","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50010353,0.0014078368,0.23526473,0.056290947,0.010529081,0.0008079967,0.00008199161,0.0001953218,0.19531855],"genre_scores_gemma":[0.95665187,0.001064719,0.00787486,0.0015111333,0.0009109089,0.000131393,0.00013620046,0.000036476806,0.031682417],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99193454,0.004813364,0.001049038,0.00041844434,0.0011482182,0.0006363785],"domain_scores_gemma":[0.9950576,0.0025551987,0.0007994524,0.00061046344,0.0006446117,0.00033267448],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.017359894,0.0003223163,0.00034923555,0.00033510415,0.0007141389,0.00042773818,0.00037104098,0.0007003858,0.0028047308],"category_scores_gemma":[0.0023570752,0.0003413984,0.00016417117,0.0016065226,0.00029441883,0.0038797355,0.000060460436,0.0008903012,0.0021746436],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008259289,0.0026409288,0.045426734,0.00025531216,0.00012016062,0.000003565165,0.2990926,0.0062537724,0.024469666,0.14317948,0.08107608,0.39739913],"study_design_scores_gemma":[0.0021033043,0.00012557373,0.3029353,0.00020531639,0.00007809699,0.00023124597,0.14283642,0.030140018,0.027370114,0.027434688,0.46565795,0.0008819923],"about_ca_topic_score_codex":0.003738203,"about_ca_topic_score_gemma":0.003093461,"teacher_disagreement_score":0.45654833,"about_ca_system_score_codex":0.0014195275,"about_ca_system_score_gemma":0.007928476,"threshold_uncertainty_score":0.9999038},"labels":[],"label_agreement":null},{"id":"W1567317673","doi":"10.1108/ce-12-2009-0005","title":"Approaches to Measuring Implementation Fidelity in School-Based Program Evaluations","year":2009,"lang":"en","type":"article","venue":"Journal of research in character education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University","funders":"","keywords":"Fidelity; Explication; Context (archaeology); Computer science; Intervention (counseling); Medical education; Psychology; Medicine","score_opus":0.8354110944629519,"score_gpt":0.7000599712227069,"score_spread":0.135351123240245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1567317673","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9576436,0.000055707726,0.00031218314,0.03979021,0.00037402025,0.000902814,0.0000013077296,0.0000051648963,0.0009149933],"genre_scores_gemma":[0.99288154,0.000013254447,0.006110374,0.00041697835,0.0003656866,0.00011076302,0.000008995798,0.000004175332,0.000088248555],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99347585,0.0012183998,0.0012426701,0.00023779567,0.0035208878,0.0003044067],"domain_scores_gemma":[0.99677306,0.0005259751,0.00036241522,0.0002952589,0.0018267469,0.00021656595],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.039118875,0.000082693354,0.00018805925,0.002691591,0.00009626048,0.00039075158,0.00046900433,0.000047812395,0.00046362393],"category_scores_gemma":[0.002725299,0.0000657468,0.00006115317,0.0024854785,0.00002375285,0.0011367988,0.000023533426,0.000512956,0.00008188169],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008806446,0.00085102697,0.19643073,0.0000059086647,0.0000025008371,9.0221425e-7,0.0011915411,0.0009948856,0.0007026774,0.0002390021,0.0014683142,0.7980245],"study_design_scores_gemma":[0.00054662797,0.00039825775,0.97911006,0.00011674484,0.0000022191605,0.0000029432165,0.0031795711,0.003000243,0.00082229223,0.0073767314,0.0053763087,0.00006801845],"about_ca_topic_score_codex":0.0000424789,"about_ca_topic_score_gemma":0.00022907976,"teacher_disagreement_score":0.7979564,"about_ca_system_score_codex":0.00082386384,"about_ca_system_score_gemma":0.0040142597,"threshold_uncertainty_score":0.9894293},"labels":[],"label_agreement":null},{"id":"W1568343591","doi":"10.18438/b83k6t","title":"Newcastle Libraries’ Evaluation Strategy: Evidence Based Practice in Challenging Times","year":2014,"lang":"en","type":"article","venue":"Evidence Based Library and Information Practice","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Library science; World Wide Web; Data science","score_opus":0.14970056324104922,"score_gpt":0.4420796375370366,"score_spread":0.2923790742959874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1568343591","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013283197,0.006923752,0.09289461,0.7452479,0.001086964,0.0027064474,0.000017226557,0.00041178984,0.13742809],"genre_scores_gemma":[0.8920895,0.0016361496,0.014611707,0.09100967,0.00015463376,0.0001292928,0.000051853436,0.000016409846,0.00030078058],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99133545,0.0033070669,0.0014732633,0.00049037306,0.0030296627,0.00036418324],"domain_scores_gemma":[0.96339214,0.033593733,0.0013083547,0.0007855481,0.0006991994,0.0002210342],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.020994728,0.00027521505,0.00030565483,0.00081951206,0.00036154475,0.0027098616,0.0006544368,0.00015968367,0.004344106],"category_scores_gemma":[0.07239628,0.00023233984,0.00006976773,0.0017787919,0.000102308186,0.5100697,0.00015730344,0.00046806328,0.0006657323],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00164345,0.0002154281,0.0035577142,0.00014223199,0.000023074466,0.0000051152015,0.0012461429,0.120763585,0.00006758885,0.33103758,0.008884455,0.5324136],"study_design_scores_gemma":[0.00074930064,0.00030086236,0.014099462,0.0005348933,0.00004170677,0.000010170353,0.0026765207,0.64517885,0.00044854646,0.0013795218,0.334323,0.00025719136],"about_ca_topic_score_codex":0.00001810917,"about_ca_topic_score_gemma":3.9941037e-7,"teacher_disagreement_score":0.8788063,"about_ca_system_score_codex":0.000048126924,"about_ca_system_score_gemma":0.0016293011,"threshold_uncertainty_score":0.9983254},"labels":[],"label_agreement":null},{"id":"W1569252761","doi":"10.1002/ev.20079","title":"Postscript: That Was Then, This Is Now","year":2014,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec; Université du Québec en Outaouais; University of Ottawa","funders":"","keywords":"Sustainability; Public relations; Organizational communication; Knowledge management; Political science; Sociology; Computer science","score_opus":0.2843044164649911,"score_gpt":0.5111892279361946,"score_spread":0.22688481147120348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1569252761","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16846041,0.00076728343,0.1952271,0.062169574,0.012724369,0.004735348,0.00008276101,0.0005188336,0.5553143],"genre_scores_gemma":[0.9078361,0.00006659588,0.0045792065,0.0028118482,0.0007122841,0.00031883872,0.000071883005,0.000027942864,0.083575346],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956877,0.0003977679,0.00053022377,0.0005117814,0.0026241962,0.0002483266],"domain_scores_gemma":[0.9965988,0.0009419183,0.00030526437,0.0006957818,0.0013222275,0.00013604078],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.010212685,0.00016349897,0.00021920323,0.00038972197,0.00055864465,0.0003484067,0.00036644356,0.000104453335,0.014008028],"category_scores_gemma":[0.0026833683,0.00012683889,0.00019767841,0.00072455686,0.000038188682,0.0007469842,0.000038958144,0.00010765733,0.0023594436],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031366428,0.000054823882,0.0043027694,0.000002792,0.000021555767,1.5861616e-8,0.0013351412,0.00040627617,0.00039873936,0.0024497386,0.38133636,0.6096604],"study_design_scores_gemma":[0.0011819873,0.00014201445,0.023521986,0.000011064852,0.000079810125,0.0000025990744,0.00030165288,0.22105752,0.002567693,0.046035934,0.7049364,0.00016134958],"about_ca_topic_score_codex":0.00008594883,"about_ca_topic_score_gemma":0.00037661055,"teacher_disagreement_score":0.73937565,"about_ca_system_score_codex":0.00017458298,"about_ca_system_score_gemma":0.00041495118,"threshold_uncertainty_score":0.9984173},"labels":[],"label_agreement":null},{"id":"W1570565511","doi":"10.3138/cjpe.27.007","title":"Funnell, S. C., and Rogers, P. J. (2011). <i>Purposeful Program Theory.</i> San Francisco, CA: Jossey-Bass. 550 pages.","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Bass (fish); Psychology; Fishery; Biology","score_opus":0.24747467403425955,"score_gpt":0.4667965692241588,"score_spread":0.21932189518989925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1570565511","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94051665,0.027369635,0.0028285503,0.005193455,0.00466042,0.0055853734,0.000045175708,0.00007903758,0.013721698],"genre_scores_gemma":[0.9922119,0.00010553411,0.005987073,0.00051822595,0.0005898173,0.00019102063,0.000027196655,0.000027515294,0.0003417412],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99360406,0.001152315,0.0013250543,0.00033739334,0.0027898927,0.00079130393],"domain_scores_gemma":[0.9941518,0.00043913882,0.0010240566,0.00049666007,0.0024067063,0.0014816732],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.029777812,0.00028097525,0.00045157562,0.0007577295,0.00044683376,0.0007934796,0.0005723688,0.00018342979,0.0085403845],"category_scores_gemma":[0.0020338648,0.00021212733,0.00017520672,0.0006829256,0.00028192505,0.0017194418,0.000030799638,0.0004410407,0.00042495326],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028822718,0.00012233776,0.06384842,0.000009514851,0.000054053708,0.0000055810006,0.0014258894,0.00013437336,0.0000420358,0.0007089689,0.024316993,0.909303],"study_design_scores_gemma":[0.0024091532,0.0015771047,0.28764936,0.00009180417,0.0003896477,0.0002710002,0.0036298751,0.011170452,0.00030760083,0.0149074225,0.676993,0.0006035415],"about_ca_topic_score_codex":0.00029411778,"about_ca_topic_score_gemma":0.006117131,"teacher_disagreement_score":0.90869945,"about_ca_system_score_codex":0.00035750234,"about_ca_system_score_gemma":0.002994394,"threshold_uncertainty_score":0.99904794},"labels":[],"label_agreement":null},{"id":"W1570703067","doi":"","title":"Evaluation and Counselling: A Reply to Hiebert","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Counselling and Psychotherapy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology","score_opus":0.14974371368120584,"score_gpt":0.47067672138019273,"score_spread":0.3209330076989869,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1570703067","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6831602,0.0153054325,0.29419038,0.0050966577,0.0010054462,0.00021447851,0.0000035870632,0.0000042753927,0.0010195583],"genre_scores_gemma":[0.92205286,0.061436404,0.0019460821,0.012790599,0.0006013448,0.000003168367,0.0000011773494,0.000024924326,0.0011434322],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99724394,0.00014372432,0.00071274297,0.00021364044,0.0014370253,0.0002489141],"domain_scores_gemma":[0.9965766,0.00046878867,0.00031172243,0.00021070208,0.0016963264,0.0007358385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0255955,0.000114212235,0.0002123849,0.00068293064,0.00022656727,0.00032414033,0.00020630097,0.00005794633,0.0005575983],"category_scores_gemma":[0.00003332699,0.00008875139,0.000049659906,0.00046139627,0.00006617441,0.00021980169,8.3406846e-8,0.00015615487,0.000020807269],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020579087,0.00001882036,0.004572958,0.0000037128075,0.000059868216,0.0000149727,0.02751921,0.0010289403,0.00040308735,0.0021616481,0.017139193,0.9468718],"study_design_scores_gemma":[0.0006985655,0.00028220427,0.0019157847,0.000052226063,0.000021017993,0.000098043,0.00027856522,0.0025029122,0.00008952288,0.14498688,0.8489448,0.00012949598],"about_ca_topic_score_codex":0.00019770488,"about_ca_topic_score_gemma":0.011050903,"teacher_disagreement_score":0.9467423,"about_ca_system_score_codex":0.000028275439,"about_ca_system_score_gemma":0.0004845984,"threshold_uncertainty_score":0.887094},"labels":[],"label_agreement":null},{"id":"W1571693603","doi":"10.18438/b88s52","title":"An Introduction to Critical Appraisal","year":2016,"lang":"en","type":"article","venue":"Evidence Based Library and Information Practice","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Critical appraisal; Computer science; Data science; Medicine; Alternative medicine","score_opus":0.07868370735992343,"score_gpt":0.47110780467720526,"score_spread":0.39242409731728184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1571693603","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010048462,0.000029896313,0.16054827,0.825445,0.00090457813,0.00017240342,0.000009877854,0.000100664794,0.0027408428],"genre_scores_gemma":[0.8779729,0.00012594997,0.02580015,0.09490507,0.0007761117,0.000045573786,0.000012777551,0.0000071140703,0.00035436783],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973383,0.0005495626,0.00061052304,0.00025634267,0.0010787417,0.00016653059],"domain_scores_gemma":[0.986793,0.011896051,0.0002145293,0.0005184928,0.00030916205,0.00026879314],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0038335358,0.0001029927,0.00011184336,0.00033770959,0.00019542054,0.0010182486,0.00032962867,0.000055169367,0.004872731],"category_scores_gemma":[0.044456672,0.000062382416,0.000025974527,0.00065126707,0.000071997674,0.41261277,0.00007029565,0.00009455487,0.001405082],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006313322,0.00005976159,0.0016592001,0.0000113523165,0.0000037170005,7.985037e-7,0.00034340046,0.00026453694,0.0008595607,0.6274169,0.04792086,0.3208286],"study_design_scores_gemma":[0.00021029,0.0003763575,0.013934105,0.000038603423,0.000007801968,0.000013281154,0.00086295034,0.004649382,0.0023469585,0.0006390432,0.9767917,0.00012954626],"about_ca_topic_score_codex":8.5937637e-7,"about_ca_topic_score_gemma":3.4978285e-8,"teacher_disagreement_score":0.9288708,"about_ca_system_score_codex":0.000010975702,"about_ca_system_score_gemma":0.00024069856,"threshold_uncertainty_score":0.9993724},"labels":[],"label_agreement":null},{"id":"W1574059025","doi":"10.1002/9781444311747.ch6","title":"Evaluation of Knowledge to Action","year":2009,"lang":"en","type":"other","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia; St. Michael's Hospital; Centre for Advancing Health Outcomes; Sunnybrook Health Science Centre; University of Toronto","funders":"","keywords":"Action (physics); Computer science; Data science; Physics","score_opus":0.5672465334025848,"score_gpt":0.6308915374916904,"score_spread":0.06364500408910556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1574059025","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018707888,0.00017786537,0.0024747583,0.00030130192,0.0006193007,0.00044715503,0.0000046499376,0.000039527655,0.99574834],"genre_scores_gemma":[0.018483305,0.000019576948,0.0011182021,0.00015418575,0.00020853867,0.000019372701,0.000007117485,0.000038277132,0.97995144],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9950187,0.00036379002,0.00041045237,0.00027945286,0.0038358457,0.00009172965],"domain_scores_gemma":[0.9979385,0.00010125276,0.0002886648,0.00049439725,0.0011169713,0.00006020548],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.010657231,0.00010752829,0.00022579529,0.00077607855,0.000019654772,0.000036725938,0.00030537025,0.00012319589,0.12098882],"category_scores_gemma":[0.0008481845,0.00007393185,0.000066139204,0.00061777025,0.000012569127,0.000068336114,0.000029709074,0.000056097044,0.006377924],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012681709,0.000023727647,0.000028937602,0.0000012480606,0.0000053183953,8.109391e-9,0.000054077682,0.00005342061,0.000023712239,0.00027195402,0.55297565,0.44656068],"study_design_scores_gemma":[0.00023025481,0.000075494565,0.0040103123,0.00003893967,0.00004970665,2.599994e-7,0.00013552025,0.0055063227,0.00024545705,0.0022872675,0.98731655,0.00010390859],"about_ca_topic_score_codex":0.000039942977,"about_ca_topic_score_gemma":0.0020746395,"teacher_disagreement_score":0.44645676,"about_ca_system_score_codex":0.0000874566,"about_ca_system_score_gemma":0.0005052234,"threshold_uncertainty_score":0.99439573},"labels":[],"label_agreement":null},{"id":"W1574893375","doi":"","title":"La formation à la recherche des enseignants au Québec","year":2008,"lang":"fr","type":"article","venue":"Recherche & formation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.906762505349791,"score_gpt":0.580926894300194,"score_spread":0.325835611049597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1574893375","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6824362,0.0025637322,0.16847658,0.009348462,0.00069023424,0.0006689878,0.000027996884,0.0001604289,0.13562731],"genre_scores_gemma":[0.8637692,0.0115330415,0.06614126,0.0006740915,0.0003015467,0.00011638736,0.00009881049,0.000050643444,0.057315063],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9787673,0.016358119,0.0017078362,0.0004679646,0.001944539,0.0007542822],"domain_scores_gemma":[0.9856921,0.011678178,0.0007298026,0.00065401604,0.0009826284,0.0002632807],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.045576844,0.0003994996,0.00044120615,0.0004566435,0.0009234321,0.0003299478,0.0006506339,0.001645915,0.0013552167],"category_scores_gemma":[0.01217516,0.00034895592,0.000262506,0.0017651991,0.0005535232,0.00777955,0.00013358031,0.0017506552,0.004603916],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.0000705671,0.00016816496,0.0017701731,0.00015771476,0.000024245708,0.0000070668284,0.13980468,0.00026339194,0.0006464935,0.0019360369,0.006329803,0.84882164],"study_design_scores_gemma":[0.0023126162,0.0004542059,0.028842585,0.0008125274,0.00012619956,0.001705994,0.027035797,0.11239251,0.016984904,0.044164684,0.76411307,0.0010549072],"about_ca_topic_score_codex":0.007993825,"about_ca_topic_score_gemma":0.015105579,"teacher_disagreement_score":0.84776676,"about_ca_system_score_codex":0.008599752,"about_ca_system_score_gemma":0.0073176334,"threshold_uncertainty_score":0.9998962},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"empirical","about_ca_system":true,"about_ca_topic":true,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"low"}],"label_agreement":"split"},{"id":"W1574895693","doi":"10.71781/6877","title":"Une évaluation qualitative d’un programme de préparation à l’examen professionnel québécois à partir de la perception des candidates infirmières","year":2012,"lang":"fr","type":"dissertation","venue":"Open MIND","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Licensure; Medical education; Psychology; Focus group; Medicine; Sociology","score_opus":0.3138167850655047,"score_gpt":0.549885459909182,"score_spread":0.23606867484367733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1574895693","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97750354,0.0003452854,0.0023781473,0.0017569505,0.00058269885,0.0025189102,0.000055323235,0.000008565076,0.014850575],"genre_scores_gemma":[0.9368681,0.00016014728,0.03759651,0.000084928964,0.00026167126,0.0010479973,0.0015732334,0.000047401107,0.022360036],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9874914,0.007012304,0.0015983523,0.00088442425,0.0019770288,0.0010364425],"domain_scores_gemma":[0.99403757,0.0022439628,0.0014315317,0.00055086793,0.0012735334,0.00046251368],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.02969254,0.00056899077,0.00065944105,0.00037097005,0.0017864058,0.002265863,0.0010130769,0.0007278851,0.016901959],"category_scores_gemma":[0.0025432748,0.00048343925,0.00018217882,0.0011898131,0.0005837267,0.0029186248,0.00016413897,0.0006036523,0.002079556],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026995665,0.00042266276,0.023397291,0.000049167735,0.000066242304,0.0000014804803,0.5148257,0.00046361436,0.006911805,0.0002612721,0.00024130705,0.4530895],"study_design_scores_gemma":[0.0012823049,0.00039752296,0.49716952,0.00057946733,0.00032399897,0.000016193006,0.43580723,0.029351875,0.0090210205,0.009508433,0.015863663,0.00067877234],"about_ca_topic_score_codex":0.023848172,"about_ca_topic_score_gemma":0.072223336,"teacher_disagreement_score":0.47377223,"about_ca_system_score_codex":0.0011227401,"about_ca_system_score_gemma":0.0054140515,"threshold_uncertainty_score":0.9997617},"labels":[],"label_agreement":null},{"id":"W1575009634","doi":"","title":"Information Seeking Experiences of Canadian Pharmaceutical Policy Makers","year":2010,"lang":"en","type":"article","venue":"E-LIS Repository (University of Naples Federico II)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Public relations; Qualitative research; Information seeking; Context (archaeology); Population; Exploratory research; Psychology; Social psychology; Political science; Medicine; Sociology","score_opus":0.06312246244477958,"score_gpt":0.3596853438530347,"score_spread":0.2965628814082551,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1575009634","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9215405,0.000013329211,0.00036340175,0.0012444627,0.0005704672,0.00012307234,0.0000076809765,0.000019348208,0.07611776],"genre_scores_gemma":[0.99671876,0.000017828579,0.0013153111,0.00013796898,0.000058725156,6.304338e-7,0.0000060984394,0.0000029145108,0.0017417656],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.99815017,0.00008485153,0.00036353339,0.00015749784,0.0010308096,0.00021316158],"domain_scores_gemma":[0.998415,0.00013601406,0.00039182213,0.0003237985,0.0004910146,0.00024238601],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008457837,0.00010145483,0.000211632,0.0009991557,0.0007730359,0.00011479248,0.00068281323,0.000102902304,0.001490399],"category_scores_gemma":[0.00026535217,0.00010138815,0.00011199979,0.0014657575,0.00029154704,0.0015255456,0.00013674263,0.0001736852,0.000050394974],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037738986,0.00030897788,0.065387435,0.00009125461,0.00018467735,0.000034214914,0.65416205,0.0005390596,0.0882505,0.017999468,0.046925873,0.12573908],"study_design_scores_gemma":[0.00083658315,0.000172646,0.046325922,0.00002291541,0.000026007621,0.000035721612,0.35225776,0.011074458,0.008563157,0.0001533871,0.5802511,0.00028035944],"about_ca_topic_score_codex":0.026472144,"about_ca_topic_score_gemma":0.014544577,"teacher_disagreement_score":0.5333252,"about_ca_system_score_codex":0.00008811372,"about_ca_system_score_gemma":0.001138175,"threshold_uncertainty_score":0.9994224},"labels":[],"label_agreement":null},{"id":"W1576984331","doi":"","title":"It's Just Plain Common(s) Sense: Grounding Space Planning in Evidence-Based Research","year":2010,"lang":"en","type":"article","venue":"Scholarship@Western (Western University)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Excellence; Library science; Space (punctuation); Public relations; Sociology; Resource (disambiguation); Computer science; Political science","score_opus":0.7509172943855567,"score_gpt":0.5750161825801468,"score_spread":0.1759011118054099,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1576984331","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99097544,0.000046351714,0.00049490866,0.005118174,0.0007679671,0.00043709384,0.000009048473,0.000081282014,0.0020697515],"genre_scores_gemma":[0.9917862,0.00001856999,0.00014666808,0.000763755,0.00015646171,0.0000033729411,0.000009355313,0.000028190214,0.007087471],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99185956,0.0020627957,0.0006869365,0.0010078878,0.0034903006,0.00089250406],"domain_scores_gemma":[0.9925217,0.004708507,0.0003355999,0.0012736502,0.0007482159,0.00041234578],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.018510532,0.00031976125,0.0004669265,0.0027858084,0.0007845652,0.0014606552,0.001875323,0.0003353078,0.00051967887],"category_scores_gemma":[0.0020375634,0.0003108053,0.0001426795,0.0031692928,0.00033909603,0.0047293543,0.0006028963,0.002515854,0.000901067],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019861422,0.00008525378,0.99390024,0.00001717857,0.00000891443,0.0004218525,0.0014235888,0.0005959413,0.001936129,0.00032017787,0.00002544863,0.0010666611],"study_design_scores_gemma":[0.001451289,0.00015761689,0.97798216,0.0005635816,0.000015231691,0.000026984675,0.004383099,0.00009929702,0.0016942155,0.00040128763,0.012832041,0.00039317162],"about_ca_topic_score_codex":0.000026742184,"about_ca_topic_score_gemma":0.011820673,"teacher_disagreement_score":0.01647297,"about_ca_system_score_codex":0.00042357907,"about_ca_system_score_gemma":0.0006656727,"threshold_uncertainty_score":0.9999344},"labels":[],"label_agreement":null},{"id":"W1578688706","doi":"10.1093/oxfordhb/9780199352722.013.21","title":"Decision Support Tools in the Evaluation of Risk for Violence","year":2015,"lang":"en","type":"book","venue":"Oxford University Press eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Strengths and weaknesses; Empirical research; Decision support system; Risk assessment; Management science; Selection (genetic algorithm); Risk management; Psychology; Risk analysis (engineering); Computer science; Knowledge management; Engineering; Business; Social psychology; Artificial intelligence; Computer security","score_opus":0.3009156719050151,"score_gpt":0.44002985768616126,"score_spread":0.13911418578114615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1578688706","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005060893,0.000054179385,0.0037217545,0.000020092948,0.0003600426,0.0016478222,0.00046608373,0.00001189983,0.98865724],"genre_scores_gemma":[0.04698543,0.00048919633,0.0028068763,0.00015260106,0.0002074379,0.000034119264,0.00029543665,0.000034672565,0.9489942],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9938717,0.0006577705,0.0006018132,0.0004613658,0.004206575,0.00020076272],"domain_scores_gemma":[0.9928864,0.0030260882,0.00089075457,0.00091270515,0.002217436,0.000066614135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019490765,0.00019929584,0.0003959412,0.000389779,0.00013949168,0.00010850193,0.0016025183,0.00024584186,0.00014494808],"category_scores_gemma":[0.0016858219,0.00014366812,0.00020113478,0.00007742779,0.0001266078,0.00031209414,0.00020777383,0.00028196545,0.0000041173794],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039826147,0.000044640892,0.00021076744,0.000017273152,0.00002764541,0.0000027450826,0.002065992,0.0016335327,0.0000012459657,0.04122907,0.05843522,0.8959336],"study_design_scores_gemma":[0.0015828016,0.00014740705,0.0010804744,0.00012863167,0.0001959451,0.0000012877655,0.00086845097,0.00929545,0.000014861102,0.0532674,0.93325025,0.00016702365],"about_ca_topic_score_codex":0.000025531383,"about_ca_topic_score_gemma":0.00023567985,"teacher_disagreement_score":0.89576656,"about_ca_system_score_codex":0.00036499917,"about_ca_system_score_gemma":0.0021756873,"threshold_uncertainty_score":0.67551494},"labels":[],"label_agreement":null},{"id":"W1578941704","doi":"","title":"Seeing Schools from the Inside Out: The Role of Students in School Self-Assessment.","year":2002,"lang":"en","type":"article","venue":"Education Canada","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Facilitator; Mandate; Class (philosophy); Focus group; Pedagogy; Psychology; Medical education; Mathematics education; Public relations; Political science; Sociology; Medicine; Computer science; Social psychology","score_opus":0.06293802923758693,"score_gpt":0.4309967134781868,"score_spread":0.36805868424059984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1578941704","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9713269,0.00054128806,0.0000135130695,0.0136542935,0.0011597243,0.00031771327,0.000011195965,0.000007098091,0.012968294],"genre_scores_gemma":[0.99524903,0.000040685853,0.00028701796,0.0031127268,0.00015133433,0.000054687924,0.00000545412,0.0000053414465,0.0010937308],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9966622,0.0003419157,0.0005466744,0.000216845,0.0020820904,0.00015025146],"domain_scores_gemma":[0.9979261,0.00081747276,0.00027189162,0.0006208371,0.0002789745,0.00008470561],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017903056,0.00009068148,0.00012946718,0.000072303395,0.00019182479,0.00021339841,0.00097318756,0.000026744006,0.0034867742],"category_scores_gemma":[0.00053653587,0.000051138937,0.000030345904,0.0005297931,0.000017978316,0.00027457898,0.00007754019,0.00023809115,0.00011153578],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011074363,0.00007699727,0.9059711,5.2435956e-7,0.000010816169,1.3805146e-7,0.00157827,0.00013895014,0.000039095314,0.00024525716,0.0748336,0.017104156],"study_design_scores_gemma":[0.00015754989,0.0000072268235,0.8113031,0.000015782793,0.0000067571796,3.4513656e-7,0.022111997,0.0022316938,0.000091326656,0.0018185638,0.16219349,0.00006218869],"about_ca_topic_score_codex":0.3185647,"about_ca_topic_score_gemma":0.73648757,"teacher_disagreement_score":0.41792285,"about_ca_system_score_codex":0.000490865,"about_ca_system_score_gemma":0.004275512,"threshold_uncertainty_score":0.9974242},"labels":[],"label_agreement":null},{"id":"W1579268629","doi":"10.18438/b8n03s","title":"A New Path: Research Methods","year":2016,"lang":"en","type":"article","venue":"Evidence Based Library and Information Practice","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Royal Saskatchewan Museum; University of Saskatchewan","funders":"","keywords":"Computer science; Path (computing); Data science; Information retrieval; Programming language","score_opus":0.3553617761240749,"score_gpt":0.5896786912896481,"score_spread":0.23431691516557324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1579268629","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001067984,0.0005223514,0.47937027,0.46754396,0.00037749886,0.00036888992,0.0000065661457,0.0000976396,0.05064484],"genre_scores_gemma":[0.12776719,0.005364567,0.6954282,0.14818451,0.0004916349,0.00009726871,0.00001362438,0.000020716592,0.022632292],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99451184,0.0023814149,0.0007491922,0.00023366927,0.0018825763,0.00024131675],"domain_scores_gemma":[0.96736276,0.031025479,0.00038486003,0.0005558596,0.0004192048,0.00025183812],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["scholarly_communication","insufficient_payload"],"category_scores_codex":[0.019096386,0.00010207174,0.00013415943,0.0005231365,0.00028695748,0.001172446,0.00051401375,0.000075293676,0.009008428],"category_scores_gemma":[0.034719285,0.000057035588,0.000040956125,0.0013277907,0.00008363216,0.35111284,0.00019947275,0.0002069481,0.0019669707],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021284696,0.000010487882,0.0008529546,0.0000064826327,0.000003702014,6.816803e-7,0.00018706132,0.0000127600515,0.00022163174,0.19971453,0.055196043,0.7435808],"study_design_scores_gemma":[0.00037021717,0.00017129918,0.008921914,0.00014281888,0.000005307685,0.000008499707,0.00077571825,0.0027823222,0.002959001,0.0070145023,0.97674435,0.00010404612],"about_ca_topic_score_codex":0.0000054252173,"about_ca_topic_score_gemma":4.56441e-8,"teacher_disagreement_score":0.9215483,"about_ca_system_score_codex":0.000017160797,"about_ca_system_score_gemma":0.0010524786,"threshold_uncertainty_score":0.99986446},"labels":[],"label_agreement":null},{"id":"W1579766672","doi":"10.1108/10650740910967348","title":"The quantitative crunch","year":2009,"lang":"en","type":"article","venue":"Campus-Wide Information Systems","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of the Fraser Valley","funders":"","keywords":"Originality; Publishing; Discipline; Transparency (behavior); Leverage (statistics); Public relations; Citation; Research Assessment Exercise; Political science; Engineering ethics; Sociology; Computer science; Library science; Qualitative research; Higher education; Engineering; Social science","score_opus":0.12414161484167445,"score_gpt":0.4548711511204507,"score_spread":0.3307295362787762,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1579766672","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13832061,0.001331624,0.16651851,0.021209791,0.008802047,0.0025679953,0.00004464906,0.00037447218,0.6608303],"genre_scores_gemma":[0.99408454,0.000042688578,0.00020796357,0.0020676013,0.000079487545,0.000039772585,0.000017370885,0.000003084785,0.0034575004],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957717,0.00028015103,0.001378173,0.0001447867,0.0021627233,0.00026247193],"domain_scores_gemma":[0.99524885,0.0019685868,0.0007768131,0.0006148061,0.0012861661,0.00010476825],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0076259775,0.00013842805,0.00021081252,0.00022606473,0.0006612202,0.001624984,0.00066463026,0.00007297367,0.00010744835],"category_scores_gemma":[0.003300349,0.00007617382,0.000092452814,0.0007479817,0.000066914734,0.0030032115,0.000033817367,0.00014732347,0.005468511],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008742851,0.00002827687,0.008550297,0.000011844864,0.00003229679,9.657914e-7,0.010073911,0.013508602,0.000044015334,0.48194206,0.29600316,0.18971714],"study_design_scores_gemma":[0.0003486152,0.00012357082,0.026481368,0.000020597157,0.00000426988,0.000008544558,0.012707009,0.046864375,0.00003902098,0.004107742,0.90915006,0.00014479947],"about_ca_topic_score_codex":0.000012765865,"about_ca_topic_score_gemma":0.000008123419,"teacher_disagreement_score":0.8557639,"about_ca_system_score_codex":0.00009615267,"about_ca_system_score_gemma":0.00021819488,"threshold_uncertainty_score":0.9994114},"labels":[],"label_agreement":null},{"id":"W1581296090","doi":"10.18438/b8t307","title":"Research Methods: The Most Significant Change Technique","year":2014,"lang":"en","type":"article","venue":"Evidence Based Library and Information Practice","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Data science","score_opus":0.3532059426890887,"score_gpt":0.5617963373297742,"score_spread":0.20859039464068546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1581296090","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006849464,0.00044837067,0.3463112,0.57487833,0.00038840546,0.0022229773,0.000008503946,0.00014596709,0.0749113],"genre_scores_gemma":[0.47444883,0.0026789517,0.16892073,0.3493578,0.0005739656,0.0024317156,0.000037961385,0.000021397476,0.0015286389],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99182004,0.0052325353,0.0007102525,0.00021934015,0.0017811767,0.00023666241],"domain_scores_gemma":[0.9669976,0.03125501,0.00044417044,0.00069640856,0.00048529153,0.00012146548],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","scholarly_communication"],"category_scores_codex":[0.045337457,0.00010962742,0.00013409772,0.00043611124,0.00063059945,0.001593075,0.0007413691,0.000080297104,0.001457264],"category_scores_gemma":[0.024962874,0.0000629548,0.00003434356,0.0019052499,0.00017847554,0.19848076,0.00022486146,0.00047200482,0.0005049004],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017848305,0.000029114806,0.0005601516,0.00002571106,0.0000053035405,4.159036e-7,0.00068456103,0.00011752786,0.00020863481,0.3939653,0.016119976,0.58810484],"study_design_scores_gemma":[0.00011801492,0.00017725199,0.006020333,0.000074020674,0.0000065654303,0.0000066790503,0.002449173,0.042862523,0.0036930097,0.0031452256,0.9413517,0.0000954971],"about_ca_topic_score_codex":0.000012535436,"about_ca_topic_score_gemma":7.175303e-8,"teacher_disagreement_score":0.92523175,"about_ca_system_score_codex":0.000012206582,"about_ca_system_score_gemma":0.00031434846,"threshold_uncertainty_score":0.9994555},"labels":[],"label_agreement":null},{"id":"W1582856777","doi":"","title":"Making it Work: Identifying the Challenges of Collaborative International Research, 10(11)","year":2006,"lang":"en","type":"article","venue":"eCite Digital Repository (University of Tasmania)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Work (physics); Sociology; Engineering ethics; Process (computing); Reflection (computer programming); Scale (ratio); Public relations; Knowledge management; Political science; Engineering; Computer science","score_opus":0.3139638232495192,"score_gpt":0.44903734616696656,"score_spread":0.13507352291744734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1582856777","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5809559,0.0002741038,0.00046572482,0.0026977672,0.00039512262,0.00018152567,0.000028161938,0.000016322023,0.4149854],"genre_scores_gemma":[0.9771395,0.0000279042,0.00024644216,0.000010205103,0.00007527396,4.6715382e-7,0.000004683972,0.0000046403366,0.02249092],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9968085,0.00020192903,0.0003347273,0.00028906827,0.0022013763,0.00016439181],"domain_scores_gemma":[0.99672645,0.00082956447,0.0004344012,0.00039357794,0.0015813602,0.0000346191],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016767057,0.00008555226,0.00017380461,0.00028794087,0.00038199968,0.0002837865,0.0010334547,0.0000532747,0.0003191748],"category_scores_gemma":[0.00026925447,0.000073189054,0.0001107875,0.00078971044,0.00037335852,0.0013019904,0.0003605554,0.000107746055,0.00007617224],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014274683,0.0013681722,0.32939142,0.000111629925,0.00055120676,0.0002620053,0.0384297,0.006223373,0.004194826,0.16877079,0.3232227,0.12604669],"study_design_scores_gemma":[0.0011131846,0.00023012367,0.5196842,0.00033806034,0.00003325745,0.000019034756,0.16309397,0.0027686874,0.0012944076,0.012935053,0.29813448,0.00035556513],"about_ca_topic_score_codex":0.000037061025,"about_ca_topic_score_gemma":0.0002562003,"teacher_disagreement_score":0.39618355,"about_ca_system_score_codex":0.0000917309,"about_ca_system_score_gemma":0.00015375474,"threshold_uncertainty_score":0.34947404},"labels":[],"label_agreement":null},{"id":"W1587899009","doi":"10.4212/cjhp.v54i2.639","title":"Research: Issues of Quantity and Quality","year":2001,"lang":"en","type":"article","venue":"The Canadian Journal of Hospital Pharmacy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Capital District Health Authority","funders":"","keywords":"Quality (philosophy); Computer science; Philosophy; Epistemology","score_opus":0.6052751011247308,"score_gpt":0.6203316606152685,"score_spread":0.015056559490537635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1587899009","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9718787,0.0014604041,0.000021312577,0.022058291,0.00042490315,0.00008501902,0.0000068649847,0.0000011679588,0.004063321],"genre_scores_gemma":[0.9984922,0.00032807767,0.00007568234,0.00019919395,0.0001549014,5.85653e-7,2.2796202e-7,0.0000035085213,0.0007456219],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.997016,0.0006077761,0.0006243925,0.000093901144,0.0014434144,0.00021448544],"domain_scores_gemma":[0.9970152,0.0006067756,0.00034134422,0.00022523767,0.0014593544,0.00035210827],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017914008,0.00006021986,0.0001854503,0.00031893357,0.0003223703,0.00020252819,0.0006617913,0.000017260432,0.0015137896],"category_scores_gemma":[0.0015819455,0.000034681423,0.00006740403,0.0005627826,0.0004032957,0.00048091644,0.00003214911,0.0003084408,0.00004763719],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006561585,0.00004857077,0.92251176,0.000005979273,0.000041027535,0.00003113441,0.005149597,0.000093743736,0.00021017109,0.010955547,0.030352017,0.030534852],"study_design_scores_gemma":[0.0009395154,0.00045585018,0.71472454,0.000032612694,0.000016300668,0.000041321597,0.0055367853,0.00034743056,0.0011404317,0.023268564,0.25336924,0.00012742895],"about_ca_topic_score_codex":0.0296657,"about_ca_topic_score_gemma":0.067689694,"teacher_disagreement_score":0.22301722,"about_ca_system_score_codex":0.00006169861,"about_ca_system_score_gemma":0.0012167566,"threshold_uncertainty_score":0.99939895},"labels":[],"label_agreement":null},{"id":"W1588229591","doi":"10.3138/cjpe.30.1.105","title":"Sharon Brisolara, Denise Seigart, &amp; Saumitra SenGupta (Eds.). (2014). <i>Feminist Evaluation and Research: Theory and Practice.</i>","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Sociology; Theology; Philosophy","score_opus":0.6285746015045411,"score_gpt":0.6044724397125063,"score_spread":0.024102161792034837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1588229591","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9379916,0.021233473,0.0015288709,0.012470287,0.0017415965,0.0042559556,0.000031004307,0.000026788293,0.020720394],"genre_scores_gemma":[0.9921243,0.00018324365,0.006197829,0.00056471047,0.00037487596,0.000090898604,0.000028791608,0.000021993523,0.00041332707],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98324734,0.008290576,0.0011732801,0.000463446,0.0063163596,0.00050900556],"domain_scores_gemma":[0.9833058,0.0026642608,0.0008519712,0.0004967732,0.011306648,0.0013745201],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.20733808,0.00019564187,0.00031794756,0.0010357104,0.00051608105,0.0014734821,0.0004307545,0.00016224188,0.0010107408],"category_scores_gemma":[0.053575754,0.00015992048,0.000075615855,0.0008157087,0.00043664116,0.0017162864,0.00005338549,0.0005710387,0.00017271713],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023293414,0.000067465706,0.0080909785,0.000008018314,0.000049433544,0.000009528453,0.008955169,0.00032385465,0.00008488313,0.00095914945,0.036448974,0.9447696],"study_design_scores_gemma":[0.0038871225,0.0015160562,0.024402313,0.00012331335,0.00049225165,0.00095062534,0.022884214,0.032655083,0.00006966918,0.07894593,0.83365595,0.0004174871],"about_ca_topic_score_codex":0.0005388154,"about_ca_topic_score_gemma":0.009860488,"teacher_disagreement_score":0.94435215,"about_ca_system_score_codex":0.00054366543,"about_ca_system_score_gemma":0.010140692,"threshold_uncertainty_score":0.9999025},"labels":[],"label_agreement":null},{"id":"W1591702131","doi":"10.3138/cjpe.28.002","title":"To Case Study or Not to Case Study: Our Experience with the Canadian Government’s Evaluation Practices and the Use of Case Studies as an Evaluation Methodology for First Nations Programs","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Case study research; Work (physics); Public relations; Comparative case; Value (mathematics); Political science; Psychology; Business; Marketing; Engineering","score_opus":0.8529623701720311,"score_gpt":0.6548419671908232,"score_spread":0.19812040298120792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1591702131","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9573239,0.00008722442,0.00039489067,0.011691123,0.00042446068,0.030031702,0.000019294432,0.0000066550156,0.00002072614],"genre_scores_gemma":[0.9816571,0.000003157354,0.00823546,0.00052307826,0.00012630966,0.009365786,0.0000048367842,0.000021635344,0.00006266864],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.98592323,0.0069124647,0.0014319639,0.0005799444,0.0046883384,0.00046405743],"domain_scores_gemma":[0.97613716,0.004511821,0.002026687,0.00078359514,0.015638463,0.000902267],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06953911,0.00029016566,0.0005130657,0.0007706098,0.0024980519,0.0015782819,0.0004826821,0.000082123566,0.0002122654],"category_scores_gemma":[0.05241201,0.00015168088,0.00008350944,0.0017156664,0.00021548822,0.0020470314,0.00004930092,0.00023928648,0.000007729383],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049932336,0.00043087572,0.020894423,0.000013091936,0.00042153645,0.001279246,0.264108,0.015010726,0.000003785824,0.00007642123,0.0007305972,0.696532],"study_design_scores_gemma":[0.0043933927,0.008173476,0.006905623,0.000038523893,0.0015711557,0.020134231,0.8394762,0.11721876,0.000011833974,0.00018849106,0.0016459246,0.00024234806],"about_ca_topic_score_codex":0.42574567,"about_ca_topic_score_gemma":0.9970624,"teacher_disagreement_score":0.69628966,"about_ca_system_score_codex":0.0014385787,"about_ca_system_score_gemma":0.007953458,"threshold_uncertainty_score":0.9994582},"labels":[],"label_agreement":null},{"id":"W1593298473","doi":"","title":"Philosophical reflections on the dilemma of the evaluation of Learning","year":2012,"lang":"fr","type":"book-chapter","venue":"Cairn.info","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Humanities; Philosophy; Dilemma; Cognitive dissonance; Sociology; Epistemology; Psychology","score_opus":0.5913540448372232,"score_gpt":0.5289488075650155,"score_spread":0.0624052372722077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1593298473","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051952712,0.000406609,0.0001336493,0.019315762,0.002155384,0.00096425205,0.00003428492,0.000014362456,0.92502296],"genre_scores_gemma":[0.9359658,0.0001748096,0.000070157126,0.00025819158,0.00046788433,0.00003931657,0.000008393551,0.000020652487,0.06299484],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9919559,0.000968522,0.0012577132,0.0003587552,0.005195306,0.00026380838],"domain_scores_gemma":[0.99270505,0.002352826,0.0014566486,0.0011071092,0.0022803312,0.00009803433],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.012972866,0.00030627637,0.0004469451,0.00023337641,0.000627935,0.000064923064,0.00088911323,0.00034193182,0.04585289],"category_scores_gemma":[0.0034927707,0.00016527237,0.00047511476,0.00033639272,0.0008574163,0.00027579183,0.00022469816,0.00090489455,0.0010639766],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033119344,0.000063258354,0.0021455986,0.000016623611,0.00007475868,1.1288531e-7,0.0020616997,0.0072027217,0.00022601447,0.9268416,0.00028560238,0.06104886],"study_design_scores_gemma":[0.0010711343,0.00078299764,0.05746336,0.0009349407,0.0009840268,0.000018877918,0.0011902734,0.024827108,0.0013353666,0.20203407,0.70879674,0.0005611359],"about_ca_topic_score_codex":0.0001322121,"about_ca_topic_score_gemma":0.00020857438,"teacher_disagreement_score":0.88401306,"about_ca_system_score_codex":0.00063603406,"about_ca_system_score_gemma":0.00085404806,"threshold_uncertainty_score":0.99971384},"labels":[],"label_agreement":null},{"id":"W1594257894","doi":"10.3138/cjpe.23.003","title":"Reframing Evaluation: Defining an Indigenous Evaluation Framework","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":159,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Cognitive reframing; Indigenous; Traditional knowledge; Focus group; Common ground; Sociology; Public relations; Political science; Engineering ethics; Psychology; Engineering; Social psychology; Anthropology; Ecology","score_opus":0.396733003676957,"score_gpt":0.552227878522765,"score_spread":0.15549487484580798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1594257894","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9838338,0.0024886692,0.0033724585,0.0007311968,0.0021983793,0.0028617538,0.0000096037575,0.00002705073,0.0044770846],"genre_scores_gemma":[0.9794262,0.00002905847,0.01921723,0.0003187683,0.0005447072,0.0002830508,0.00009365455,0.00002850955,0.000058832764],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98321295,0.0031676001,0.0019695074,0.00051777344,0.010528704,0.00060347194],"domain_scores_gemma":[0.9810528,0.00060452166,0.0017087096,0.0007943672,0.014908279,0.0009313123],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07245219,0.00027363116,0.00044934405,0.0015225584,0.0011889397,0.0006292202,0.0009150127,0.0002739923,0.008595575],"category_scores_gemma":[0.016429527,0.00023582413,0.00021223616,0.0018826234,0.00019531064,0.0021857934,0.000021591834,0.0005971259,0.00028063555],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022613933,0.00008495262,0.03465482,0.0000029002297,0.00004113437,0.000010910337,0.013490658,0.020558959,0.000019560815,0.00035578271,0.00076892995,0.9299888],"study_design_scores_gemma":[0.0029245117,0.001940261,0.2955871,0.00018039207,0.0006329354,0.00059994886,0.007993684,0.6049691,0.00014065817,0.06572765,0.018678201,0.00062559836],"about_ca_topic_score_codex":0.0005223277,"about_ca_topic_score_gemma":0.008125919,"teacher_disagreement_score":0.9293632,"about_ca_system_score_codex":0.0017303753,"about_ca_system_score_gemma":0.025611255,"threshold_uncertainty_score":0.9923107},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":["sts"],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W1594443358","doi":"10.3138/cjpe.027.002","title":"Research on Evaluation: A Needs Assessment","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Psychology; Survey research; Engineering ethics; Management science; Sociology; Applied psychology; Engineering","score_opus":0.7833440326357193,"score_gpt":0.6849524617018541,"score_spread":0.09839157093386519,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1594443358","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8563039,0.0013305342,0.0007642173,0.008681882,0.004203503,0.003315702,0.000007656716,0.000015551783,0.12537709],"genre_scores_gemma":[0.9957566,0.00000809221,0.00238996,0.00027981214,0.0009232257,0.0002489675,0.000014368592,0.000014112289,0.00036483363],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9827187,0.003858387,0.0011765591,0.00020591597,0.01133779,0.0007026419],"domain_scores_gemma":[0.9852979,0.00091060955,0.0006316192,0.0005442426,0.011528704,0.001086911],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.15748209,0.00015182221,0.0002654825,0.002936783,0.00053879834,0.0006491278,0.0006902911,0.00012323735,0.012865041],"category_scores_gemma":[0.0051429947,0.00011351662,0.00015687302,0.002851841,0.00015058632,0.0012358662,0.000021887661,0.00062629755,0.0005924988],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017175269,0.00015189614,0.04477359,0.000002554974,0.000032005868,0.0000014275106,0.001778282,0.0032154012,0.000019357181,0.0061797407,0.020454517,0.92337406],"study_design_scores_gemma":[0.002224075,0.0018813098,0.52186775,0.00010426188,0.00017037799,0.00006762116,0.013439269,0.09685926,0.00012897392,0.01783021,0.34512892,0.0002979787],"about_ca_topic_score_codex":0.00022226623,"about_ca_topic_score_gemma":0.0022425815,"teacher_disagreement_score":0.9230761,"about_ca_system_score_codex":0.0018759632,"about_ca_system_score_gemma":0.013326426,"threshold_uncertainty_score":0.9922671},"labels":[],"label_agreement":null},{"id":"W1594828522","doi":"","title":"The key functions of collaborative logic modeling: Insights from the British Columbia Early Childhood Dental Programs","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Documentation; General partnership; Logic model; Government (linguistics); Key (lock); Early childhood; Computer science; Knowledge management; Public relations; Political science; Process management; Psychology; Public administration; Business; Programming language; Developmental psychology","score_opus":0.20652292156545762,"score_gpt":0.41826608559438194,"score_spread":0.21174316402892432,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1594828522","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9909539,0.00360914,0.00070162734,0.0008663235,0.0012718947,0.0014677115,0.000027224909,0.0000069699468,0.0010951952],"genre_scores_gemma":[0.99840343,0.000033585795,0.0007566561,0.000107291555,0.0003571857,0.00011565982,0.000028839038,0.000009431153,0.0001879396],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9954096,0.0009132915,0.0009770483,0.00015667816,0.002231909,0.00031148235],"domain_scores_gemma":[0.9941575,0.00042073254,0.00082723977,0.0003174707,0.0038892278,0.00038784507],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.007147104,0.00009983339,0.00021045505,0.00008282742,0.0014787638,0.002942876,0.000527884,0.0000825168,0.0005081347],"category_scores_gemma":[0.0018418037,0.000071937095,0.00014499374,0.0010572232,0.00022228192,0.00087617704,0.000021347538,0.00026909084,0.000039305694],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011965947,0.00016402708,0.1989762,7.863421e-7,0.00010675544,0.0000015704832,0.00773501,0.001529809,0.000008587137,0.00017457087,0.00497416,0.7863166],"study_design_scores_gemma":[0.0012892223,0.00084949797,0.8684277,0.0000957409,0.00025481754,0.00005167888,0.024907097,0.044228587,0.00000897217,0.016914342,0.042765863,0.00020648068],"about_ca_topic_score_codex":0.021821758,"about_ca_topic_score_gemma":0.6984774,"teacher_disagreement_score":0.7861101,"about_ca_system_score_codex":0.00022684064,"about_ca_system_score_gemma":0.003724285,"threshold_uncertainty_score":0.9998212},"labels":[],"label_agreement":null},{"id":"W1596745603","doi":"10.3138/cjpe.027.005","title":"Bamberger, Michael, Rugh, Jim, and Mabry, Linda. (2012). <i>Real World Evaluation: Working Under Budget, Time, Data, and Political Constraints</i> (2nd ed.). Thousand Oaks, CA: Sage. 666 Pages.","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Politics; Economic history; Media studies; Gerontology; Sociology; Political science; History; Medicine; Law","score_opus":0.18890778587147808,"score_gpt":0.45984872552332184,"score_spread":0.27094093965184374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1596745603","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8429125,0.04741677,0.0051109176,0.02941402,0.008736129,0.007799847,0.00041124359,0.00008955003,0.058109038],"genre_scores_gemma":[0.9933839,0.00023870518,0.003613438,0.0007370612,0.0010252526,0.000049436087,0.00012610292,0.000029111941,0.0007970312],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9925921,0.0014085716,0.0013608801,0.00050362374,0.003217881,0.0009169581],"domain_scores_gemma":[0.9942109,0.0009088225,0.00078792847,0.0006506423,0.0017388182,0.0017028842],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03265146,0.00031137967,0.00049862,0.0008293639,0.0005014343,0.0010543627,0.000548204,0.00017768073,0.008355154],"category_scores_gemma":[0.0014649846,0.00025953326,0.00008728475,0.00074391736,0.0006180567,0.0019533406,0.000102423975,0.00047900976,0.00011270918],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003539172,0.00009390558,0.08623342,0.000012081596,0.000111555855,0.0000073702304,0.0006459382,0.00015844358,0.000047183134,0.0017226655,0.04817069,0.8627614],"study_design_scores_gemma":[0.0061735543,0.0005236868,0.32273987,0.00042756693,0.0015772614,0.00073880976,0.005286636,0.16388266,0.000110207104,0.010584729,0.48678285,0.0011721862],"about_ca_topic_score_codex":0.00052693166,"about_ca_topic_score_gemma":0.014460982,"teacher_disagreement_score":0.8615892,"about_ca_system_score_codex":0.0005673881,"about_ca_system_score_gemma":0.0048225243,"threshold_uncertainty_score":0.9999857},"labels":[],"label_agreement":null},{"id":"W1599644470","doi":"10.1080/08941920.2015.1037876","title":"Linking Research Findings and Decision Makers: Insights and Recommendations From a Wildfire Study","year":2015,"lang":"en","type":"article","venue":"Society & Natural Resources","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge","funders":"Government of Canada","keywords":"USable; Dissemination; Government (linguistics); Process (computing); Knowledge translation; Knowledge management; Political science; Business; Engineering ethics; Public relations; Computer science; Engineering","score_opus":0.25870586098185333,"score_gpt":0.5149695545701918,"score_spread":0.25626369358833845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1599644470","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9921303,0.0030182987,0.00004206012,0.0036693427,0.00026341525,0.00033994997,0.00000537832,0.000031212876,0.0005000555],"genre_scores_gemma":[0.99454474,0.00025276415,0.0040496117,0.00042404773,0.00014947841,0.000015663052,0.000011719039,0.000009187527,0.0005427909],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.995706,0.000404496,0.0004580823,0.0005762737,0.0025960417,0.00025907267],"domain_scores_gemma":[0.9953755,0.0035019598,0.000114260154,0.0003482508,0.0004541613,0.00020586187],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007149946,0.00014150959,0.00022717411,0.00016798223,0.00085289835,0.00095395424,0.0003973735,0.00011235392,0.00006977032],"category_scores_gemma":[0.0016342322,0.000094732066,0.0000699359,0.0009348901,0.00020821017,0.0006470198,0.00047306775,0.00057839166,0.000051406474],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012654503,0.0001486546,0.27358377,0.0000033631543,0.00007007524,0.0000037618172,0.21592794,0.000014664592,0.0002005298,0.00013879998,0.04921805,0.4605638],"study_design_scores_gemma":[0.0027116076,0.0004767246,0.30412477,0.00014246364,0.000029303248,0.0000045007514,0.3552213,0.01968681,0.000048808666,0.05345132,0.2637771,0.00032529398],"about_ca_topic_score_codex":0.0001727954,"about_ca_topic_score_gemma":0.00036658623,"teacher_disagreement_score":0.46023852,"about_ca_system_score_codex":0.00009330527,"about_ca_system_score_gemma":0.000108411645,"threshold_uncertainty_score":0.9199003},"labels":[],"label_agreement":null},{"id":"W1601125040","doi":"10.1002/9781405198431.wbeal0040","title":"Assessment and Evaluation: Mixed Methods Research","year":2012,"lang":"en","type":"other","venue":"The Encyclopedia of Applied Linguistics","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Multimethodology; Computer science; Psychology; Mathematics education","score_opus":0.2818256688112279,"score_gpt":0.5961989653327529,"score_spread":0.31437329652152496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1601125040","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000046929697,0.0010813872,0.0014431806,0.00013182277,0.0029480136,0.0010201593,0.000028420312,0.000034111345,0.993266],"genre_scores_gemma":[0.059727002,0.0045246314,0.2686007,0.00021086996,0.0110823,0.00054365915,0.000101505815,0.00048346352,0.65472585],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9918492,0.0014692316,0.00091669057,0.00050835725,0.004849075,0.0004074795],"domain_scores_gemma":[0.9908177,0.005432125,0.00078611413,0.0014336054,0.0013782823,0.00015213463],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.051083643,0.0002638779,0.00055117987,0.0005431796,0.00021236089,0.00009882658,0.000993613,0.00027310816,0.009772749],"category_scores_gemma":[0.0058527766,0.00016172524,0.00006962203,0.00074765907,0.00048052493,0.000013387149,0.000450761,0.0006515527,0.00027468067],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012227405,0.000075059026,0.0002603164,0.000040375002,0.00006310251,2.5749145e-7,0.0007353071,0.00003903395,0.000008506093,0.1992947,0.52068293,0.27878818],"study_design_scores_gemma":[0.00026558206,0.000032457327,0.002049031,0.000031702217,0.00012604284,4.5038112e-7,0.0009065044,0.0015411208,0.000018055242,0.051333483,0.94351983,0.00017575096],"about_ca_topic_score_codex":0.000035973717,"about_ca_topic_score_gemma":0.000042061074,"teacher_disagreement_score":0.4228369,"about_ca_system_score_codex":0.00008605671,"about_ca_system_score_gemma":0.00089689926,"threshold_uncertainty_score":0.99113244},"labels":[],"label_agreement":null},{"id":"W1603616381","doi":"10.1177/160940690700600208","title":"Redefining Case Study","year":2007,"lang":"en","type":"article","venue":"International Journal of Qualitative Methods","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":371,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Case study research; Relation (database); Computer science; Case analysis; Research design; Management science; Sociology; Knowledge management; Engineering; Artificial intelligence; Data mining; Social science","score_opus":0.9205268197323564,"score_gpt":0.8096859168208992,"score_spread":0.1108409029114572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1603616381","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49997136,0.00005634335,0.4923038,0.00085637264,0.0017346012,0.000059388993,0.0000019529484,0.0000039613524,0.005012206],"genre_scores_gemma":[0.7305536,0.0000027273684,0.26843694,0.00029104788,0.00024610787,0.0000010396999,2.790733e-7,0.0000048688594,0.00046335513],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.98874354,0.005564181,0.0020317796,0.00019401287,0.003308058,0.00015840356],"domain_scores_gemma":[0.98068756,0.013536037,0.0013782469,0.00017457221,0.004106742,0.00011682453],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.16279984,0.00010237992,0.00028286251,0.00080608856,0.00008828375,0.00018592646,0.0007079623,0.000032754284,0.00091132516],"category_scores_gemma":[0.013385193,0.00006895462,0.00016435243,0.0004471365,0.00007326257,0.0005677063,0.000089432906,0.0002656639,0.000040393083],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002731669,0.0004121674,0.011696637,8.4580324e-7,0.00031736997,0.003129658,0.25756857,0.00022077563,0.0008266115,0.006370225,0.0010142919,0.7181697],"study_design_scores_gemma":[0.0017463397,0.00086833996,0.010402166,0.000023008944,0.000031961867,0.004696809,0.9159033,0.00063791283,0.0013552855,0.04498458,0.01918657,0.00016375302],"about_ca_topic_score_codex":0.00004470091,"about_ca_topic_score_gemma":0.000054491396,"teacher_disagreement_score":0.71800596,"about_ca_system_score_codex":0.00012970487,"about_ca_system_score_gemma":0.00018460683,"threshold_uncertainty_score":0.9978371},"labels":[],"label_agreement":null},{"id":"W1605140183","doi":"10.21225/d53s33","title":"How to Conduct Surveys: A Step-by-Step Guide","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of University Continuing Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":405,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Sociology","score_opus":0.07307313749290577,"score_gpt":0.37441708903417004,"score_spread":0.30134395154126425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1605140183","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9581265,0.000041959865,0.0129503785,0.017375201,0.0031986726,0.00013121901,0.00002067372,0.0000045916536,0.0081508355],"genre_scores_gemma":[0.9500477,0.0000033274334,0.005409362,0.00034570595,0.00017532558,1.4167145e-7,0.000004540051,0.0000047745234,0.04400917],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99851274,0.00037174884,0.00027267102,0.00015357709,0.00050335284,0.00018591972],"domain_scores_gemma":[0.9964969,0.00028098575,0.00036954845,0.00025651391,0.0018828972,0.0007131272],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0056514987,0.000081179125,0.00016425509,0.0007123547,0.00016471012,0.00040200097,0.0006306921,0.000062191524,0.00061842037],"category_scores_gemma":[0.0022996508,0.00007607167,0.00007218146,0.0005463226,0.00005347948,0.00079777616,0.0000145037475,0.00023868334,0.00004930961],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000070701717,0.000017678998,0.04211196,0.0000013960544,0.000010635229,0.000005974947,0.0012704817,0.000007990356,0.00265996,0.0007853992,0.73692185,0.21619958],"study_design_scores_gemma":[0.00021304269,0.00004953849,0.045271512,0.000023120012,0.00001196724,0.00002029818,0.013654558,0.00006082483,0.00017373286,0.000035821122,0.9403935,0.00009207797],"about_ca_topic_score_codex":0.0041180463,"about_ca_topic_score_gemma":0.110298224,"teacher_disagreement_score":0.2161075,"about_ca_system_score_codex":0.00022779436,"about_ca_system_score_gemma":0.0037956985,"threshold_uncertainty_score":0.90593654},"labels":[],"label_agreement":null},{"id":"W1605513489","doi":"","title":"Likert or not? Is there a linkage between the qualitative and quantitative results of faculty evaluations?","year":2015,"lang":"en","type":"article","venue":"The Journal of Macrodynamic Analysis (Memorial University of Newfoundland)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Likert scale; Linkage (software); Qualitative research; Medical education; Psychology; Computer science; Medicine; Sociology; Genetics; Social science; Biology; Developmental psychology","score_opus":0.2814967189280761,"score_gpt":0.49397898266563767,"score_spread":0.21248226373756157,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1605513489","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97428364,0.00010513291,0.017599465,0.0066537173,0.00017085896,0.00016632487,0.00023929004,0.0000032184118,0.0007783544],"genre_scores_gemma":[0.99668664,0.00017532818,0.001263998,0.00005121457,0.00011305102,7.057593e-8,0.000014571138,0.0000039879537,0.0016911556],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9941259,0.0022409544,0.0009875464,0.00018073923,0.0023266887,0.00013816415],"domain_scores_gemma":[0.9891876,0.0050779376,0.002454184,0.00043612486,0.002728683,0.000115471026],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02056994,0.0001414723,0.0006908332,0.00043470573,0.0002752361,0.000057586203,0.0010040512,0.000073382755,0.00023947218],"category_scores_gemma":[0.0018995192,0.00006970862,0.000320413,0.0016971787,0.0004980262,0.0004352338,0.00015610784,0.0002522333,0.000015548398],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.042788737,0.00041992785,0.06293028,0.00003690837,0.013263102,0.000022497125,0.78166676,0.059498116,0.00041947095,0.0017307467,0.017587796,0.019635689],"study_design_scores_gemma":[0.011227186,0.0027924124,0.33623028,0.00009113228,0.008230646,0.000016734899,0.500911,0.120998695,0.00006006163,0.012030715,0.0070494926,0.00036163794],"about_ca_topic_score_codex":0.0019793697,"about_ca_topic_score_gemma":0.0048658364,"teacher_disagreement_score":0.28075573,"about_ca_system_score_codex":0.00012916156,"about_ca_system_score_gemma":0.0006075528,"threshold_uncertainty_score":0.71291715},"labels":[],"label_agreement":null},{"id":"W1606264377","doi":"10.18438/b8z59k","title":"Editorial: Small steps forward through critical appraisal","year":2006,"lang":"en","type":"editorial","venue":"Evidence Based Library and Information Practice","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Critical appraisal; Computer science; Data science; Operations research; Information retrieval; Management science; Economics; Medicine; Mathematics","score_opus":0.07144121798009767,"score_gpt":0.44837886007946903,"score_spread":0.37693764209937136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1606264377","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000006208564,0.0005330923,0.015339941,0.041122887,0.9230901,0.00041295314,0.00021962286,0.00018302092,0.019092156],"genre_scores_gemma":[0.00009402517,0.0014600157,0.012319953,0.012336749,0.9716397,0.00007217364,0.00092907634,0.0000328529,0.0011154909],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98931414,0.0013487056,0.0022277741,0.000641888,0.0059909304,0.00047658835],"domain_scores_gemma":[0.8681658,0.12701276,0.0017999985,0.0010689476,0.0016816595,0.0002708444],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["scholarly_communication","insufficient_payload"],"category_scores_codex":[0.0076095215,0.00049336086,0.0006113489,0.00048504624,0.0005018006,0.0048727496,0.0011895939,0.0010704492,0.0014950746],"category_scores_gemma":[0.16176447,0.0003967317,0.00019095009,0.0010274716,0.00024198569,0.3402943,0.0003751236,0.0015502826,0.0010913742],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005992637,0.0000558508,0.000019198334,0.00013152487,0.000014800252,0.0000019935267,0.00013972688,0.00020599204,9.4857126e-7,0.019993445,0.9759501,0.0028871263],"study_design_scores_gemma":[0.00061490544,0.0003363051,0.00005931732,0.00036942665,0.000104664345,0.0000035909818,0.0005904425,0.00301583,0.000045169883,0.0011675219,0.9932063,0.00048651546],"about_ca_topic_score_codex":0.000028974993,"about_ca_topic_score_gemma":4.1627084e-7,"teacher_disagreement_score":0.33542153,"about_ca_system_score_codex":0.00004539413,"about_ca_system_score_gemma":0.0030125438,"threshold_uncertainty_score":0.9998485},"labels":[],"label_agreement":null},{"id":"W1611881142","doi":"10.3138/cjpe.30.1.64","title":"Exploring the Leadership Dimension of Developmental Evaluation: The Evaluator as a Servant-Leader","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Servant leadership; Situational ethics; Leadership development; Situated; Psychology; Servant; Dimension (graph theory); Adaptation (eye); Applied psychology; Knowledge management; Computer science; Public relations; Social psychology; Leadership style; Political science; Artificial intelligence; Software engineering","score_opus":0.8742798159456303,"score_gpt":0.541068240408882,"score_spread":0.3332115755367483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1611881142","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9743785,0.0013387072,0.00015987935,0.0168748,0.0020215313,0.0022547753,0.0000033059835,0.000008662094,0.0029597855],"genre_scores_gemma":[0.9974394,0.000010654086,0.001221593,0.00060257956,0.0002761204,0.0002507102,0.000008867381,0.00001496504,0.00017509927],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9879959,0.0023611118,0.0013947608,0.00025461963,0.007609979,0.0003836323],"domain_scores_gemma":[0.98848534,0.0006575296,0.0010890061,0.00047113735,0.0087936185,0.000503385],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.067509554,0.00018820804,0.00029231986,0.00047405428,0.0004233911,0.00036562615,0.00096792344,0.0000658768,0.0016607019],"category_scores_gemma":[0.010696696,0.00010035661,0.00017062166,0.0013067363,0.00027027793,0.0012348951,0.00003674313,0.0003391315,0.00021427401],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000073892224,0.00005642104,0.011533383,0.000006637216,0.00009016189,0.0000033189485,0.022064995,0.008344198,0.000099286604,0.00049314747,0.007891587,0.94934297],"study_design_scores_gemma":[0.0071023786,0.0025062705,0.19854136,0.00043526836,0.0011509687,0.0005642766,0.31739128,0.31547427,0.0030360064,0.023390796,0.12966952,0.0007376097],"about_ca_topic_score_codex":0.0005954907,"about_ca_topic_score_gemma":0.008308214,"teacher_disagreement_score":0.94860536,"about_ca_system_score_codex":0.00095750357,"about_ca_system_score_gemma":0.01982355,"threshold_uncertainty_score":0.9992519},"labels":[],"label_agreement":null},{"id":"W1619911812","doi":"10.22329/celt.v6i0.3718","title":"1. La communauté d’apprentissage : une approche innovante au développement pédagogique des formateurs","year":2013,"lang":"fr","type":"article","venue":"Collected Essays on Learning and Teaching","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Humanities; Political science; Art","score_opus":0.07515437873239561,"score_gpt":0.40412171516017775,"score_spread":0.32896733642778214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1619911812","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7955155,0.0007415803,0.01408165,0.0061971117,0.0006027104,0.0005783732,0.0000054025136,0.00017230077,0.18210539],"genre_scores_gemma":[0.932295,0.0006672449,0.004574389,0.00023718657,0.000092598384,0.000117531505,0.00003612703,0.000043095333,0.06193678],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9927967,0.003672803,0.0009875096,0.0006125204,0.0011286485,0.0008017813],"domain_scores_gemma":[0.99536455,0.003011353,0.0005029907,0.0004219528,0.000411683,0.00028747274],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008267012,0.00045793573,0.0005323837,0.0005648631,0.003078774,0.001376357,0.0005324401,0.0003380487,0.0015442609],"category_scores_gemma":[0.0029183542,0.0003913043,0.000115564944,0.0010688396,0.00047713425,0.0009493796,0.00033978568,0.002609595,0.000534575],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005232668,0.00035143876,0.031049773,0.00012693852,0.00009574862,0.0000091137035,0.07527827,0.0015219795,0.00051896006,0.007489991,0.006061716,0.87744373],"study_design_scores_gemma":[0.0052480153,0.0020871607,0.13990054,0.0034906832,0.00016106032,0.00020787845,0.13132577,0.25722998,0.00061513984,0.0204594,0.43744475,0.0018296189],"about_ca_topic_score_codex":0.0009189049,"about_ca_topic_score_gemma":0.00026846022,"teacher_disagreement_score":0.8756141,"about_ca_system_score_codex":0.00036277066,"about_ca_system_score_gemma":0.00048094647,"threshold_uncertainty_score":0.9998539},"labels":[],"label_agreement":null},{"id":"W1633075290","doi":"","title":"Unbolting Evaluation: Putting it into the Workings and into the Research Agenda for Counselling","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Counselling and Psychotherapy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Physics; Stereochemistry; Chemistry","score_opus":0.3858029120178218,"score_gpt":0.5532705011308505,"score_spread":0.16746758911302873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1633075290","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6007122,0.05708905,0.29925513,0.03999501,0.0015941806,0.0006753098,0.0000016741511,0.0000053529425,0.0006721129],"genre_scores_gemma":[0.9259857,0.06461118,0.002790848,0.0046114563,0.0013023086,0.0000143524685,0.0000011523965,0.000027636112,0.0006553707],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962134,0.0004584997,0.0008786017,0.00025795042,0.0017737803,0.0004177989],"domain_scores_gemma":[0.99096614,0.0056115864,0.000469504,0.00029225837,0.0023677268,0.00029275988],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.09236471,0.00013365327,0.00020304034,0.00044601652,0.002155632,0.0009915087,0.0005668913,0.000082128,0.00018580224],"category_scores_gemma":[0.00013527,0.00007469676,0.00008124459,0.00078087737,0.00033400572,0.00024372336,5.171489e-7,0.00047921808,0.0000053543044],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008911179,0.0000058913847,0.0011289048,0.000006607586,0.000042781987,0.0000026166606,0.18669797,0.00082117575,0.00013934204,0.00205374,0.007029441,0.8019824],"study_design_scores_gemma":[0.000531911,0.00012221513,0.00018519515,0.000111237765,0.000015491258,0.000028533628,0.006650884,0.014421554,0.000057939804,0.27435613,0.70343417,0.000084750965],"about_ca_topic_score_codex":0.00045015468,"about_ca_topic_score_gemma":0.02698274,"teacher_disagreement_score":0.80189764,"about_ca_system_score_codex":0.000047746158,"about_ca_system_score_gemma":0.0006617829,"threshold_uncertainty_score":0.9991434},"labels":[],"label_agreement":null},{"id":"W1641303712","doi":"10.1016/j.jash.2015.03.256","title":"Building community capacity: engaging individuals in knowledge-transfer on the determinants of hypertension","year":2015,"lang":"en","type":"article","venue":"Journal of the American Society of Hypertension","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cape Breton University","funders":"","keywords":"Sense of agency; Stimulus (psychology); Agency (philosophy); Feeling; Social psychology; Cognitive psychology; Action selection; Psychology; Medicine; Neuroscience; Perception","score_opus":0.4507427140516922,"score_gpt":0.4448486957677882,"score_spread":0.005894018283904012,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1641303712","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99488664,0.00010874421,0.00018842726,0.0042559756,0.00029090547,0.0001303758,0.000003448303,0.0000031377574,0.0001323543],"genre_scores_gemma":[0.99541855,0.00008760758,0.0023851297,0.0020300127,0.00004963811,0.0000010759206,1.11392914e-7,0.00001011934,0.000017768565],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9946358,0.0020062688,0.0011235914,0.00012806457,0.0019111615,0.00019512196],"domain_scores_gemma":[0.9938242,0.00294362,0.0011919808,0.00062481064,0.0013261624,0.0000892481],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016981415,0.00015041826,0.0007151511,0.00015661676,0.0002684249,0.000034089582,0.0011046516,0.000050706185,0.000013586938],"category_scores_gemma":[0.0021085648,0.00007037674,0.0004369789,0.0010070468,0.000560778,0.00024512087,0.0002067695,0.0008281156,0.0000043008754],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044149137,0.0018849453,0.55323625,0.00005494889,0.00021499992,0.0000064650308,0.042194106,0.004634793,0.21761051,0.0002827956,0.045210816,0.13422787],"study_design_scores_gemma":[0.0030595865,0.0017613177,0.7795778,0.0013055203,0.0001676033,0.00028736185,0.10164225,0.03770491,0.06361038,0.0066218507,0.0038983165,0.00036312654],"about_ca_topic_score_codex":0.00018936288,"about_ca_topic_score_gemma":0.000036058053,"teacher_disagreement_score":0.22634152,"about_ca_system_score_codex":0.00009565235,"about_ca_system_score_gemma":0.00030459865,"threshold_uncertainty_score":0.5885454},"labels":[],"label_agreement":null},{"id":"W1646487061","doi":"10.1080/10632921.2015.1039739","title":"Advancing Knowledge through Grassroots Experiments: Connecting Culture and Sustainability","year":2015,"lang":"en","type":"article","venue":"The Journal of Arts Management Law and Society","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"Canadian Patient Safety Institute","keywords":"Grassroots; Sustainability; Pillar; Organizational culture; Sociology; Engineering ethics; Public relations; Knowledge management; Political science; Process management; Business; Engineering; Ecology; Computer science","score_opus":0.11442268198658742,"score_gpt":0.46293240407804037,"score_spread":0.3485097220914529,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1646487061","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7592066,0.0060982965,0.034674995,0.008743705,0.0009930978,0.00069264864,0.0000017687529,0.00003077226,0.18955813],"genre_scores_gemma":[0.9948287,0.0005969622,0.0021511747,0.0011617276,0.00009440686,0.0000016688238,2.7214364e-7,0.00000448557,0.00116058],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983644,0.00020621372,0.00043840698,0.00012754489,0.00070037774,0.00016306723],"domain_scores_gemma":[0.9985497,0.00023182564,0.00032713133,0.00018932828,0.0006052509,0.00009674148],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008270461,0.000098089324,0.00018377358,0.000018718316,0.00041382897,0.00018831495,0.000223389,0.0000294166,0.00003003453],"category_scores_gemma":[0.00016304936,0.000051985782,0.000076320546,0.00015403822,0.0001366873,0.00076755154,0.00020900898,0.00014444701,0.0000029153266],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020760835,0.00046093934,0.0068469443,0.00016917351,0.0004766134,0.000012386669,0.4039251,0.0019983316,0.00013260118,0.3848146,0.15662867,0.04432707],"study_design_scores_gemma":[0.0012765629,0.00024169442,0.0014367758,0.000038574723,0.000074437434,0.00002611197,0.36542234,0.0017452188,0.00012611426,0.08718053,0.542307,0.00012459987],"about_ca_topic_score_codex":0.000011381508,"about_ca_topic_score_gemma":0.00001436303,"teacher_disagreement_score":0.38567838,"about_ca_system_score_codex":0.00009346561,"about_ca_system_score_gemma":0.000049558454,"threshold_uncertainty_score":0.31828797},"labels":[],"label_agreement":null},{"id":"W1651616628","doi":"","title":"Développement de l’évaluation externe et restructuration du métier de direction d’établissements scolaires au Canada","year":2011,"lang":"fr","type":"article","venue":"Digital Access to Libraries (Université catholique de Louvain (UCL), l'Université de Namur (UNamur) and the Université Saint-Louis (USL-B))","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Humanities; Philosophy","score_opus":0.0331062612799946,"score_gpt":0.2769753304873505,"score_spread":0.2438690692073559,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1651616628","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85269195,0.0005609091,0.01547277,0.02197499,0.00088030746,0.0012687918,0.00030259683,0.00015762409,0.106690064],"genre_scores_gemma":[0.9553165,0.0013969159,0.0021280155,0.0030523299,0.00021683743,0.000015313484,0.00021476127,0.00007876789,0.03758055],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9932753,0.0015042268,0.0007502938,0.0012372065,0.0017158093,0.0015171765],"domain_scores_gemma":[0.9953692,0.00096613175,0.0008593308,0.0009090038,0.0008068479,0.0010894847],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0030591304,0.00084407197,0.0007943444,0.0011977515,0.002721991,0.0019637616,0.0024245922,0.0005215745,0.0019300275],"category_scores_gemma":[0.00057968043,0.0008601301,0.00033949004,0.0023516784,0.000790631,0.003859058,0.002270334,0.00071158016,0.00006069935],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00659297,0.00045727147,0.20777288,0.00022194612,0.0008144383,0.0011449391,0.4145909,0.0055744825,0.00034495487,0.23005113,0.016447715,0.11598637],"study_design_scores_gemma":[0.006212747,0.00052974076,0.4115082,0.00043647824,0.0006792722,0.0004342041,0.024296096,0.021835426,0.0015222421,0.012927508,0.51801807,0.0016000204],"about_ca_topic_score_codex":0.20458633,"about_ca_topic_score_gemma":0.1050327,"teacher_disagreement_score":0.50157034,"about_ca_system_score_codex":0.009991938,"about_ca_system_score_gemma":0.006865442,"threshold_uncertainty_score":0.99938494},"labels":[],"label_agreement":null},{"id":"W1655576730","doi":"10.1080/15555240.2014.999078","title":"Applying the Logic Model Process to Employee Assistance Programming","year":2015,"lang":"en","type":"article","venue":"Journal of Workplace Behavioral Health","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The King's University","funders":"","keywords":"Logic model; Process (computing); Strengths and weaknesses; Computer science; Process management; Psychology; Engineering; Sociology; Programming language; Social psychology; Social science","score_opus":0.45143382903059526,"score_gpt":0.5800756226383668,"score_spread":0.1286417936077715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1655576730","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91921955,0.00054900825,0.056616083,0.020568289,0.0009273898,0.0016015798,0.0000046970995,0.000031328378,0.00048205213],"genre_scores_gemma":[0.97364885,0.0000136693425,0.022537302,0.002426796,0.0001791532,0.00012560844,6.9034604e-7,0.000013629669,0.0010543289],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9945723,0.00030564942,0.00128185,0.00023097417,0.0032041424,0.00040510413],"domain_scores_gemma":[0.9963045,0.00016598139,0.0010852236,0.0003715727,0.0014974028,0.00057532184],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014059257,0.00015271337,0.0003913354,0.00023234639,0.00030576886,0.00033864638,0.0009166801,0.00005485282,0.00004383471],"category_scores_gemma":[0.00030117703,0.00008351367,0.000113249815,0.0010857028,0.00004852971,0.00058542617,0.00006909924,0.00044895735,0.000062308434],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039678442,0.00041851553,0.22099514,0.0000182679,0.000009010091,0.000013563503,0.011436094,0.10507639,0.000015685804,0.00040218706,0.03729779,0.62392056],"study_design_scores_gemma":[0.010784658,0.01727179,0.15379108,0.0021160352,0.00029426368,0.0010306449,0.2486044,0.10293487,0.00030770706,0.06548614,0.39468813,0.0026902838],"about_ca_topic_score_codex":0.000016142681,"about_ca_topic_score_gemma":0.00017427365,"teacher_disagreement_score":0.6212303,"about_ca_system_score_codex":0.00037102553,"about_ca_system_score_gemma":0.0022547115,"threshold_uncertainty_score":0.4872686},"labels":[],"label_agreement":null},{"id":"W1658636278","doi":"10.3138/cjpe.0028.004","title":"Introduction à la professionnalisation de l’évaluation : perspective globale sur les compétences des évaluateurs","year":2014,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Political science; Humanities; Philosophy","score_opus":0.2965364943297302,"score_gpt":0.4989688669957872,"score_spread":0.20243237266605696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1658636278","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8552853,0.010967167,0.039899208,0.07422197,0.0083395075,0.0026699246,0.000026192944,0.000040556795,0.008550164],"genre_scores_gemma":[0.97425234,0.0002954483,0.020702057,0.00018279869,0.0026876456,0.00010884271,0.000042576146,0.000028666458,0.0016996408],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9841292,0.010200477,0.0015548909,0.000496148,0.0029467384,0.0006725686],"domain_scores_gemma":[0.98224354,0.0008491164,0.0016114316,0.000397511,0.014125447,0.0007729414],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.069766246,0.0003264517,0.00047017366,0.0009883501,0.0009508865,0.0009910959,0.0005975593,0.0003500249,0.0050129863],"category_scores_gemma":[0.01833701,0.00029203846,0.00026922362,0.0015460822,0.0008669293,0.0020564776,0.000024083818,0.0006032789,0.00013886935],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008586707,0.00017462276,0.019889234,0.000040791554,0.00007495707,0.0000032123717,0.010375401,0.020269105,0.00009228635,0.01466203,0.008267547,0.92606497],"study_design_scores_gemma":[0.0020723732,0.002354024,0.13636222,0.0006242412,0.00067834667,0.0002956116,0.024224788,0.44980037,0.00022276628,0.21409756,0.16881359,0.00045407997],"about_ca_topic_score_codex":0.011808013,"about_ca_topic_score_gemma":0.0664695,"teacher_disagreement_score":0.92561084,"about_ca_system_score_codex":0.0031223383,"about_ca_system_score_gemma":0.015265293,"threshold_uncertainty_score":0.99995315},"labels":[],"label_agreement":null},{"id":"W1666893058","doi":"","title":"M&E Competencies in Support of the AIDS Response: A Sector-Specific Example","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Human immunodeficiency virus (HIV); Context (archaeology); Political science; Humanities; Medicine; Nursing; Family medicine; Geography","score_opus":0.41677236886577906,"score_gpt":0.4821539888231361,"score_spread":0.06538161995735703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1666893058","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99443513,0.00013578088,0.0005646181,0.0021040144,0.00076402654,0.0005599895,0.000004824366,0.000002862255,0.0014287361],"genre_scores_gemma":[0.9975237,0.0000033999577,0.0019972553,0.00020428166,0.00007704582,0.000020479718,0.0000021267053,0.000005929445,0.00016576743],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9946891,0.001783333,0.0010163576,0.00014707584,0.0021482983,0.00021584526],"domain_scores_gemma":[0.9962227,0.0006618342,0.0007196767,0.00039034232,0.0018073245,0.00019812932],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.035467044,0.00008869215,0.00023233243,0.00064533384,0.0001191595,0.00014880614,0.0006272635,0.000056752124,0.0025275978],"category_scores_gemma":[0.0034789434,0.000056456065,0.00012284199,0.0011047948,0.00014834011,0.00031474838,0.000016137174,0.0001865952,0.000028499468],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014490206,0.000070918635,0.2865972,0.0000066258694,0.0000176736,0.000002567411,0.0054339864,0.004673774,0.0012134586,0.0034921817,0.01087097,0.68747574],"study_design_scores_gemma":[0.00088087795,0.00069706334,0.6254288,0.00003264284,0.000016290604,0.000022332562,0.0010146908,0.0063165855,0.00031537062,0.007775457,0.35741737,0.00008251859],"about_ca_topic_score_codex":0.00069834053,"about_ca_topic_score_gemma":0.028779041,"teacher_disagreement_score":0.68739325,"about_ca_system_score_codex":0.00029489104,"about_ca_system_score_gemma":0.004113502,"threshold_uncertainty_score":0.99838424},"labels":[],"label_agreement":null},{"id":"W1687498483","doi":"10.47678/cjhe.v44i1.183548","title":"Revealing the complexity of community-campus interactions","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Higher Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"HIV Legal Network; York University","funders":"","keywords":"Reciprocity (cultural anthropology); Flexibility (engineering); Process (computing); Public relations; Qualitative research; Sociology; Political science; Knowledge management; Psychology; Social psychology; Computer science; Management; Social science","score_opus":0.3442590748454243,"score_gpt":0.5094467348510978,"score_spread":0.16518766000567353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1687498483","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92761123,0.00029108708,0.0009925304,0.038372293,0.0052509787,0.00009080997,0.0000051368083,0.0000022238612,0.02738373],"genre_scores_gemma":[0.99355763,0.0000019282427,0.00043983094,0.0016532362,0.00025320685,0.0000013503553,0.0000025252998,0.0000031205686,0.0040871673],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982696,0.00069392315,0.0005273551,0.00003878541,0.00037773442,0.00009256469],"domain_scores_gemma":[0.9973287,0.00057541433,0.0006051553,0.00032084325,0.0009987248,0.00017115918],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0039726226,0.000047808713,0.00012159657,0.00027600827,0.0003518505,0.00009981895,0.0005185904,0.0000197658,0.0022073148],"category_scores_gemma":[0.00062196836,0.000030234105,0.00006391515,0.00033049227,0.00018090985,0.00026769406,0.000008906693,0.00029242074,0.000039931558],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019830912,0.00018388931,0.15675724,0.000017051394,0.00006008364,3.2942955e-7,0.017721636,0.0013340904,0.0004537975,0.106508285,0.6059032,0.11104058],"study_design_scores_gemma":[0.00008123344,0.0000435657,0.43174183,0.000027886157,0.0000123313785,0.000012217845,0.002680848,0.00009826341,0.00007610946,0.050519183,0.5146708,0.00003573593],"about_ca_topic_score_codex":0.0031897072,"about_ca_topic_score_gemma":0.016940894,"teacher_disagreement_score":0.2749846,"about_ca_system_score_codex":0.00010620668,"about_ca_system_score_gemma":0.001623767,"threshold_uncertainty_score":0.9987048},"labels":[],"label_agreement":null},{"id":"W1687953441","doi":"10.37119/ojs2015.v21i1.200","title":"School-Linked Services: Practice, Policy, and Constructing Sustainable Collaboration","year":2014,"lang":"en","type":"article","venue":"in education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"Vision of Children Foundation","keywords":"Government (linguistics); Public relations; Poverty; Political science; Service (business); Newspaper; Public policy; Public administration; Sociology; Business; Marketing; Media studies","score_opus":0.044458899362159826,"score_gpt":0.48714274129403007,"score_spread":0.44268384193187027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1687953441","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90482545,0.000106235304,0.000335476,0.01251833,0.0004490391,0.00028436191,6.280469e-7,0.000018393694,0.08146211],"genre_scores_gemma":[0.9910089,0.00004009177,0.004107158,0.002064834,0.00027603944,0.000034079298,0.000008749191,0.000004493889,0.0024556504],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99839216,0.00030478573,0.0003858568,0.00022765339,0.0005414257,0.00014810031],"domain_scores_gemma":[0.99747413,0.00081767875,0.0002790136,0.00024561465,0.0011051624,0.00007841859],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042466917,0.00006721338,0.00010041354,0.00041039695,0.00012843347,0.0005017033,0.00013954799,0.00005239027,0.00013861133],"category_scores_gemma":[0.0075546787,0.00005870771,0.000009738014,0.0011590524,0.000031275194,0.0016582051,0.00003739203,0.000087634966,0.00010615339],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037640766,0.000279232,0.44369805,0.00006366397,0.000005202026,4.391973e-7,0.0110481605,0.00061123614,0.0003486508,0.32039154,0.0023369151,0.22117928],"study_design_scores_gemma":[0.0005784738,0.00007094294,0.15411372,0.00004308154,0.000008558195,0.000016889355,0.23967366,0.0105506545,0.00009725579,0.08277918,0.51189923,0.00016833465],"about_ca_topic_score_codex":0.0005608963,"about_ca_topic_score_gemma":0.00020822346,"teacher_disagreement_score":0.5095623,"about_ca_system_score_codex":0.00018759283,"about_ca_system_score_gemma":0.001646687,"threshold_uncertainty_score":0.90442014},"labels":[],"label_agreement":null},{"id":"W1688463168","doi":"10.3138/cjpe.30.1.99","title":"McDavid, J. C., Huse, I., &amp; Hawthorn, L. R. L. (2013). <i>Program Evaluation and Performance Measurement: An Introduction to Practice (2nd ed.).</i>","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"SAGE; Psychology; Sociology; Library science; Computer science; Physics; Nuclear physics","score_opus":0.4454211636939176,"score_gpt":0.5224499535137422,"score_spread":0.07702878981982464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1688463168","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89109904,0.005220444,0.0066035036,0.07016871,0.0090706395,0.013540212,0.000018000957,0.00011233936,0.0041671433],"genre_scores_gemma":[0.95079774,0.00009349319,0.045068517,0.0008195569,0.0022017448,0.0007393796,0.00006743162,0.00003768024,0.0001744734],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9865812,0.0022847499,0.0015846257,0.0006309751,0.008364446,0.0005540208],"domain_scores_gemma":[0.9701762,0.00015902352,0.0012264615,0.0007454481,0.025907904,0.0017849215],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.092325784,0.00029045698,0.00041062388,0.0011810751,0.0004404948,0.001333436,0.0005931676,0.00016223814,0.00092025683],"category_scores_gemma":[0.019842615,0.0002476252,0.00009339632,0.0014789508,0.00013699022,0.004159481,0.00003438337,0.00041925296,0.00022227477],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017054618,0.00016450194,0.00439332,0.000006834644,0.000040321436,0.0000013450942,0.0020325978,0.00831285,0.00004781897,0.00006958533,0.04668925,0.938071],"study_design_scores_gemma":[0.0017400312,0.0031942292,0.017640729,0.0000463701,0.00034451773,0.0001769117,0.0021053532,0.06597871,0.000062121595,0.0011785891,0.9072153,0.00031714325],"about_ca_topic_score_codex":0.00082128623,"about_ca_topic_score_gemma":0.028914152,"teacher_disagreement_score":0.9377539,"about_ca_system_score_codex":0.0014908459,"about_ca_system_score_gemma":0.008658291,"threshold_uncertainty_score":0.9999976},"labels":[],"label_agreement":null},{"id":"W1694133900","doi":"10.1111/aswp.12063","title":"Issues and Challenges in Performing Family Impact Analysis – Implications for <scp>H</scp>ong <scp>K</scp>ong","year":2015,"lang":"en","type":"article","venue":"Asian Social Work and Policy Review","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Grassroots; Obligation; Policy analysis; Political science; Public relations; Public administration; Politics; Business; Law","score_opus":0.3656154087647494,"score_gpt":0.5364960733007456,"score_spread":0.17088066453599615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1694133900","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25167456,0.56024855,0.00026494407,0.10801661,0.0001817196,0.002113526,0.000119222634,0.000083717925,0.07729714],"genre_scores_gemma":[0.7623387,0.23285721,0.000498733,0.0016539973,0.0006372581,0.00022996396,0.00004233619,0.000025853606,0.0017159536],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.997199,0.00037017773,0.0008289124,0.00051123806,0.00060560677,0.0004850555],"domain_scores_gemma":[0.99714065,0.0013839513,0.0004187517,0.0003896943,0.00035889313,0.00030807202],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005132909,0.00026828615,0.00088783813,0.00053379196,0.00048046213,0.0002787407,0.0003639574,0.00014099116,0.000019698044],"category_scores_gemma":[0.0034581472,0.00020225183,0.0003043271,0.003301957,0.000119928714,0.00046253015,0.000114113005,0.0001745552,0.000040854335],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000026360701,0.000051454914,0.101200745,0.00022755975,0.0001764182,5.4614895e-7,0.013069347,0.000007316762,0.0000028895763,0.012815501,0.025747623,0.846698],"study_design_scores_gemma":[0.00031943698,0.000068091314,0.5411278,0.00018640552,0.00021905429,0.0000023706407,0.006090437,0.000069382535,0.0000012315363,0.0079809185,0.44386518,0.00006971983],"about_ca_topic_score_codex":0.00009236981,"about_ca_topic_score_gemma":0.00022071152,"teacher_disagreement_score":0.84662825,"about_ca_system_score_codex":0.00010742938,"about_ca_system_score_gemma":0.00033614834,"threshold_uncertainty_score":0.82475907},"labels":[],"label_agreement":null},{"id":"W1699112913","doi":"10.29173/cjs6675","title":"Patrick White, Developing Research Questions: A Guide for Social Scientists","year":2009,"lang":"en","type":"article","venue":"The Canadian Journal of Sociology","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"White (mutation); Sociology; White paper; Social science; Engineering ethics; Epistemology; Political science; Engineering; Law; Biology; Philosophy","score_opus":0.5191648593210411,"score_gpt":0.6026277398303749,"score_spread":0.08346288050933381,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1699112913","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49715,0.0011323487,0.01371096,0.46990803,0.0022547692,0.0005910071,0.000027289732,0.000008928968,0.015216661],"genre_scores_gemma":[0.99172735,0.000013169545,0.0029615997,0.0026795322,0.0005246412,0.0000044478975,0.0000013627656,0.0000035018068,0.0020844017],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973832,0.0007174164,0.0006165076,0.00012760429,0.00076157844,0.0003936921],"domain_scores_gemma":[0.9955612,0.0010642807,0.0003022156,0.00014949615,0.0027390476,0.00018377707],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.024438234,0.00006157251,0.00018359855,0.00058650423,0.0018375294,0.00019887631,0.0008495479,0.00009772443,0.00031579434],"category_scores_gemma":[0.0044102105,0.00003783612,0.00010340371,0.00059512263,0.00056793867,0.00018210644,0.000014521968,0.00033749672,0.00006171316],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003334089,0.000014671527,0.018584514,0.0000027840815,0.000030839336,0.000015811078,0.020247508,0.00021089638,0.000083905084,0.23079883,0.63799185,0.09198508],"study_design_scores_gemma":[0.0003807919,0.00024544343,0.24677663,0.000013254998,0.000008416333,0.00005592667,0.0035034912,0.00019216632,0.000009885522,0.44400877,0.30472606,0.00007915962],"about_ca_topic_score_codex":0.00033831105,"about_ca_topic_score_gemma":0.021719929,"teacher_disagreement_score":0.49457732,"about_ca_system_score_codex":0.0004865176,"about_ca_system_score_gemma":0.007932126,"threshold_uncertainty_score":0.99946195},"labels":[],"label_agreement":null},{"id":"W1700780107","doi":"10.3138/cjpe.0028.006","title":"Evaluator Competencies: The Canadian Experience","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Foundation (evidence); Engineering ethics; Context (archaeology); Political science; Psychology; Sociology; Public relations; Management; Engineering; History; Law","score_opus":0.36189769178651315,"score_gpt":0.5260247839748239,"score_spread":0.16412709218831073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1700780107","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91652256,0.00085300417,0.0021480932,0.025982305,0.0047823973,0.002723355,0.000013483178,0.00002222019,0.0469526],"genre_scores_gemma":[0.99634606,0.0000034015009,0.0016682553,0.0013213819,0.0003248088,0.0000882931,0.0000050138456,0.000009712614,0.00023306503],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9936276,0.0011964686,0.00097487005,0.00022544443,0.003518889,0.000456721],"domain_scores_gemma":[0.9925585,0.00048556697,0.00064116635,0.0005516667,0.004682443,0.0010806737],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.031174932,0.00014419107,0.00023345728,0.0006912653,0.00096278917,0.0009863564,0.001173106,0.000087475455,0.004890842],"category_scores_gemma":[0.00868959,0.00008814901,0.00014537784,0.0010004417,0.0002788492,0.0006024689,0.000012933352,0.0002878207,0.00030257294],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006124753,0.000015275364,0.040434137,0.0000018261464,0.000020041616,0.0000029113935,0.0058868425,0.0035147497,0.000018814973,0.0036942847,0.009606996,0.936798],"study_design_scores_gemma":[0.000586992,0.00037094706,0.14086269,0.000028674576,0.000058016678,0.000061057486,0.00340962,0.18189299,0.00004260425,0.011544553,0.66096973,0.0001721335],"about_ca_topic_score_codex":0.07267068,"about_ca_topic_score_gemma":0.9269716,"teacher_disagreement_score":0.93662584,"about_ca_system_score_codex":0.0008618571,"about_ca_system_score_gemma":0.015880954,"threshold_uncertainty_score":0.9996606},"labels":[],"label_agreement":null},{"id":"W1701527280","doi":"","title":"King, J. A., & Stevahn, L. (2013). Interactive Evaluation Practice: Mastering the Interpersonal Dynamics of Program Evaluation","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Dynamics (music); Interpersonal communication; Psychology; Interpersonal relationship; Applied psychology; Social psychology; Pedagogy","score_opus":0.29701047840383554,"score_gpt":0.5445591158437647,"score_spread":0.24754863743992916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1701527280","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92683095,0.0015826722,0.0051974915,0.02719356,0.004764677,0.020848418,0.000025196081,0.000040089573,0.013516963],"genre_scores_gemma":[0.9909401,0.000020182253,0.006720948,0.0002448648,0.0002881937,0.0015890903,0.000076689146,0.000026278996,0.00009363383],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98559874,0.0035366276,0.0021295836,0.00043290987,0.0078038992,0.00049822096],"domain_scores_gemma":[0.9696128,0.0010738553,0.003229207,0.0006362311,0.025019346,0.00042860606],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05144329,0.00029279004,0.00043536827,0.0010085256,0.00037166633,0.0013537024,0.0009799715,0.00016480846,0.01067692],"category_scores_gemma":[0.01443191,0.00020248661,0.00027382877,0.0012727102,0.00026015218,0.004076652,0.00005735023,0.0005941084,0.00020010164],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053788543,0.00015377047,0.0039314367,0.000009375816,0.00012790777,0.000001030336,0.003661172,0.008165937,0.00005703431,0.00017866533,0.0024613529,0.98119855],"study_design_scores_gemma":[0.0014753954,0.001144537,0.047944035,0.00016598414,0.000564154,0.00008472572,0.018048054,0.90927386,0.00006503767,0.0060080485,0.015011633,0.00021451521],"about_ca_topic_score_codex":0.0028140908,"about_ca_topic_score_gemma":0.030148966,"teacher_disagreement_score":0.98098403,"about_ca_system_score_codex":0.0021142934,"about_ca_system_score_gemma":0.007869059,"threshold_uncertainty_score":0.99968296},"labels":[],"label_agreement":null},{"id":"W1713678554","doi":"10.56645/jmde.v1i1.144","title":"Unpacking the Participatory Process","year":2004,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":116,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Unpacking; Citizen journalism; Process (computing); Participatory action research; Sociology; Computer science; Linguistics; Anthropology; World Wide Web","score_opus":0.4185578280274691,"score_gpt":0.5807891987238559,"score_spread":0.16223137069638682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1713678554","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9832875,0.00025033441,0.0044285594,0.009536241,0.00086458755,0.00030063116,0.0000010211846,0.0000071525897,0.0013239892],"genre_scores_gemma":[0.9988037,0.000017224576,0.0006321574,0.00012968568,0.0003247077,0.00001664283,0.0000012067696,0.000007606176,0.00006708209],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.99306774,0.0005869774,0.0011801729,0.000174227,0.004807885,0.0001829753],"domain_scores_gemma":[0.99508786,0.00055989745,0.0012376412,0.00034902574,0.0026695495,0.000096052296],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.029263932,0.00011214218,0.00020867134,0.00024467896,0.00038554883,0.00016044626,0.00061566854,0.00005013071,0.0005789404],"category_scores_gemma":[0.002714318,0.000057794005,0.00015183864,0.0006487271,0.00009244587,0.0010406333,0.00006436052,0.0002526594,0.00013876543],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020613658,0.00038435747,0.042560697,0.00000975351,0.000057395016,0.000009186549,0.03173842,0.8148253,0.0022789612,0.001044969,0.0006851172,0.1061997],"study_design_scores_gemma":[0.0045359344,0.0007419103,0.5798056,0.00016863881,0.00022664902,0.00014674317,0.026245572,0.15641181,0.0052519664,0.22499977,0.0011938454,0.0002715633],"about_ca_topic_score_codex":0.0000017855043,"about_ca_topic_score_gemma":0.000024414361,"teacher_disagreement_score":0.6584135,"about_ca_system_score_codex":0.00022936927,"about_ca_system_score_gemma":0.0012991783,"threshold_uncertainty_score":0.99957705},"labels":[],"label_agreement":null},{"id":"W1720965121","doi":"10.3138/cjpe.28.001","title":"Measuring Organizational Evaluation Capacity in the Canadian Federal Government","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Saint Paul University; Carleton University; École Nationale d'Administration Publique","funders":"","keywords":"Government (linguistics); Identification (biology); Organization development; Business; Evaluation methods; Organizational effectiveness; Organizational learning; Organizational identification; Public relations; Process management; Organizational commitment; Knowledge management; Political science; Computer science; Engineering","score_opus":0.5879919298116747,"score_gpt":0.4514966114809471,"score_spread":0.1364953183307276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1720965121","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96937543,0.00016347649,0.00017823227,0.012695644,0.00082978647,0.0027482733,0.000009060739,0.000004392744,0.013995704],"genre_scores_gemma":[0.9976972,0.0000020508205,0.0010447514,0.0007699055,0.00020085777,0.00020690056,0.00001590529,0.0000093738045,0.000053080494],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98997384,0.0014660769,0.0009977651,0.00021529279,0.0069556595,0.00039136998],"domain_scores_gemma":[0.99312586,0.0002471033,0.00054846436,0.00030832842,0.0052393572,0.0005309196],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.034078192,0.00014051955,0.00018818994,0.00053922815,0.0005719237,0.0013775311,0.0006910252,0.0000983563,0.008415329],"category_scores_gemma":[0.0062744627,0.000096590265,0.00008399943,0.0011660238,0.00008285926,0.0010360737,0.000008824198,0.00032009534,0.00023655027],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000052069113,0.00006601281,0.36801237,0.0000036660288,0.00003054914,0.0000042802067,0.0051844027,0.01159351,0.000046744604,0.0014999626,0.008538914,0.6050144],"study_design_scores_gemma":[0.0008491836,0.00014267981,0.8455033,0.000028657709,0.000041643736,0.000045529454,0.002684727,0.122380644,0.00003949021,0.01958001,0.008557946,0.0001462025],"about_ca_topic_score_codex":0.13232444,"about_ca_topic_score_gemma":0.948618,"teacher_disagreement_score":0.81629354,"about_ca_system_score_codex":0.0035107515,"about_ca_system_score_gemma":0.013134344,"threshold_uncertainty_score":0.9996591},"labels":[],"label_agreement":null},{"id":"W1721955292","doi":"10.7202/007185ar","title":"Évaluation d’implantation dans un contexte participatif : Le processus suivi à Relais-Méthadone","year":2003,"lang":"fr","type":"article","venue":"Drogues santé et société","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Montréal; Douglas College; McGill University","funders":"","keywords":"Humanities; Political science; Valuation (finance); Art; Business","score_opus":0.1790190407347403,"score_gpt":0.4794635818741903,"score_spread":0.30044454113945,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1721955292","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6294108,0.00502578,0.03162191,0.007992325,0.0067784493,0.0013525267,0.0001244045,0.00018007481,0.31751373],"genre_scores_gemma":[0.9687955,0.0012921082,0.0031702593,0.0014923414,0.000213742,0.00018941176,0.00018382806,0.000047887715,0.024614967],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99146336,0.0027331007,0.0015005028,0.0008640953,0.0025160483,0.0009228961],"domain_scores_gemma":[0.99531287,0.0018873642,0.00081536145,0.000684343,0.0009803835,0.0003196684],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.012928682,0.0004419237,0.000604274,0.00019675904,0.0008568253,0.00053997315,0.0005047496,0.0003535666,0.0065041035],"category_scores_gemma":[0.0031896236,0.00041993038,0.00025007065,0.0011059494,0.00041084536,0.0018036189,0.000078874706,0.0004953171,0.0020424114],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000112618814,0.0009897397,0.021573365,0.000112430316,0.00018817106,0.00002863878,0.081451006,0.0023612014,0.0009156236,0.09340366,0.008033232,0.7908303],"study_design_scores_gemma":[0.0100880675,0.0012817825,0.18145373,0.0005773982,0.0007847014,0.00025789518,0.23851395,0.08501179,0.026330963,0.2635602,0.18983853,0.0023009882],"about_ca_topic_score_codex":0.00026836531,"about_ca_topic_score_gemma":0.0012377342,"teacher_disagreement_score":0.78852934,"about_ca_system_score_codex":0.000279881,"about_ca_system_score_gemma":0.0021655075,"threshold_uncertainty_score":0.99982524},"labels":[],"label_agreement":null},{"id":"W1723825527","doi":"","title":"Contributing Factors to the Continued Blurring of Research and Evaluation: Strategies for Moving Forward","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Confusion; Terminology; Political science; Humanities; Psychology; Philosophy","score_opus":0.5525192653748852,"score_gpt":0.6023241883787067,"score_spread":0.049804923003821555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1723825527","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98349273,0.00027839927,0.009238467,0.003210124,0.000470454,0.0023918794,0.0000095015575,0.0000038514427,0.00090457755],"genre_scores_gemma":[0.99784285,0.0000017633306,0.0017261257,0.000050789604,0.00020373368,0.00012323058,0.0000063526973,0.00000719059,0.00003798495],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9944559,0.0010735667,0.0009121165,0.00019489261,0.0029941422,0.00036938462],"domain_scores_gemma":[0.985023,0.0021720764,0.0005987038,0.00025542246,0.011639814,0.0003109524],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09206989,0.00009541503,0.00025020813,0.00063317566,0.00054735946,0.0006758998,0.00042933342,0.00005897651,0.00020432434],"category_scores_gemma":[0.019291226,0.00006120194,0.000079827776,0.0007328683,0.00013383226,0.0005045364,0.00002489952,0.00018422236,0.0000041409457],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004635203,0.000024196546,0.053295493,0.000018179784,0.00004681656,2.2090423e-7,0.0072000017,0.013966802,0.00021300119,0.0064587733,0.0017563268,0.9169738],"study_design_scores_gemma":[0.0027099515,0.0024739606,0.23714213,0.00025189004,0.00017560388,0.000011640575,0.042325076,0.58124167,0.0009458035,0.091983415,0.04051334,0.00022554137],"about_ca_topic_score_codex":0.00039724528,"about_ca_topic_score_gemma":0.015078692,"teacher_disagreement_score":0.9167483,"about_ca_system_score_codex":0.00023272456,"about_ca_system_score_gemma":0.0036672093,"threshold_uncertainty_score":0.9889697},"labels":[],"label_agreement":null},{"id":"W1724770786","doi":"10.3138/cjpe.30.1.23","title":"Reflexivity in Evaluating an Aboriginal Women Heart Health Promotion Program","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"B.C. Women's Hospital & Health Centre","funders":"","keywords":"Reflexivity; Context (archaeology); Process (computing); Promotion (chess); Rework; Sociology; Power (physics); Psychology; Computer science; Political science; Social science","score_opus":0.6574517143601347,"score_gpt":0.6690681666853625,"score_spread":0.011616452325227788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1724770786","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9898873,0.0002455334,0.00023882133,0.0052304645,0.00088268175,0.0025039893,0.000004562412,0.000026610067,0.0009800423],"genre_scores_gemma":[0.97892886,0.000005345002,0.02003118,0.00026806726,0.0002868173,0.0003658955,0.000023422339,0.000015399402,0.0000750365],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9903514,0.002829826,0.00161485,0.0003705458,0.0041680215,0.0006653506],"domain_scores_gemma":[0.992336,0.000108794426,0.0010940818,0.0004149587,0.004376627,0.0016695863],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0842098,0.00018116312,0.0004293545,0.0011682493,0.00021065501,0.00063363585,0.0005043781,0.00010084556,0.00068120926],"category_scores_gemma":[0.003290886,0.00014953622,0.00008381655,0.0016540266,0.000094813986,0.001812091,0.0000106653615,0.00039789386,0.00006560972],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049633323,0.0003443919,0.056346968,0.000007845292,0.0000078684825,0.000003840615,0.0060884655,0.0038190568,0.00001567732,0.00018376335,0.000943326,0.93218917],"study_design_scores_gemma":[0.0057404544,0.029070377,0.34797975,0.0002620389,0.00004250948,0.00018401764,0.012537658,0.44239467,0.000046499757,0.0397419,0.12145916,0.0005409378],"about_ca_topic_score_codex":0.0015898745,"about_ca_topic_score_gemma":0.048774797,"teacher_disagreement_score":0.93164825,"about_ca_system_score_codex":0.003112326,"about_ca_system_score_gemma":0.029185064,"threshold_uncertainty_score":0.97631854},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"qualitative","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W1727891101","doi":"","title":"S. N. Hesse-Biber. (2010). Mixed Methods Research: Merging Theory with Practice. New York, NY: Guildford. 242 pages.","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics; Sociology; Information retrieval; Computer science","score_opus":0.7558464177977277,"score_gpt":0.634052245019063,"score_spread":0.12179417277866467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1727891101","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29800794,0.06606645,0.28605396,0.122990474,0.025756769,0.014784735,0.000032243755,0.00020450098,0.18610293],"genre_scores_gemma":[0.76379395,0.000076098164,0.23180969,0.0005615311,0.0011336548,0.00010337666,0.000013466132,0.00004216533,0.0024660944],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9840943,0.008182966,0.0012446824,0.00032887392,0.0052082334,0.000940895],"domain_scores_gemma":[0.98693144,0.0035876725,0.0012158124,0.0006990973,0.005867297,0.0016986794],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.16947855,0.00022005514,0.00038762914,0.0015544608,0.0005842444,0.0009099912,0.0008894643,0.00014610282,0.004230434],"category_scores_gemma":[0.024021843,0.00015017741,0.00014829922,0.0022683947,0.00024797916,0.0027309724,0.00003746582,0.0007942582,0.00023125806],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008663866,0.000068307316,0.004157092,0.0000042721126,0.00008408856,0.000005843816,0.0036362577,0.0005239592,0.000054418768,0.0026903034,0.057015385,0.9316734],"study_design_scores_gemma":[0.0015985556,0.0009945132,0.033919524,0.00012816694,0.00031298888,0.0002446962,0.018073032,0.0058001885,0.0006185965,0.024429286,0.91354406,0.00033636764],"about_ca_topic_score_codex":0.0010128497,"about_ca_topic_score_gemma":0.008278984,"teacher_disagreement_score":0.93133706,"about_ca_system_score_codex":0.00073335896,"about_ca_system_score_gemma":0.0118340235,"threshold_uncertainty_score":0.99667984},"labels":[],"label_agreement":null},{"id":"W1731146079","doi":"10.5281/zenodo.31995","title":"A Monitoring And Evaluation Platform For Nonprofits: Dhis2 Quick Start","year":2015,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"LogicalOutcomes","funders":"","keywords":"Computer science","score_opus":0.3946235449976357,"score_gpt":0.45240510533995876,"score_spread":0.05778156034232307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1731146079","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8520855,0.00045072692,0.013197503,0.0034214433,0.0010028506,0.0027375533,0.00019446474,0.00058634655,0.12632361],"genre_scores_gemma":[0.9962465,0.00004624662,0.001565705,0.00009756305,0.00026713772,5.172213e-7,0.00026090903,0.00034478644,0.0011706429],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99669653,0.00030232177,0.00042989978,0.00044260806,0.001839394,0.00028923317],"domain_scores_gemma":[0.99563,0.00013537072,0.00018521481,0.0004358254,0.003355697,0.00025789326],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0101413075,0.000120674355,0.00015589716,0.00029763946,0.0013744637,0.0013280921,0.0006928243,0.000057669396,0.0037968196],"category_scores_gemma":[0.004688781,0.00010541506,0.000039634993,0.00057740003,0.00009018983,0.0008595391,0.0005066089,0.000133994,0.002913897],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021607778,0.000095424926,0.00028940447,0.000024521953,0.000030500034,0.0000010520033,0.0063331416,0.0005306567,0.0013360175,0.002479668,0.13917308,0.84949046],"study_design_scores_gemma":[0.0015957768,0.00045635193,0.0030199431,0.000024624354,0.000019389208,0.000021630038,0.004396868,0.025132556,0.0006722082,0.0037645162,0.9607248,0.00017134375],"about_ca_topic_score_codex":0.000009212259,"about_ca_topic_score_gemma":7.528496e-7,"teacher_disagreement_score":0.8493191,"about_ca_system_score_codex":0.00023488191,"about_ca_system_score_gemma":0.000030126417,"threshold_uncertainty_score":0.9999256},"labels":[],"label_agreement":null},{"id":"W1731692312","doi":"10.3138/cjpe.023.010","title":"Professional Identity of Evaluators in Israel","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Diversity (politics); Identity (music); Context (archaeology); Public relations; Professional association; Professional development; Political science; Publication; Sociology; Pedagogy; Law; Geography","score_opus":0.5165946088532868,"score_gpt":0.591396369755435,"score_spread":0.07480176090214818,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1731692312","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99498165,0.000386979,0.0002394747,0.0008648437,0.0011319966,0.00073221774,0.000004538316,0.0000029623898,0.0016553691],"genre_scores_gemma":[0.997711,0.000014034973,0.001844072,0.000094106974,0.00009185199,0.00003373078,0.000005145343,0.000006281554,0.00019979622],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9935228,0.0008191996,0.0014079206,0.0001705669,0.003840655,0.00023881393],"domain_scores_gemma":[0.99390656,0.00023069062,0.0012767614,0.0002512719,0.004007021,0.00032769778],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.021700958,0.0001018093,0.0002923712,0.0012058287,0.00014803764,0.000064768035,0.0005260654,0.00008624579,0.0023626648],"category_scores_gemma":[0.0060066134,0.000078418096,0.00013555147,0.0013552338,0.00015957993,0.0012025138,0.00001598131,0.0002335529,0.000057154397],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027148848,0.000118266194,0.77717155,0.0000058761616,0.000015777463,0.000013702463,0.001813459,0.0025934288,0.0000841317,0.00094179506,0.0024764384,0.2147384],"study_design_scores_gemma":[0.0013471084,0.0003400268,0.95414096,0.000078068326,0.000030734212,0.00006859617,0.0017825165,0.025649356,0.00017552871,0.012397327,0.0038781913,0.00011158574],"about_ca_topic_score_codex":0.0012523024,"about_ca_topic_score_gemma":0.034479685,"teacher_disagreement_score":0.2146268,"about_ca_system_score_codex":0.00042564768,"about_ca_system_score_gemma":0.011557061,"threshold_uncertainty_score":0.9985493},"labels":[],"label_agreement":null},{"id":"W1746934302","doi":"10.3138/cjpe.0028.012","title":"Evaluator Competencies and Professionalizing the Field: Where Are We Now?","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Professionalization; Globe; Narrative; Field (mathematics); Core competency; Happening; Engineering ethics; Sociology; Epistemology; Pedagogy; Psychology; Management; Engineering; Social science; Linguistics; History; Philosophy","score_opus":0.27667815328718687,"score_gpt":0.51874720227499,"score_spread":0.24206904898780318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1746934302","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.661557,0.0075194705,0.003806208,0.31475365,0.0033898423,0.002640774,0.000008162366,0.00002454613,0.0063003153],"genre_scores_gemma":[0.99577975,0.00010206976,0.0021107898,0.0012770781,0.00030693036,0.000053510415,0.0000018397059,0.000008042242,0.00036000935],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99558544,0.0011082382,0.00069597765,0.00017314001,0.002208029,0.00022919157],"domain_scores_gemma":[0.99503845,0.0011835634,0.0007570415,0.0002833003,0.0024096526,0.0003279956],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.020262536,0.00011406765,0.00021193699,0.0002988071,0.0004910763,0.00046541955,0.00045429647,0.00007229306,0.0016228047],"category_scores_gemma":[0.0034514957,0.00006473122,0.00008447996,0.00042517326,0.00011539815,0.00044991885,0.000023147282,0.00025713988,0.000046765832],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013325651,0.000018397664,0.07032406,0.000010817682,0.000021844942,0.0000014599445,0.0017240966,0.000585368,0.00002581445,0.0012867008,0.05593716,0.87005097],"study_design_scores_gemma":[0.00080454425,0.0004739039,0.115902685,0.00023001556,0.00008985761,0.00004401563,0.005221462,0.12490412,0.000043148444,0.021762721,0.7303718,0.00015173755],"about_ca_topic_score_codex":0.00012915608,"about_ca_topic_score_gemma":0.027589168,"teacher_disagreement_score":0.8698992,"about_ca_system_score_codex":0.000121379504,"about_ca_system_score_gemma":0.002199836,"threshold_uncertainty_score":0.9992899},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"},{"model":"grok","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W1752506239","doi":"10.3138/cjpe.29.3.21","title":"Professional Standards for Evaluators: The Development of an Action Plan for the Canadian Evaluation Society","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Action plan; Plan (archaeology); Action (physics); Professional association; Professional standards; Political science; Public relations; Professional development; Medical education; Engineering ethics; Management; Medicine; Engineering; Geography","score_opus":0.710120940519769,"score_gpt":0.6227491034315585,"score_spread":0.0873718370882105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1752506239","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91536313,0.0014649505,0.030387638,0.019860791,0.008992401,0.02251944,0.00038023194,0.00001938925,0.0010120387],"genre_scores_gemma":[0.9822046,0.0000020727186,0.015637826,0.0002443311,0.00046186135,0.0012163088,0.00011949363,0.000016734899,0.00009672683],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9912493,0.0008931622,0.001296657,0.00024293805,0.005928547,0.00038935174],"domain_scores_gemma":[0.976522,0.0007736501,0.0011628943,0.00038307058,0.020487754,0.0006705731],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.119444855,0.00016329235,0.00024617524,0.00035220975,0.0013298601,0.00042598275,0.0007535038,0.00014124392,0.00040877808],"category_scores_gemma":[0.007435805,0.00009033641,0.0002123744,0.0005808564,0.00015514059,0.0007293827,0.000011781632,0.00021362572,0.000004448323],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000107924636,0.00004164055,0.0016850134,0.000010287489,0.00009495397,7.520438e-8,0.011813538,0.009294713,0.000022598553,0.0002789198,0.021058168,0.95559216],"study_design_scores_gemma":[0.0029041213,0.00083309517,0.028908325,0.000060016973,0.00035215862,0.000011223468,0.021144694,0.63838863,0.00029925597,0.013191081,0.2937275,0.00017991035],"about_ca_topic_score_codex":0.0047379625,"about_ca_topic_score_gemma":0.78774965,"teacher_disagreement_score":0.95541227,"about_ca_system_score_codex":0.0030097403,"about_ca_system_score_gemma":0.1187729,"threshold_uncertainty_score":0.99997026},"labels":[],"label_agreement":null},{"id":"W1756635678","doi":"10.1007/s00038-015-0752-1","title":"Trashing bibliometry? In defence of a unique approach for disciplinary development","year":2015,"lang":"en","type":"letter","venue":"International Journal of Public Health","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Public health; Discipline; Environmental health; Engineering ethics; Medicine; Political science; Engineering; Law; Nursing","score_opus":0.6431299511284877,"score_gpt":0.5869885382185964,"score_spread":0.056141412909891275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1756635678","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009102844,0.00037382383,0.23545799,0.75112146,0.0018086256,0.00041897074,0.00007211812,0.000006249307,0.0016379075],"genre_scores_gemma":[0.36598924,0.000553123,0.24053314,0.38320965,0.006193648,0.00012708253,0.00063584285,0.00009298886,0.0026652925],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9896695,0.0007049697,0.0030561308,0.0003128772,0.00587181,0.00038468567],"domain_scores_gemma":[0.99005574,0.0012194772,0.003246026,0.0002450335,0.005017101,0.00021664459],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.037762687,0.00019113849,0.0006791016,0.010477142,0.00005608611,0.00033541498,0.002274932,0.00023665254,0.00013662854],"category_scores_gemma":[0.0031887165,0.0001386381,0.00019460412,0.0026382906,0.00006631197,0.0009795082,0.00017541483,0.0010133827,0.0000054709362],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046210807,0.00030588015,0.012571289,0.00010035469,0.00012687693,0.000024955827,0.0039038335,0.0005922152,0.0000045445117,0.00034371638,0.8530214,0.12895875],"study_design_scores_gemma":[0.0012351898,0.00031371933,0.011314279,0.00026159536,0.0000044508674,0.00012735173,0.0013857768,0.003547251,0.000012842226,0.003995169,0.977602,0.00020035366],"about_ca_topic_score_codex":0.000026733473,"about_ca_topic_score_gemma":0.000035162364,"teacher_disagreement_score":0.36791182,"about_ca_system_score_codex":0.0011041013,"about_ca_system_score_gemma":0.012291309,"threshold_uncertainty_score":0.99330807},"labels":[],"label_agreement":null},{"id":"W1757766395","doi":"10.1139/cjp-2015-0432","title":"Introduction to the Proceedings of Theory Canada 9","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Physics","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Canadian Association of Physicists","funders":"","keywords":"Physics; Theoretical physics; Engineering physics","score_opus":0.11426001542786478,"score_gpt":0.380071499764719,"score_spread":0.2658114843368542,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1757766395","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9276407,0.00010090783,0.0015342848,0.057300795,0.002792058,0.00014274893,0.000015282563,0.0000014104843,0.010471811],"genre_scores_gemma":[0.9967601,6.8657965e-7,0.00016080854,0.00072962715,0.0013492518,6.083384e-7,2.4254993e-7,0.000002976028,0.0009957573],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986356,0.000032564618,0.00031830263,0.00006438204,0.0008427368,0.00010643371],"domain_scores_gemma":[0.9972077,0.00007464284,0.0002784241,0.000102749575,0.0019670795,0.0003693977],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034893546,0.00004391081,0.00011022845,0.0000814746,0.00006307869,0.000066918554,0.00040212375,0.000011668564,0.00017486761],"category_scores_gemma":[0.0010975858,0.000025523665,0.000031671298,0.0004820917,0.00003420081,0.00023278393,0.000008515511,0.00009709351,0.000018036679],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013794645,0.000004371118,0.0052283234,0.0000012901745,0.00001217744,0.0000010132076,0.002492541,0.0030628527,0.000085167194,0.03023375,0.9179302,0.04093455],"study_design_scores_gemma":[0.00019238766,0.00015101279,0.00964223,0.00001195265,0.00001538868,0.000021074662,0.010349028,0.0002953512,0.0022286298,0.04310278,0.9339153,0.00007485837],"about_ca_topic_score_codex":0.068759136,"about_ca_topic_score_gemma":0.6628271,"teacher_disagreement_score":0.59406793,"about_ca_system_score_codex":0.00020632998,"about_ca_system_score_gemma":0.006892765,"threshold_uncertainty_score":0.9987372},"labels":[],"label_agreement":null},{"id":"W1758177958","doi":"10.3138/cjpe.29.3.86","title":"View from the Credentialing Board: Where We've Been and Where We're Going","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Government of Northwest Territories; Barrie Urology Group","funders":"","keywords":"Credentialing; On board; Editorial board; Psychology; Engineering ethics; Medical education; Management; Computer science; Library science; Engineering; Medicine","score_opus":0.4342804105770348,"score_gpt":0.5121123250234277,"score_spread":0.07783191444639292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1758177958","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7009358,0.15436551,0.0032217926,0.12756038,0.004674381,0.0029791538,0.000052645137,0.000036370897,0.0061739907],"genre_scores_gemma":[0.9925637,0.0011216986,0.004496711,0.0005207267,0.0007999169,0.000041853466,0.0000115951325,0.000018907494,0.00042487073],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99524385,0.0008757367,0.0008802396,0.00023664719,0.0024855512,0.00027795686],"domain_scores_gemma":[0.9957508,0.00041518823,0.0007117679,0.00032330208,0.0021411872,0.0006577716],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.014447307,0.00014809848,0.00027014443,0.00022330701,0.00034069733,0.001218063,0.0005523192,0.00009423861,0.00210463],"category_scores_gemma":[0.0016557542,0.000095897274,0.00010244342,0.0004913503,0.00010654813,0.0008606438,0.000030650644,0.00028736974,0.0001258195],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014683463,0.000013538648,0.028135052,0.000007573422,0.000044452878,0.0000062550644,0.006871191,0.0008475753,0.000013369211,0.000096705386,0.03992717,0.92402244],"study_design_scores_gemma":[0.0020040926,0.00048268164,0.026797026,0.00074960955,0.00030414914,0.000042211286,0.027142843,0.07422037,0.000030161604,0.021558415,0.84638494,0.0002835278],"about_ca_topic_score_codex":0.0017876322,"about_ca_topic_score_gemma":0.15782678,"teacher_disagreement_score":0.9237389,"about_ca_system_score_codex":0.00030990003,"about_ca_system_score_gemma":0.0041759685,"threshold_uncertainty_score":0.99981874},"labels":[],"label_agreement":null},{"id":"W1758542515","doi":"","title":"Interviewing Nookomis and Other Reflections: The Promise of Community Collaboration","year":2010,"lang":"en","type":"article","venue":"Oral History Forum d'histoire orale","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University","funders":"","keywords":"Interview; Sociology; Public relations; Engineering ethics; Political science; Engineering; Anthropology","score_opus":0.23706157670783917,"score_gpt":0.45610286863253513,"score_spread":0.21904129192469596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1758542515","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89673764,0.001591343,0.00051389856,0.009196603,0.0036323268,0.0006919527,0.000029687928,0.00007590861,0.08753063],"genre_scores_gemma":[0.9770346,0.000009722133,0.0011856568,0.0014767213,0.00003903781,0.00004811469,0.0000046621494,0.00001426394,0.020187167],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99806315,0.00045492855,0.00054379785,0.00017170944,0.000609883,0.0001565133],"domain_scores_gemma":[0.99811643,0.00026584326,0.00040052546,0.00074386795,0.00040605429,0.000067302164],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0036799547,0.00012651729,0.00023027917,0.00016971522,0.00080982613,0.000056841087,0.0004908338,0.00008144633,0.0015973871],"category_scores_gemma":[0.0005614759,0.0000848892,0.0000756554,0.00037005483,0.00059553847,0.00047927283,0.00011244419,0.00040727365,0.00006449728],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002221302,0.00047370573,0.022257265,0.000054965836,0.00004130206,9.0949015e-7,0.0353479,0.00004628068,0.050494935,0.012695155,0.6325483,0.24581717],"study_design_scores_gemma":[0.00034249233,0.00012596819,0.0027552042,0.0000129469645,0.000014866752,0.000005058057,0.004717711,0.0006428664,0.00038741733,0.0020651193,0.9888224,0.00010796754],"about_ca_topic_score_codex":0.00051169324,"about_ca_topic_score_gemma":0.015584143,"teacher_disagreement_score":0.3562741,"about_ca_system_score_codex":0.00023701499,"about_ca_system_score_gemma":0.00026505644,"threshold_uncertainty_score":0.99931526},"labels":[],"label_agreement":null},{"id":"W1758924022","doi":"10.71781/24082","title":"Questionnaire du climat social de l’équipe d’intervenants (QCSÉI) : structure factorielle et validité de critère dans un échantillon d’intervenants québécois","year":2010,"lang":"fr","type":"dissertation","venue":"Open MIND","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Humanities; Psychology; Sociology; Philosophy","score_opus":0.09731131170191733,"score_gpt":0.4669325806018168,"score_spread":0.3696212688998995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1758924022","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9783771,0.00022183348,0.0017585761,0.0039919643,0.0061609726,0.0011252667,0.0011565723,0.000011094632,0.0071965973],"genre_scores_gemma":[0.97975355,0.00020113192,0.0038626904,0.00037366655,0.00078051595,0.000069874535,0.0010304621,0.000099933764,0.013828147],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99163514,0.0016107559,0.001964586,0.0014841147,0.0021492867,0.0011560977],"domain_scores_gemma":[0.9951926,0.00049482874,0.0016711036,0.00089626433,0.001255902,0.0004892996],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0061660185,0.0009288137,0.001193021,0.00036816148,0.0015968666,0.0022618277,0.0032351338,0.0015146254,0.032888506],"category_scores_gemma":[0.0016610839,0.0007929049,0.00065807026,0.0007251375,0.00026051415,0.0017401378,0.00057379407,0.0016976694,0.0010926964],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004933231,0.00076164404,0.1425228,0.00020726943,0.0002563466,0.00011303176,0.33551994,0.00012281782,0.014257986,0.0010841611,0.0019549844,0.5027057],"study_design_scores_gemma":[0.0036156303,0.0008941433,0.6248545,0.0028490152,0.0006825049,0.0002178344,0.13033886,0.011264428,0.082296886,0.004938083,0.13561967,0.0024284488],"about_ca_topic_score_codex":0.015363732,"about_ca_topic_score_gemma":0.28214964,"teacher_disagreement_score":0.5002772,"about_ca_system_score_codex":0.0007090597,"about_ca_system_score_gemma":0.0044514183,"threshold_uncertainty_score":0.9997816},"labels":[],"label_agreement":null},{"id":"W1767493202","doi":"","title":"The 5 Cs for innovating in evaluation: Lessons from the field","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Ontario Centre of Excellence for Child and Youth Mental Health","funders":"","keywords":"Excellence; Courage; Coaching; Humanities; Political science; Sociology; Management; Art; Economics","score_opus":0.5293170350997406,"score_gpt":0.5948341961710625,"score_spread":0.06551716107132188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1767493202","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7709296,0.0020506224,0.0032893845,0.21023566,0.0026689789,0.0066294475,0.000013298142,0.000008153687,0.004174906],"genre_scores_gemma":[0.99489844,0.000010634173,0.0024937526,0.0014726244,0.00035559165,0.00066324597,0.000012121581,0.000006899301,0.000086704385],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956437,0.00078588387,0.0010327911,0.00016105798,0.0021074228,0.00026914504],"domain_scores_gemma":[0.9885219,0.00464954,0.0007307067,0.0003618914,0.005590657,0.00014531458],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03478024,0.00009406649,0.00014816849,0.00021163355,0.0005573776,0.0009869754,0.0007141387,0.000067372755,0.0019074812],"category_scores_gemma":[0.022350699,0.000049407783,0.00009040958,0.0008848711,0.000070393624,0.0005700022,0.000014215486,0.00024269728,0.000048424085],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006017097,0.000008869807,0.015049563,5.151868e-7,0.000012486088,1.6198634e-7,0.0008273089,0.0008907751,0.00001323154,0.0009852444,0.0275379,0.9546679],"study_design_scores_gemma":[0.0012957426,0.00028942447,0.3096844,0.000056844525,0.000061469465,0.0000043782356,0.0046412037,0.43540618,0.00007100738,0.119301274,0.12906657,0.00012152551],"about_ca_topic_score_codex":0.0027463413,"about_ca_topic_score_gemma":0.07745856,"teacher_disagreement_score":0.9545464,"about_ca_system_score_codex":0.00030134135,"about_ca_system_score_gemma":0.004691143,"threshold_uncertainty_score":0.9990049},"labels":[],"label_agreement":null},{"id":"W1769680758","doi":"10.3138/cjpe.29.3.70","title":"Launching the Credentialed Evaluator (CE) Designation","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Credentialing; Credibility; Process (computing); Stakeholder; Corporate governance; Politics; Political science; Public relations; Business; Engineering ethics; Public administration; Process management; Management; Engineering management; Law; Computer science; Engineering; Economics","score_opus":0.6094119450625466,"score_gpt":0.5671337020641761,"score_spread":0.04227824299837046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1769680758","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9430896,0.0020462354,0.017930994,0.012171728,0.0049366374,0.0030488677,0.0000068436857,0.000027933422,0.016741129],"genre_scores_gemma":[0.99607307,0.0000039017054,0.0028416514,0.0002976402,0.00041646822,0.00005167833,0.000007891162,0.000010192861,0.00029752523],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9925676,0.0015539078,0.0010018975,0.00018128537,0.0044285925,0.00026672526],"domain_scores_gemma":[0.9910981,0.00035469086,0.00088549557,0.0003479372,0.006706581,0.00060716236],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05226286,0.00012035437,0.00019775279,0.00056886644,0.00033552325,0.0008829695,0.0007153524,0.000074592506,0.0022414445],"category_scores_gemma":[0.010249908,0.00007372851,0.00013414283,0.0009041427,0.00009814138,0.0009559852,0.000015731528,0.00023796425,0.00020427576],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026203064,0.000032444997,0.010418268,0.0000014463569,0.000035829282,0.0000042430092,0.0037607215,0.012159996,0.00005714811,0.0007842952,0.02308716,0.9496322],"study_design_scores_gemma":[0.0038169995,0.0012292113,0.07685768,0.000076958764,0.00038827598,0.00016949215,0.009786886,0.55481714,0.00033094105,0.08518075,0.26697597,0.00036970808],"about_ca_topic_score_codex":0.00044999752,"about_ca_topic_score_gemma":0.010230511,"teacher_disagreement_score":0.94926256,"about_ca_system_score_codex":0.0006172784,"about_ca_system_score_gemma":0.0112705985,"threshold_uncertainty_score":0.99867064},"labels":[],"label_agreement":null},{"id":"W1769901993","doi":"10.3138/cjpe.29.3.33","title":"A Made-in-Canada Credential: Developing an Evaluation Professional Designation","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Credential; Context (archaeology); Public relations; Political science; Process (computing); Service (business); Credentialing; Sociology; Business; Law; Marketing; Geography; Computer science","score_opus":0.6273699174603828,"score_gpt":0.566949663297369,"score_spread":0.06042025416301389,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1769901993","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98645616,0.00039126605,0.0031397606,0.0031691382,0.0033142527,0.0019391099,0.000004652568,0.000007091765,0.0015785712],"genre_scores_gemma":[0.9929635,0.000002879657,0.0062706787,0.00026579504,0.0002081249,0.00014006802,0.000044529705,0.000012160276,0.00009228142],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98933583,0.002012182,0.0013967034,0.0002818966,0.0066190455,0.00035434845],"domain_scores_gemma":[0.98921335,0.00019585484,0.00094187225,0.00027112654,0.008650867,0.00072691514],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.04134887,0.00015282742,0.00026275704,0.0010037754,0.00017160345,0.00036754893,0.00055268814,0.0000876741,0.0018056348],"category_scores_gemma":[0.005319535,0.00012715034,0.00005791832,0.0012165277,0.000040847786,0.001693507,0.000014597065,0.00024402705,0.00003484086],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000037463848,0.000043294058,0.06534165,0.0000031577931,0.000014454356,0.000008898328,0.0016274354,0.025328629,0.00004050421,0.00036316246,0.0040249876,0.90316635],"study_design_scores_gemma":[0.0027140353,0.00036312992,0.35940024,0.00011048611,0.00007967413,0.00005347608,0.00826917,0.5896924,0.00020948457,0.0244212,0.014400416,0.00028628533],"about_ca_topic_score_codex":0.22928691,"about_ca_topic_score_gemma":0.97741014,"teacher_disagreement_score":0.9028801,"about_ca_system_score_codex":0.005771371,"about_ca_system_score_gemma":0.13170047,"threshold_uncertainty_score":0.9991068},"labels":[],"label_agreement":null},{"id":"W1773568500","doi":"10.3138/cjpe.0028.007","title":"Evaluator Competencies: The Aotearoa New Zealand Experience","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Aotearoa; Credentialing; Underpinning; Pedagogy; Set (abstract data type); Engineering ethics; Cultural competence; Sociology; Psychology; Medical education; Engineering; Computer science; Medicine; Gender studies","score_opus":0.27326673436579285,"score_gpt":0.4978504535242318,"score_spread":0.22458371915843894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1773568500","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9601,0.00050744216,0.0032624237,0.024327734,0.0029190346,0.0017242897,0.0000038728344,0.000020559224,0.007134626],"genre_scores_gemma":[0.992255,0.0000065285267,0.0031381517,0.00078305404,0.00055100373,0.00004212911,0.0000035427267,0.000009693078,0.003210928],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99412745,0.0010179012,0.0009415319,0.00021195551,0.0033748616,0.00032631974],"domain_scores_gemma":[0.99503493,0.0005683614,0.00073250424,0.00049236574,0.002497347,0.00067446765],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.022611402,0.00013340499,0.00023308567,0.00036111264,0.00034064412,0.0006817573,0.0009588725,0.00006542286,0.0042918627],"category_scores_gemma":[0.0066402755,0.000077745965,0.00014050744,0.00078268227,0.00017118709,0.00058937573,0.0000174055,0.00023828112,0.00022859505],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011136319,0.000015790807,0.02331101,9.8664e-7,0.000015102757,9.828595e-7,0.0074380725,0.0027453555,0.000041551233,0.00045945297,0.046281997,0.91967857],"study_design_scores_gemma":[0.0009977571,0.0005403476,0.09661956,0.000033332348,0.00006556979,0.000056166227,0.002278227,0.12262968,0.000073853334,0.028980656,0.7475715,0.00015330252],"about_ca_topic_score_codex":0.0016144427,"about_ca_topic_score_gemma":0.015463129,"teacher_disagreement_score":0.91952527,"about_ca_system_score_codex":0.00024426705,"about_ca_system_score_gemma":0.0062298966,"threshold_uncertainty_score":0.99940383},"labels":[],"label_agreement":null},{"id":"W1779597108","doi":"","title":"Implementation: The Ongoing Crisis of Method","year":2010,"lang":"en","type":"article","venue":"The Journal of Macrodynamic Analysis (Memorial University of Newfoundland)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Saint Vincent University","funders":"","keywords":"Business; Computer science","score_opus":0.04404451201301395,"score_gpt":0.41229333752143443,"score_spread":0.3682488255084205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1779597108","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9016347,0.000019569794,0.092404276,0.0041051297,0.0006821989,0.00008726887,0.000013696255,0.000002703302,0.0010504582],"genre_scores_gemma":[0.9959093,0.00007451419,0.0033692194,0.0000619889,0.00020622138,3.155626e-8,0.0000026422422,0.0000031992583,0.00037292374],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9965504,0.0007444483,0.0007814275,0.00012252684,0.0016682786,0.00013293054],"domain_scores_gemma":[0.99461484,0.0016580495,0.0019658115,0.00052287296,0.0011749279,0.00006351834],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01256227,0.00010059936,0.00047486436,0.0004896354,0.0003164952,0.00004910431,0.0014329397,0.00005024618,0.0035151567],"category_scores_gemma":[0.00022244178,0.000055156706,0.00052080734,0.0016086327,0.00017449273,0.0003347796,0.0001354859,0.00030714445,0.000010861],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004231302,0.0006019788,0.524849,0.00003844324,0.0140389735,0.000031278196,0.054657474,0.17643668,0.041565303,0.015494495,0.023614297,0.14444079],"study_design_scores_gemma":[0.006169163,0.00072768587,0.63063926,0.00002148913,0.012863189,0.00010295605,0.17207624,0.1329867,0.0005994493,0.017808476,0.025563825,0.00044157647],"about_ca_topic_score_codex":0.002637744,"about_ca_topic_score_gemma":0.030754732,"teacher_disagreement_score":0.1439992,"about_ca_system_score_codex":0.000057267214,"about_ca_system_score_gemma":0.00029528336,"threshold_uncertainty_score":0.99739575},"labels":[],"label_agreement":null},{"id":"W1781634349","doi":"10.1016/j.evalprogplan.2015.09.003","title":"Mapping the spatial dimensions of participatory practice: A discussion of context in evaluation","year":2015,"lang":"en","type":"article","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Citizen journalism; Participatory GIS; Bridge (graph theory); Context (archaeology); Sociology; Field (mathematics); Relation (database); Set (abstract data type); Politics; Process (computing); Knowledge management; Epistemology; Management science; Computer science; Political science; Engineering; Geography; Data mining","score_opus":0.571163556037539,"score_gpt":0.5995651283814842,"score_spread":0.028401572343945247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1781634349","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.985914,0.0022622866,0.0014762004,0.0043758727,0.00038041,0.0019769392,0.000003658456,0.000017368067,0.0035932534],"genre_scores_gemma":[0.9985191,0.000011844719,0.0010417717,0.00013616309,0.00003184359,0.00020103305,0.000016798309,0.0000046909304,0.000036733105],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9932777,0.002115079,0.00090042746,0.00024516325,0.0033092317,0.00015235615],"domain_scores_gemma":[0.99609166,0.001049505,0.0006811364,0.00029322115,0.0018056462,0.000078833335],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.041714016,0.00009722273,0.0002185398,0.00025647436,0.00010021411,0.00006694071,0.00015870712,0.00005806115,0.00018288386],"category_scores_gemma":[0.010475355,0.000046191493,0.00003995435,0.0006686093,0.00011441383,0.0004468706,0.00006910499,0.00013221068,0.000010300719],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009411052,0.00013083009,0.09589,0.0000055044784,0.000012294789,2.892326e-7,0.024364764,0.009257197,0.00010792375,0.00015812418,0.0004438651,0.8695351],"study_design_scores_gemma":[0.0015456046,0.00024258596,0.16093668,0.00012705545,0.00005111507,0.0000026738164,0.04576763,0.7804164,0.000112672264,0.0026621928,0.008055467,0.000079858764],"about_ca_topic_score_codex":0.000090356465,"about_ca_topic_score_gemma":0.00007281646,"teacher_disagreement_score":0.8694552,"about_ca_system_score_codex":0.000061090635,"about_ca_system_score_gemma":0.00062801054,"threshold_uncertainty_score":0.99785984},"labels":[],"label_agreement":null},{"id":"W1782129283","doi":"","title":"ARTICLE 5: DISSEMINATION AND EARLY USE OF THE PARIS DECLARATION EVALUATION","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Champion; Declaration; Transparency (behavior); Stakeholder; Corporate governance; Politics; Stakeholder engagement; Public relations; Political science; Evaluation methods; Process management; Business; Management science; Engineering; Law","score_opus":0.4613107564983002,"score_gpt":0.5371820478652425,"score_spread":0.07587129136694226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1782129283","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99560523,0.00059825875,0.00069676683,0.0011493635,0.00061868975,0.0010119502,0.0000031799148,0.000002772262,0.00031377096],"genre_scores_gemma":[0.998409,0.000009552693,0.0012995324,0.00004607872,0.00010977495,0.000043371223,0.0000035915857,0.00000581055,0.00007328899],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99533117,0.00097134744,0.00082858175,0.00011229434,0.0025542632,0.00020233271],"domain_scores_gemma":[0.9946276,0.0003815169,0.0009205871,0.00025575154,0.003543192,0.00027137407],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020253738,0.00008565668,0.00015104513,0.00033198833,0.00020536529,0.0003013843,0.00018652507,0.000072069255,0.0005301494],"category_scores_gemma":[0.0059494046,0.000056088968,0.00008198868,0.00069565605,0.00010102409,0.0019656317,0.000013576004,0.00012966231,0.000010238524],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007889583,0.00003204475,0.4874599,0.0000019244874,0.000011288908,5.4170364e-8,0.0022952263,0.0006634039,0.00039092707,0.00034930362,0.00087632675,0.50791174],"study_design_scores_gemma":[0.00035483425,0.0001258529,0.9304673,0.00003555685,0.00013712623,0.000010734216,0.00052440836,0.0601847,0.0011780548,0.0020604078,0.0048562707,0.000064733256],"about_ca_topic_score_codex":0.00034353044,"about_ca_topic_score_gemma":0.0028324896,"teacher_disagreement_score":0.507847,"about_ca_system_score_codex":0.00024413728,"about_ca_system_score_gemma":0.0013321879,"threshold_uncertainty_score":0.7122423},"labels":[],"label_agreement":null},{"id":"W1782687918","doi":"10.3138/cjpe.027.001","title":"L’évaluateur éthiquement engagé: sur le sens et la pertinence d’un nouveau référentiel","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"École Nationale d'Administration Publique","funders":"","keywords":"Meaning (existential); Commit; Neutrality; Subject (documents); Sociology; Epistemology; Psychology; Social psychology; Philosophy; Library science","score_opus":0.32017871900978256,"score_gpt":0.4955612199298118,"score_spread":0.17538250092002922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1782687918","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97823346,0.0009901009,0.0022304303,0.008362999,0.0016539232,0.0010112815,0.000008576703,0.000018962755,0.0074902675],"genre_scores_gemma":[0.9927689,0.000036273,0.00590277,0.0006555574,0.00025751162,0.00006473492,0.000014476246,0.000016392283,0.0002833727],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9927997,0.0023320944,0.0011488678,0.00022083132,0.002990616,0.00050786266],"domain_scores_gemma":[0.99430585,0.0005196949,0.000847791,0.0003682593,0.0031776899,0.0007806976],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.048080932,0.00018273029,0.0002730971,0.0004746725,0.00040670583,0.000627948,0.000497242,0.00011391792,0.0025598896],"category_scores_gemma":[0.0046998095,0.00014368028,0.00017479708,0.0006421796,0.000120150136,0.00146222,0.000027537644,0.00041938733,0.00016462678],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019515292,0.00024544273,0.081964515,0.00000677675,0.000057324385,0.00000730766,0.009300447,0.002421528,0.00021175841,0.0018808715,0.006786475,0.89709806],"study_design_scores_gemma":[0.0028418726,0.00063239253,0.40037057,0.000120710734,0.00021324203,0.00025192296,0.005064973,0.08373912,0.0008479571,0.0062051243,0.4992233,0.0004888331],"about_ca_topic_score_codex":0.00081549,"about_ca_topic_score_gemma":0.00470478,"teacher_disagreement_score":0.8966092,"about_ca_system_score_codex":0.0002876096,"about_ca_system_score_gemma":0.008231035,"threshold_uncertainty_score":0.99835193},"labels":[],"label_agreement":null},{"id":"W1787889380","doi":"10.47678/cjhe.v35i1.183494","title":"Liberal Arts vs. Applied Programming: The Evolution of University Programs in Manitoba","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Higher Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Liberal arts education; Politics; Power (physics); Period (music); Perception; Sociology; Public administration; Public relations; Political science; Marketing; Higher education; Psychology; Law; Business; Aesthetics","score_opus":0.11774632363215562,"score_gpt":0.37217211618093116,"score_spread":0.2544257925487755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1787889380","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9795422,0.0003523758,0.000080892445,0.010170921,0.00083067484,0.00025837735,0.0000010274583,0.0000026009584,0.008760953],"genre_scores_gemma":[0.99547046,0.000002981176,0.0009606541,0.00019535904,0.00022211114,0.0000020082202,0.0000019840004,0.000003214362,0.0031412248],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9987996,0.00010892244,0.00039188276,0.000091159476,0.00045856205,0.00014983142],"domain_scores_gemma":[0.9987833,0.00006972804,0.00038003622,0.00016652222,0.00043242567,0.00016799623],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017093016,0.000057860336,0.00011159822,0.00043142046,0.00009204623,0.000078479876,0.0003571208,0.000040194376,0.00034699036],"category_scores_gemma":[0.000046736222,0.000040984534,0.000049171467,0.00066603674,0.00007511171,0.00033760583,0.000006626681,0.0001348237,0.000027764248],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000683928,0.00020658747,0.5980177,0.000006390968,0.000016296759,0.0000021991389,0.0037949968,0.0007669869,0.00004664486,0.025465203,0.030053278,0.34155533],"study_design_scores_gemma":[0.00018343964,0.000048130853,0.54229856,0.000017262586,0.00000827067,0.0000064609785,0.0047851717,0.000038689028,0.000016008476,0.0015494756,0.4510062,0.000042337928],"about_ca_topic_score_codex":0.001951115,"about_ca_topic_score_gemma":0.08135367,"teacher_disagreement_score":0.42095292,"about_ca_system_score_codex":0.00076136447,"about_ca_system_score_gemma":0.0038587064,"threshold_uncertainty_score":0.93540925},"labels":[],"label_agreement":null},{"id":"W1788049718","doi":"10.3138/cjpe.29.3.54","title":"The Development and Initial Validation of Competencies and Descriptors for Canadian Evaluation Practice","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Barrie Urology Group","funders":"","keywords":"Psychology; Medical education; Computer science; Medicine","score_opus":0.5926820838299982,"score_gpt":0.5503943550828988,"score_spread":0.04228772874709941,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1788049718","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9862911,0.0016056435,0.0012469358,0.0053730947,0.0010938843,0.0022840668,0.00000968877,0.0000034212815,0.0020921328],"genre_scores_gemma":[0.98571754,0.000010032862,0.01393009,0.00010065897,0.00008656414,0.000105298685,0.000017341807,0.0000060821258,0.00002642177],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960951,0.0007106824,0.0008716945,0.00014506684,0.001962329,0.00021510724],"domain_scores_gemma":[0.9881629,0.00075801386,0.0007788375,0.00014221482,0.009561853,0.00059620524],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.043922786,0.00009438348,0.00016143298,0.00047238704,0.00046316636,0.00045581744,0.00020094367,0.00006044584,0.000047098176],"category_scores_gemma":[0.017467503,0.00006588786,0.00003310546,0.00034691958,0.00014335405,0.0008496452,0.000009427393,0.000094735915,0.000002942593],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004115309,0.000012399821,0.008434552,0.00000444604,0.000035249806,4.427167e-7,0.0071563576,0.00071321963,0.00001227822,0.0008879027,0.0013649943,0.981337],"study_design_scores_gemma":[0.0048334277,0.0017911079,0.08849833,0.00011697696,0.00057934894,0.00013483148,0.059203394,0.16749951,0.0015812024,0.028413692,0.646953,0.0003952071],"about_ca_topic_score_codex":0.007592434,"about_ca_topic_score_gemma":0.4071365,"teacher_disagreement_score":0.9809418,"about_ca_system_score_codex":0.0005907952,"about_ca_system_score_gemma":0.020310659,"threshold_uncertainty_score":0.9990161},"labels":[],"label_agreement":null},{"id":"W1790388803","doi":"","title":"Hurteau, M., Houle, S., & Guillemette, F. (Éds.). (2012). L’évaluation de programme axée sur le jugement crédible. Québec, QC : Presses de l’Université du Québec, 200 pages","year":2013,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Valuation (finance); Physics; Mathematical physics; Economics; Accounting","score_opus":0.1689980442060935,"score_gpt":0.37409090493899916,"score_spread":0.20509286073290567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1790388803","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47207505,0.087820746,0.007484293,0.41453037,0.0035851959,0.007878604,0.000055392647,0.000091246475,0.0064791045],"genre_scores_gemma":[0.95783883,0.006004789,0.021629116,0.0017182367,0.0015310268,0.0008027789,0.00012416553,0.00010763032,0.010243394],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98992383,0.002487754,0.0020111345,0.00060402375,0.0034696707,0.0015035537],"domain_scores_gemma":[0.98649275,0.00070499926,0.001846507,0.0007236135,0.008361166,0.001870952],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.021179644,0.0005247872,0.0006672081,0.0012862678,0.00095733826,0.0017269647,0.0013288384,0.00037506653,0.055036884],"category_scores_gemma":[0.0051271995,0.00049734133,0.00043833334,0.0013812704,0.00044240215,0.0035522599,0.00008228754,0.0006726572,0.0008443813],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000024093679,0.00028487114,0.042855494,0.000040639276,0.00015822191,0.000017057355,0.0034033624,0.0056147673,0.000110896624,0.00008667276,0.3471255,0.60027844],"study_design_scores_gemma":[0.0026356718,0.001028281,0.2212999,0.00027319018,0.0006328621,0.00014744021,0.003909115,0.10579574,0.00019855332,0.003337642,0.6602398,0.00050181756],"about_ca_topic_score_codex":0.6276516,"about_ca_topic_score_gemma":0.8590168,"teacher_disagreement_score":0.5997766,"about_ca_system_score_codex":0.004555434,"about_ca_system_score_gemma":0.081709966,"threshold_uncertainty_score":0.9999336},"labels":[],"label_agreement":null},{"id":"W1791293590","doi":"10.33524/cjar.v12i1.6","title":"Action Research: A Cross-Country Checkup","year":2011,"lang":"en","type":"article","venue":"The Canadian Journal of Action Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Nipissing University","funders":"","keywords":"Annals; Thriving; Action research; Action (physics); Resource (disambiguation); Sociology; Bridge (graph theory); Public relations; Publishing; Political science; Media studies; Social science; Pedagogy; History; Law; Medicine; Computer science","score_opus":0.9437347599344647,"score_gpt":0.7142029446563354,"score_spread":0.22953181527812927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1791293590","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91207516,0.0001595052,0.000113245194,0.0071880217,0.0014634356,0.00026243957,0.0000073028505,0.0000056866384,0.07872518],"genre_scores_gemma":[0.98845714,0.00007919267,0.000100792065,0.0001547801,0.0005291016,0.000008200065,7.790561e-7,0.00001049454,0.010659537],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99110544,0.002050452,0.00068624504,0.0002051158,0.0052866912,0.0006660782],"domain_scores_gemma":[0.99022377,0.0012191975,0.00027505826,0.00058189937,0.0070111635,0.000688917],"candidate_categories":["metaresearch","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.07262261,0.00008542822,0.0001614991,0.0019878976,0.0022192094,0.0011126377,0.00143239,0.0001207881,0.012928764],"category_scores_gemma":[0.0057340153,0.0000514505,0.00009702622,0.002504008,0.00088225416,0.0011424589,0.00005412082,0.0019175527,0.0013165552],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013286727,0.00022625228,0.17054915,0.000035035027,0.00019727639,0.00023385364,0.030170178,0.00063342805,0.004566196,0.024937667,0.4946929,0.2724294],"study_design_scores_gemma":[0.0005858525,0.0005681595,0.39215773,0.00004298261,0.0000072024063,0.0002330064,0.01625796,0.00085234386,0.004934223,0.045430858,0.5387994,0.00013024724],"about_ca_topic_score_codex":0.026238509,"about_ca_topic_score_gemma":0.22170518,"teacher_disagreement_score":0.27229914,"about_ca_system_score_codex":0.00085554115,"about_ca_system_score_gemma":0.0074774963,"threshold_uncertainty_score":0.9999243},"labels":[],"label_agreement":null},{"id":"W1793639688","doi":"","title":"Ryan, K. E., & Cousins, J. B. (Eds.). (2009). The Sage International Handbook of Educational Evaluation. Thousand Oaks, CA: Sage. 608 pages.","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"SAGE; Sociology; Library science; Psychology; Computer science; Physics","score_opus":0.17227601125528205,"score_gpt":0.4771476743022029,"score_spread":0.3048716630469208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1793639688","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6144475,0.1830024,0.011026323,0.09187676,0.037118714,0.012893677,0.00048461684,0.000048335707,0.049101707],"genre_scores_gemma":[0.993535,0.00048616,0.0023455983,0.0004819902,0.0012168309,0.00017378008,0.00009714338,0.00002042855,0.0016430626],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99111825,0.0012243993,0.0015784326,0.00024981247,0.005367028,0.00046205497],"domain_scores_gemma":[0.9908458,0.0008743944,0.0016150181,0.00050556933,0.0056011765,0.0005580491],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03157545,0.00021684314,0.00032981628,0.0007672578,0.00042554436,0.0004175744,0.00095404516,0.0001257134,0.022507554],"category_scores_gemma":[0.00589625,0.00014843294,0.00022628355,0.00083536387,0.000272102,0.0013548046,0.00003523854,0.00033658926,0.00019126572],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029242248,0.00018260108,0.0540803,0.0000058830924,0.00011687984,7.7720233e-7,0.0020447136,0.0031432167,0.000115776704,0.00042445862,0.059175927,0.8806802],"study_design_scores_gemma":[0.0026160027,0.0003349482,0.32395357,0.0002746121,0.0005413828,0.0001466403,0.0019866019,0.06330124,0.00044371394,0.010107063,0.5959004,0.00039379217],"about_ca_topic_score_codex":0.00041649738,"about_ca_topic_score_gemma":0.008238757,"teacher_disagreement_score":0.88028646,"about_ca_system_score_codex":0.00071957475,"about_ca_system_score_gemma":0.009908886,"threshold_uncertainty_score":0.99719685},"labels":[],"label_agreement":null},{"id":"W1825190017","doi":"","title":"What Do We Measure? Methodological Versus Institutional Validity in Student Surveys","year":2011,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Operationalization; Construct (python library); Construct validity; Psychology; Argumentative; Conformity; Argument (complex analysis); Social psychology; Applied psychology; Political science; Computer science; Psychometrics; Epistemology; Law","score_opus":0.6585648230742892,"score_gpt":0.5432329866595138,"score_spread":0.1153318364147754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1825190017","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91265655,0.0058829137,0.06882428,0.0023443864,0.004827364,0.00026747413,0.0000020197697,0.000028107912,0.0051668915],"genre_scores_gemma":[0.9861024,0.012395475,0.00075653003,0.00006204004,0.00023381053,0.000010063897,0.0000012845769,0.0000065449826,0.00043186854],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98964787,0.004790762,0.0008826545,0.0004069727,0.0027842831,0.0014874617],"domain_scores_gemma":[0.99762446,0.0011653692,0.00031676397,0.00031337148,0.00043817336,0.00014183873],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.10790162,0.00017412062,0.0003233521,0.0003492555,0.00028229502,0.00035753244,0.00093787344,0.00011638757,0.0018237516],"category_scores_gemma":[0.0020870944,0.000116892006,0.0001683399,0.0006676207,0.0001135851,0.0014099799,0.00011408746,0.0016686559,0.00034621506],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00052686594,0.00040602978,0.12095602,0.0000014869624,0.0001132256,0.000018186003,0.0023444078,0.00046577927,0.00007496407,0.19401051,0.000093363196,0.68098915],"study_design_scores_gemma":[0.0034805252,0.0010653143,0.3216065,0.000047595568,0.000027870008,0.0001790694,0.018507116,0.0003012916,0.00014038639,0.6477597,0.006553695,0.00033098148],"about_ca_topic_score_codex":0.000035016208,"about_ca_topic_score_gemma":0.0028121644,"teacher_disagreement_score":0.68065816,"about_ca_system_score_codex":0.0012039003,"about_ca_system_score_gemma":0.0038835772,"threshold_uncertainty_score":0.9990887},"labels":[],"label_agreement":null},{"id":"W1825391705","doi":"10.33524/cjar.v12i3.19","title":"PROBLEM BASED INSTRUCTION: GETTING AT THE BIG IDEAS AND DEVELOPING LEARNERS","year":2012,"lang":"en","type":"article","venue":"The Canadian Journal of Action Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Action research; Mathematics education; Team teaching; Conjunction (astronomy); Pedagogy; Process (computing); Action (physics); Action learning; Psychology; Teaching method; Computer science; Cooperative learning","score_opus":0.5869474003487628,"score_gpt":0.5572754393011009,"score_spread":0.0296719610476619,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1825391705","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93001807,0.00034490952,0.0003214816,0.06338271,0.00065012823,0.0001470323,0.0000010021323,0.00000231004,0.0051323706],"genre_scores_gemma":[0.99693274,0.000028842716,0.00040261028,0.00047302432,0.00038924193,0.0000037365191,3.36197e-7,0.000005151056,0.0017643245],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965603,0.00093787163,0.0003736149,0.00008668196,0.0016897296,0.00035184392],"domain_scores_gemma":[0.99727356,0.0010168245,0.00022743124,0.00019984189,0.00095093093,0.0003314179],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.027244572,0.000057360114,0.000089990055,0.00048614552,0.0020015985,0.00042983063,0.00038283257,0.000041261235,0.00086518214],"category_scores_gemma":[0.0013953068,0.00002814785,0.000040101808,0.0008423486,0.00030723607,0.00042140073,0.00003756927,0.0005532055,0.000087060725],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008912468,0.000009392169,0.22683738,0.000014204346,0.000043147833,0.0000053671133,0.006378449,0.002172771,0.00047470193,0.0053864922,0.02883729,0.7297517],"study_design_scores_gemma":[0.00061665673,0.0001055436,0.21778937,0.000060174778,0.00001138805,0.00038666188,0.016654346,0.0019955335,0.0014625401,0.0062541524,0.75453347,0.00013016946],"about_ca_topic_score_codex":0.0023582168,"about_ca_topic_score_gemma":0.062489007,"teacher_disagreement_score":0.7296215,"about_ca_system_score_codex":0.00055422576,"about_ca_system_score_gemma":0.0032435805,"threshold_uncertainty_score":0.9992977},"labels":[],"label_agreement":null},{"id":"W1826075361","doi":"10.3138/cjpe.22.007","title":"Participatory Impact Pathways Analysis: A Practical Application of Program Theory in Research-for-Development","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":104,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Logic model; Citizen journalism; Food security; Computer science; Poverty; Narrative; Theory of change; Management science; Knowledge management; Process management; Sociology; Business; Engineering; Economics; Economic growth; Social science","score_opus":0.815960147008348,"score_gpt":0.6979548155552535,"score_spread":0.11800533145309444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1826075361","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9548617,0.00028468316,0.040286914,0.0005058593,0.00014225913,0.0031305542,0.0000060289094,0.000008852585,0.0007731308],"genre_scores_gemma":[0.9805804,0.0000029744892,0.018841403,0.000027651962,0.00007662437,0.00042455996,0.000021885586,0.000008829913,0.000015682926],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9926903,0.0013819669,0.0018437118,0.0002733814,0.0032567354,0.00055385137],"domain_scores_gemma":[0.99094075,0.0015363888,0.0009826467,0.00035973958,0.0056157066,0.0005647854],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.14730027,0.00012232988,0.00036439567,0.002815181,0.00017612746,0.0001823291,0.00038743071,0.00011985639,0.0003676154],"category_scores_gemma":[0.0082124,0.000091870876,0.00021804847,0.0034948168,0.00018922101,0.0004923323,0.000015227959,0.00032723122,0.000017776945],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000138129,0.00025186082,0.108076945,0.0000073473884,0.00011302966,0.0000035010542,0.0029257624,0.002346568,0.000077492434,0.0024206298,0.00019387911,0.88344485],"study_design_scores_gemma":[0.001252024,0.0013600072,0.8425184,0.000046928628,0.0002727489,0.000009805493,0.0048161433,0.10636667,0.00062225,0.02439897,0.018159667,0.00017637067],"about_ca_topic_score_codex":0.0002999508,"about_ca_topic_score_gemma":0.035373718,"teacher_disagreement_score":0.8832685,"about_ca_system_score_codex":0.0009958664,"about_ca_system_score_gemma":0.010924259,"threshold_uncertainty_score":0.9946829},"labels":[],"label_agreement":null},{"id":"W1827185674","doi":"10.7202/001547ar","title":"Approches qualitative et quantitative en évaluation de programmes","year":2002,"lang":"fr","type":"article","venue":"Sociologie et sociétés","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Valuation (finance); Humanities; Philosophy; Economics","score_opus":0.8651647523844471,"score_gpt":0.7170385777255025,"score_spread":0.14812617465894462,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1827185674","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2901098,0.024253413,0.064421706,0.49779972,0.006251808,0.0024512033,0.00020447983,0.0004226592,0.11408518],"genre_scores_gemma":[0.86467046,0.008799579,0.09049448,0.0051428406,0.00021716075,0.00041988006,0.00008796805,0.000042255353,0.030125389],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9819146,0.013858704,0.0010077202,0.00077464525,0.0016480698,0.0007962696],"domain_scores_gemma":[0.9797713,0.018218352,0.0006220882,0.00043869266,0.0007814761,0.00016809643],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.035137646,0.00039430335,0.00061817555,0.00016937283,0.00044810033,0.0003699388,0.0006779901,0.00060683093,0.016032051],"category_scores_gemma":[0.015129303,0.00033284625,0.0003984353,0.0006342147,0.0011079258,0.0011891534,0.00019057628,0.0009222562,0.002721676],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030729283,0.00045635644,0.0021724037,0.00004436688,0.0001871818,0.0000038554167,0.52971166,0.00089845946,0.00014708578,0.22589257,0.022083575,0.21837175],"study_design_scores_gemma":[0.001002726,0.0007744747,0.006246363,0.000080933314,0.000077398916,0.000004078268,0.4552217,0.03421515,0.0001732557,0.4814872,0.020233482,0.0004832001],"about_ca_topic_score_codex":0.00009175512,"about_ca_topic_score_gemma":0.00004194531,"teacher_disagreement_score":0.57456064,"about_ca_system_score_codex":0.0005296955,"about_ca_system_score_gemma":0.00097430375,"threshold_uncertainty_score":0.9999124},"labels":[],"label_agreement":null},{"id":"W1828725948","doi":"10.18438/b8f32k","title":"Call for Studies on Quality Improvement for Inclusion in Systematic Review","year":2010,"lang":"en","type":"article","venue":"Evidence Based Library and Information Practice","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Inclusion (mineral); Computer science; Quality (philosophy); Data science; Psychology; Epistemology","score_opus":0.17937228853144896,"score_gpt":0.5163316952823939,"score_spread":0.33695940675094493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1828725948","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032151207,0.013658076,0.026375605,0.89496726,0.0030142409,0.024776198,0.00015949529,0.00020227369,0.004695624],"genre_scores_gemma":[0.3452598,0.013001995,0.023664277,0.61298746,0.00015524376,0.0038830352,0.00010728082,0.000017386077,0.0009235323],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99650824,0.00041622698,0.0017111864,0.00020816243,0.0010110501,0.00014515588],"domain_scores_gemma":[0.97630787,0.021419255,0.0012996503,0.00044575386,0.00045370968,0.000073766125],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.02082291,0.00013169227,0.00039354002,0.00023385085,0.00033398072,0.0003249713,0.00036217552,0.00005890905,0.0000858759],"category_scores_gemma":[0.0677953,0.00008625349,0.00007471552,0.00040817738,0.000035612647,0.08085435,0.0002725281,0.00016966135,0.000035847486],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002298656,0.00035394568,0.0005564411,0.24499717,0.00007711956,7.6471184e-7,0.003792659,0.0006715626,0.00059781224,0.6631367,0.025779597,0.057737567],"study_design_scores_gemma":[0.0056720083,0.0040155617,0.0034717238,0.1268689,0.0004524823,0.000011143451,0.011244055,0.13585268,0.009319082,0.02392887,0.67781955,0.0013439371],"about_ca_topic_score_codex":0.0000015663765,"about_ca_topic_score_gemma":9.800223e-7,"teacher_disagreement_score":0.65203995,"about_ca_system_score_codex":0.000020255087,"about_ca_system_score_gemma":0.0002658196,"threshold_uncertainty_score":0.94005704},"labels":[],"label_agreement":null},{"id":"W183054821","doi":"10.1007/978-94-007-6555-9_51","title":"Leadership for Social Justice Throughout Fifteen Years of Intervention in a Disadvantaged and Multicultural Canadian Urban Area: The Supporting Montréal Schools Program","year":2013,"lang":"en","type":"book-chapter","venue":"Springer international handbooks of education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Disadvantaged; Social justice; Intervention (counseling); Multiculturalism; Sociology; Pedagogy; Geography; Criminology; Political science; Medicine; Nursing; Law","score_opus":0.19660041132206912,"score_gpt":0.47140876964903655,"score_spread":0.27480835832696743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W183054821","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69634867,0.0045768484,0.00095524616,0.027642956,0.011283573,0.013961062,0.0009767428,0.00009012432,0.24416476],"genre_scores_gemma":[0.9419275,0.000033468397,0.0011536998,0.00012980928,0.00030809376,0.00019641542,0.00015307762,0.000016588452,0.056081347],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9979124,0.000035713332,0.0008854227,0.00028745746,0.0007113335,0.00016766928],"domain_scores_gemma":[0.9977835,0.00028374486,0.00088102126,0.00017219348,0.0008160454,0.00006349078],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012551901,0.00015405173,0.00025771695,0.0003499111,0.00009283793,0.00014066193,0.00039174885,0.00013131525,0.0003285577],"category_scores_gemma":[0.0006434918,0.000119775745,0.00015886583,0.00004582453,0.000121603276,0.00031539082,0.00005474965,0.00022656251,0.000013391371],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017743396,0.00026305811,0.0119918985,0.00025636004,0.0002393255,7.52739e-7,0.016338546,0.00006311313,0.00026019497,0.0631742,0.017942475,0.88929266],"study_design_scores_gemma":[0.004978706,0.0007442993,0.43067452,0.0036572178,0.0007139443,0.000015425841,0.07037031,0.014550223,0.0008958028,0.07026568,0.40164283,0.001491039],"about_ca_topic_score_codex":0.0051623257,"about_ca_topic_score_gemma":0.02331877,"teacher_disagreement_score":0.8878016,"about_ca_system_score_codex":0.00021864164,"about_ca_system_score_gemma":0.00042909253,"threshold_uncertainty_score":0.99450314},"labels":[],"label_agreement":null},{"id":"W1830586542","doi":"","title":"Municipal newcomer assistance in Lloydminster: evaluating policy networks in immigration settlement services","year":2015,"lang":"en","type":"dissertation","venue":"Memorial University Research Repository (Memorial University)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Immigration; General partnership; Community cohesion; Settlement (finance); Business; Government (linguistics); Cohesion (chemistry); Service delivery framework; Public relations; Service (business); Political science; Local government; Service provider; Public administration; Economic growth; Marketing; Economics; Finance","score_opus":0.1492537087259517,"score_gpt":0.4599010718303257,"score_spread":0.310647363104374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1830586542","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88849705,0.00010461126,0.000022656677,0.00029609734,0.008315852,0.0013068131,0.000050512695,0.0000555461,0.10135087],"genre_scores_gemma":[0.8771547,0.00025460182,0.00017023743,0.000028982911,0.004307107,0.000004191198,0.0008066727,0.000052064217,0.11722146],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.98473364,0.0052060555,0.0011572386,0.0015716517,0.006208724,0.0011226891],"domain_scores_gemma":[0.9934032,0.0011756374,0.0008882721,0.0012625864,0.0027838347,0.00048649387],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.012682455,0.0005416325,0.0009817473,0.006358711,0.0009848964,0.0006888395,0.0030627418,0.0008511997,0.00020862692],"category_scores_gemma":[0.0007570513,0.00060375757,0.0002932472,0.0077931834,0.00022123955,0.0020511833,0.0006378569,0.0019299361,0.000110991205],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.13617924,0.0066532916,0.21740283,0.0016212413,0.0013995141,0.01293438,0.18469058,0.21573661,0.015284488,0.048177943,0.036584463,0.12333543],"study_design_scores_gemma":[0.025197212,0.0023515273,0.06022701,0.001746563,0.00028776962,0.000016503609,0.31773582,0.1629354,0.00073440315,0.0029840863,0.42287925,0.0029044496],"about_ca_topic_score_codex":0.02211312,"about_ca_topic_score_gemma":0.11150943,"teacher_disagreement_score":0.38629478,"about_ca_system_score_codex":0.005816334,"about_ca_system_score_gemma":0.005136349,"threshold_uncertainty_score":0.99964136},"labels":[],"label_agreement":null},{"id":"W1836020270","doi":"","title":"ARTICLE 2: PREPARING, GOVERNING AND MANAGING THE PARIS DECLARATION EVALUATION","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Credibility; Declaration; Stakeholder; Corporate governance; Joint (building); Process management; Stakeholder engagement; Quality (philosophy); Business; Public relations; Political science; Environmental resource management; Economics; Engineering; Law","score_opus":0.37383956162570414,"score_gpt":0.523925339424259,"score_spread":0.15008577779855486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1836020270","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9816403,0.002954805,0.002702538,0.0027334772,0.0008498379,0.0012370948,0.0000016613578,0.000008599047,0.0078716865],"genre_scores_gemma":[0.9979579,0.000023469822,0.0013896888,0.00018977717,0.00027808695,0.00007551455,0.0000056170147,0.0000073317137,0.00007264747],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9952787,0.0009671743,0.0007137076,0.00014493917,0.002592792,0.00030265373],"domain_scores_gemma":[0.99660724,0.00030143035,0.0006954179,0.00025706412,0.0017794608,0.00035935774],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.041642934,0.00009948691,0.00014082073,0.00027007758,0.0004478223,0.00059737393,0.00023781904,0.00005624954,0.0010165852],"category_scores_gemma":[0.003279526,0.000065880115,0.00006426364,0.0005004323,0.00007899624,0.0015418342,0.000018141269,0.00018588455,0.00006764111],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007970233,0.000018430328,0.16390926,0.00000192744,0.000019580999,1.902686e-7,0.003282625,0.0032336623,0.00004474957,0.0005212721,0.0025350095,0.8264253],"study_design_scores_gemma":[0.0006677435,0.00014458122,0.47867575,0.000028577144,0.00020288472,0.00004751246,0.0030779617,0.46066055,0.00012527968,0.0061088777,0.050145406,0.0001148701],"about_ca_topic_score_codex":0.00034012715,"about_ca_topic_score_gemma":0.0060267798,"teacher_disagreement_score":0.82631046,"about_ca_system_score_codex":0.00039386845,"about_ca_system_score_gemma":0.0015011667,"threshold_uncertainty_score":0.99989665},"labels":[],"label_agreement":null},{"id":"W183745815","doi":"10.3138/cjpe.0023.006","title":"Participatory Evaluation as Seen in a Vygotskian Framework","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Interview; Categorization; Psychology; Citizen journalism; Participatory evaluation; Coding (social sciences); Medical education; Pedagogy; Applied psychology; Computer science; Sociology; Medicine","score_opus":0.567309139198488,"score_gpt":0.6135182252392328,"score_spread":0.04620908604074481,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W183745815","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98064154,0.0010619703,0.00074058975,0.0067750886,0.000910466,0.0017283844,0.0000024626393,0.000011109141,0.00812837],"genre_scores_gemma":[0.9962595,0.000011949873,0.002459546,0.00087833713,0.00022512724,0.00008479621,0.000008511976,0.000008121076,0.000064111664],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99231434,0.0014341546,0.0013707739,0.00023930949,0.004220153,0.00042128933],"domain_scores_gemma":[0.99456525,0.0003168487,0.00076892227,0.00040067165,0.0033420997,0.00060622324],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03944305,0.0001545448,0.0003007496,0.0012349257,0.0001671258,0.00031889966,0.0005173829,0.00015742551,0.005436751],"category_scores_gemma":[0.011244202,0.00012830428,0.00013577926,0.0015009101,0.00006840915,0.0009091181,0.000007062291,0.00038906327,0.00025491684],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022870781,0.00007222243,0.03246291,0.0000012477026,0.000010539889,0.000007907454,0.003546256,0.006475137,0.00002096871,0.0011755988,0.001393458,0.95481086],"study_design_scores_gemma":[0.0015420789,0.001137351,0.5932045,0.00014619582,0.000120380464,0.00003928577,0.0030038788,0.13650517,0.00009208657,0.24665907,0.01731039,0.00023963314],"about_ca_topic_score_codex":0.00035700144,"about_ca_topic_score_gemma":0.011639098,"teacher_disagreement_score":0.95457125,"about_ca_system_score_codex":0.0009145058,"about_ca_system_score_gemma":0.009518293,"threshold_uncertainty_score":0.9970845},"labels":[],"label_agreement":null},{"id":"W1841398597","doi":"10.4212/cjhp.v61i1.16","title":"What’s a Nice Pharmacist like You Doing on the CBC?","year":2008,"lang":"en","type":"article","venue":"The Canadian Journal of Hospital Pharmacy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Public relations; Pharmacist; Economic shortage; Political science; Nice; Public administration; Pharmacy; Law","score_opus":0.22535806957101123,"score_gpt":0.44942676582361013,"score_spread":0.2240686962525989,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1841398597","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8895139,0.0012728974,0.000035963156,0.09292604,0.007053427,0.0002438544,0.0000089990235,0.000006539297,0.0089383805],"genre_scores_gemma":[0.9879847,0.00045607597,0.000038331476,0.008415003,0.00060976495,0.000004736665,5.6619183e-7,0.000013080876,0.0024777167],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99667406,0.00037495454,0.00071105466,0.0001712644,0.0016970949,0.00037159197],"domain_scores_gemma":[0.99706715,0.00075674005,0.000556025,0.00041252378,0.0006903306,0.00051719777],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.004508173,0.00016428009,0.00021041319,0.00025604403,0.0012897542,0.00075546786,0.0016594416,0.000022551403,0.0034021013],"category_scores_gemma":[0.00043124403,0.00007910469,0.00021840968,0.00059097,0.00032125408,0.0012988746,0.000035023553,0.0006271267,0.00087469025],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019187051,0.00016068669,0.044768773,0.0000044979547,0.00023891077,0.00064490497,0.027486121,0.0030961237,0.00019155465,0.0022200535,0.84358895,0.07740754],"study_design_scores_gemma":[0.0011957563,0.0002880813,0.0054873517,0.000046021967,0.000039266462,0.00035639084,0.004547158,0.0023110784,0.0007553633,0.0014614518,0.9833056,0.00020650233],"about_ca_topic_score_codex":0.001232771,"about_ca_topic_score_gemma":0.00394286,"teacher_disagreement_score":0.13971661,"about_ca_system_score_codex":0.0002018366,"about_ca_system_score_gemma":0.0023795578,"threshold_uncertainty_score":0.99990326},"labels":[],"label_agreement":null},{"id":"W1841863553","doi":"","title":"ARTICLE 3: THE PARIS DECLARATION EVALUATION PROCESS AND METHODS","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Declaration; Process (computing); Engineering ethics; Corporate governance; Process management; Perspective (graphical); Quality (philosophy); Management science; Political science; Computer science; Business; Engineering; Epistemology; Law","score_opus":0.516238008344546,"score_gpt":0.625758530785327,"score_spread":0.10952052244078092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1841863553","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9760802,0.0035279174,0.010005054,0.0049853665,0.0010189075,0.0017768985,0.0000016979623,0.00000797634,0.0025959928],"genre_scores_gemma":[0.99136865,0.0000146022,0.007896553,0.00024603726,0.00027991782,0.00014415226,0.000004889112,0.000007190412,0.000037990438],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9940564,0.0022056885,0.0008073423,0.00014605279,0.0024836692,0.0003008711],"domain_scores_gemma":[0.9943749,0.0004923781,0.0006743093,0.00025561143,0.0037692862,0.000433531],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.072847724,0.00010478913,0.00016566805,0.00032945364,0.00039479168,0.00048388183,0.00026706836,0.00007386537,0.0015690381],"category_scores_gemma":[0.006074889,0.00006401387,0.00006640521,0.00076687796,0.000109657325,0.0014934109,0.000010031554,0.00019566492,0.000040338364],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007804543,0.000026292519,0.079280496,0.0000020509974,0.00001668596,1.2301938e-7,0.0036512702,0.0012312246,0.000076332835,0.00038576583,0.0009201774,0.91440177],"study_design_scores_gemma":[0.0009915075,0.00027056155,0.5219434,0.000024263996,0.00033199647,0.00007108075,0.005697153,0.40985703,0.0010202419,0.027190944,0.032434523,0.00016730605],"about_ca_topic_score_codex":0.00013369304,"about_ca_topic_score_gemma":0.0022768024,"teacher_disagreement_score":0.91423446,"about_ca_system_score_codex":0.00025283385,"about_ca_system_score_gemma":0.0026580233,"threshold_uncertainty_score":0.99934363},"labels":[],"label_agreement":null},{"id":"W1847924206","doi":"10.6017/ihe.2000.21.6896","title":"The Canada Research Chairs Program","year":2015,"lang":"en","type":"article","venue":"International Higher Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Political science; Higher education; Quality (philosophy); Public administration; Regional science; Library science; Economic growth; Sociology; Economics; Computer science; Law","score_opus":0.5635702261382207,"score_gpt":0.6558405463534538,"score_spread":0.09227032021523307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1847924206","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.169203,0.0003673141,0.000028460347,0.22235984,0.02422402,0.0005240298,0.000006358047,0.000042835523,0.58324414],"genre_scores_gemma":[0.8469449,0.000008827261,0.00021035505,0.0005702507,0.0006972729,0.00017256057,0.000016695374,0.0000042494476,0.15137485],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99534035,0.00022011742,0.00031598192,0.00019965092,0.003758691,0.00016522977],"domain_scores_gemma":[0.9957155,0.00061633135,0.0001054412,0.00032406102,0.0031136898,0.00012498954],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0046587577,0.000056034645,0.000050605653,0.00012063893,0.00023232105,0.00044451043,0.0008560999,0.000024973737,0.0010171483],"category_scores_gemma":[0.00089662167,0.000033714812,0.000021687021,0.00047499136,0.00007112253,0.00026120068,0.00007551741,0.00014367311,0.0004921591],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014459213,0.00008797708,0.012488395,2.992036e-7,0.000007820718,2.4275792e-7,0.00019836874,0.000089640984,0.000004128947,0.06591941,0.74885696,0.17233229],"study_design_scores_gemma":[0.00008857246,0.000024840576,0.077302344,0.000003419484,7.647955e-7,0.0000014470381,0.00117037,0.00087995146,0.000026219703,0.027001474,0.8934604,0.00004020276],"about_ca_topic_score_codex":0.059273288,"about_ca_topic_score_gemma":0.14051042,"teacher_disagreement_score":0.67774194,"about_ca_system_score_codex":0.0006073525,"about_ca_system_score_gemma":0.005573161,"threshold_uncertainty_score":0.99989605},"labels":[],"label_agreement":null},{"id":"W1861458450","doi":"10.33524/cjar.v15i2.136","title":"A NEW PATRON FOR THE AR","year":2015,"lang":"en","type":"article","venue":"The Canadian Journal of Action Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Nipissing University","funders":"","keywords":"Passion; Determinacy; Disadvantaged; Action (physics); Intervention (counseling); Solitude; Sociology; Public relations; Political science; Psychology; Social psychology; Mathematics; Law","score_opus":0.9042495585883354,"score_gpt":0.6899941629999163,"score_spread":0.2142553955884191,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1861458450","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21925516,0.0020103152,0.023018043,0.7154312,0.008200592,0.0014648688,0.000013978232,0.000008385195,0.030597461],"genre_scores_gemma":[0.9855402,0.000025821626,0.00030761198,0.0003553063,0.0007469795,0.0000034475718,2.818033e-7,0.0000044607395,0.013015862],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968857,0.00044475624,0.000314449,0.00006952549,0.0020434186,0.00024212607],"domain_scores_gemma":[0.99409866,0.0017457585,0.00015629544,0.00028252733,0.0031636292,0.0005531095],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03035005,0.000039542418,0.0000799893,0.00034651352,0.00068807765,0.00052278873,0.00084498065,0.000030944677,0.0011155595],"category_scores_gemma":[0.004930484,0.000017125867,0.00006236203,0.00072033994,0.00010530668,0.00027233333,0.000014999857,0.00039015285,0.00018963295],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009585447,0.0000032133516,0.0016669427,6.316355e-7,0.000016705313,0.0000017532576,0.001659746,0.0016549119,0.0000380748,0.0023058308,0.8443188,0.14823754],"study_design_scores_gemma":[0.000351533,0.00029207583,0.006101356,0.000005413476,0.000005829294,0.000033903496,0.0061349296,0.0026774518,0.00014876448,0.030810697,0.9534104,0.000027665139],"about_ca_topic_score_codex":0.009557457,"about_ca_topic_score_gemma":0.16779055,"teacher_disagreement_score":0.76628506,"about_ca_system_score_codex":0.00031915482,"about_ca_system_score_gemma":0.01200599,"threshold_uncertainty_score":0.9997976},"labels":[{"model":"gemma","categories":["scholarly_communication"],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":true,"about_ca_topic":true,"confidence":"low"},{"model":"gpt","categories":["insufficient_payload"],"domain":null,"study_design":"design_other","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W1865612267","doi":"10.3138/cjpe.30.1.1","title":"From New Public Management to New Political Governance: Implications for Evaluation","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Bureaucracy; Public administration; Politics; Corporate governance; Institution; Context (archaeology); Political science; New public management; Public service; Democracy; Power (physics); Public management; Public relations; Economics; Public sector; Management; Law","score_opus":0.627667754868374,"score_gpt":0.5924472023472562,"score_spread":0.035220552521117776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1865612267","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18555595,0.0021853552,0.30238184,0.44158384,0.007869515,0.017266717,0.00023423941,0.000070453556,0.04285209],"genre_scores_gemma":[0.93203974,0.0000037953996,0.0633811,0.001382278,0.0014645713,0.00032356504,0.0000997988,0.000019446787,0.0012856848],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99456465,0.00037249867,0.0010832986,0.00034431482,0.0031404858,0.000494759],"domain_scores_gemma":[0.9897596,0.00025945337,0.0005947204,0.0005087133,0.0059559653,0.0029215366],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.014781953,0.00015457573,0.0002543003,0.00054295035,0.00016145867,0.00080985395,0.000754682,0.00008871367,0.001650048],"category_scores_gemma":[0.0066520236,0.00013184844,0.00014646031,0.0010284187,0.00003638949,0.0008758787,0.000026275799,0.00012517124,0.00020853517],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020047006,0.000028021597,0.0034565656,0.0000010503942,0.00003488673,3.4297355e-7,0.00070691854,0.0011668552,0.000004201627,0.021812107,0.1639288,0.8088402],"study_design_scores_gemma":[0.003295201,0.00050520484,0.09525937,0.000032869902,0.00023132827,0.000009182207,0.0016343337,0.018589607,0.00002263551,0.43075016,0.4494797,0.00019038767],"about_ca_topic_score_codex":0.0033606188,"about_ca_topic_score_gemma":0.02292435,"teacher_disagreement_score":0.8086498,"about_ca_system_score_codex":0.0019335665,"about_ca_system_score_gemma":0.020745873,"threshold_uncertainty_score":0.9992626},"labels":[],"label_agreement":null},{"id":"W1871704657","doi":"10.33524/cjar.v15i2.141","title":"1s Annual Conference of The Canadian Association of Action Research in Education","year":2015,"lang":"en","type":"article","venue":"The Canadian Journal of Action Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Action research; Association (psychology); Action (physics); Political science; Library science; Work (physics); Canadian studies; Sociology; Media studies; Pedagogy; Psychology; Engineering","score_opus":0.8111364368777915,"score_gpt":0.6529326709212719,"score_spread":0.15820376595651953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1871704657","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9366029,0.000077393095,0.0000082538345,0.047510274,0.0011942836,0.00031739913,0.000018463015,8.7414935e-7,0.014270181],"genre_scores_gemma":[0.9952283,0.000033060856,0.000027785976,0.00007542693,0.00017355841,0.0000067020333,0.0000014507058,0.000005148177,0.0044485596],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9904511,0.003587658,0.0007196815,0.0001320879,0.0046948674,0.00041463706],"domain_scores_gemma":[0.9817885,0.0011082292,0.000559097,0.0003958267,0.015606379,0.000541962],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06166706,0.000063214786,0.00017473857,0.0021964214,0.0005892768,0.00028264587,0.0010379028,0.00013334332,0.00052253716],"category_scores_gemma":[0.009607519,0.00003898666,0.00006400376,0.0028697832,0.0003161797,0.00067437656,0.000034495937,0.0012037726,0.00005284571],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00023014763,0.00014860737,0.51658183,0.000029833926,0.000061308936,0.0000047937883,0.035220556,0.0033307169,0.0012768811,0.008252956,0.28817177,0.1466906],"study_design_scores_gemma":[0.0007444713,0.0004050358,0.68619245,0.00017399188,0.000010518302,0.000030046427,0.09374554,0.0017542714,0.0036096224,0.032847334,0.18037565,0.00011105035],"about_ca_topic_score_codex":0.6424665,"about_ca_topic_score_gemma":0.990193,"teacher_disagreement_score":0.34772652,"about_ca_system_score_codex":0.004339347,"about_ca_system_score_gemma":0.062145285,"threshold_uncertainty_score":0.9994828},"labels":[],"label_agreement":null},{"id":"W1873333392","doi":"10.56645/jmde.v4i8.30","title":"Culturally Competent Evaluation for Aboriginal Communities: A Review of the Empirical Literature","year":2007,"lang":"en","type":"review","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":56,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Health Canada","keywords":"Multiculturalism; Context (archaeology); Cultural diversity; Cultural competence; Sociology; Psychology; Social psychology; Public relations; Pedagogy; Political science; Anthropology","score_opus":0.6594573931484259,"score_gpt":0.6618411843139824,"score_spread":0.002383791165556537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1873333392","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00036127027,0.9900548,0.00063884037,0.0014445833,0.0021555054,0.004742222,0.000106393345,0.0000054161146,0.0004909953],"genre_scores_gemma":[0.00022092302,0.9957064,0.0025816027,0.00019578991,0.0005950106,0.00019174643,0.0002752665,0.000028616607,0.00020468417],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.97747386,0.0058592986,0.005416411,0.0003497076,0.010596241,0.00030448107],"domain_scores_gemma":[0.9682752,0.0042628543,0.008837668,0.0011082953,0.0173806,0.00013539927],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.08787859,0.0004867588,0.002260601,0.0007389896,0.00041175782,0.00018363832,0.001978773,0.00034709554,0.0007540873],"category_scores_gemma":[0.004595303,0.00023604969,0.002144278,0.0020182198,0.00016422119,0.00075664045,0.00018611042,0.0009844512,0.000021125968],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006665403,0.00023924415,0.00009602359,0.014389375,0.00017291428,7.9186754e-7,0.003222875,0.00040333584,0.000001256136,0.00006472092,0.009323987,0.97201884],"study_design_scores_gemma":[0.0013051105,0.00047671938,0.0008452882,0.15312105,0.003649068,0.00019024081,0.0012434163,0.01675828,0.0000018469145,0.0012702647,0.8208398,0.00029886633],"about_ca_topic_score_codex":0.0000017828313,"about_ca_topic_score_gemma":0.000025194273,"teacher_disagreement_score":0.97172,"about_ca_system_score_codex":0.0009445695,"about_ca_system_score_gemma":0.0063041425,"threshold_uncertainty_score":0.9993292},"labels":[],"label_agreement":null},{"id":"W1873852261","doi":"","title":"Indicateurs et pratique pharmaceutique : Le point de vue des cinq centres hospitaliers universitaires du Québec","year":2010,"lang":"fr","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Centre hospitalier universitaire de Québec; Centre Hospitalier Universitaire de Sherbrooke; Université de Montréal; McGill University Health Centre; Centre Hospitalier Universitaire Sainte-Justine","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.050368301614253395,"score_gpt":0.41204717469200247,"score_spread":0.3616788730777491,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1873852261","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7062531,0.00050466845,0.0038977559,0.22825468,0.0010323048,0.00032627926,0.000018991379,0.000076788434,0.059635453],"genre_scores_gemma":[0.9633297,0.0011819021,0.004579277,0.0049887635,0.000138304,0.000012726954,0.000008494514,0.000021641828,0.025739241],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99674815,0.000700382,0.00055425905,0.0005180089,0.00088597526,0.00059323484],"domain_scores_gemma":[0.99746287,0.0008418066,0.0003027955,0.00044858566,0.00044180037,0.0005021311],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.004262282,0.00029038286,0.0002782428,0.00030185643,0.0005523417,0.0004247937,0.0008258559,0.00025134676,0.030621203],"category_scores_gemma":[0.0008778302,0.000248241,0.00016951613,0.00059931073,0.00092172605,0.0021074165,0.00022730941,0.0007046145,0.00095262687],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008915756,0.0007198843,0.4585786,0.000047534366,0.00013271176,0.0000655949,0.054123793,0.0013322417,0.004174966,0.14154613,0.18064463,0.15854475],"study_design_scores_gemma":[0.001790731,0.00029555577,0.16483705,0.000074644646,0.00007908583,0.000092102426,0.08473576,0.020095149,0.020472368,0.015572672,0.6912828,0.0006720971],"about_ca_topic_score_codex":0.053195696,"about_ca_topic_score_gemma":0.23918414,"teacher_disagreement_score":0.5106382,"about_ca_system_score_codex":0.00033902485,"about_ca_system_score_gemma":0.009021401,"threshold_uncertainty_score":0.99999696},"labels":[],"label_agreement":null},{"id":"W1874375828","doi":"10.3138/cjpe.29.3.x","title":"Introduction à la professionnalisation de l’évaluation au Canada","year":2015,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Humanities; Philosophy","score_opus":0.34891936041679567,"score_gpt":0.5163978479684853,"score_spread":0.16747848755168965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1874375828","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.734942,0.006173278,0.009697753,0.18690994,0.039153397,0.0034245816,0.00004742557,0.00002314898,0.019628445],"genre_scores_gemma":[0.98249763,0.00004134249,0.006850231,0.00041714325,0.005556925,0.000097640615,0.00008428615,0.000025322808,0.004429454],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98772997,0.005431334,0.0015218663,0.0003197183,0.0043769768,0.00062012067],"domain_scores_gemma":[0.98741823,0.00038747114,0.0014057956,0.00036710472,0.008909225,0.0015121835],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06386427,0.00023819236,0.00034473615,0.0006994692,0.00037120303,0.00051808165,0.0004689444,0.00026532417,0.003221341],"category_scores_gemma":[0.012989111,0.00021955774,0.00012448036,0.0012685395,0.00021253226,0.00155405,0.000017262186,0.0005398839,0.0000865591],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000039186838,0.00007093223,0.018632049,0.00001936536,0.00004498381,0.000014209979,0.005593382,0.030164,0.00001849374,0.0018019638,0.13913143,0.80447],"study_design_scores_gemma":[0.0015977576,0.0005725536,0.043932155,0.00019354545,0.00030731063,0.00030027417,0.007910865,0.13707899,0.00012459047,0.010564379,0.79715866,0.00025893335],"about_ca_topic_score_codex":0.7088732,"about_ca_topic_score_gemma":0.98135155,"teacher_disagreement_score":0.8042111,"about_ca_system_score_codex":0.010384981,"about_ca_system_score_gemma":0.2691125,"threshold_uncertainty_score":0.99768984},"labels":[],"label_agreement":null},{"id":"W1876976565","doi":"10.1111/j.1745-3992.2010.00198.x","title":"Reporting the Percentage of Students above a Cut Score: The Effect of Group Size","year":2011,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Mathematics education; Scale (ratio); Statistics; Psychology; Reading (process); Mathematics; Geography; Cartography; Political science","score_opus":0.3899556216284745,"score_gpt":0.5438855402313928,"score_spread":0.15392991860291827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1876976565","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9649192,0.0015737412,0.000058896014,0.014492251,0.0007190075,0.00061666785,0.0000028237985,0.0000044260487,0.01761299],"genre_scores_gemma":[0.9981534,0.0001425018,0.0005780228,0.00034284216,0.00012012136,0.000040174393,0.0000010794581,0.000004540211,0.00061735796],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9940634,0.0011411776,0.0010606196,0.00021245483,0.0034116793,0.00011069735],"domain_scores_gemma":[0.99053085,0.0061100973,0.00207376,0.00043031684,0.0008130316,0.00004193594],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.039537046,0.00009783889,0.0001913273,0.000039678132,0.00021304924,0.000094444236,0.00045509537,0.000023940232,0.0013732683],"category_scores_gemma":[0.033174224,0.000045382443,0.00006488707,0.00021398686,0.00011799181,0.0004297386,0.00008153635,0.00011820608,0.000024733654],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00052025646,0.0005024013,0.95315707,0.000046844423,0.00018360355,6.400788e-7,0.020300506,0.000010992564,0.0019341097,0.004738849,0.006600878,0.0120038595],"study_design_scores_gemma":[0.00031388013,0.00037836705,0.95808226,0.000056254587,0.000118240656,0.0000177112,0.00786855,0.000028603052,0.0018743606,0.0014653207,0.029722976,0.000073499206],"about_ca_topic_score_codex":0.00037005506,"about_ca_topic_score_gemma":0.00005052711,"teacher_disagreement_score":0.033234164,"about_ca_system_score_codex":0.000030480485,"about_ca_system_score_gemma":0.0001512515,"threshold_uncertainty_score":0.9995396},"labels":[],"label_agreement":null},{"id":"W1882622474","doi":"10.14507/epaa.v23.1905","title":"Research and evidence in education decision-making: A comparison of results from two pan-Canadian studies","year":2015,"lang":"en","type":"article","venue":"Education Policy Analysis Archives","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Politics; Research policy; Ranking (information retrieval); Situated; Education policy; Christian ministry; Experiential learning; Political science; Sociology; Professional development; Public relations; Psychology; Public administration; Higher education; Pedagogy","score_opus":0.5941704478135588,"score_gpt":0.6709369743148683,"score_spread":0.07676652650130955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1882622474","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97660327,0.005568376,0.00020957906,0.011157888,0.0002278083,0.00022458505,0.000022092545,0.000005508327,0.0059808814],"genre_scores_gemma":[0.9936359,0.00042583683,0.0048174923,0.00021414066,0.00022570774,0.00002562078,0.000023677097,0.000004999285,0.00062664994],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9954368,0.0010338105,0.0012037171,0.0005510138,0.0015136735,0.00026102384],"domain_scores_gemma":[0.9856019,0.011566003,0.00047974955,0.0008309897,0.0012139424,0.00030740906],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006638242,0.00012283152,0.000450734,0.0059568714,0.0001856761,0.00019403643,0.00056422147,0.00003804691,0.00006069269],"category_scores_gemma":[0.027730357,0.000098854056,0.00007910897,0.005696502,0.00031227624,0.0005082143,0.00013275823,0.00020002094,0.000057467336],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012258811,0.0002458143,0.45174637,0.000004271453,0.00010492179,1.14665774e-7,0.058566228,0.00307852,0.00002287993,0.005101256,0.0055781538,0.47542888],"study_design_scores_gemma":[0.00023952588,0.000073751326,0.66729164,0.00026494634,0.000055058965,3.3147828e-7,0.09565488,0.014079194,0.000047462498,0.2184405,0.003737726,0.00011499565],"about_ca_topic_score_codex":0.08907437,"about_ca_topic_score_gemma":0.24206483,"teacher_disagreement_score":0.47531387,"about_ca_system_score_codex":0.00024165079,"about_ca_system_score_gemma":0.008426493,"threshold_uncertainty_score":0.9971948},"labels":[],"label_agreement":null},{"id":"W18830643","doi":"10.3138/cjpe.026.001","title":"Advancing Empirical Scholarship to Further Develop Evaluation Theory and Practice","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Scholarship; Grounded theory; Context (archaeology); Development theory; Field (mathematics); Empirical research; Contingency; Epistemology; Sociology; Intersection (aeronautics); Contingency theory; Management science; Engineering ethics; Qualitative research; Knowledge management; Computer science; Social science; Political science; Economics","score_opus":0.580695406400756,"score_gpt":0.5966934622915074,"score_spread":0.015998055890751428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W18830643","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95835876,0.0011522237,0.012184186,0.009083507,0.0012170443,0.0024928611,0.0000035847697,0.000016497663,0.015491336],"genre_scores_gemma":[0.9545121,0.000008134364,0.043626048,0.0015564202,0.00013059122,0.00008400523,0.000003412745,0.000012935748,0.00006631498],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99107146,0.004155572,0.00097298826,0.0002907674,0.003171006,0.00033821282],"domain_scores_gemma":[0.98735696,0.0012313337,0.0006682547,0.00029010285,0.009655432,0.00079791533],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12308104,0.00013874995,0.0002115006,0.0008215165,0.00024052465,0.000378912,0.00037496377,0.00009107417,0.0035454333],"category_scores_gemma":[0.07867451,0.00010810104,0.00005783772,0.0011407435,0.00007516366,0.001823277,0.000023330236,0.00026060297,0.0001565621],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000121847406,0.0000388359,0.02729316,0.000001902025,0.000027836692,0.0000045341217,0.011401465,0.00024130885,0.000042896474,0.00065825914,0.0008976988,0.95927024],"study_design_scores_gemma":[0.0018349319,0.0014084749,0.76386946,0.000118944205,0.0003783461,0.00034879465,0.018395618,0.01073665,0.0002738029,0.10190985,0.100315034,0.00041010487],"about_ca_topic_score_codex":0.00011581395,"about_ca_topic_score_gemma":0.0070660547,"teacher_disagreement_score":0.95886016,"about_ca_system_score_codex":0.00053235533,"about_ca_system_score_gemma":0.007967063,"threshold_uncertainty_score":0.9976568},"labels":[],"label_agreement":null},{"id":"W1891559475","doi":"10.56105/cjsae.v22i2.972","title":"Scenario testing in undergraduate nursing education: Assessment for learning","year":2010,"lang":"en","type":"article","venue":"Canadian Journal for the Study of Adult Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Laurentian University","funders":"","keywords":"Adult education; Psychology; Nursing; Pedagogy; Sociology; Medical education; Medicine","score_opus":0.13927348509050647,"score_gpt":0.5063640040421861,"score_spread":0.3670905189516796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1891559475","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9716003,0.00005040084,0.0022918717,0.014653541,0.0067133224,0.0013888117,0.0000029769544,0.00000431563,0.00329447],"genre_scores_gemma":[0.9916435,0.000002888325,0.0058336793,0.00018030682,0.0004694235,0.00015274077,0.0000050362733,0.000011385744,0.0017010692],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9982953,0.00012991835,0.0006449441,0.00019991267,0.00048200446,0.00024793082],"domain_scores_gemma":[0.9954681,0.0012204564,0.000498169,0.00025689806,0.00233227,0.00022411118],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035916618,0.00010255617,0.00015641644,0.0004970303,0.001207185,0.00036205552,0.00046184383,0.00003978039,0.000073807896],"category_scores_gemma":[0.0044124275,0.00007382873,0.00006414432,0.00059030484,0.00006306566,0.00031205517,0.000006020593,0.000401413,0.00000387301],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014819752,0.0004888782,0.304457,0.000007855007,0.000017389171,9.397352e-8,0.010204364,0.002704109,0.00012341164,0.0057687857,0.0057419827,0.6704713],"study_design_scores_gemma":[0.0013746301,0.00084566185,0.6392126,0.00022545137,0.000076973614,0.000047366448,0.23766068,0.027088305,0.000041803916,0.07066128,0.02251732,0.00024793122],"about_ca_topic_score_codex":0.0034791206,"about_ca_topic_score_gemma":0.10212769,"teacher_disagreement_score":0.67022336,"about_ca_system_score_codex":0.0002870173,"about_ca_system_score_gemma":0.013611732,"threshold_uncertainty_score":0.9919802},"labels":[],"label_agreement":null},{"id":"W1891772057","doi":"","title":"ARTICLE 1: THE PARIS DECLARATION ON AID EFFECTIVENESS: HISTORY AND SIGNIFICANCE","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Declaration; Context (archaeology); Relevance (law); Harmonization; Diversity (politics); Accountability; Political science; Public administration; Law; History","score_opus":0.39254754268677033,"score_gpt":0.488255545621587,"score_spread":0.09570800293481668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1891772057","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9902515,0.0025377823,0.0010673284,0.0017073012,0.0010867747,0.00088807615,0.0000012739226,0.000005368167,0.0024545914],"genre_scores_gemma":[0.998901,0.000014391808,0.00042000067,0.00031400053,0.00020267695,0.0000724404,0.0000015739402,0.000005248925,0.00006866972],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99693125,0.0010529518,0.00042907213,0.00011122149,0.0012652951,0.00021021446],"domain_scores_gemma":[0.99756694,0.00061951653,0.00038296782,0.0002001995,0.0009122108,0.00031814855],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021092167,0.0000796532,0.00012635412,0.00021925909,0.00019750936,0.00014956713,0.00018060699,0.00004737729,0.0007947814],"category_scores_gemma":[0.0018440083,0.00004906555,0.000053228163,0.00026448717,0.00010934445,0.00068984414,0.0000054715324,0.00016502124,0.00007163395],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004648256,0.00006220028,0.17700933,0.0000042193083,0.000021276759,8.613512e-7,0.002614927,0.0014084169,0.00028571408,0.0025409418,0.0064761452,0.8095295],"study_design_scores_gemma":[0.000696519,0.00046770694,0.79051197,0.000031236796,0.00006718476,0.000019777453,0.0008100391,0.01853297,0.0004947087,0.003573839,0.18468973,0.00010431328],"about_ca_topic_score_codex":0.00021068435,"about_ca_topic_score_gemma":0.0016761492,"teacher_disagreement_score":0.8094252,"about_ca_system_score_codex":0.000654661,"about_ca_system_score_gemma":0.0016434536,"threshold_uncertainty_score":0.8702299},"labels":[],"label_agreement":null},{"id":"W1894985460","doi":"10.1155/2006/953706","title":"Learning from Mistakes","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Infectious Diseases and Medical Microbiology","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Psychology; Computer science","score_opus":0.029076298048055296,"score_gpt":0.3392408944069485,"score_spread":0.3101645963588932,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1894985460","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99274373,0.0022078676,0.00043036716,0.0018010507,0.0006627686,0.000030009702,0.000025381103,0.0000044296517,0.0020944201],"genre_scores_gemma":[0.99844843,0.000050965336,0.000022752165,0.00085150474,0.00036042606,6.53487e-7,0.0000123137725,0.0000035732996,0.0002493951],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988491,0.00017931082,0.00046434184,0.0001240481,0.00019912797,0.0001840631],"domain_scores_gemma":[0.9983394,0.0004599573,0.00022511251,0.0000743564,0.0002686931,0.0006324903],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00075413287,0.00007338218,0.00021387002,0.0002245724,0.00016266234,0.00008562313,0.00017303573,0.00008979608,0.005342791],"category_scores_gemma":[0.0018432597,0.00004968178,0.00008314784,0.00013205515,0.00021405623,0.00008578462,0.000008072926,0.00020164327,0.00003972614],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012212507,0.000027470756,0.92650586,0.0000022143618,0.000027948296,0.00010507809,0.00014822038,0.00014490879,0.00056512596,0.00070645893,0.016826775,0.054927725],"study_design_scores_gemma":[0.0012752904,0.00039146852,0.44276014,0.000051402512,0.000048253605,0.0005559378,0.0006709139,0.0002761999,0.000042108815,0.0130244335,0.54074323,0.00016059549],"about_ca_topic_score_codex":0.006729723,"about_ca_topic_score_gemma":0.030459013,"teacher_disagreement_score":0.5239165,"about_ca_system_score_codex":0.000057316724,"about_ca_system_score_gemma":0.0015326405,"threshold_uncertainty_score":0.99988455},"labels":[],"label_agreement":null},{"id":"W1895207828","doi":"10.19173/irrodl.v12i1.971","title":"Evaluating prior learning assessment programs: A suggested framework","year":2011,"lang":"en","type":"article","venue":"The International Review of Research in Open and Distributed Learning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Work (physics); Program evaluation; Computer science; Standards-based assessment; Educational assessment; Knowledge management; Management science; Psychology; Mathematics education; Political science; Engineering","score_opus":0.6299882356731104,"score_gpt":0.664118574676885,"score_spread":0.0341303390037746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1895207828","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80691016,0.016057732,0.010864274,0.026603984,0.00059283245,0.0059988825,0.000035301076,0.000077966724,0.13285889],"genre_scores_gemma":[0.98639214,0.0073572136,0.004991455,0.00017973706,0.000035375466,0.0002116685,0.000072899435,0.000009307662,0.00075022184],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9917008,0.002882955,0.0009914234,0.00042040355,0.00367684,0.00032753425],"domain_scores_gemma":[0.9937402,0.0036783894,0.0004897615,0.00037134637,0.0016212739,0.00009905752],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.059318904,0.00012120993,0.00034112175,0.00023785517,0.00037540557,0.00047872067,0.0020598131,0.000054534226,0.0027541127],"category_scores_gemma":[0.020637799,0.0000742163,0.00007080093,0.001370383,0.00021926822,0.00046387225,0.0012409608,0.0012830092,0.00006408199],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012911594,0.00024305382,0.41435975,0.00031185604,0.000048937334,0.000007959631,0.0012168217,0.0002851729,0.00004015695,0.02670828,0.00047340055,0.5561755],"study_design_scores_gemma":[0.0027530747,0.0020092998,0.5568139,0.034942325,0.00005008368,0.00004697702,0.04023181,0.13807464,0.00013925668,0.07377388,0.15058118,0.0005835532],"about_ca_topic_score_codex":0.00024091118,"about_ca_topic_score_gemma":0.0000243231,"teacher_disagreement_score":0.55559194,"about_ca_system_score_codex":0.00013842214,"about_ca_system_score_gemma":0.00056870736,"threshold_uncertainty_score":0.9981575},"labels":[],"label_agreement":null},{"id":"W1898353232","doi":"10.1155/2001/893540","title":"Research Committee: Building on Excellence in 2001","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Gastroenterology","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"Canadian Institutes of Health Research; AstraZeneca","keywords":"Excellence; Political science; Engineering; Law","score_opus":0.29106068546956454,"score_gpt":0.5022200015996576,"score_spread":0.2111593161300931,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1898353232","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9753208,0.000056261386,0.00050481525,0.01770728,0.0005894376,0.00006362388,0.0000021040553,0.000001184482,0.0057544527],"genre_scores_gemma":[0.9973598,0.00004976394,0.00038253528,0.0014121224,0.00014060443,0.0000019399786,2.5973034e-7,0.0000052869805,0.00064765016],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.996669,0.0008995455,0.0006942502,0.00017271732,0.00092400983,0.00064046035],"domain_scores_gemma":[0.99782354,0.0005318846,0.00021847396,0.00027076303,0.0006161754,0.00053918816],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.012241162,0.00007951939,0.0002445213,0.0019625137,0.00014415012,0.00009769182,0.00084838126,0.000057255373,0.0024782186],"category_scores_gemma":[0.0010824691,0.00006285884,0.00006110414,0.000634445,0.0001810733,0.00022023775,0.00002460285,0.00063411606,0.00015424695],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019601668,0.000027419292,0.94709414,6.986797e-7,0.0000053761955,0.00036426276,0.0002473917,0.0019672974,0.00007939079,0.00041072431,0.0436208,0.005986498],"study_design_scores_gemma":[0.001563808,0.0030186553,0.75675905,0.00008580168,0.0000034718807,0.00074175216,0.0017349512,0.0018706332,0.00003638007,0.006460795,0.22764415,0.000080537764],"about_ca_topic_score_codex":0.0013164844,"about_ca_topic_score_gemma":0.11067222,"teacher_disagreement_score":0.19033507,"about_ca_system_score_codex":0.00027978633,"about_ca_system_score_gemma":0.00085076015,"threshold_uncertainty_score":0.99843365},"labels":[],"label_agreement":null},{"id":"W1898948615","doi":"10.18438/b8bc92","title":"Project Output versus Influence in Practice: Impact as a Dimension of Research Quality","year":2011,"lang":"en","type":"article","venue":"Evidence Based Library and Information Practice","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Nature","keywords":"Dimension (graph theory); Quality (philosophy); Computer science; Mathematics; Physics","score_opus":0.40472709101969134,"score_gpt":0.5841443670341144,"score_spread":0.1794172760144231,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1898948615","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.905446,0.00040433678,0.00029817937,0.020662673,0.0002684064,0.0011302582,0.000014451349,0.00006384728,0.071711846],"genre_scores_gemma":[0.98706,0.00087458483,0.0058449483,0.006009979,0.000019357461,0.00004163233,0.000010292708,0.0000052755177,0.00013393977],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99228334,0.0030408562,0.0014170599,0.0002876268,0.002685511,0.00028557554],"domain_scores_gemma":[0.9733225,0.023365278,0.0012038199,0.0006833019,0.0012882532,0.000136813],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.022437515,0.00014499408,0.00023732214,0.0010453997,0.00018008788,0.00046625343,0.00050267123,0.00011268712,0.0007308032],"category_scores_gemma":[0.08609818,0.00010627404,0.0000579637,0.0025598921,0.00019101072,0.31369162,0.00023390325,0.00048768846,0.00032718986],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.12899989,0.0020110838,0.18923248,0.0005670467,0.00017930736,0.000053838587,0.046797346,0.007465642,0.0009057541,0.4640656,0.011993799,0.1477282],"study_design_scores_gemma":[0.0032304195,0.00317344,0.725008,0.00071951427,0.000044153247,0.00003417684,0.037524376,0.0148752965,0.0043729665,0.0015646091,0.20898327,0.00046978594],"about_ca_topic_score_codex":0.00042644632,"about_ca_topic_score_gemma":0.000001007584,"teacher_disagreement_score":0.5357755,"about_ca_system_score_codex":0.000043528653,"about_ca_system_score_gemma":0.0019161733,"threshold_uncertainty_score":0.9216},"labels":[],"label_agreement":null},{"id":"W1899766649","doi":"10.3917/spub.140.0021","title":"L'évaluation, une voie pour faire progresser la promotion de la santé en Afrique ?","year":2014,"lang":"fr","type":"article","venue":"Santé Publique","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.047053064792894006,"score_gpt":0.4450277984900634,"score_spread":0.3979747336971694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1899766649","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48455915,0.0020391976,0.15026589,0.17446737,0.0020639533,0.0018278065,0.00005295729,0.0003274576,0.18439622],"genre_scores_gemma":[0.96757686,0.0005174768,0.012290051,0.0010535535,0.0010535864,0.00025642294,0.000040453317,0.000052409996,0.01715917],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9855695,0.009686866,0.0010907502,0.0008263244,0.002065902,0.00076068763],"domain_scores_gemma":[0.9930326,0.003887964,0.0005428491,0.0008395317,0.001347181,0.00034992857],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.03649318,0.00041838083,0.00046514368,0.00047554745,0.00035715417,0.0014396829,0.00092384743,0.0006932492,0.0074379966],"category_scores_gemma":[0.007696692,0.00035830314,0.0002157083,0.0014865035,0.00041431875,0.00193446,0.000197437,0.00074897846,0.0011459289],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049503273,0.00080629217,0.05190551,0.00012261719,0.00006352174,0.000015197213,0.008064288,0.0012373287,0.0008992888,0.12960671,0.042923637,0.7643061],"study_design_scores_gemma":[0.0012195779,0.0003484575,0.32493067,0.00030308176,0.00006261394,0.00010036357,0.0013550607,0.114135884,0.0017417494,0.17029649,0.3849858,0.0005202492],"about_ca_topic_score_codex":0.00014716887,"about_ca_topic_score_gemma":0.0003578995,"teacher_disagreement_score":0.76378584,"about_ca_system_score_codex":0.00037182576,"about_ca_system_score_gemma":0.004177847,"threshold_uncertainty_score":0.9998869},"labels":[],"label_agreement":null},{"id":"W1901172133","doi":"10.7202/1027406ar","title":"Une recherche documentaire sur les politiques, les pratiques et les principes directeurs d’évaluation des élèves du système scolaire public (1re à 12e année) des provinces de l’Ouest canadien","year":2014,"lang":"fr","type":"article","venue":"Éducation et francophonie","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Saint-Boniface","funders":"","keywords":"Valuation (finance); Humanities; Political science; Art; Business","score_opus":0.21484346182885053,"score_gpt":0.4520809290985353,"score_spread":0.23723746726968478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1901172133","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9026883,0.0076580327,0.0071290536,0.061948203,0.0017213108,0.0012180717,0.000088289155,0.00028267226,0.017266026],"genre_scores_gemma":[0.9716463,0.005818411,0.011385618,0.00073191937,0.0006254244,0.0004962933,0.00020830044,0.000084092004,0.009003643],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9834149,0.010899501,0.0015861996,0.0011431649,0.0018646906,0.0010915815],"domain_scores_gemma":[0.99002784,0.0039542536,0.001110829,0.00089744874,0.0034175452,0.0005920569],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.027683852,0.00070163235,0.00072083826,0.0006072136,0.0018248153,0.0016565062,0.0010284141,0.000751838,0.0016922517],"category_scores_gemma":[0.015193565,0.000633634,0.00023176019,0.0020513698,0.001207674,0.0046071485,0.00016263514,0.00091673725,0.00012329429],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00004179926,0.0005690802,0.31893575,0.0005120008,0.00008625228,0.0000040028626,0.082684495,0.00076341926,0.0003378734,0.031241352,0.0043917443,0.56043226],"study_design_scores_gemma":[0.00093247474,0.0006048911,0.77645534,0.0013884328,0.00010663167,0.00007362005,0.06327125,0.010876823,0.0018873989,0.050287355,0.093148656,0.00096712995],"about_ca_topic_score_codex":0.17156316,"about_ca_topic_score_gemma":0.59889096,"teacher_disagreement_score":0.5594651,"about_ca_system_score_codex":0.0042060846,"about_ca_system_score_gemma":0.012831,"threshold_uncertainty_score":0.99961656},"labels":[],"label_agreement":null},{"id":"W1901463763","doi":"10.21432/t2d90t","title":"Profile: The Importance of Involving Experts and Learners in Formative Evaluation","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Learning and Technology","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Mathematics education; Psychology; Teaching method; Evaluation methods; Research methodology; Higher education; Qualitative research; Pedagogy; Computer science; Sociology; Engineering; Political science","score_opus":0.0764359852411186,"score_gpt":0.418714089995772,"score_spread":0.34227810475465337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1901463763","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9878968,0.0023688625,0.00004367928,0.008347589,0.000047449128,0.0000740919,2.641276e-7,0.0000021804308,0.0012190741],"genre_scores_gemma":[0.99955285,0.00010059124,0.0001932623,0.000073069095,0.000009537547,0.0000014760067,2.704547e-7,0.000001591503,0.00006735618],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989369,0.00014574784,0.00040444202,0.000080014615,0.00031465758,0.00011826599],"domain_scores_gemma":[0.9989424,0.00015179034,0.0003971547,0.000079065416,0.00036434474,0.00006529785],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004158183,0.00004897065,0.00014433767,0.0006854605,0.00011927944,0.000039155653,0.00014463345,0.00006276805,0.000100142934],"category_scores_gemma":[0.002372837,0.000030690026,0.000014372727,0.0005421785,0.00014580677,0.00020319119,0.000008827385,0.0002598128,8.2609307e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005083952,0.0000031561424,0.7270999,0.0000013276598,0.000004188802,0.0000041358962,0.0041582254,0.00021462416,0.00017785093,0.0020406519,0.00020533624,0.2660855],"study_design_scores_gemma":[0.0024990554,0.0018983809,0.53210753,0.00031486148,0.00004036565,0.00049002084,0.2795798,0.070127,0.0012905034,0.08900288,0.022334078,0.00031553282],"about_ca_topic_score_codex":0.00004721489,"about_ca_topic_score_gemma":0.003216457,"teacher_disagreement_score":0.27542156,"about_ca_system_score_codex":0.000047642767,"about_ca_system_score_gemma":0.0005647333,"threshold_uncertainty_score":0.28406787},"labels":[],"label_agreement":null},{"id":"W1902104534","doi":"10.33524/cjar.v13i2.34","title":"THE ENDS AND THE MEAN-SPIRITED IN ACTION RESEARCH","year":2012,"lang":"en","type":"article","venue":"The Canadian Journal of Action Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Nipissing University","funders":"","keywords":"Pretext; Action (physics); Action research; Psychology; Perspective (graphical); Qualitative research; Sociology; Epistemology; Social psychology; Pedagogy; Law; Social science; Political science; Computer science; Philosophy","score_opus":0.844950779407255,"score_gpt":0.6879624217218409,"score_spread":0.1569883576854142,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1902104534","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85333335,0.0011960451,0.000028639197,0.13177727,0.00086511415,0.0003563928,0.0000017545901,0.0000019588504,0.012439486],"genre_scores_gemma":[0.9942456,0.0005391225,0.000011409301,0.00016459495,0.00045493164,0.000013548051,2.57101e-7,0.000005802829,0.004564739],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9890059,0.006005963,0.000535784,0.00011171745,0.0036923292,0.000648285],"domain_scores_gemma":[0.9888767,0.007984418,0.00017741117,0.0004272983,0.0021335408,0.00040065337],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.1518726,0.00006403952,0.00012899567,0.0010476183,0.0028262066,0.0010007612,0.0009279887,0.00006619501,0.0006777335],"category_scores_gemma":[0.006198673,0.000025823954,0.00005657075,0.0020604439,0.0011705061,0.00068925036,0.000060053502,0.0017899218,0.00013905138],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013973638,0.00007226761,0.08659704,0.000010522639,0.00009696941,0.000014823405,0.033509154,0.00048423483,0.00084998686,0.06941954,0.16947214,0.63807595],"study_design_scores_gemma":[0.0011609679,0.00015645249,0.26464477,0.000029075367,0.0000060423486,0.00013218861,0.041554872,0.0027525902,0.0004620789,0.021372847,0.66765594,0.000072143026],"about_ca_topic_score_codex":0.013549499,"about_ca_topic_score_gemma":0.3367885,"teacher_disagreement_score":0.6380038,"about_ca_system_score_codex":0.00051931705,"about_ca_system_score_gemma":0.0021264744,"threshold_uncertainty_score":0.998472},"labels":[],"label_agreement":null},{"id":"W1902618013","doi":"10.1596/978-1-60244-250-4","title":"The Changing Landscape of Development Evaluation Training: A Rapid Review","year":2014,"lang":"en","type":"review","venue":"World Bank, Washington, DC eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mandate; Context (archaeology); General partnership; Excellence; Curriculum; Political science; Public relations; Knowledge management; Psychology; Computer science; Pedagogy; Geography","score_opus":0.30540179624282715,"score_gpt":0.47836841531708063,"score_spread":0.17296661907425348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1902618013","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00001005825,0.92476594,0.00013128266,0.00030696532,0.0009905843,0.002211051,0.0000069656094,0.00004714373,0.07153002],"genre_scores_gemma":[0.00020114776,0.97669834,0.00058356597,0.00048565553,0.0003479089,0.00076314603,0.000088405715,0.000060974377,0.02077083],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9872625,0.0023879944,0.0037039649,0.00089823816,0.005047056,0.00070025056],"domain_scores_gemma":[0.99044746,0.0036366929,0.0031345533,0.0015775067,0.0010406709,0.00016311795],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.05865731,0.0006233812,0.0024623808,0.0011258218,0.0007579763,0.00039365535,0.0020701962,0.0001720033,0.0016752429],"category_scores_gemma":[0.0025025657,0.00034779636,0.00076976244,0.001353856,0.00013913253,0.00015761078,0.00033233652,0.00059672585,0.00043874444],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028757238,0.0000108521845,0.0000038040787,0.0031855595,0.000086303146,3.9671855e-7,0.001271895,0.0000026457067,1.2425433e-7,0.00083117484,0.007067189,0.9875372],"study_design_scores_gemma":[0.00022658924,0.000027572447,0.000014166979,0.030535687,0.00052939204,0.000008243446,0.00021738495,0.00034426642,0.000004643608,0.00041847388,0.9672728,0.00040075716],"about_ca_topic_score_codex":0.0000018791268,"about_ca_topic_score_gemma":0.00016017763,"teacher_disagreement_score":0.9871364,"about_ca_system_score_codex":0.00022100606,"about_ca_system_score_gemma":0.0033275906,"threshold_uncertainty_score":0.9998974},"labels":[],"label_agreement":null},{"id":"W1904031896","doi":"10.1111/j.1365-2753.2012.01879.x","title":"The 2011 <scp>P</scp>rogram <scp>E</scp>valuation <scp>S</scp>tandards: a framework for quality in medical education programme evaluations","year":2012,"lang":"en","type":"article","venue":"Journal of Evaluation in Clinical Practice","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University; Centre for Advancing Health Outcomes","funders":"","keywords":"Valuation (finance); Accountability; Quality (philosophy); Computer science; Business; Political science; Accounting","score_opus":0.4121633544668809,"score_gpt":0.6581448782419245,"score_spread":0.24598152377504356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1904031896","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81248784,0.008637863,0.09894874,0.038038228,0.017781252,0.0075280233,0.000037198068,0.00008083959,0.016459992],"genre_scores_gemma":[0.9066002,0.002955195,0.07412715,0.007162616,0.005494236,0.0016107114,0.000104292456,0.00010031104,0.0018452858],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.93711495,0.024366358,0.012934187,0.0012138945,0.02268472,0.0016859054],"domain_scores_gemma":[0.38842,0.56182367,0.01787298,0.0025075208,0.027453475,0.0019224093],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.41080216,0.00049648184,0.0011643901,0.00094880577,0.00073955633,0.0010524464,0.0015428549,0.0009855203,0.00039236277],"category_scores_gemma":[0.8869654,0.0003550275,0.00076308846,0.0024717848,0.00044111907,0.0049447785,0.00021560169,0.002867152,0.0004566732],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001839187,0.007685776,0.1923999,0.000050424685,0.00028778176,0.0000035341513,0.009363551,0.0023828668,0.0000129145155,0.024626415,0.118206866,0.644796],"study_design_scores_gemma":[0.0044756713,0.001008771,0.32625026,0.0002901095,0.0005316515,0.000087052395,0.03765704,0.045508903,0.000024249981,0.15648295,0.4275824,0.00010091735],"about_ca_topic_score_codex":0.00006747536,"about_ca_topic_score_gemma":0.00043780985,"teacher_disagreement_score":0.6446951,"about_ca_system_score_codex":0.0010171791,"about_ca_system_score_gemma":0.01142328,"threshold_uncertainty_score":0.99998456},"labels":[],"label_agreement":null},{"id":"W1904300077","doi":"10.1186/s13012-015-0345-7","title":"The concept of mechanism from a realist approach: a scoping review to facilitate its operationalization in public health program evaluation","year":2015,"lang":"en","type":"review","venue":"Implementation Science","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":312,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Montreal Clinical Research Institute; Université de Montréal","funders":"Institut National Du Cancer; Agence Nationale de la Recherche","keywords":"Operationalization; Referent; CLARITY; Mechanism (biology); Epistemology; Public health; Context (archaeology); Health informatics; Psychological intervention; Sociology; Medicine; Nursing","score_opus":0.9035080940398004,"score_gpt":0.7158287156651659,"score_spread":0.18767937837463444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1904300077","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000008849111,0.9618493,0.014241512,0.0022990128,0.00039041977,0.020330468,0.00031117155,0.000026685428,0.00054263667],"genre_scores_gemma":[0.00034863196,0.98796916,0.0038887972,0.0007858086,0.000039017224,0.0058109676,0.0010767096,0.000014785998,0.000066124034],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9834861,0.0029917452,0.003690773,0.0010715706,0.0082205,0.000539318],"domain_scores_gemma":[0.9918543,0.0008985871,0.0021878993,0.00085910276,0.0039000665,0.0003000628],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0650932,0.00029288072,0.0011314605,0.00075242313,0.00053863437,0.0008836623,0.0016599409,0.000059082933,0.00055473694],"category_scores_gemma":[0.0055300533,0.00018701724,0.00014040762,0.006375848,0.000204605,0.0014195621,0.00027899147,0.00015357275,0.000088291774],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010713134,0.000035026053,0.000004690248,0.0007991921,0.0000060728694,4.6437354e-8,0.001454129,0.000066752924,5.359228e-7,0.0049206135,0.000918358,0.9917935],"study_design_scores_gemma":[0.00086782733,0.00033621668,0.000103502054,0.030212108,0.00009246726,0.000004319717,0.0049692844,0.0124004865,0.0000069063412,0.002477335,0.94802845,0.0005010712],"about_ca_topic_score_codex":0.00022825965,"about_ca_topic_score_gemma":0.0012793286,"teacher_disagreement_score":0.9912924,"about_ca_system_score_codex":0.0010696632,"about_ca_system_score_gemma":0.018410502,"threshold_uncertainty_score":0.9871542},"labels":[],"label_agreement":null},{"id":"W1908430601","doi":"10.1161/str.32.12.2729","title":"The Impact of Impact Factors","year":2001,"lang":"en","type":"article","venue":"Stroke","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Medicine","score_opus":0.2101437297773358,"score_gpt":0.5473477314722393,"score_spread":0.33720400169490344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1908430601","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9691907,0.00005453541,0.00017634535,0.00017210389,0.00014232998,0.00007346659,0.000025136505,0.000008263645,0.03015709],"genre_scores_gemma":[0.9946316,0.000044874905,0.00002031268,0.000010640723,0.00003739445,0.0000017076939,0.0000018740234,0.0000031235468,0.005248492],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983376,0.00009378207,0.0003199447,0.00011524742,0.00095457793,0.00017883479],"domain_scores_gemma":[0.9984122,0.00072182267,0.00017368988,0.00041044506,0.00021042659,0.000071451694],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017228322,0.000077155484,0.00012746782,0.00008388508,0.00014176543,0.0001113291,0.00040394822,0.000025724166,0.0038852156],"category_scores_gemma":[0.0005391873,0.000030459469,0.00024885876,0.00033240556,0.00006161464,0.00018962995,0.00003544446,0.00007084869,0.00017505727],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026694908,0.000018257182,0.96645504,1.4169922e-7,0.000023562758,2.901178e-7,0.00026786892,0.00095052616,0.000650263,0.00014272203,0.0062758117,0.025188819],"study_design_scores_gemma":[0.00015758256,0.00019377944,0.9889479,0.0000014639612,0.0000027069834,0.0000016186839,0.0006191746,0.002685761,0.0003406419,0.0013818464,0.0056241523,0.000043315682],"about_ca_topic_score_codex":0.00022350112,"about_ca_topic_score_gemma":0.00006234819,"teacher_disagreement_score":0.02544085,"about_ca_system_score_codex":0.000055953537,"about_ca_system_score_gemma":0.00020815035,"threshold_uncertainty_score":0.9970254},"labels":[],"label_agreement":null},{"id":"W1912834704","doi":"10.33524/cjar.v16i1.181","title":"Coghlan, D., &amp; Brydon-Miller, M. (2014). The Sage encyclopedia of action research. Thousand Oaks, CA: SAGE.","year":2015,"lang":"en","type":"article","venue":"The Canadian Journal of Action Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Encyclopedia; Action research; Participatory action research; Miller; Action (physics); Sociology; Agency (philosophy); Library science; Social science; Anthropology; Pedagogy; Computer science","score_opus":0.5380583400494583,"score_gpt":0.5781384781325769,"score_spread":0.04008013808311861,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1912834704","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8426455,0.0032418673,0.00087084906,0.08537737,0.0041579544,0.0010681989,0.00005925781,0.000011755056,0.06256725],"genre_scores_gemma":[0.9592869,0.0021471381,0.00009295907,0.0001730023,0.0008364108,0.000013337183,0.0000035863325,0.000017836423,0.03742882],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9867134,0.004761129,0.00092261797,0.00024775657,0.006647829,0.00070724916],"domain_scores_gemma":[0.9884766,0.0035672882,0.00048923073,0.0008818777,0.005665689,0.00091934326],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.07928981,0.00013299442,0.00028290556,0.0014506058,0.0015595823,0.000613709,0.0016655179,0.00013757798,0.0043735],"category_scores_gemma":[0.008268533,0.000070156806,0.00013474525,0.002069855,0.00092025095,0.00069731066,0.00010211681,0.0019285617,0.00087619846],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024750477,0.000044044824,0.005481162,0.00000922135,0.000056988658,0.000018285557,0.006223122,0.0012711021,0.00043545777,0.00032000072,0.87773997,0.10815313],"study_design_scores_gemma":[0.00055424945,0.0002762998,0.023173526,0.00005168974,0.000012101806,0.0001120748,0.0139624,0.0005189714,0.0003748754,0.0072830203,0.95359135,0.00008943128],"about_ca_topic_score_codex":0.030796481,"about_ca_topic_score_gemma":0.39388296,"teacher_disagreement_score":0.3630865,"about_ca_system_score_codex":0.0008120806,"about_ca_system_score_gemma":0.010044025,"threshold_uncertainty_score":0.9999017},"labels":[],"label_agreement":null},{"id":"W1920912451","doi":"10.24124/c677/2015631","title":"Thawing the tuition freeze: The politics of policy change in comparative perspective","year":2015,"lang":"en","type":"article","venue":"Canadian Political Science Review","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Politics; Nonprobability sampling; Perspective (graphical); Public administration; Political science; Policy analysis; Sampling (signal processing); Comparative politics; Comparative case; Policy learning; Regional science; Sociology; Law; Engineering","score_opus":0.5935756441775055,"score_gpt":0.5982464091983081,"score_spread":0.0046707650208025475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1920912451","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041300345,0.018133078,0.00006292501,0.6488633,0.00043064452,0.0019892985,0.00010320447,0.000013226295,0.28910393],"genre_scores_gemma":[0.98114485,0.00031424576,0.00003382913,0.018154897,0.00016645742,0.00004409722,9.538243e-7,0.0000026794546,0.00013799086],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99613434,0.00043846015,0.000507001,0.0002806955,0.0016728704,0.00096664677],"domain_scores_gemma":[0.9963512,0.0007052332,0.00012460627,0.0005722753,0.0011474972,0.0010991786],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012315304,0.00010722682,0.0002867245,0.00035028334,0.00031164906,0.00013087735,0.0012353574,0.000028956123,0.00024728267],"category_scores_gemma":[0.010052828,0.00005155288,0.00007049197,0.003399784,0.001516681,0.00047335264,0.00008847945,0.0001874376,0.0001764529],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[3.551949e-7,0.0000074885784,0.0021879745,0.000008753118,0.0000011700938,7.459741e-7,0.0027096076,0.000002848723,0.0000014180051,0.9918575,0.0011427369,0.0020793548],"study_design_scores_gemma":[0.0003646442,0.00017903242,0.29418397,0.0010965657,0.000037098744,0.000046378726,0.043660525,0.005468348,0.00011627467,0.54092026,0.11356248,0.00036443205],"about_ca_topic_score_codex":0.23331396,"about_ca_topic_score_gemma":0.123859555,"teacher_disagreement_score":0.9398445,"about_ca_system_score_codex":0.002157142,"about_ca_system_score_gemma":0.009199125,"threshold_uncertainty_score":0.9982859},"labels":[],"label_agreement":null},{"id":"W1922643933","doi":"10.21500/20112084.841","title":"Gaining confidence with intervals: practical guidelines, advices and tricks of the trade to face real-life situations.","year":2010,"lang":"en","type":"article","venue":"International journal of psychological research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Confidence interval; Face (sociological concept); Bayesian probability; Interpretation (philosophy); Credible interval; Statistics; Psychology; Computer science; Artificial intelligence; Mathematics; Social science; Sociology","score_opus":0.718899948039882,"score_gpt":0.7159798591573202,"score_spread":0.0029200888825617888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1922643933","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8503476,0.000034738605,0.016641123,0.12724276,0.00058818964,0.0001620555,0.000005460148,0.0000033498145,0.0049747163],"genre_scores_gemma":[0.98958015,0.00012237784,0.008637781,0.0011523174,0.00022331026,0.000005640496,3.4256024e-7,0.0000039040087,0.00027418396],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99304414,0.0005786341,0.0010212832,0.00023570156,0.0049492195,0.00017102114],"domain_scores_gemma":[0.99085635,0.0039235125,0.0005315708,0.00027793576,0.0041892086,0.00022141654],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016475912,0.000081540325,0.00020021458,0.00038278,0.00010010295,0.00025388956,0.0013667513,0.000075219556,0.0009409584],"category_scores_gemma":[0.031781897,0.00003838358,0.00007603608,0.00062756555,0.00032168507,0.00039187953,0.00019573087,0.0008455487,0.000024654693],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0044588135,0.0014469167,0.1418577,0.000010696392,0.00026623474,0.00012217503,0.0063294233,0.0016419443,0.04835896,0.08947121,0.08296769,0.6230682],"study_design_scores_gemma":[0.002076464,0.0020525332,0.8998703,0.00024831656,0.000018482602,0.000623268,0.008169146,0.00456088,0.0014169732,0.02688776,0.053885423,0.00019046362],"about_ca_topic_score_codex":0.000017068089,"about_ca_topic_score_gemma":0.000062054685,"teacher_disagreement_score":0.7580126,"about_ca_system_score_codex":0.000028870774,"about_ca_system_score_gemma":0.00038439978,"threshold_uncertainty_score":0.99997234},"labels":[],"label_agreement":null},{"id":"W1922690797","doi":"","title":"Toward the Development of a Program Evaluation Business Model: Promoting the Longevity of Counselling in Schools","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Counselling and Psychotherapy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Accountability; Human services; Context (archaeology); Service (business); Public relations; Service model; Business; Psychology; Medical education; Process management; Marketing; Medicine; Political science","score_opus":0.3397690171651494,"score_gpt":0.45414715616452633,"score_spread":0.11437813899937693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1922690797","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87191176,0.009949647,0.11433592,0.0028703348,0.00023137318,0.0005949942,0.0000026680966,0.0000023666953,0.00010090258],"genre_scores_gemma":[0.9804299,0.017262517,0.002046653,0.00014611689,0.00005388463,0.000017829458,5.143057e-7,0.000008806906,0.000033789445],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99693835,0.00028129586,0.0011302826,0.00014667072,0.0013067013,0.00019668917],"domain_scores_gemma":[0.9968346,0.00031012014,0.0008333727,0.00023057676,0.0016668368,0.00012451594],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01409966,0.000113551454,0.0002605682,0.0002923889,0.00018704764,0.00015501522,0.0004556367,0.00005577312,0.00019036407],"category_scores_gemma":[0.000029175275,0.00006222878,0.000059958536,0.000808981,0.00011373677,0.0002183129,2.1000096e-7,0.00024550036,0.0000022686331],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052391562,0.00007789398,0.003290961,0.000024904184,0.000046107412,0.0000010215521,0.13541268,0.06804633,0.00016189546,0.00021734786,0.00028576545,0.7923827],"study_design_scores_gemma":[0.0013849393,0.00017157747,0.0032594788,0.00050794514,0.000033818775,0.00002770277,0.0016579799,0.895149,0.00032168019,0.07101481,0.026282405,0.00018867817],"about_ca_topic_score_codex":0.00005414813,"about_ca_topic_score_gemma":0.00538088,"teacher_disagreement_score":0.82710266,"about_ca_system_score_codex":0.00002674307,"about_ca_system_score_gemma":0.0007278025,"threshold_uncertainty_score":0.48866892},"labels":[],"label_agreement":null},{"id":"W1926091675","doi":"10.47678/cjhe.v32i2.183415","title":"Review of The Art of Evaluation: A Handbook for Educators and Trainers","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Higher Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Medical education; Sociology; Engineering ethics; Pedagogy; Medicine; Engineering","score_opus":0.2106208343712564,"score_gpt":0.4851260776622077,"score_spread":0.27450524329095133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1926091675","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17281087,0.6699422,0.00018376422,0.11532596,0.010561965,0.0020819344,0.000042210304,0.0000024659466,0.029048648],"genre_scores_gemma":[0.9764246,0.0014970505,0.00065614365,0.0038453762,0.00024032943,0.000021195729,0.000002289566,0.0000060763396,0.017306976],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985623,0.00013819431,0.00059889304,0.00007370514,0.0005468504,0.00008009136],"domain_scores_gemma":[0.99731165,0.00016696013,0.00066544284,0.00018818252,0.0015162932,0.0001514479],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0026323863,0.000051709707,0.00016403123,0.0002046582,0.000063997875,0.00002429143,0.00019439407,0.000023771576,0.0050876173],"category_scores_gemma":[0.0007291258,0.000032142678,0.00008988749,0.0003386523,0.00008029082,0.00017319032,0.0000032529158,0.000053512584,0.0000057804527],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020725365,0.000026297148,0.008178832,0.00013171558,0.000013278888,2.7674416e-8,0.0009867405,0.000014057145,0.000032883712,0.00051838043,0.9517732,0.038322486],"study_design_scores_gemma":[0.00026416496,0.00007668461,0.042904567,0.0015482986,0.00008413745,0.000017242886,0.00049239426,0.00012392101,0.00012486265,0.0031675561,0.951143,0.000053124753],"about_ca_topic_score_codex":0.000049279064,"about_ca_topic_score_gemma":0.00038636054,"teacher_disagreement_score":0.80361366,"about_ca_system_score_codex":0.000087930996,"about_ca_system_score_gemma":0.0032370558,"threshold_uncertainty_score":0.9958219},"labels":[],"label_agreement":null},{"id":"W1928180478","doi":"","title":"The research collective: a model for developing timely, contextually relevant and dynamic approaches to research synthesis?","year":2006,"lang":"en","type":"article","venue":"PubMed","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Process (computing); Management science; Knowledge management; Triangulation; Process management; Data science; Systematic review; Computer science; Psychology; Engineering ethics; MEDLINE; Business; Political science; Engineering","score_opus":0.7910169743460724,"score_gpt":0.5366783620728309,"score_spread":0.2543386122732415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1928180478","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5250917,0.0013701472,0.16280012,0.21282172,0.00042540237,0.019662594,0.00010663439,0.00012067346,0.077601],"genre_scores_gemma":[0.94701046,0.000031433727,0.0040043825,0.00011101637,0.000049237275,0.011484282,0.0000019703239,0.000015004765,0.037292194],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99440664,0.0008902043,0.00052341,0.00057364977,0.0027525304,0.0008535635],"domain_scores_gemma":[0.98337716,0.01461944,0.00007731337,0.00046427123,0.0013339645,0.0001278635],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.054491136,0.00010898707,0.00019859613,0.000537007,0.0017212105,0.0009240906,0.0007406253,0.000069889145,0.000008575612],"category_scores_gemma":[0.011559051,0.00006645585,0.00004533455,0.0014898889,0.00029652895,0.00021987333,0.00029920298,0.00025994732,0.000046826583],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005472715,0.00009231097,0.0012100211,0.000019946749,0.000034146375,0.000001056183,0.0018068823,0.0027589686,0.000076006625,0.112808526,0.062446415,0.81819844],"study_design_scores_gemma":[0.000396961,0.000046141788,0.09257965,0.000014886841,0.0000046848636,0.0000024556887,0.0020383429,0.70881,0.0003321318,0.16554578,0.030064404,0.00016457212],"about_ca_topic_score_codex":0.000039067287,"about_ca_topic_score_gemma":0.0019104615,"teacher_disagreement_score":0.8180339,"about_ca_system_score_codex":0.00045279905,"about_ca_system_score_gemma":0.0008162898,"threshold_uncertainty_score":0.9995784},"labels":[],"label_agreement":null},{"id":"W1929107339","doi":"10.1002/ev.20078","title":"Cross‐Case Analysis and Implications for Research, Theory, and Practice","year":2014,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec en Outaouais; University of Ottawa","funders":"","keywords":"Leverage (statistics); Theory of change; Organizational change; Affect (linguistics); Thematic analysis; Context (archaeology); Order (exchange); Evaluation methods; Organization development; Knowledge management; Management science; Public relations; Sociology; Computer science; Political science; Management; Business; Qualitative research; Social science; Engineering; Economics","score_opus":0.46899379184883316,"score_gpt":0.6700118587679306,"score_spread":0.2010180669190974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1929107339","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16821696,0.00037160795,0.8029016,0.014942619,0.000306054,0.0024834492,0.00006344786,0.000056910794,0.010657331],"genre_scores_gemma":[0.97459424,0.0000751635,0.018669145,0.0002709866,0.00022749831,0.0010364907,0.00005721204,0.000012077852,0.0050572157],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9963924,0.0015691604,0.00046021005,0.00051489886,0.0008598513,0.00020344359],"domain_scores_gemma":[0.9725251,0.023042355,0.00022071245,0.00046855595,0.0036005194,0.0001427526],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.066208236,0.00009258839,0.00017106887,0.0007911834,0.001371108,0.0006310081,0.00012488608,0.000071628674,0.00025703447],"category_scores_gemma":[0.05830085,0.00007662498,0.00009255832,0.0016372924,0.0001235872,0.00078315916,0.000043060332,0.000083338615,0.000014930996],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018846082,0.000059619564,0.0076149683,0.0000052409646,0.00013129688,4.2490072e-8,0.00086670864,0.00086525496,0.00022649315,0.081115566,0.00452521,0.9044011],"study_design_scores_gemma":[0.0019016346,0.00028072068,0.15956196,0.0000046446476,0.0009821125,0.00006834728,0.0013353026,0.18739453,0.00014879818,0.40618458,0.24197708,0.00016025809],"about_ca_topic_score_codex":0.00010353562,"about_ca_topic_score_gemma":0.0006853878,"teacher_disagreement_score":0.9042409,"about_ca_system_score_codex":0.00008131051,"about_ca_system_score_gemma":0.0002454568,"threshold_uncertainty_score":0.99992895},"labels":[],"label_agreement":null},{"id":"W193071","doi":"10.3138/cjpe.17.006","title":"Developing an Evaluation Habit of Mind","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Habit; Accountability; Sustainability; Psychology; Political science; Sociology; Social psychology; Law","score_opus":0.6840143153944287,"score_gpt":0.5727226976961833,"score_spread":0.11129161769824536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W193071","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9869411,0.00082448364,0.0023342634,0.0024525858,0.00094303436,0.0012369608,0.0000057679026,0.0000046372634,0.0052571944],"genre_scores_gemma":[0.98433673,0.000010414944,0.015231156,0.000101542435,0.00015811253,0.00003865218,0.00001195881,0.000008789544,0.00010261567],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9931573,0.0009862486,0.001342561,0.000215445,0.0040437584,0.00025466172],"domain_scores_gemma":[0.9902801,0.0001923993,0.001167115,0.0003438836,0.0076159057,0.00040058923],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.027047213,0.00012206964,0.00026460827,0.00096495147,0.00017670366,0.0002582843,0.0005041179,0.00009143713,0.01233043],"category_scores_gemma":[0.004134873,0.000099318146,0.000114584705,0.001006828,0.00009670808,0.0011620821,0.000008937411,0.00015441427,0.00011182527],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000058350365,0.000040488467,0.014100325,0.0000028923866,0.000017766472,0.0000012438761,0.001804494,0.002914849,0.000053380645,0.00031391412,0.0009203903,0.9798244],"study_design_scores_gemma":[0.0022482593,0.001048947,0.13231403,0.00010391226,0.0002124083,0.000059581347,0.0025474438,0.80464363,0.0008518737,0.016034957,0.039667703,0.00026726836],"about_ca_topic_score_codex":0.0002050906,"about_ca_topic_score_gemma":0.012636933,"teacher_disagreement_score":0.97955716,"about_ca_system_score_codex":0.0005813457,"about_ca_system_score_gemma":0.00451257,"threshold_uncertainty_score":0.9885724},"labels":[],"label_agreement":null},{"id":"W1935247981","doi":"10.7202/1027405ar","title":"La politique d’évaluation du rendement en Ontario : un alignement qui se précise dans la persévérance et la durée","year":2014,"lang":"fr","type":"article","venue":"Éducation et francophonie","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Political science; Humanities; Valuation (finance); Art; Business","score_opus":0.06425335793578017,"score_gpt":0.4100504526657799,"score_spread":0.3457970947299997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1935247981","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.56046563,0.0006459772,0.04043836,0.055045445,0.0065265475,0.0012185934,0.00006103621,0.00011803276,0.33548036],"genre_scores_gemma":[0.968033,0.0017551843,0.004929322,0.0040439344,0.00045540548,0.0003697575,0.00013998347,0.000052699972,0.020220673],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.98576695,0.008647521,0.0013997561,0.0010083611,0.0025889513,0.00058849296],"domain_scores_gemma":[0.993703,0.003349195,0.00075419404,0.0010778381,0.0007857037,0.00033003677],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.028806593,0.00050739234,0.0005074893,0.00035636223,0.0004292943,0.00064206956,0.00072449615,0.0004299918,0.011878945],"category_scores_gemma":[0.0013357494,0.00049139047,0.00024920786,0.00076861045,0.00029815227,0.0011777851,0.00016570413,0.0006801885,0.0016375411],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012381718,0.0022252141,0.031385016,0.0001664653,0.00015236596,0.000015664897,0.54592544,0.012464156,0.0008187745,0.18924214,0.03273204,0.18474889],"study_design_scores_gemma":[0.001720511,0.00020663592,0.29356748,0.00022777652,0.00008331489,0.000056276236,0.0143006155,0.01221213,0.00046114213,0.011571385,0.6651043,0.00048844155],"about_ca_topic_score_codex":0.024398146,"about_ca_topic_score_gemma":0.114473924,"teacher_disagreement_score":0.63237226,"about_ca_system_score_codex":0.0018144436,"about_ca_system_score_gemma":0.0066655944,"threshold_uncertainty_score":0.9997538},"labels":[],"label_agreement":null},{"id":"W1937782511","doi":"","title":"Critical Incident Stress Debriefing as a Trauma Intervention in First Nation Communities","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Counselling and Psychotherapy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Debriefing; Facilitator; Psychology; Narrative inquiry; Narrative; Population; Psychological intervention; Coping (psychology); Psychotherapist; Clinical psychology; Social psychology; Medicine; Psychiatry","score_opus":0.13513312867855898,"score_gpt":0.43250142320695567,"score_spread":0.2973682945283967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1937782511","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9497294,0.006146819,0.039854392,0.0030584962,0.0004859465,0.000058557885,0.000005496216,0.0000026229222,0.00065825466],"genre_scores_gemma":[0.9942885,0.004895708,0.00013821742,0.00041214415,0.00011795261,0.0000019741803,0.0000022234508,0.0000062845925,0.00013697353],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99842197,0.00018348,0.0006460869,0.00008111721,0.0005151293,0.00015220718],"domain_scores_gemma":[0.99858373,0.00051656005,0.00020905101,0.00011140556,0.000444776,0.00013446157],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028693383,0.00007861889,0.00015794662,0.0005590083,0.00020405678,0.0004130733,0.00020552527,0.00005169321,0.0006505807],"category_scores_gemma":[0.000015279835,0.000066415334,0.00006181122,0.00023628205,0.000085450905,0.00037571226,1.4519335e-7,0.00018207675,0.000007627672],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000439073,0.0003656621,0.2447381,0.00006709969,0.00006347494,0.000100141006,0.089931674,0.017549483,0.00007335925,0.07192254,0.0077042324,0.56704515],"study_design_scores_gemma":[0.0023201038,0.00048739192,0.04678607,0.0007657376,0.000012669748,0.0001625996,0.003953822,0.0121195,0.00014640087,0.7690533,0.16392346,0.00026894017],"about_ca_topic_score_codex":0.011999034,"about_ca_topic_score_gemma":0.47490016,"teacher_disagreement_score":0.6971308,"about_ca_system_score_codex":0.000033809683,"about_ca_system_score_gemma":0.0001308883,"threshold_uncertainty_score":0.99458015},"labels":[],"label_agreement":null},{"id":"W1940118918","doi":"","title":"Barrières à l’apprentissage en ligne dans un contexte de développement des compétences chez les professionnels de santé publique au Québec","year":2011,"lang":"fr","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Humanities; Political science; Occupational training; Context (archaeology); Geography; Art","score_opus":0.12547912764434033,"score_gpt":0.42834637133974457,"score_spread":0.30286724369540424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1940118918","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8415284,0.0018882925,0.10763473,0.0107235955,0.0010190305,0.00063689024,0.000023063903,0.00010063289,0.03644532],"genre_scores_gemma":[0.9329151,0.0007901006,0.042952217,0.00073490595,0.00022206747,0.00014475668,0.0000071087084,0.00002724542,0.022206511],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9931234,0.0022299527,0.0013116624,0.00074093713,0.0014631889,0.0011308561],"domain_scores_gemma":[0.99640965,0.0012830913,0.00046476058,0.0006485954,0.00058910105,0.00060480664],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01138351,0.0004565945,0.0005371527,0.00025572622,0.0012918056,0.0003747133,0.0014848738,0.00032235606,0.039162703],"category_scores_gemma":[0.0010024392,0.0003338651,0.00022611325,0.00068962347,0.0011023559,0.001182957,0.00043223586,0.0004082826,0.0005306612],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005256291,0.00043526036,0.5945963,0.000055105207,0.000083476814,0.000015027266,0.17408834,0.000039835773,0.0018724629,0.005045185,0.0025145703,0.22120185],"study_design_scores_gemma":[0.0009077746,0.00037425323,0.7699485,0.00039324028,0.00008323503,0.00004068403,0.1481188,0.008883364,0.04355133,0.02259305,0.0045744204,0.0005313928],"about_ca_topic_score_codex":0.118997015,"about_ca_topic_score_gemma":0.28314015,"teacher_disagreement_score":0.22067046,"about_ca_system_score_codex":0.0011738441,"about_ca_system_score_gemma":0.006417243,"threshold_uncertainty_score":0.99991137},"labels":[],"label_agreement":null},{"id":"W1951995802","doi":"10.3138/cjpe.027.004","title":"Propositions théoriques et pratiques pour l’évaluation de programmes en négligence","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières; Université du Québec en Outaouais","funders":"Université de Montréal; Université du Québec en Outaouais; Université du Québec à Montréal","keywords":"Neglect; Fidelity; Valuation (finance); Psychological intervention; Psychology; Variety (cybernetics); Intervention (counseling); Sustainability; Program evaluation; Social psychology; Computer science; Political science; Business","score_opus":0.3343002875915336,"score_gpt":0.5692418239309505,"score_spread":0.2349415363394169,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1951995802","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9421958,0.0014374173,0.027118284,0.015412911,0.0011062087,0.0029143733,0.000012308008,0.000053526805,0.009749211],"genre_scores_gemma":[0.94576216,0.000045991208,0.052802745,0.0003993823,0.00046791858,0.0002445577,0.000023533843,0.000014716778,0.00023897678],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99357045,0.0023972432,0.0010262087,0.0001876401,0.0023105838,0.0005078953],"domain_scores_gemma":[0.99397373,0.00047867285,0.0008211832,0.00028892767,0.0037483035,0.0006891892],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0413558,0.00016678631,0.00023817453,0.0006917299,0.00027995137,0.0006399518,0.0004510961,0.00013069459,0.0015031003],"category_scores_gemma":[0.005987529,0.00012854359,0.0001503691,0.00074743363,0.00008835352,0.0021322917,0.000015708609,0.0003116435,0.00010163827],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001287852,0.0001751142,0.13408089,0.000007447351,0.00003863311,0.0000022961235,0.012927565,0.0010825203,0.00027236078,0.0072659864,0.00444325,0.83969104],"study_design_scores_gemma":[0.0013709848,0.0016099276,0.719276,0.000216569,0.00035998784,0.00035584287,0.012216979,0.0730926,0.0040695304,0.077282794,0.109554134,0.00059463806],"about_ca_topic_score_codex":0.00045903848,"about_ca_topic_score_gemma":0.008150474,"teacher_disagreement_score":0.8390964,"about_ca_system_score_codex":0.00071851263,"about_ca_system_score_gemma":0.012349084,"threshold_uncertainty_score":0.9994097},"labels":[],"label_agreement":null},{"id":"W1958376939","doi":"10.56645/jmde.v6i11.207","title":"Debating Professional Designations for Evaluators","year":2009,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Process (computing); Psychology; Political science; Sociology; Engineering ethics; Pedagogy; Computer science; Engineering","score_opus":0.3373365539722523,"score_gpt":0.5875076878738227,"score_spread":0.25017113390157036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1958376939","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9128692,0.00024368153,0.07229954,0.010476411,0.0018326549,0.0011468045,0.000007337244,0.000014545256,0.001109783],"genre_scores_gemma":[0.96894455,0.000009200168,0.029874012,0.00014855765,0.00045147652,0.00003439159,0.000013308761,0.000008480579,0.00051599846],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9922615,0.00079351483,0.0016943987,0.0002543337,0.0047758357,0.00022041217],"domain_scores_gemma":[0.9899909,0.0018789162,0.0017074401,0.00028147054,0.0060031833,0.00013812947],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03696182,0.00015148766,0.00031434486,0.00062124967,0.0005063645,0.00013901808,0.00049906236,0.00009280973,0.0007632069],"category_scores_gemma":[0.008092914,0.00010298167,0.00026559946,0.0006307475,0.000028721324,0.0012682946,0.00003737884,0.00019790817,0.00003998446],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00064160576,0.000892545,0.010934904,0.000010242321,0.000060763417,0.0000022535507,0.007500732,0.12086389,0.018735198,0.0027448093,0.013029884,0.8245832],"study_design_scores_gemma":[0.0026137223,0.0010525789,0.18711813,0.00007884251,0.00011669784,0.000026815796,0.002565079,0.6972905,0.0011804441,0.1069339,0.0008625199,0.00016080253],"about_ca_topic_score_codex":3.2957482e-7,"about_ca_topic_score_gemma":0.0000051117568,"teacher_disagreement_score":0.82442236,"about_ca_system_score_codex":0.00027002295,"about_ca_system_score_gemma":0.0014708759,"threshold_uncertainty_score":0.99165046},"labels":[],"label_agreement":null},{"id":"W1960015609","doi":"","title":"ARTICLE 7: LESSONS LEARNED AND THE CONTRIBUTIONS OF THE PARIS DECLARATION EVALUATION TO EVALUATION THEORY AND PRACTICE","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Declaration; General partnership; Stakeholder; Declaration of independence; Political science; Engineering ethics; Management; Public relations; Sociology; Engineering; Law; Economics","score_opus":0.4814292938080387,"score_gpt":0.5829727740956275,"score_spread":0.1015434802875888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1960015609","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9101662,0.004609041,0.0069774687,0.06975766,0.00093723513,0.0051537473,0.000016934942,0.000006101351,0.0023756009],"genre_scores_gemma":[0.99815935,0.000043736225,0.00084669783,0.0005366923,0.0001443742,0.000222226,0.000006368822,0.0000068153818,0.00003375225],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9846269,0.010198305,0.0010081126,0.000195192,0.0036532404,0.00031827952],"domain_scores_gemma":[0.9872946,0.0031232627,0.0010825275,0.0003781459,0.0077701877,0.00035129016],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.17772475,0.00011668253,0.00022189377,0.00028510872,0.00062016695,0.0003346571,0.00026504748,0.00008491596,0.00047335206],"category_scores_gemma":[0.06991262,0.00006602547,0.00008639953,0.0008653775,0.00030143288,0.0014926995,0.00003709339,0.00021861082,0.000014608472],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024316598,0.00006696698,0.0075412085,0.0000030033195,0.00006498517,7.913851e-8,0.008319969,0.0038494978,0.0005005039,0.036225,0.0008914293,0.9422942],"study_design_scores_gemma":[0.0076347734,0.0004610959,0.4991877,0.000101339516,0.0024548718,0.00012989991,0.017841715,0.280705,0.0017142395,0.16496666,0.02453052,0.00027215676],"about_ca_topic_score_codex":0.00030081943,"about_ca_topic_score_gemma":0.0025241894,"teacher_disagreement_score":0.942022,"about_ca_system_score_codex":0.00038906393,"about_ca_system_score_gemma":0.0032610646,"threshold_uncertainty_score":0.9379219},"labels":[],"label_agreement":null},{"id":"W1960541735","doi":"10.5553/beleidsonderzoek.000035","title":"Bespreking van: J.E. Furobo, R.C. Rist &amp; S. Speer (Eds.), Evaluation and turbulent times. Reflections on a discipline in disarray, New Brunswick/London: Transaction Publishers 2013","year":2014,"lang":"nl","type":"article","venue":"Beleidsonderzoek Online","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Database transaction; Turbulence; Sociology; Physics; Thermodynamics; Computer science; Database","score_opus":0.14590331545069404,"score_gpt":0.4549502592622838,"score_spread":0.3090469438115897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1960541735","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71375436,0.006941847,0.061635613,0.1914373,0.006048353,0.005293024,0.0001467723,0.00037559881,0.014367161],"genre_scores_gemma":[0.9437345,0.0027484593,0.006207991,0.002455473,0.0017796248,0.00007140086,0.0009969766,0.00013675862,0.0418688],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.989241,0.0013688337,0.002178151,0.001842791,0.0043780445,0.0009911509],"domain_scores_gemma":[0.99510676,0.0010576356,0.00086071464,0.0013710081,0.00092331314,0.0006805941],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0086427275,0.00082115596,0.0009799422,0.0013813305,0.0007220737,0.0015214363,0.0007487445,0.00050115754,0.012230748],"category_scores_gemma":[0.0013185053,0.0007217308,0.00030793925,0.0024947016,0.00026127236,0.002658945,0.00013948498,0.0011930192,0.0012207619],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010602667,0.003582615,0.011936114,0.00013414248,0.00022072802,0.000007966862,0.007716864,0.0896853,0.001368071,0.0014156883,0.12862486,0.7542474],"study_design_scores_gemma":[0.008183357,0.0011427095,0.10045639,0.0005554365,0.0004117081,0.000059027592,0.0021149057,0.35845637,0.000120184646,0.0093654785,0.5177779,0.0013565063],"about_ca_topic_score_codex":0.0021422666,"about_ca_topic_score_gemma":0.07062383,"teacher_disagreement_score":0.7528909,"about_ca_system_score_codex":0.0006908005,"about_ca_system_score_gemma":0.002055696,"threshold_uncertainty_score":0.9995569},"labels":[],"label_agreement":null},{"id":"W1961623975","doi":"10.5334/ijic.1578","title":"Health Systems Integration: Competing or Shared Mental Models?","year":2014,"lang":"en","type":"article","venue":"International Journal of Integrated Care","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Institute of Health Services and Policy Research","funders":"","keywords":"Mental health; Integrated care; Process management; Computer science; Psychology; Knowledge management; Health care; Business; Psychiatry; Political science","score_opus":0.16790085721995568,"score_gpt":0.4831766692752655,"score_spread":0.3152758120553098,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1961623975","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3614635,0.0031894392,0.50555474,0.038686287,0.03565137,0.0010053033,0.0005916241,0.00014981277,0.05370797],"genre_scores_gemma":[0.9951427,0.00008492069,0.0024116375,0.0010362404,0.0005163379,0.000005106092,0.00008969301,0.000012305373,0.00070106116],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9943973,0.0004801263,0.0016066367,0.00022144619,0.0031139364,0.00018058266],"domain_scores_gemma":[0.9915373,0.0004303614,0.001399786,0.0002160591,0.006248272,0.00016824693],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003575686,0.00017247608,0.00040841367,0.00056817255,0.00013680485,0.0007860414,0.001244012,0.00006494095,0.0010958087],"category_scores_gemma":[0.0012027263,0.000100334,0.00018147622,0.0003853485,0.00004602986,0.0010567921,0.00007096212,0.00035041632,0.00008181406],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013507128,0.00026846447,0.013579407,0.000030686046,0.00041660032,0.000050822393,0.027326358,0.072515145,0.0006969847,0.026956724,0.079849534,0.7769586],"study_design_scores_gemma":[0.0030280882,0.0012127156,0.0019369402,0.0012353626,0.000021875576,0.0007231765,0.15734133,0.64367497,0.0005697777,0.0024923591,0.18737984,0.00038357018],"about_ca_topic_score_codex":0.00018853202,"about_ca_topic_score_gemma":0.0002780282,"teacher_disagreement_score":0.77657497,"about_ca_system_score_codex":0.0009484835,"about_ca_system_score_gemma":0.0012955159,"threshold_uncertainty_score":0.9998173},"labels":[],"label_agreement":null},{"id":"W1963550721","doi":"10.3917/rsi.097.0050","title":"Les méthodes mixtes stratégies prometteuses pour l'évaluation des interventions infirmières","year":2009,"lang":"fr","type":"article","venue":"Recherche en soins infirmiers","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université de Montréal","funders":"","keywords":"Humanities; Sociology; Political science; Art","score_opus":0.7884021167046253,"score_gpt":0.6276181377956187,"score_spread":0.16078397890900664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1963550721","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.759363,0.01622119,0.118258156,0.056263365,0.0017847072,0.001369932,0.000091502436,0.00034452765,0.046303637],"genre_scores_gemma":[0.66548747,0.004275473,0.2846563,0.0008050998,0.0005355054,0.00008414658,0.000042342086,0.000046308534,0.044067368],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98438084,0.010084458,0.0018110899,0.00087746687,0.0019765743,0.00086955825],"domain_scores_gemma":[0.9879241,0.00908467,0.0006473035,0.0009132007,0.0011017771,0.00032897433],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.03306335,0.0005841487,0.0006997095,0.0009005097,0.00074339105,0.0010015293,0.0011588389,0.0009648993,0.006757503],"category_scores_gemma":[0.020976353,0.00052333606,0.0007148445,0.0021921736,0.00066195766,0.0021975953,0.00016356222,0.0014564078,0.0012185656],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004621502,0.0005434768,0.0134430695,0.00013623128,0.00012268797,0.000005587613,0.006926194,0.002763795,0.0013489117,0.032485418,0.004259377,0.937919],"study_design_scores_gemma":[0.0018631263,0.0015267472,0.28742385,0.0022992576,0.0004783923,0.00007459747,0.028447466,0.024346983,0.008045828,0.53909016,0.105008416,0.0013951906],"about_ca_topic_score_codex":0.00097524736,"about_ca_topic_score_gemma":0.0016277378,"teacher_disagreement_score":0.93652385,"about_ca_system_score_codex":0.0012769942,"about_ca_system_score_gemma":0.0022660494,"threshold_uncertainty_score":0.9997218},"labels":[],"label_agreement":null},{"id":"W1964714699","doi":"10.1016/j.evalprogplan.2009.03.003","title":"Power and perceptions in participatory monitoring and evaluation","year":2009,"lang":"en","type":"article","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":43,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Accountability; Citizen journalism; Participatory evaluation; Bureaucracy; Perception; Power (physics); Participatory action research; Participant observation; Participatory design; Public relations; Politics; Psychology; Business; Political science; Economic growth; Sociology; Engineering; Public administration; Operations management; Economics","score_opus":0.37164481194313714,"score_gpt":0.6018709322341447,"score_spread":0.23022612029100753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1964714699","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9929388,0.0017220875,0.000080288846,0.0010410257,0.00013360962,0.00073849084,9.0680476e-7,0.000033431632,0.0033113444],"genre_scores_gemma":[0.99820113,0.000066577704,0.0013740036,0.00012337595,0.00004770341,0.00012939014,0.0000076197607,0.0000040901855,0.000046125988],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9969747,0.00052249845,0.00043503154,0.0003643426,0.0015105592,0.0001928355],"domain_scores_gemma":[0.9989929,0.00025509766,0.00012385339,0.000158869,0.00035854842,0.00011068398],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012876503,0.00011523495,0.00015432472,0.00028289636,0.00022609183,0.00035811137,0.00006622229,0.000067850364,0.00043044286],"category_scores_gemma":[0.00082506466,0.00009649183,0.00001778114,0.00034325285,0.00005574514,0.000561394,0.000027039847,0.00013359568,0.000012717448],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001347234,0.000036246005,0.37043935,0.0000016710115,0.0000028466288,3.9976328e-7,0.0055772867,0.00049628154,0.00016068257,0.00013981355,0.000063395426,0.6230686],"study_design_scores_gemma":[0.0007268778,0.00017970335,0.8164224,0.00004786882,0.000020673464,0.000004645942,0.0038957307,0.17311536,0.000019007157,0.004780173,0.0006865731,0.00010096302],"about_ca_topic_score_codex":0.000004837704,"about_ca_topic_score_gemma":0.000007465026,"teacher_disagreement_score":0.6229676,"about_ca_system_score_codex":0.00005056155,"about_ca_system_score_gemma":0.00010591704,"threshold_uncertainty_score":0.47130474},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W1965125050","doi":"10.1590/s1413-81232008000600005","title":"'Undisciplinary' comments from evaluative research in health","year":2008,"lang":"pt","type":"letter","venue":"Ciência & Saúde Coletiva","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"MEDLINE; Psychology; Medicine; Political science","score_opus":0.48698443547197673,"score_gpt":0.5842803896367217,"score_spread":0.09729595416474496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1965125050","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05304327,0.003900209,0.00072893465,0.89484715,0.0047680708,0.0062059294,0.0011070349,0.000091311595,0.035308067],"genre_scores_gemma":[0.5009614,0.007752711,0.0018354653,0.41918775,0.0061068116,0.0017383342,0.0034714127,0.0003648459,0.05858126],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.95905566,0.015137204,0.0043008197,0.0032141944,0.015491247,0.0028008933],"domain_scores_gemma":[0.98171633,0.010328168,0.0018736416,0.0029587247,0.0024105904,0.00071255857],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.030243637,0.0011213585,0.0023351533,0.003011276,0.0022174774,0.00072562206,0.003956494,0.001285521,0.019159643],"category_scores_gemma":[0.0019133227,0.0009972649,0.00049512554,0.005256467,0.0012251143,0.0007800342,0.0019450946,0.0072025713,0.015391017],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.0002676943,0.0006071393,0.0233313,0.00009599987,0.000093901355,0.0002801465,0.012603001,0.00024881918,0.000024366685,0.00007280021,0.9203182,0.04205665],"study_design_scores_gemma":[0.003188507,0.0010973242,0.10939259,0.002332977,0.000022972314,0.000014123778,0.0043213717,0.010458799,0.000046189532,0.0060297567,0.86207294,0.0010224357],"about_ca_topic_score_codex":0.0025790953,"about_ca_topic_score_gemma":0.00094644906,"teacher_disagreement_score":0.47565943,"about_ca_system_score_codex":0.004669773,"about_ca_system_score_gemma":0.009479048,"threshold_uncertainty_score":0.9992478},"labels":[],"label_agreement":null},{"id":"W1965650468","doi":"10.1016/j.jcjd.2013.03.301","title":"Wicked Problem Calls for Innovative Comprehensive Systems Thinking Evaluation","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Diabetes","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université Laval; Institut universitaire de cardiologie et de pneumologie de Québec","funders":"","keywords":"Medicine; Health promotion; Conceptual framework; Equity (law); Promotion (chess); Relevance (law); Politics; Public relations; Public health; Active living; Management science; Gerontology; Political science; Sociology; Engineering; Social science; Nursing","score_opus":0.17454843917270152,"score_gpt":0.4180196888771395,"score_spread":0.24347124970443795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1965650468","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99145335,0.00069288124,0.0008082118,0.0028840166,0.0010904161,0.0010043391,0.000018041295,0.0000041270537,0.0020446326],"genre_scores_gemma":[0.9969106,0.0000012698081,0.001850765,0.0007269966,0.00019662283,0.00006394078,0.000007793474,0.00000949513,0.00023256007],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.997008,0.00028230104,0.0009400488,0.00015769951,0.0012967826,0.00031515592],"domain_scores_gemma":[0.9870204,0.0009076528,0.0008401044,0.00018966643,0.010711803,0.0003304042],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0053995033,0.00011731896,0.0003163051,0.00062978844,0.0002549053,0.0005345382,0.0004827978,0.000065229986,0.0007868858],"category_scores_gemma":[0.0015502167,0.000083520994,0.00008165542,0.00070335297,0.00012963804,0.00089477433,0.0000115311805,0.00014998642,0.000106598505],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009332824,0.00006345032,0.4185432,0.000112347225,0.00048337775,0.0000023831883,0.021099707,0.027716625,0.0033278018,0.019046169,0.27350947,0.23608615],"study_design_scores_gemma":[0.0039793714,0.0011095173,0.5117782,0.00064616726,0.00014442518,0.000010001312,0.03475949,0.17424913,0.0010605975,0.16325648,0.10828041,0.0007262439],"about_ca_topic_score_codex":0.0004006252,"about_ca_topic_score_gemma":0.0011408904,"teacher_disagreement_score":0.23535989,"about_ca_system_score_codex":0.00027554124,"about_ca_system_score_gemma":0.003138604,"threshold_uncertainty_score":0.8615848},"labels":[],"label_agreement":null},{"id":"W1965824013","doi":"10.1177/1098214013478142","title":"The Case for Participatory Evaluation in an Era of Accountability","year":2013,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":165,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Accountability; Technocracy; Citizen journalism; Participatory evaluation; Context (archaeology); Participatory GIS; Public sector; Sociology; Politics; Public administration; Public relations; Government (linguistics); Social accounting; Political science; Business; Accounting; Law","score_opus":0.3658990701241563,"score_gpt":0.5819220676204166,"score_spread":0.21602299749626036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1965824013","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9956147,0.00010957475,0.0012915941,0.001679054,0.0002966348,0.0008882008,0.0000025109907,0.0000018029875,0.00011589483],"genre_scores_gemma":[0.9986309,0.000011099897,0.0009842381,0.00012726316,0.00008269704,0.00015102219,0.000002187676,0.0000053179797,0.000005267404],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99331063,0.0022231645,0.0014915783,0.00015018921,0.0026553317,0.0001690883],"domain_scores_gemma":[0.98764414,0.0025079807,0.0017769705,0.00041052172,0.007575229,0.0000851332],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.061524533,0.00008670531,0.00026805632,0.00017315483,0.00013880213,0.00013956577,0.00028528282,0.000025744705,0.00085244473],"category_scores_gemma":[0.0064954823,0.000051667073,0.00010185917,0.0006170449,0.0002068225,0.0012213981,0.000018501709,0.00014855116,0.000014559758],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009059246,0.00009918122,0.03286157,0.0000015467712,0.00001130706,4.0646654e-7,0.0024718784,0.009100755,0.0004589886,0.00007705129,0.0002700547,0.95455664],"study_design_scores_gemma":[0.0011461996,0.0011114717,0.35569516,0.00001653843,0.000077552715,0.00004219375,0.02528007,0.5954453,0.00029707165,0.020622417,0.00018571394,0.00008033651],"about_ca_topic_score_codex":0.0001816407,"about_ca_topic_score_gemma":0.0008789924,"teacher_disagreement_score":0.95447636,"about_ca_system_score_codex":0.00022916561,"about_ca_system_score_gemma":0.0010467374,"threshold_uncertainty_score":0.966358},"labels":[],"label_agreement":null},{"id":"W1966883262","doi":"10.1016/j.jneb.2005.11.007","title":"Evaluating Food Stamp Nutrition Education: A View from the Field of Program Evaluation","year":2006,"lang":"en","type":"review","venue":"Journal of Nutrition Education and Behavior","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Food and Nutrition Service","keywords":"Accountability; Nutrition Education; Field (mathematics); Value (mathematics); Computer science; Evaluation methods; Program evaluation; Food stamps; Monitoring and evaluation; Process management; Management science; Medicine; Political science; Business; Engineering; Gerontology; Public administration; Mathematics","score_opus":0.4103269712639934,"score_gpt":0.6265815540769605,"score_spread":0.21625458281296706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1966883262","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0079401,0.9817873,0.0000662822,0.0013758714,0.0028736945,0.0056502186,0.00007626861,0.000011382689,0.00021886418],"genre_scores_gemma":[0.0020732358,0.98038816,0.008199036,0.0003203495,0.0023101778,0.006049363,0.0004547331,0.000027156691,0.0001777803],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99207616,0.0015085472,0.0029678026,0.00038676633,0.0028850536,0.00017565819],"domain_scores_gemma":[0.9883772,0.0020745648,0.0043465197,0.0005423417,0.0045274184,0.00013196969],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006548022,0.00032354853,0.0011079721,0.0006623613,0.00023040439,0.0004124324,0.00061407546,0.00028254243,0.0011445889],"category_scores_gemma":[0.001504606,0.00020736075,0.0005539557,0.0011046495,0.000082631785,0.0006630623,0.000048320042,0.0005132798,0.000018590172],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007671252,0.009604293,0.000105104875,0.0009109633,0.000031120562,1.3219133e-7,0.0001509177,5.3861044e-7,0.000002979213,0.00007463156,0.01940869,0.96970296],"study_design_scores_gemma":[0.0007627419,0.0010785686,0.0018371729,0.010124164,0.0023693033,0.000075726355,0.0024766487,0.00004571984,0.000011296087,0.0025262085,0.9784692,0.00022325978],"about_ca_topic_score_codex":0.000035502606,"about_ca_topic_score_gemma":0.000046477766,"teacher_disagreement_score":0.9694797,"about_ca_system_score_codex":0.00026108054,"about_ca_system_score_gemma":0.004917392,"threshold_uncertainty_score":0.9997685},"labels":[],"label_agreement":null},{"id":"W1967096767","doi":"10.1108/jaoc.2011.31507baa.001","title":"Social accounting and organisational change: an exploration of the sustainability assessment model","year":2011,"lang":"en","type":"article","venue":"Journal of Accounting & Organizational Change","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Mashhad University of Medical Sciences; McGill University","keywords":"Sustainability; Accounting; Accountability; Social accounting; Accounting research; Sustainability reporting; Extant taxon; Empirical research; Corporate social responsibility; Management accounting; Business; Public relations; Political science","score_opus":0.42650710310886975,"score_gpt":0.47860384852184706,"score_spread":0.05209674541297732,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1967096767","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98123074,0.000033993074,0.012055439,0.005606155,0.0003573978,0.00034167242,0.000012690394,0.000011754089,0.00035017612],"genre_scores_gemma":[0.99519426,0.000013509375,0.0032069779,0.0006662551,0.00084888993,0.000008864861,0.0000070817628,0.000017770615,0.00003640045],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9961248,0.00021239203,0.0009989387,0.00021216842,0.002282488,0.00016920613],"domain_scores_gemma":[0.9918605,0.00018508192,0.0017220146,0.00020231382,0.0059726634,0.00005744559],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0054293675,0.00014106718,0.00026079916,0.00027529048,0.00044833607,0.00017934458,0.00055024296,0.00009080325,0.0005694583],"category_scores_gemma":[0.0013967864,0.00009586585,0.0000740413,0.0009688276,0.00011543467,0.005884081,0.00018906746,0.00021606649,0.0000030072006],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050072955,0.00034206224,0.90763897,0.0000416446,0.000038261987,9.55287e-7,0.03982915,0.00033019192,0.00074256916,0.043651108,0.0003324348,0.007002573],"study_design_scores_gemma":[0.0004386967,0.00008305088,0.8893546,0.000020883253,0.000041747488,0.000012923392,0.006281301,0.02152296,0.00038904283,0.08154313,0.00017398948,0.00013771556],"about_ca_topic_score_codex":0.000023462993,"about_ca_topic_score_gemma":0.000033199776,"teacher_disagreement_score":0.037892025,"about_ca_system_score_codex":0.00019340459,"about_ca_system_score_gemma":0.00079888495,"threshold_uncertainty_score":0.62351686},"labels":[],"label_agreement":null},{"id":"W1968516213","doi":"10.3138/cjpe.29.2.67","title":"Positive Thinking Approaches to Evaluation and Program Perspectives","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Perspective (graphical); Value (mathematics); Nothing; Management science; Yield (engineering); Psychology; Sociology; Computer science; Epistemology; Economics; Artificial intelligence; Philosophy","score_opus":0.5279838688003321,"score_gpt":0.5159939137242172,"score_spread":0.011989955076114889,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968516213","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9528537,0.0013167482,0.007100212,0.014710015,0.0007713555,0.005568655,0.000006048685,0.000032175863,0.017641095],"genre_scores_gemma":[0.9787909,0.00000544106,0.020406378,0.00021480814,0.0002717011,0.00023040947,0.000010450893,0.00001199467,0.000057935147],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9938121,0.0013697738,0.0007558634,0.0003491377,0.003403202,0.00030994095],"domain_scores_gemma":[0.9941518,0.0003404289,0.0005662517,0.00027624745,0.0040459195,0.00061937474],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.037148044,0.00015903059,0.00026714342,0.00089556945,0.00038796742,0.0009504135,0.00039077224,0.000086050844,0.0005860477],"category_scores_gemma":[0.0067699347,0.00012372942,0.000097366,0.00084460696,0.00011658663,0.00078323367,0.00002309725,0.00021271354,0.00004193263],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015887385,0.000053043816,0.0068796463,0.000002466778,0.00002654236,5.731037e-7,0.010757599,0.0023219972,0.000010755137,0.004618143,0.00042100772,0.9748923],"study_design_scores_gemma":[0.001776503,0.0027966644,0.35188204,0.00014805609,0.00029769368,0.00007364943,0.018958779,0.52719307,0.00011166335,0.07574715,0.020643713,0.000370989],"about_ca_topic_score_codex":0.00023316228,"about_ca_topic_score_gemma":0.0072515956,"teacher_disagreement_score":0.97452134,"about_ca_system_score_codex":0.00051621336,"about_ca_system_score_gemma":0.0027869178,"threshold_uncertainty_score":0.9914587},"labels":[],"label_agreement":null},{"id":"W1969780486","doi":"10.1037/cap0000018","title":"“Giving back” to the profession of psychology is a personal responsibility.","year":2015,"lang":"en","type":"article","venue":"Canadian Psychology/Psychologie canadienne","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Psychology; Psychoanalysis; Applied psychology; Consulting psychology; Professional psychology; Social psychology; Engineering ethics; School psychology; Clinical psychology; Burnout","score_opus":0.4085705895032351,"score_gpt":0.5478829521600967,"score_spread":0.13931236265686164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969780486","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71129084,0.00028214278,0.0005219742,0.21771659,0.005079842,0.00093695056,0.00024900812,0.00003487784,0.063887775],"genre_scores_gemma":[0.90856516,0.000022582622,0.0011488259,0.08191895,0.00022545781,0.00009418875,0.000014186956,0.00003234794,0.007978308],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9933796,0.0012703156,0.001344386,0.0014984816,0.0010201985,0.0014870202],"domain_scores_gemma":[0.9926244,0.00063441717,0.00044316472,0.0027023363,0.001308666,0.0022869948],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.014312197,0.0003853555,0.0006164965,0.0014101753,0.0003450793,0.0000985302,0.0026709961,0.0004309622,0.007367772],"category_scores_gemma":[0.004747777,0.00026589973,0.00020146412,0.0028290574,0.00053238263,0.00026959935,0.00013326487,0.000649861,0.0035609559],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030680138,0.00007150506,0.046087425,0.000003829315,0.00003428232,0.000030394964,0.0086402055,0.000024645045,0.0002925117,0.00070234155,0.87900275,0.064803295],"study_design_scores_gemma":[0.0010610694,0.0006358775,0.23136447,0.00002675216,0.000012231934,0.00008851838,0.0040044934,0.00020460594,0.00002777422,0.006552076,0.755705,0.0003171003],"about_ca_topic_score_codex":0.024053143,"about_ca_topic_score_gemma":0.6092706,"teacher_disagreement_score":0.5852174,"about_ca_system_score_codex":0.00060695386,"about_ca_system_score_gemma":0.0025559363,"threshold_uncertainty_score":0.9999793},"labels":[],"label_agreement":null},{"id":"W1969982338","doi":"10.1016/s1499-4046(06)60064-x","title":"Integrating Evaluation Tools to Assess Nutrition Education","year":2001,"lang":"en","type":"article","venue":"Journal of Nutrition Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Accountability; Nutrition Education; Resource (disambiguation); Special education; Medical education; Computer science; Psychology; Political science; Pedagogy; Gerontology; Medicine","score_opus":0.35017616386980843,"score_gpt":0.5662611885449959,"score_spread":0.21608502467518742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969982338","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.927123,0.00092699146,0.02383181,0.023167755,0.007666948,0.0023753794,0.000007641063,0.000028158844,0.014872326],"genre_scores_gemma":[0.9699606,0.00035336765,0.023692321,0.0017378994,0.002711856,0.000667777,0.000078674595,0.000016142973,0.0007813802],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99410194,0.000700525,0.0016727598,0.00031028318,0.003002628,0.00021184886],"domain_scores_gemma":[0.98884416,0.00061287207,0.0013922281,0.00038885823,0.008501231,0.0002606467],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008731534,0.00017947296,0.0003202063,0.001447232,0.00023729818,0.00071934116,0.0004927004,0.000115873685,0.0019109667],"category_scores_gemma":[0.005121326,0.00015174373,0.00018492,0.001809577,0.000026650241,0.0029977337,0.000027012347,0.00027965492,0.00026678538],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000093253126,0.0050655953,0.0039915973,0.000027497601,0.000014274022,4.9503416e-7,0.0008314901,0.000218735,0.005199298,0.0025217198,0.07865232,0.90338373],"study_design_scores_gemma":[0.002119825,0.000887024,0.08550189,0.0012320229,0.00013415997,0.00039939393,0.043315977,0.0037756097,0.0032794878,0.07419742,0.7847182,0.00043897374],"about_ca_topic_score_codex":0.00001143217,"about_ca_topic_score_gemma":0.000030740015,"teacher_disagreement_score":0.90294474,"about_ca_system_score_codex":0.00077283557,"about_ca_system_score_gemma":0.003046025,"threshold_uncertainty_score":0.99900144},"labels":[],"label_agreement":null},{"id":"W1970796066","doi":"10.1332/174426407781172180","title":"Balancing rigour and relevance: researchers’ contributions to children’s mental health policy in Canada","year":2007,"lang":"en","type":"article","venue":"Evidence & Policy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Canadian Foundation for Healthcare Improvement; McMaster University; Simon Fraser University","funders":"Canadian Institutes of Health Research; Health Canada; Michael Smith Health Research BC","keywords":"Rigour; Relevance (law); Mental health; Public policy; Public relations; Qualitative research; Policy studies; Public health; Political science; Psychology; Sociology; Engineering ethics; Medicine; Social science; Nursing; Epistemology; Engineering; Psychiatry","score_opus":0.15319652787606328,"score_gpt":0.5603694646730364,"score_spread":0.4071729367969731,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1970796066","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7466268,0.0008378436,0.0004205165,0.25048757,0.0001333044,0.00058130815,0.00008296299,0.000015413987,0.00081429345],"genre_scores_gemma":[0.98656875,0.00057919894,0.0003064692,0.011424926,0.00036144123,0.000015235472,0.0000048060188,0.000007797298,0.0007314063],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9956213,0.00032759726,0.0007815315,0.00044488235,0.0019824286,0.00084221194],"domain_scores_gemma":[0.99692464,0.0015441654,0.0001812957,0.00043597794,0.0002684005,0.0006455067],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010355959,0.00014221923,0.00027539418,0.00081172184,0.00036195203,0.00015318277,0.00048586744,0.000039988074,0.00016030132],"category_scores_gemma":[0.018309,0.0001196385,0.00003307638,0.002393128,0.000066633824,0.0005609862,0.00019115912,0.00027519764,0.00010564386],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00009242455,0.00003897349,0.77029717,0.000008935802,0.000009959154,0.000006778913,0.006215123,0.00034454925,0.00037762453,0.012583272,0.04515799,0.1648672],"study_design_scores_gemma":[0.0003763376,0.00009385307,0.96978307,0.00014767573,8.2271634e-7,0.000016856957,0.0016155842,0.00043049606,0.00019847383,0.0016823312,0.025513306,0.00014117736],"about_ca_topic_score_codex":0.9493264,"about_ca_topic_score_gemma":0.9652655,"teacher_disagreement_score":0.23994192,"about_ca_system_score_codex":0.0049204146,"about_ca_system_score_gemma":0.014986547,"threshold_uncertainty_score":0.9988995},"labels":[],"label_agreement":null},{"id":"W1970961043","doi":"10.1002/meet.2011.14504801250","title":"Customer feedback management: Developing an organizational process of information use","year":2011,"lang":"en","type":"article","venue":"Proceedings of the American Society for Information Science and Technology","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Canadian Pharmacists Association; McGill University","funders":"","keywords":"Process (computing); Knowledge management; Perspective (graphical); Cognition; Process management; Business; Psychology; Computer science","score_opus":0.07176214390010151,"score_gpt":0.37560488087895144,"score_spread":0.30384273697884995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1970961043","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99108094,0.0000018017572,0.002730439,0.0008650166,0.00006400981,0.00047244644,0.0000140527745,0.000042840897,0.004728452],"genre_scores_gemma":[0.9669658,0.000030474568,0.03225348,0.0006846213,0.0000048580678,0.000033646193,0.0000026161354,0.0000026476087,0.000021860125],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9976857,0.0000027620667,0.000676968,0.00013855955,0.0012920431,0.00020399959],"domain_scores_gemma":[0.99241066,0.000042100157,0.0013811064,0.00016052654,0.005963623,0.0000419682],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026952461,0.00009352741,0.00018058546,0.00060979254,0.0003469552,0.00015455802,0.0010300264,0.000044702636,0.00001376286],"category_scores_gemma":[0.0009934187,0.00006282367,0.000053453605,0.006594692,0.0016296343,0.011070973,0.00024120834,0.00007047587,0.000008201517],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006391832,0.00005339181,0.14662299,0.0001781519,0.000047870835,4.699657e-9,0.02295865,0.000021079699,0.0015380016,0.6629578,0.0016280652,0.16393012],"study_design_scores_gemma":[0.001962897,0.0007161361,0.35838252,0.00013545669,0.00010823277,0.000023763045,0.34349212,0.022776335,0.12025227,0.10694077,0.044412978,0.0007965108],"about_ca_topic_score_codex":0.000007247301,"about_ca_topic_score_gemma":5.3947775e-7,"teacher_disagreement_score":0.556017,"about_ca_system_score_codex":0.000055609715,"about_ca_system_score_gemma":0.00028951402,"threshold_uncertainty_score":0.80261886},"labels":[],"label_agreement":null},{"id":"W1971555857","doi":"10.1016/j.polsoc.2010.03.004","title":"Policy analysis and policy work in federal systems: Policy advice and its contribution to evidence-based policy-making in multi-level governance systems","year":2010,"lang":"en","type":"article","venue":"Policy and Society","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":154,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Work (physics); Policy analysis; Corporate governance; Public administration; Policy studies; Political science; Public policy; Order (exchange); Public economics; Economics; Management; Finance; Law","score_opus":0.1679909213834969,"score_gpt":0.489356959801353,"score_spread":0.32136603841785616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971555857","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95413876,0.0016283987,0.0017007546,0.040363725,0.00017665059,0.0011670325,0.0002731663,0.00006635095,0.0004851382],"genre_scores_gemma":[0.99094415,0.0010673027,0.00046485427,0.005212374,0.001200422,0.0001398276,0.000009167671,0.000021993716,0.00093992846],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9949786,0.00058758614,0.0012630469,0.0009051101,0.0013058337,0.0009598026],"domain_scores_gemma":[0.9962405,0.0016069667,0.00059266586,0.00056806154,0.0005081976,0.0004836214],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.005337303,0.00042582594,0.00090902275,0.0017950117,0.0005315993,0.0010871218,0.0004773378,0.00037346376,0.000011033443],"category_scores_gemma":[0.010510173,0.00036491218,0.00019863575,0.009520574,0.00019514994,0.001013232,0.0002879978,0.0005338478,0.000018419965],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033279764,0.00034133458,0.63717264,0.0003748611,0.00031744427,0.000008584677,0.025355022,0.019904656,0.0021656398,0.29169884,0.0009215054,0.021406692],"study_design_scores_gemma":[0.0018111584,0.00007087327,0.83431655,0.0004173537,0.000032911445,0.000011454442,0.0010132308,0.15857702,0.00003954406,0.0007212744,0.0025318444,0.00045677062],"about_ca_topic_score_codex":0.06257301,"about_ca_topic_score_gemma":0.008750222,"teacher_disagreement_score":0.29097757,"about_ca_system_score_codex":0.0008280825,"about_ca_system_score_gemma":0.0025910875,"threshold_uncertainty_score":0.9999499},"labels":[],"label_agreement":null},{"id":"W197313653","doi":"","title":"The canadian CPI and the bias issue: present and future outlooks","year":2000,"lang":"es","type":"article","venue":"Hispana","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Economics; Public economics; Development economics","score_opus":0.08409069400577329,"score_gpt":0.39808431018602325,"score_spread":0.31399361618024996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W197313653","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2649577,0.021812838,0.000002216561,0.5125898,0.0013188764,0.0009011328,0.000040037823,0.000019471292,0.19835791],"genre_scores_gemma":[0.91414064,0.013371978,0.00003791192,0.0037636631,0.0013527613,0.000027087633,0.0000028832567,0.000011321547,0.06729175],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99742615,0.0004601435,0.00038079426,0.00032931336,0.0010430805,0.00036051296],"domain_scores_gemma":[0.998035,0.0008267103,0.00011154523,0.00059165043,0.0001419456,0.00029312028],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003856091,0.00016906633,0.00020484232,0.00008555304,0.0019480337,0.0016075817,0.00046124758,0.00010322613,0.0059039616],"category_scores_gemma":[0.000103919214,0.0000763105,0.00005672532,0.00027961825,0.00064486015,0.00018895962,0.000058699792,0.00024307062,0.0006507863],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000616999,0.000007772505,0.0075231674,0.0000053862104,0.000029202503,0.0000030999292,0.0040319585,0.000021539536,4.6582878e-7,0.012699947,0.13774398,0.8378718],"study_design_scores_gemma":[0.0006132445,0.000032641194,0.0909031,0.000012086731,0.000028674838,0.00000889349,0.002062543,0.0077818288,0.0000032247135,0.0011594977,0.8972892,0.000105061925],"about_ca_topic_score_codex":0.045268614,"about_ca_topic_score_gemma":0.24118659,"teacher_disagreement_score":0.8377667,"about_ca_system_score_codex":0.000057241614,"about_ca_system_score_gemma":0.00051183975,"threshold_uncertainty_score":0.99942887},"labels":[],"label_agreement":null},{"id":"W1973373172","doi":"10.3138/cjpe.29.1.118","title":"Evaluating Humanitarian Action in Real Time: Recent Practices, Challenges, and Innovations","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Accountability; Bridge (graph theory); Action (physics); Process management; Business; Computer science; Risk analysis (engineering); Political science; Sociology; Law","score_opus":0.7423398199910727,"score_gpt":0.610782611392342,"score_spread":0.13155720859873066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1973373172","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9657997,0.0014325205,0.00019181934,0.012062823,0.00085736666,0.0013525848,0.0000024651365,0.000015840067,0.018284917],"genre_scores_gemma":[0.991486,0.00064852886,0.0072004218,0.0001366399,0.0003108226,0.00006907357,0.000019802943,0.000012746731,0.00011595392],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99503565,0.0014614038,0.0011026176,0.00026095583,0.0018847554,0.0002546425],"domain_scores_gemma":[0.9937544,0.00058043975,0.0017887526,0.00026715652,0.0033417894,0.00026750157],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04204954,0.00012058322,0.00023512966,0.0011079069,0.00022822722,0.0003401719,0.0002636681,0.000099136625,0.001077243],"category_scores_gemma":[0.016112067,0.00010421884,0.000038148242,0.0008264993,0.000064741966,0.0011631175,0.000014588846,0.00029601203,0.000056477806],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000146353905,0.000037427802,0.0030688716,0.0000045002494,0.000010491868,0.0000010489921,0.0013828109,0.0006287749,0.00014583448,0.0019409931,0.00032548216,0.99243915],"study_design_scores_gemma":[0.0023485948,0.0016369164,0.51166326,0.00012200298,0.00011109178,0.000077581884,0.003337605,0.2933215,0.000040456867,0.040117715,0.14693607,0.00028722177],"about_ca_topic_score_codex":0.000791261,"about_ca_topic_score_gemma":0.07126598,"teacher_disagreement_score":0.9921519,"about_ca_system_score_codex":0.00049723766,"about_ca_system_score_gemma":0.0031508715,"threshold_uncertainty_score":0.9998359},"labels":[],"label_agreement":null},{"id":"W1973768863","doi":"10.1108/02621710310467631","title":"Manager attention to multisource feedback","year":2003,"lang":"en","type":"article","venue":"Journal of Management Development","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Supervisor; Psychology; Dimension (graph theory); Social psychology; Applied psychology; Management","score_opus":0.13139911598350623,"score_gpt":0.43487246110192385,"score_spread":0.3034733451184176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1973768863","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6856713,0.000095244075,0.1579279,0.0038275674,0.00221769,0.0006436564,6.045887e-7,0.000022606255,0.14959338],"genre_scores_gemma":[0.8184351,0.000043042117,0.13328665,0.0016259917,0.000060324564,0.000013859608,0.0000010028799,0.000013788175,0.046520256],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9953462,0.00019322224,0.0012821001,0.00024067695,0.00268634,0.00025146655],"domain_scores_gemma":[0.9983268,0.00010471492,0.0005738074,0.0003010435,0.00050116045,0.00019246779],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.007956706,0.0001461749,0.00025218588,0.0007886953,0.00015538809,0.00023973142,0.0005658449,0.000031990414,0.0018558498],"category_scores_gemma":[0.0002676832,0.000105611725,0.00011340812,0.0007670172,0.00001467517,0.00037855844,0.000114240625,0.000114799375,0.0017478946],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010632912,0.00040845582,0.053659733,0.000037031925,0.00033365694,0.00010183704,0.0021415134,0.005748615,0.00026636917,0.009342434,0.10181476,0.82603925],"study_design_scores_gemma":[0.000661015,0.000054256252,0.29960525,0.000044335382,0.000016516402,0.000014089765,0.0017699591,0.000068826506,0.00025862208,0.000790195,0.69658744,0.00012947313],"about_ca_topic_score_codex":4.0310988e-7,"about_ca_topic_score_gemma":0.0000047217327,"teacher_disagreement_score":0.8259098,"about_ca_system_score_codex":0.00019722876,"about_ca_system_score_gemma":0.00009618715,"threshold_uncertainty_score":0.9990566},"labels":[],"label_agreement":null},{"id":"W1974257054","doi":"10.1177/0163278703026002005","title":"Evaluability Assessment","year":2003,"lang":"en","type":"article","venue":"Evaluation & the Health Professions","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Logic model; Process (computing); Process management; Outcome (game theory); Product (mathematics); Key (lock); Theory of change; Program evaluation; Reflection (computer programming); Psychology; Management science; Knowledge management; Medical education; Medicine; Nursing; Computer science; Political science; Sociology; Engineering","score_opus":0.5915797188746392,"score_gpt":0.6761750254876046,"score_spread":0.08459530661296533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1974257054","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2822975,0.0013272945,0.04665357,0.42999485,0.010640373,0.012558151,0.000039882267,0.0002657029,0.21622269],"genre_scores_gemma":[0.9841757,0.000036071804,0.0030656906,0.0067490176,0.00009651526,0.0007625415,0.000018768042,0.000014185631,0.0050815023],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9713912,0.017895838,0.001804691,0.00072130613,0.0075761196,0.00061085244],"domain_scores_gemma":[0.9922036,0.002994475,0.00085403497,0.001690903,0.001984538,0.00027245816],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.12746377,0.00019890809,0.00033493817,0.00020109896,0.002327385,0.00016745448,0.0006986897,0.00009120511,0.023349516],"category_scores_gemma":[0.00942204,0.00010673578,0.0001420122,0.0013632042,0.00013518578,0.00043554942,0.00010716992,0.0005319179,0.0013628037],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057720554,0.0010341693,0.09281694,0.000042703465,0.0000637919,4.2777606e-7,0.014620522,0.009110641,0.0001442622,0.22035089,0.26205412,0.39970383],"study_design_scores_gemma":[0.0016340289,0.0002721365,0.4281308,0.000060884726,0.000042633492,0.0000059471236,0.012688615,0.07883973,0.000043519027,0.23908085,0.23892944,0.00027143728],"about_ca_topic_score_codex":0.000026321213,"about_ca_topic_score_gemma":0.00014631992,"teacher_disagreement_score":0.7018782,"about_ca_system_score_codex":0.00064561254,"about_ca_system_score_gemma":0.007972847,"threshold_uncertainty_score":0.99941474},"labels":[],"label_agreement":null},{"id":"W1974376560","doi":"10.1007/s10734-009-9230-0","title":"The Canada Research Chairs Program: the good, the bad, and the ugly","year":2009,"lang":"en","type":"article","venue":"Higher Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Windsor; University of Manitoba","funders":"Canada Research Chairs","keywords":"Dialectic; Higher education; Qualitative research; Context (archaeology); Identity (music); Public relations; Sample (material); Psychology; Social psychology; Sociology; Pedagogy; Social science; Political science","score_opus":0.21495898991063767,"score_gpt":0.5558507896736344,"score_spread":0.34089179976299677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1974376560","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15530756,0.002413846,0.0000048165293,0.7690225,0.0018516583,0.001336903,0.0000013395111,0.000015575533,0.0700458],"genre_scores_gemma":[0.9533537,0.00018869797,0.000022265864,0.0038518477,0.00037728378,0.00023948784,0.0000020432158,0.0000035367111,0.04196116],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99639183,0.0009608923,0.00028070356,0.00019875038,0.0019283921,0.00023940588],"domain_scores_gemma":[0.9962673,0.002260945,0.00011828582,0.000767478,0.0005351993,0.00005076799],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.01073174,0.00007693737,0.0000728156,0.000033663353,0.0018984531,0.0007756445,0.0008808023,0.000026248823,0.0003080202],"category_scores_gemma":[0.00039100685,0.000023246794,0.000030012445,0.00075062015,0.00035877508,0.00013130138,0.000053641044,0.0002732693,0.00006520327],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025419491,0.00004833191,0.002318422,6.955264e-7,0.0000071181926,6.7653964e-8,0.0018541234,0.000020050582,0.0000052848122,0.19613574,0.36660525,0.43297946],"study_design_scores_gemma":[0.00011587851,0.000025484704,0.32275796,0.0000030780216,0.000003915141,0.0000014018366,0.0031146859,0.00035882017,0.0000070068254,0.020497441,0.65308475,0.000029599641],"about_ca_topic_score_codex":0.022220496,"about_ca_topic_score_gemma":0.085572004,"teacher_disagreement_score":0.7980461,"about_ca_system_score_codex":0.000091839036,"about_ca_system_score_gemma":0.0017673849,"threshold_uncertainty_score":0.9994009},"labels":[],"label_agreement":null},{"id":"W1974781045","doi":"10.1108/17479886200800011","title":"International Comparative ACT Study Process and Data: How ACT teams compare in Toronto, Birmingham, Nashville and Auckland","year":2008,"lang":"en","type":"article","venue":"The International Journal of Leadership in Public Services","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Canadian Mental Health Association","funders":"","keywords":"Assertive community treatment; Mental health; Outreach; Public relations; Library science; Political science; Sociology; Medicine; Mental illness; Law; Computer science","score_opus":0.5290409119853758,"score_gpt":0.5165674985896868,"score_spread":0.012473413395689081,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1974781045","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9603341,0.0004790506,0.000016343412,0.036080513,0.00059449644,0.00018776412,0.000012090578,0.0000058759415,0.00228972],"genre_scores_gemma":[0.9985016,0.00017842883,0.0000865712,0.0008282869,0.00023396709,0.0000064407,0.000012725372,0.000006108426,0.00014587567],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99600244,0.00034303998,0.0007581264,0.00031708242,0.0023841653,0.00019516695],"domain_scores_gemma":[0.9971068,0.00093712105,0.0007041097,0.00028262354,0.0008792872,0.00009008217],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0052882857,0.0001592008,0.0003316815,0.00043092703,0.00010790132,0.00072129973,0.0027252436,0.000039666822,0.0003299741],"category_scores_gemma":[0.00032914436,0.000098284756,0.000031704105,0.00029631154,0.00014293777,0.0039047985,0.00034659286,0.00032147835,0.0000047243307],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018924102,0.00031844364,0.96139777,0.000007936088,0.0001163802,0.000030009918,0.031902216,0.00012766742,0.000018844268,0.00011262334,0.0004522194,0.0053266254],"study_design_scores_gemma":[0.0019218037,0.00011351838,0.72435033,0.000075362994,0.0000075956436,0.00021652694,0.2547835,0.0136856325,0.000016725367,0.00023986616,0.0044735717,0.00011556252],"about_ca_topic_score_codex":0.00049819937,"about_ca_topic_score_gemma":0.02471126,"teacher_disagreement_score":0.23704748,"about_ca_system_score_codex":0.00020006433,"about_ca_system_score_gemma":0.00027881924,"threshold_uncertainty_score":0.9930852},"labels":[],"label_agreement":null},{"id":"W1975060078","doi":"10.1080/09614520903220891","title":"SAS<sup>2</sup>: A Guide to Collaborative Inquiry and Social Engagement","year":2009,"lang":"en","type":"article","venue":"Development in Practice","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Sociology; Political science; Public relations; Social science","score_opus":0.1953621287511273,"score_gpt":0.5241511835865291,"score_spread":0.32878905483540183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975060078","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7920988,0.00013347683,0.005239044,0.09017296,0.00046188204,0.0013935895,0.000006019882,0.000071485796,0.11042271],"genre_scores_gemma":[0.8723505,0.000058253794,0.0999386,0.024739232,0.00013184831,0.00009196895,0.000011630932,0.000009234706,0.0026687323],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960771,0.00066661893,0.0008127873,0.000466769,0.0016932047,0.00028346994],"domain_scores_gemma":[0.9974552,0.0013022057,0.0002449049,0.0002128298,0.00068303494,0.00010186241],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010950053,0.0001613333,0.00022998815,0.0003727773,0.0003460315,0.00036400225,0.00031343717,0.000065536806,0.00040825378],"category_scores_gemma":[0.0039976244,0.00013614501,0.000018188352,0.0012228371,0.00003227828,0.0011393869,0.00014651284,0.00021387948,0.0006069161],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003348247,0.00042777075,0.00497905,0.000005578889,0.000050785227,0.00003660505,0.30197546,0.0014027823,0.00015293318,0.010396725,0.11908912,0.56114835],"study_design_scores_gemma":[0.00061775657,0.00009979241,0.053286646,0.00001285578,0.000008076398,0.0000044377166,0.046303827,0.00054573634,0.00017969756,0.00045295397,0.8982921,0.00019612335],"about_ca_topic_score_codex":0.000005933567,"about_ca_topic_score_gemma":0.00002651188,"teacher_disagreement_score":0.779203,"about_ca_system_score_codex":0.00023564091,"about_ca_system_score_gemma":0.0008193091,"threshold_uncertainty_score":0.7800881},"labels":[],"label_agreement":null},{"id":"W1975564755","doi":"10.1177/1098214013477235","title":"Understanding Dimensions of Organizational Evaluation Capacity","year":2013,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":118,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa; École Nationale d'Administration Publique","funders":"Australian Government","keywords":"Dimension (graph theory); Capacity building; Government (linguistics); Knowledge management; Organization development; Business; Organizational learning; Process management; Computer science; Economics; Economic growth","score_opus":0.5129125946126178,"score_gpt":0.4844682783398096,"score_spread":0.028444316272808245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975564755","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9566416,0.000042039355,0.038054843,0.0020623284,0.00045433588,0.0004082503,0.0000030512288,0.0000047843837,0.002328777],"genre_scores_gemma":[0.995521,0.000019256106,0.004124605,0.0001777771,0.00009882332,0.000009666234,0.0000067658902,0.000008409908,0.000033716857],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99075204,0.0012754337,0.0013202219,0.00017663519,0.0063333036,0.00014234446],"domain_scores_gemma":[0.98663145,0.0010338967,0.0023680418,0.00028099393,0.009570603,0.000115013914],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.019100176,0.000109466746,0.00033167662,0.00057141506,0.00013476444,0.00009478243,0.00026150365,0.00003310406,0.008698439],"category_scores_gemma":[0.006523244,0.00007107978,0.00011202178,0.0014964523,0.00021009058,0.0009792264,0.000032897566,0.00013830882,0.00012090871],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016246365,0.0007334481,0.27357244,0.00001296341,0.0004161826,0.000001011216,0.010865044,0.1709167,0.04356529,0.017433697,0.02258581,0.45973495],"study_design_scores_gemma":[0.0017692255,0.0009835371,0.28060743,0.00006787218,0.00028520636,0.000049696868,0.013046647,0.49726197,0.001848736,0.20356487,0.00029099974,0.00022379073],"about_ca_topic_score_codex":0.000037106725,"about_ca_topic_score_gemma":0.000016391039,"teacher_disagreement_score":0.45951116,"about_ca_system_score_codex":0.0004922193,"about_ca_system_score_gemma":0.0011243908,"threshold_uncertainty_score":0.99220777},"labels":[],"label_agreement":null},{"id":"W1975977486","doi":"10.1007/s10612-009-9083-y","title":"Methodology as a Knife Fight: The Process, Politics and Paradox of Evaluating Surveillance","year":2009,"lang":"en","type":"article","venue":"Critical Criminology","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":25,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Rhetorical question; Politics; Analogy; Adversary; Disadvantaged; Sociology; Position (finance); Process (computing); Style (visual arts); Political science; Law and economics; Epistemology; Law; Computer security; Economics; Computer science","score_opus":0.6313472855110329,"score_gpt":0.6196195568159659,"score_spread":0.011727728695066997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975977486","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93687475,0.00065486424,0.003550797,0.049449075,0.00026571285,0.00018494409,0.00000694827,0.000024881878,0.008988017],"genre_scores_gemma":[0.99117374,0.000024732304,0.0037284782,0.004795285,0.000069226604,0.000011049085,0.000001718186,0.0000044125295,0.00019135298],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99638146,0.0013378861,0.00071121706,0.00037884485,0.00080996414,0.00038061396],"domain_scores_gemma":[0.9887264,0.009775614,0.0001373764,0.00044561242,0.0008121103,0.00010292719],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005781584,0.00012784381,0.00038759212,0.00012143986,0.00020878404,0.0000564005,0.00046585206,0.00013132424,0.0008802962],"category_scores_gemma":[0.03374569,0.00007679811,0.00005716416,0.00021875383,0.0007483265,0.00013369432,0.00006962869,0.00022930698,0.000086946566],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006099111,0.00009701681,0.006797302,0.000026488282,0.000011261823,0.000006106434,0.0021070256,0.000046132576,0.0011890692,0.88378906,0.00071182655,0.10515773],"study_design_scores_gemma":[0.00032279137,0.0008671292,0.13217837,0.000009130505,0.000028516715,0.000108535685,0.0019098347,0.0056308587,0.0013916505,0.85576737,0.001662645,0.00012318553],"about_ca_topic_score_codex":0.000016872837,"about_ca_topic_score_gemma":0.000008078344,"teacher_disagreement_score":0.12538107,"about_ca_system_score_codex":0.000014543074,"about_ca_system_score_gemma":0.00025621988,"threshold_uncertainty_score":0.9743935},"labels":[],"label_agreement":null},{"id":"W1976093258","doi":"10.3167/ghs.2010.030114","title":"Starting with the Self, Starting with Jackie: The Enduring Memory of Jackie Kirk in our Practices of Reflexivity","year":2010,"lang":"en","type":"article","venue":"Girlhood Studies","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Reflexivity; Psychoanalysis; Psychology; Sociology; Social science","score_opus":0.27154251861738604,"score_gpt":0.5347865802965799,"score_spread":0.26324406167919384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976093258","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98148054,0.0002512154,0.00003640624,0.0141324615,0.00014102469,0.00035899197,0.0000032588337,0.000019872517,0.0035762298],"genre_scores_gemma":[0.99726355,0.00004909152,0.0021448643,0.00023986725,0.000075050884,0.00004040166,3.1737906e-7,0.000009791434,0.0001770508],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9965264,0.00042138682,0.0007309819,0.0003246969,0.0017101028,0.0002863895],"domain_scores_gemma":[0.9944318,0.0020937566,0.0019314506,0.00067006017,0.0008390303,0.00003393053],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011173064,0.00017277936,0.0003994158,0.00012252234,0.00039826168,0.00008175901,0.00057499326,0.000036447753,0.00003435821],"category_scores_gemma":[0.0024366565,0.000070532245,0.000047908106,0.0007210381,0.00020179676,0.000564069,0.00024383157,0.00044629228,0.000010789843],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00059684284,0.0004901568,0.78804094,0.00018429493,0.0006787448,0.000010949528,0.149058,0.004383264,0.01293042,0.0010903154,0.0025982158,0.03993786],"study_design_scores_gemma":[0.0017637186,0.0008264128,0.36395463,0.0002254686,0.00015825526,0.000005967405,0.5991003,0.0024767772,0.02731231,0.0023908261,0.0014221874,0.00036315864],"about_ca_topic_score_codex":0.00010250639,"about_ca_topic_score_gemma":0.0069209826,"teacher_disagreement_score":0.45004228,"about_ca_system_score_codex":0.000027214237,"about_ca_system_score_gemma":0.00027551752,"threshold_uncertainty_score":0.38723832},"labels":[],"label_agreement":null},{"id":"W197622962","doi":"10.3138/cjpe.16.006","title":"Softly, Softly Catch the Monkey: Innovative Approaches to Measure Socially Sensitive and Complex Issues in Evaluation Research","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Respondent; Reliability (semiconductor); Measure (data warehouse); Psychology; Government (linguistics); Focus (optics); Research design; Management science; Knowledge management; Computer science; Data science; Applied psychology; Sociology; Engineering; Political science; Social science; Data mining","score_opus":0.8765369178333454,"score_gpt":0.6071075175501194,"score_spread":0.26942940028322604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W197622962","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91809833,0.00062007055,0.00094201777,0.070605464,0.0003801281,0.004285957,0.000007716958,0.000008821932,0.0050514936],"genre_scores_gemma":[0.99617916,0.000020025389,0.0027245968,0.00041058895,0.00027040558,0.00020735028,0.000017404409,0.000013182778,0.00015727009],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98820215,0.0040938626,0.0010628537,0.00036915942,0.0057772803,0.0004946873],"domain_scores_gemma":[0.985811,0.0008278887,0.00048237285,0.00031635712,0.012195498,0.00036691286],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.089231774,0.00016708636,0.0003221543,0.0014022854,0.00060300704,0.00074123294,0.00050155784,0.00011742711,0.00045551758],"category_scores_gemma":[0.011014511,0.000116640775,0.00005981872,0.0040314095,0.00030309078,0.0006794963,0.00004164402,0.0005415292,0.000052516847],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006695125,0.00005212197,0.03018452,0.000002839743,0.00003278046,0.0000066146067,0.020572351,0.0034838498,0.00008087797,0.0012028335,0.005320245,0.938994],"study_design_scores_gemma":[0.0016550735,0.00080170645,0.731254,0.00010857281,0.00006633645,0.00006573484,0.040650357,0.15855819,0.00009715914,0.037761766,0.028710915,0.00027020014],"about_ca_topic_score_codex":0.0028216436,"about_ca_topic_score_gemma":0.1582799,"teacher_disagreement_score":0.9387238,"about_ca_system_score_codex":0.0010166377,"about_ca_system_score_gemma":0.009901623,"threshold_uncertainty_score":0.9973161},"labels":[],"label_agreement":null},{"id":"W1976259764","doi":"10.4296/cwrj2801021","title":"Drought Contingency Planning and Implementation at the Local Level in Ontario","year":2003,"lang":"en","type":"article","venue":"Canadian Water Resources Journal / Revue canadienne des ressources hydriques","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"Ministry of Natural Resources; U.S. Environmental Protection Agency","keywords":"Watershed; Local government; Environmental planning; Government (linguistics); Contingency plan; Business; Plan (archaeology); Watershed management; Environmental resource management; Agriculture; Contingency; Water resource management; Geography; Public administration; Political science; Environmental science; Management; Economics","score_opus":0.13092347615034444,"score_gpt":0.3655215050458314,"score_spread":0.23459802889548698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976259764","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99153554,0.0010790627,0.00012340439,0.0014441987,0.000247299,0.00026561334,0.000017628841,0.000009096119,0.0052781245],"genre_scores_gemma":[0.9921692,0.00006125458,0.00012766414,0.0006820373,0.00008964043,0.00002111781,0.000013119704,0.000024983432,0.006810999],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962494,0.0007015175,0.0010075714,0.00047615072,0.00048449324,0.001080915],"domain_scores_gemma":[0.9978087,0.00027722894,0.00030561752,0.00038633865,0.00031012288,0.0009119675],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005691592,0.00027910076,0.00036750024,0.000787457,0.0014308967,0.0008218419,0.0006032453,0.000116913296,0.0025303583],"category_scores_gemma":[0.00030346384,0.00017339955,0.00010320429,0.0003682826,0.0003825764,0.00053505495,0.000059639646,0.0005831106,0.00003620498],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022215449,0.0000057464804,0.43559322,0.000007937662,0.000028708891,0.00021208217,0.5478845,0.0017471508,0.0001154548,0.000026182139,0.00013541084,0.014221346],"study_design_scores_gemma":[0.00050834386,0.0001044528,0.11556656,0.00008411977,0.000017427785,0.00092498265,0.01339465,0.0003639445,0.00081109075,0.0032446643,0.86470485,0.00027491074],"about_ca_topic_score_codex":0.6729135,"about_ca_topic_score_gemma":0.99901336,"teacher_disagreement_score":0.8645694,"about_ca_system_score_codex":0.0022952626,"about_ca_system_score_gemma":0.00008369705,"threshold_uncertainty_score":0.9998691},"labels":[],"label_agreement":null},{"id":"W1976829658","doi":"10.1076/ilee.9.2.143.7440","title":"Evaluating Technology-Supported Teaching Learning: A Catalyst to Organizational Change","year":2001,"lang":"en","type":"article","venue":"Interactive Learning Environments","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Knowledge management; Set (abstract data type); Project team; Project-based learning; Engineering management; Engineering; Psychology; Mathematics education","score_opus":0.18165562801650076,"score_gpt":0.49735786050994374,"score_spread":0.315702232493443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976829658","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97967905,0.000014782337,0.008821011,0.0042752717,0.00025938623,0.00038963987,0.0000021950566,0.00010961278,0.006449068],"genre_scores_gemma":[0.971004,0.000008370412,0.001968496,0.0006236158,0.00013988612,0.000101896316,0.000052619132,0.000032640477,0.026068456],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99597144,0.0005795118,0.0005780818,0.00068036176,0.0018313022,0.00035932555],"domain_scores_gemma":[0.99836075,0.0005675652,0.00044835836,0.0003583964,0.00012287802,0.0001420647],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003046146,0.00021784901,0.00025637844,0.0006904518,0.0005746767,0.00018573698,0.0005338892,0.000102981234,0.0061732195],"category_scores_gemma":[0.0065626637,0.00019079635,0.00006501253,0.0008063907,0.000056070254,0.00074221316,0.00036734625,0.00092462316,0.006162769],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007388927,0.0001785043,0.7262171,0.0000014557992,0.000059123427,0.000016268552,0.0065354155,0.01634869,0.03142358,0.00009087177,0.00044856372,0.21860653],"study_design_scores_gemma":[0.0011011594,0.0009398934,0.38499764,0.00009245528,0.00004250183,0.00007257229,0.0113878455,0.053460974,0.0034067559,0.0008571953,0.5430303,0.00061065814],"about_ca_topic_score_codex":0.000026229256,"about_ca_topic_score_gemma":0.000009367313,"teacher_disagreement_score":0.5425818,"about_ca_system_score_codex":0.00031600107,"about_ca_system_score_gemma":0.00004979696,"threshold_uncertainty_score":0.9947353},"labels":[],"label_agreement":null},{"id":"W1977156883","doi":"10.5130/ijcre.v7i1.3395","title":"Engaging evaluation research: Reflecting on the process of sexual assault/domestic violence protocol evaluation research","year":2014,"lang":"en","type":"article","venue":"Gateways International Journal of Community Research and Engagement","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"General partnership; Scholarship; Sociology; Sexual assault; Theme (computing); Community engagement; Domestic violence; Protocol (science); Engaged scholarship; Public relations; Community-based participatory research; Psychology; Participatory action research; Poison control; Human factors and ergonomics; Political science; Medicine; Computer science","score_opus":0.8815832168568917,"score_gpt":0.7376941228375049,"score_spread":0.14388909401938677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977156883","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9685056,0.00003158541,0.00039075868,0.005759019,0.00023791046,0.010455622,0.0000041674925,0.0000069933994,0.014608337],"genre_scores_gemma":[0.9953633,0.000038231814,0.00020180971,0.000083808256,0.00028304875,0.003919999,0.0000068318222,0.00001264385,0.0000903184],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8719662,0.088403106,0.0017500345,0.00034440338,0.03684025,0.0006960202],"domain_scores_gemma":[0.923584,0.033780526,0.00065366516,0.0008506818,0.040944584,0.00018655107],"candidate_categories":["metaresearch","sts","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6078596,0.00014594237,0.0002642212,0.0020171835,0.002983216,0.00073031045,0.0028544033,0.000087214255,0.0007763185],"category_scores_gemma":[0.11400509,0.000091873924,0.000051842144,0.0015866521,0.00075098424,0.0006434149,0.00077587436,0.0063212,0.000049290626],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001592303,0.0015112248,0.004757839,0.000120257224,0.0002038946,0.0000040630025,0.031149741,0.011520485,0.008398678,0.010037079,0.006098957,0.9246055],"study_design_scores_gemma":[0.0049946834,0.008075362,0.03215668,0.0015605163,0.000033938926,0.000042821408,0.19257016,0.14483094,0.014228854,0.59132314,0.009906497,0.00027642853],"about_ca_topic_score_codex":0.00014445436,"about_ca_topic_score_gemma":0.000107030086,"teacher_disagreement_score":0.92432904,"about_ca_system_score_codex":0.000630668,"about_ca_system_score_gemma":0.0015325944,"threshold_uncertainty_score":0.99831474},"labels":[],"label_agreement":null},{"id":"W1977740368","doi":"10.7202/900717ar","title":"Un plan de carrière pour les enseignants :l’expérience américaine","year":2009,"lang":"fr","type":"article","venue":"Revue des sciences de l éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Carrion; Humanities; Art; Political science; Biology","score_opus":0.6055411861049815,"score_gpt":0.5154141452797969,"score_spread":0.09012704082518463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977740368","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92672795,0.0030192463,0.019583758,0.02543984,0.0014184883,0.00027832104,0.000017379029,0.000052436968,0.023462601],"genre_scores_gemma":[0.9611456,0.0009440704,0.025828436,0.0012814236,0.0005068332,0.000017337123,0.000007499801,0.000008328447,0.010260487],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99581164,0.00072095176,0.0007192989,0.00073278265,0.0011861876,0.0008291259],"domain_scores_gemma":[0.99760956,0.00063244964,0.0004389833,0.0004842036,0.0004975815,0.000337254],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0080713825,0.00025367682,0.00028644913,0.00035975804,0.0016140722,0.00066649204,0.0012094119,0.00017499304,0.0019661423],"category_scores_gemma":[0.0019057782,0.00022677296,0.00012234565,0.0022004594,0.0011129479,0.0013483299,0.000059161557,0.000250583,0.0006528925],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022086031,0.00048642498,0.052228417,0.0000625077,0.000011437732,0.000024211797,0.10240684,0.01109734,0.0039157923,0.041429754,0.006214321,0.78210086],"study_design_scores_gemma":[0.0005774284,0.0011292578,0.39301628,0.0006994419,0.00007223827,0.0008748709,0.060354996,0.32786104,0.003910434,0.18561545,0.025097165,0.0007913843],"about_ca_topic_score_codex":0.00037173816,"about_ca_topic_score_gemma":0.00028860715,"teacher_disagreement_score":0.7813095,"about_ca_system_score_codex":0.0010154519,"about_ca_system_score_gemma":0.0029584817,"threshold_uncertainty_score":0.9996857},"labels":[],"label_agreement":null},{"id":"W1977960824","doi":"10.1016/j.evalprogplan.2014.04.003","title":"Taking stock of four decades of quantitative research on stakeholder participation and evaluation use: A systematic map","year":2014,"lang":"en","type":"review","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":33,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ministry of Labour, Employment and Social Solidarity","funders":"","keywords":"Stakeholder; Stock (firearms); Stakeholder engagement; Stakeholder analysis; Environmental planning; Business; Environmental resource management; Geography; Political science; Environmental science; Public relations; Archaeology","score_opus":0.9237604363882755,"score_gpt":0.7285006439353664,"score_spread":0.19525979245290914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977960824","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023071304,0.96526396,0.00080074405,0.00006319011,0.00026833685,0.009801521,0.00002095147,0.000029457215,0.000680513],"genre_scores_gemma":[0.6417393,0.34407473,0.007533412,0.00004231188,0.000150695,0.005765997,0.00032544858,0.00008691047,0.0002812028],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9795019,0.010037118,0.0024337198,0.0007033616,0.007007329,0.00031656332],"domain_scores_gemma":[0.9822555,0.01027158,0.0030675025,0.00054332876,0.0037525916,0.0001094722],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0759058,0.0003095739,0.0015842564,0.0013606582,0.00028108776,0.00042127052,0.00028033357,0.00024635863,0.00021592421],"category_scores_gemma":[0.015474351,0.00021506031,0.00014398819,0.0012187039,0.00019229874,0.00046487772,0.000090378,0.00038501495,0.00002382339],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031918087,0.0000818664,0.0007044342,0.028520126,0.00011076365,2.9086834e-7,0.0023368758,0.0008881291,0.0000011554752,0.001386885,0.00012057815,0.965817],"study_design_scores_gemma":[0.0019669274,0.003030404,0.010977639,0.22636166,0.0030038722,0.000010988403,0.0046628374,0.7026354,0.000011465294,0.0033876577,0.04319855,0.0007526116],"about_ca_topic_score_codex":0.000016676016,"about_ca_topic_score_gemma":0.000018185847,"teacher_disagreement_score":0.96506435,"about_ca_system_score_codex":0.00013199577,"about_ca_system_score_gemma":0.00067683065,"threshold_uncertainty_score":0.9928187},"labels":[{"model":"gemma","categories":["metaresearch","bibliometrics"],"domain":"evaluation","study_design":"systematic_review","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":[],"domain":null,"study_design":"systematic_review","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W1978303279","doi":"10.1002/ev.382","title":"Integrating a new evaluation unit with an old institution: See no evil; hear no evil; speak no evil","year":2011,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Unit (ring theory); CLARITY; Institution; Evaluation methods; Association (psychology); Psychology; Sociology; Computer science; Mathematics education; Social science; Engineering; Psychotherapist","score_opus":0.39098050530506484,"score_gpt":0.5034779046174458,"score_spread":0.11249739931238095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978303279","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35947865,0.0008401606,0.122312106,0.0025218362,0.012616978,0.013830661,0.00009228828,0.0009065377,0.48740077],"genre_scores_gemma":[0.83747685,0.00017748134,0.09508414,0.0013198295,0.004451561,0.0017989994,0.00082730677,0.00014432208,0.05871948],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99045914,0.0012412453,0.0014722667,0.0011885612,0.0050962465,0.0005425385],"domain_scores_gemma":[0.9869133,0.0006028721,0.0008953673,0.0012966604,0.009825579,0.00046619197],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.017360294,0.00048490812,0.0005230155,0.0008294718,0.0011495486,0.0005766048,0.0006473174,0.00024707674,0.022103969],"category_scores_gemma":[0.008323997,0.00038155567,0.00023837572,0.0021613336,0.00013011084,0.003536137,0.00007265158,0.00038371966,0.004990346],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015569028,0.00081251696,0.012331729,0.0000509591,0.0002271055,0.0000010925879,0.0073950593,0.012334615,0.0012205209,0.00660834,0.051664777,0.9057964],"study_design_scores_gemma":[0.006232469,0.0028454147,0.038905386,0.000318862,0.00068989,0.000027631837,0.001579132,0.73067474,0.00071280624,0.009590889,0.20760496,0.00081778626],"about_ca_topic_score_codex":0.0017020858,"about_ca_topic_score_gemma":0.00627782,"teacher_disagreement_score":0.9049786,"about_ca_system_score_codex":0.00078441214,"about_ca_system_score_gemma":0.0047859726,"threshold_uncertainty_score":0.9998636},"labels":[],"label_agreement":null},{"id":"W1978537098","doi":"10.7202/900371ar","title":"La pratique de l’évaluation des enseignants au Nouveau-Brunswick, au Québec et en Ontario","year":2009,"lang":"fr","type":"article","venue":"Revue des sciences de l éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Political science; Humanities; Art","score_opus":0.47628197168330144,"score_gpt":0.5050913986793818,"score_spread":0.028809426996080356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978537098","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91481805,0.000592555,0.024406033,0.013512385,0.0010620708,0.00040663092,0.0000039130337,0.00003931236,0.045159075],"genre_scores_gemma":[0.941904,0.00038594956,0.031253215,0.0013038488,0.00030676418,0.00003172184,0.000012399924,0.000011666286,0.024790436],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99338275,0.0029164194,0.0008706072,0.00072549557,0.0012834544,0.00082128914],"domain_scores_gemma":[0.99642265,0.0016282164,0.0005149678,0.00047638195,0.0006425471,0.0003152484],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02810724,0.0002980387,0.00031799698,0.00043277413,0.0017022627,0.00084505626,0.0008693641,0.00029004863,0.0010621189],"category_scores_gemma":[0.0036573014,0.00027437165,0.00014659275,0.0014874013,0.0013713259,0.0024887635,0.000060997303,0.0004199711,0.00049157836],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000015412512,0.0002892066,0.13555562,0.000041275365,0.000009004416,0.0000037878224,0.5601218,0.009445577,0.00073941046,0.014683022,0.00039617228,0.2786997],"study_design_scores_gemma":[0.00033788627,0.000726752,0.8495186,0.0005343736,0.000065994194,0.00027043367,0.02624101,0.048020545,0.00072182476,0.05337043,0.019787075,0.00040510515],"about_ca_topic_score_codex":0.5151171,"about_ca_topic_score_gemma":0.9491042,"teacher_disagreement_score":0.7139629,"about_ca_system_score_codex":0.018276459,"about_ca_system_score_gemma":0.118665904,"threshold_uncertainty_score":0.99997085},"labels":[],"label_agreement":null},{"id":"W1978602095","doi":"10.7202/1024963ar","title":"L’évaluation dans la formation supérieure et professionnelle","year":2014,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Valuation (finance); Political science; Humanities; Economics; Art; Finance","score_opus":0.21182207873160477,"score_gpt":0.5085262752061539,"score_spread":0.29670419647454915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978602095","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32155094,0.00047679772,0.44958413,0.13165036,0.008639714,0.001895587,0.00003398739,0.00018537906,0.08598313],"genre_scores_gemma":[0.9514424,0.00045013783,0.008474079,0.0021567666,0.000569606,0.0002733314,0.00089973904,0.000061584244,0.03567234],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.95463103,0.037100546,0.0020375364,0.0009979659,0.004650094,0.000582855],"domain_scores_gemma":[0.99003434,0.00536896,0.0012227792,0.0010810031,0.0020808054,0.00021212934],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.12899771,0.00050643785,0.0005075576,0.00066421967,0.00066664984,0.00080136163,0.00064605934,0.0005936766,0.0054950616],"category_scores_gemma":[0.010583425,0.00046601924,0.0002388641,0.0014766409,0.00016933172,0.004883768,0.00013860845,0.0007182358,0.0034638494],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008196907,0.0008640182,0.008150639,0.00023042348,0.00005888585,8.5306135e-7,0.48148477,0.04435128,0.003018078,0.09312216,0.06286986,0.30576703],"study_design_scores_gemma":[0.0016151541,0.0002596313,0.33912322,0.000406878,0.00017882462,0.000035337634,0.018825246,0.47127497,0.0012695038,0.043142863,0.123286255,0.0005821091],"about_ca_topic_score_codex":0.00015128517,"about_ca_topic_score_gemma":0.0013311426,"teacher_disagreement_score":0.6298915,"about_ca_system_score_codex":0.00081578264,"about_ca_system_score_gemma":0.004199753,"threshold_uncertainty_score":0.99977916},"labels":[],"label_agreement":null},{"id":"W1979608959","doi":"10.3138/cjpe.29.2.139","title":"Spaulding, D. T. (2014). <i>Program evaluation in practice: Core concepts and examples for discussion and analysis</i> (2nd ed.).","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Core (optical fiber); Psychology; Mathematics education; Computer science","score_opus":0.2714138296030427,"score_gpt":0.5558037051431876,"score_spread":0.28438987554014483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979608959","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9661616,0.0034715976,0.011605441,0.007847168,0.0010292192,0.008220849,0.00003058286,0.00002472461,0.001608794],"genre_scores_gemma":[0.97878826,0.00009819929,0.020119544,0.000251818,0.00017433672,0.00042654114,0.00007788916,0.000013101706,0.000050296927],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.994524,0.0011773442,0.0011836445,0.00043015394,0.0023244682,0.00036041636],"domain_scores_gemma":[0.993229,0.0010944162,0.001176424,0.00031348414,0.0036629539,0.0005237334],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.042265426,0.00019192029,0.00044502097,0.0012120293,0.00029713917,0.00072891515,0.00026422937,0.00013661858,0.00055432075],"category_scores_gemma":[0.011375988,0.00012838865,0.0001245657,0.001012731,0.00017771173,0.0011796054,0.000021765507,0.00021727465,0.0000063646926],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004308046,0.000055845776,0.08831149,0.000007713578,0.000072309456,8.390016e-7,0.0010471055,0.0020229013,0.000024324387,0.0004657226,0.0017812314,0.90616745],"study_design_scores_gemma":[0.002667191,0.0011391591,0.24509616,0.00006521647,0.0012005612,0.00002909034,0.0028438873,0.5725437,0.000018043345,0.0089121265,0.16526063,0.00022422647],"about_ca_topic_score_codex":0.00051015744,"about_ca_topic_score_gemma":0.028923646,"teacher_disagreement_score":0.9059432,"about_ca_system_score_codex":0.0002949724,"about_ca_system_score_gemma":0.0019195237,"threshold_uncertainty_score":0.99695164},"labels":[],"label_agreement":null},{"id":"W1983302984","doi":"10.1016/j.evalprogplan.2004.04.004","title":"How was the UNAIDS drug access initiative implemented in Chile?","year":2004,"lang":"en","type":"article","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Douglas College","funders":"Canadian Institutes of Health Research; U.S. Public Health Service; UNICEF; World Bank Group","keywords":"Context (archaeology); Human immunodeficiency virus (HIV); Political science; Program evaluation; Process (computing); Public relations; Economic growth; Business; Public administration; Medicine; Computer science; Geography; Family medicine; Economics","score_opus":0.3930404716333926,"score_gpt":0.5941593581888461,"score_spread":0.2011188865554535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1983302984","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9637114,0.0005862005,0.001302478,0.024388397,0.00028766243,0.0017314124,0.0000074881427,0.00005979448,0.007925157],"genre_scores_gemma":[0.9977231,0.000025983241,0.000752788,0.0009096064,0.00007050601,0.00031888287,0.0000495919,0.0000066714815,0.00014285406],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9964647,0.0005754645,0.00044918517,0.0003456418,0.0019162822,0.0002487025],"domain_scores_gemma":[0.9984915,0.000500495,0.00025670195,0.00025762545,0.0004251318,0.00006850809],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.011018866,0.00013733981,0.00017048903,0.00027590303,0.0003344113,0.0013103691,0.00039143892,0.000040776104,0.0004077967],"category_scores_gemma":[0.0011331722,0.000083124876,0.000042107127,0.0010308461,0.00007933587,0.0010530015,0.00011481833,0.00020615489,0.00002270683],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046981688,0.0001228848,0.19697373,0.000006288622,0.00002581758,0.0000027046995,0.016689029,0.007887333,0.000026992948,0.0026093076,0.0014402098,0.7741687],"study_design_scores_gemma":[0.0037680797,0.00022648797,0.8257657,0.000120852565,0.000038952472,0.000008583786,0.019249517,0.06819779,0.00042392808,0.0473438,0.034561556,0.00029475012],"about_ca_topic_score_codex":0.000034208984,"about_ca_topic_score_gemma":0.00024113282,"teacher_disagreement_score":0.773874,"about_ca_system_score_codex":0.000085912594,"about_ca_system_score_gemma":0.00030215236,"threshold_uncertainty_score":0.99972636},"labels":[],"label_agreement":null},{"id":"W1986224130","doi":"10.1002/ev.133","title":"Background and history of the Joint Committee's Program Evaluation Standards","year":2004,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Joint (building); Context (archaeology); Political science; Library science; Engineering ethics; Computer science; Engineering; History; Archaeology; Civil engineering","score_opus":0.3548191126107928,"score_gpt":0.5240969201650518,"score_spread":0.16927780755425903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986224130","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86351424,0.00509544,0.031235427,0.013740216,0.009536527,0.01705874,0.000098494245,0.00019509274,0.059525814],"genre_scores_gemma":[0.9904878,0.000048853803,0.004656688,0.0001779834,0.0001726649,0.0010214078,0.000029634204,0.000015389442,0.0033895394],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99416995,0.00046323636,0.0006914855,0.0003459838,0.0041742073,0.000155136],"domain_scores_gemma":[0.99522215,0.0002799276,0.00047953267,0.0005274784,0.0034167278,0.00007418441],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01762353,0.00012710881,0.00020121313,0.000237916,0.0002751182,0.00009502291,0.00020820252,0.00007783092,0.0011565782],"category_scores_gemma":[0.003021478,0.00008801436,0.00014460852,0.00056353275,0.00014282974,0.00047172073,0.00004642344,0.00010403926,0.000012890381],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042603806,0.00017343486,0.0010507968,0.000010696426,0.000031497657,1.31522855e-8,0.0017770802,0.007806424,0.00068231864,0.003472627,0.032583088,0.9523694],"study_design_scores_gemma":[0.006239746,0.0005079239,0.13986789,0.00007369381,0.0004004885,0.0000068044133,0.0013747902,0.13020828,0.0015595215,0.10205649,0.617464,0.00024040656],"about_ca_topic_score_codex":0.00018356238,"about_ca_topic_score_gemma":0.0010729159,"teacher_disagreement_score":0.952129,"about_ca_system_score_codex":0.0021885536,"about_ca_system_score_gemma":0.0046141264,"threshold_uncertainty_score":0.9997565},"labels":[],"label_agreement":null},{"id":"W1986767263","doi":"10.1111/j.1552-6356.2005.tb00796.x","title":"From Paper to Practice Change","year":2005,"lang":"en","type":"article","venue":"AWHONN Lifelines","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"CancerCare Manitoba","funders":"","keywords":"Business; Computer science","score_opus":0.348585282103451,"score_gpt":0.5630503638802744,"score_spread":0.21446508177682339,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986767263","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32366613,0.0010675981,0.004957107,0.65115327,0.010872404,0.00080869737,0.00009501748,0.00020113777,0.0071786707],"genre_scores_gemma":[0.66483825,0.00010234149,0.042635657,0.07278422,0.21284552,0.00010304036,0.000020842968,0.000016969909,0.0066531515],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99736434,0.0001553034,0.0005079641,0.00036681528,0.0014091644,0.0001963888],"domain_scores_gemma":[0.9972452,0.0012434305,0.0001499417,0.00056398776,0.00063142565,0.000165995],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00213042,0.00011547847,0.0001682966,0.00013546925,0.00011306482,0.00021553102,0.00045736603,0.000052291776,0.00078391336],"category_scores_gemma":[0.0041872463,0.00008065731,0.000058249432,0.0005134202,0.000018937464,0.0016201931,0.00011365347,0.000087031556,0.017065406],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052868425,0.000111018635,0.0052978336,6.703136e-7,0.000015440093,0.0000023983996,0.0050837933,0.00029461202,0.0006294468,0.000078898294,0.46670035,0.5217327],"study_design_scores_gemma":[0.00020984103,0.000041073472,0.0136887105,0.000008033189,0.000010145342,0.000001981038,0.0015023398,0.0025008272,0.0002758534,0.0010818766,0.98055667,0.00012263583],"about_ca_topic_score_codex":0.00025782536,"about_ca_topic_score_gemma":0.0004710066,"teacher_disagreement_score":0.578369,"about_ca_system_score_codex":0.00002765313,"about_ca_system_score_gemma":0.000072636445,"threshold_uncertainty_score":0.9836999},"labels":[],"label_agreement":null},{"id":"W1987011032","doi":"10.1017/s1463423607000072","title":"Does discourse matter? Using critical inquiry to engage in knowledge development for practice","year":2007,"lang":"en","type":"article","venue":"Primary Health Care Research & Development","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Canadian Health Services Research Foundation; Canadian Nurses Foundation","keywords":"Converse; Context (archaeology); Scholarship; Health care; Sociology; Critical discourse analysis; Public relations; Critical practice; Epistemology; Political science; Social science; Politics; Law","score_opus":0.43840351733486843,"score_gpt":0.6697416131807675,"score_spread":0.2313380958458991,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987011032","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62483597,0.0043511284,0.22551768,0.10469497,0.005963757,0.011008625,0.000038592167,0.00014721061,0.023442054],"genre_scores_gemma":[0.48688024,0.00008378615,0.5016324,0.009392315,0.00034884101,0.0006411736,0.0000578699,0.000056170287,0.00090719876],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9891491,0.0015255272,0.0020462284,0.0010494139,0.00441764,0.001812077],"domain_scores_gemma":[0.9860671,0.009230186,0.00018692361,0.00058858114,0.003016294,0.0009108933],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.07353392,0.00026740786,0.0004962746,0.0016570708,0.0013304469,0.0003234377,0.0008532471,0.000117919386,0.00030974386],"category_scores_gemma":[0.007563329,0.0001802874,0.00005771745,0.001791682,0.00017088205,0.00075039605,0.0007238679,0.00071194366,0.00075511856],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.0005747928,0.00064496417,0.013055081,0.0006452816,0.000022441229,0.000025179337,0.16702437,0.0000685106,0.00014418332,0.0007028951,0.018080039,0.79901224],"study_design_scores_gemma":[0.0007759606,0.00018320471,0.15235499,0.00028346563,0.0000027548658,0.0000069797193,0.062780626,0.00010328637,0.0010717802,0.0002462115,0.7818094,0.0003813422],"about_ca_topic_score_codex":0.000063558226,"about_ca_topic_score_gemma":0.0014693477,"teacher_disagreement_score":0.7986309,"about_ca_system_score_codex":0.0062272,"about_ca_system_score_gemma":0.017239837,"threshold_uncertainty_score":0.99996966},"labels":[],"label_agreement":null},{"id":"W1988375386","doi":"10.1016/j.healthpol.2009.02.006","title":"Overcoming barriers to priority setting using interdisciplinary methods","year":2009,"lang":"en","type":"article","venue":"Health Policy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":94,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Fraser Health; Child and Family Research Institute; Okanagan University College; University of British Columbia, Okanagan Campus; University of British Columbia; BC Cancer Agency","funders":"Economic and Social Research Council; National Institute for Health and Care Research","keywords":"Management science; Engineering ethics; Sociology; Psychology; Computer science; Engineering","score_opus":0.2925853698660447,"score_gpt":0.675866110525475,"score_spread":0.38328074065943024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1988375386","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49070272,0.000151228,0.16023743,0.32830113,0.0010166203,0.00088869774,0.000016415353,0.00013387267,0.018551901],"genre_scores_gemma":[0.75493467,0.000007766553,0.187794,0.0562617,0.0005532183,0.000004997013,0.0000013459529,0.00000937651,0.00043290923],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964993,0.0008748103,0.0008342379,0.00038531897,0.0008818749,0.0005244492],"domain_scores_gemma":[0.9977547,0.00048759254,0.00029400017,0.00049944216,0.00016234763,0.0008019012],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012772005,0.00013336178,0.0003034614,0.00058147,0.00077826466,0.0001621136,0.00039193357,0.000053035586,0.00040538708],"category_scores_gemma":[0.0033929918,0.000108680775,0.000081554295,0.0012689576,0.000024095769,0.00036439113,0.00025051515,0.00019667645,0.000116542804],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002419828,0.000020288351,0.0036607292,0.000010567767,0.0000036736735,0.0000010399826,0.017604012,0.0015727214,0.00069669733,0.0044479393,0.0067553683,0.96520275],"study_design_scores_gemma":[0.0014039099,0.001227234,0.26064888,0.0003151239,0.000014100488,0.00006393594,0.015874228,0.24047056,0.0010719959,0.12748954,0.3505004,0.0009201094],"about_ca_topic_score_codex":0.00024490058,"about_ca_topic_score_gemma":0.000050691815,"teacher_disagreement_score":0.96428263,"about_ca_system_score_codex":0.0005437818,"about_ca_system_score_gemma":0.0025567508,"threshold_uncertainty_score":0.59858614},"labels":[],"label_agreement":null},{"id":"W1989835141","doi":"10.1177/1098214009349865","title":"A Review and Synthesis of Current Research on Cross-Cultural Evaluation","year":2009,"lang":"en","type":"review","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":91,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Construct (python library); Context (archaeology); Indigenous; Sociology; Empirical research; Management science; Knowledge management; Engineering ethics; Epistemology; Computer science; Ecology","score_opus":0.7361957222054291,"score_gpt":0.7346471200265722,"score_spread":0.0015486021788568838,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1989835141","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006474273,0.99580795,0.000023927025,0.00040834807,0.0003158376,0.0014421426,0.000015109212,0.0000030890442,0.0013361668],"genre_scores_gemma":[0.0037736408,0.9955565,0.00018416313,0.000104879124,0.00022217826,0.00010277998,0.000015173022,0.000015455222,0.000025268659],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.974152,0.010589377,0.0034207408,0.000498248,0.011056174,0.00028344482],"domain_scores_gemma":[0.9716466,0.005050879,0.006201261,0.0006613212,0.016266141,0.00017378197],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.119118944,0.00031750574,0.0023654136,0.001395263,0.00017104753,0.000255148,0.00070117053,0.00008867722,0.0009152797],"category_scores_gemma":[0.030492466,0.00018881568,0.00056124775,0.0025435768,0.0005078126,0.0006769135,0.00006806621,0.0007822441,0.00009445599],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018082517,0.0001043053,0.0000175072,0.0011218422,0.00005718975,3.051532e-7,0.00007649527,0.000053970612,2.7859338e-7,0.000068130015,0.0031394823,0.99534243],"study_design_scores_gemma":[0.00060135114,0.0021459023,0.001269944,0.067504644,0.0044620824,0.00011218164,0.00035773753,0.0013266862,0.0000042626402,0.0023553323,0.91949034,0.00036950945],"about_ca_topic_score_codex":0.0000047880785,"about_ca_topic_score_gemma":0.0000028743723,"teacher_disagreement_score":0.9949729,"about_ca_system_score_codex":0.0006106913,"about_ca_system_score_gemma":0.0033277047,"threshold_uncertainty_score":0.99999803},"labels":[],"label_agreement":null},{"id":"W1990626823","doi":"10.1002/jid.1057","title":"Donor participatory governance evaluation: initial trends, implications, opportunities, constraints","year":2004,"lang":"en","type":"article","venue":"Journal of International Development","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"International Development Research Centre","keywords":"Citizen journalism; Corporate governance; Politics; Power (physics); Participatory evaluation; Political science; Public administration; Participatory development; Good governance; Quality (philosophy); Sociology; Economics; Management; Law","score_opus":0.5032255939483171,"score_gpt":0.5302268788801364,"score_spread":0.027001284931819303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1990626823","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7978292,0.0006404669,0.016908547,0.06255027,0.0070936815,0.0003425505,0.00007123202,0.000030401465,0.114533626],"genre_scores_gemma":[0.98978746,0.00010671026,0.0075355056,0.001157955,0.00032079977,0.000026977556,0.000019874404,0.00000745399,0.0010372463],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99407816,0.00013566043,0.0016696886,0.00020336968,0.0037342776,0.00017881686],"domain_scores_gemma":[0.99503285,0.00020835601,0.001326039,0.00021063413,0.003043299,0.00017885448],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006673703,0.00013947616,0.00023051517,0.00038488416,0.00014370744,0.00020544814,0.0007838786,0.00005259429,0.00923883],"category_scores_gemma":[0.0009775374,0.00010731745,0.00011897806,0.00029110673,0.00011381686,0.000813683,0.00007789711,0.00017582803,0.00016681051],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007978335,0.0002882074,0.014064585,0.0000022835063,0.0001750954,0.000022124848,0.0017221746,0.0033150509,0.00012547552,0.020929402,0.011259869,0.9480159],"study_design_scores_gemma":[0.0025251154,0.00009623295,0.5916747,0.000089566136,0.000029305707,0.00022810284,0.0010094951,0.00033165814,0.0013882047,0.009017242,0.3933878,0.00022258074],"about_ca_topic_score_codex":0.0000030102078,"about_ca_topic_score_gemma":0.000029550116,"teacher_disagreement_score":0.94779336,"about_ca_system_score_codex":0.00085870654,"about_ca_system_score_gemma":0.003796501,"threshold_uncertainty_score":0.99166685},"labels":[],"label_agreement":null},{"id":"W1990863981","doi":"10.7202/018966ar","title":"Évolution de la fonction de l’évaluation formative des apprentissages à travers le discours ministériel québécois entre 1981 et 2002","year":2008,"lang":"fr","type":"article","venue":"Revue des sciences de l éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université du Québec en Abitibi-Témiscamingue; Université Laval","funders":"","keywords":"Political science; Humanities; Philosophy","score_opus":0.4189993060300545,"score_gpt":0.4987226851785737,"score_spread":0.07972337914851924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1990863981","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.797605,0.0015047552,0.15376784,0.006541557,0.0012330534,0.00038847432,0.000022994578,0.000051046114,0.038885314],"genre_scores_gemma":[0.95590746,0.003826014,0.024860874,0.00030412222,0.0002653129,0.00008693797,0.00003425161,0.000015782034,0.014699224],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99446136,0.0023925127,0.0006764431,0.00057773385,0.0011820319,0.00070994004],"domain_scores_gemma":[0.9970624,0.0012940336,0.00059116347,0.00032067928,0.0004754006,0.0002563129],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":["sts"],"category_scores_codex":[0.01229809,0.00027468696,0.00027007243,0.0004596443,0.0023418842,0.00057772966,0.00055663363,0.00023423007,0.0008970211],"category_scores_gemma":[0.0020667708,0.00027214087,0.00016053746,0.001667457,0.004020237,0.0030455347,0.000053258787,0.00028407932,0.00022877999],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058077618,0.0008432362,0.037989628,0.00020444716,0.00004568069,0.000007673269,0.4894974,0.06656152,0.0029073376,0.040522132,0.010636929,0.35072595],"study_design_scores_gemma":[0.0008993247,0.00060887414,0.29487795,0.0005286276,0.00013337682,0.00088889315,0.13249472,0.47478002,0.0028731,0.072332926,0.018996224,0.00058595993],"about_ca_topic_score_codex":0.007705256,"about_ca_topic_score_gemma":0.009989349,"teacher_disagreement_score":0.4082185,"about_ca_system_score_codex":0.0028534052,"about_ca_system_score_gemma":0.009228143,"threshold_uncertainty_score":0.99997306},"labels":[],"label_agreement":null},{"id":"W1991275501","doi":"10.1017/s0003055402294319","title":"Making Social Science Matter: Why Social Inquiry Fails and How It Can Succeed Again. By Bent Flyvbjerg. Cambridge: Cambridge University Press, 2001. 201p. $54.95 cloth, $19.95 paper.","year":2002,"lang":"en","type":"article","venue":"American Political Science Review","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Silence; Quarter (Canadian coin); Norm (philosophy); Bent molecular geometry; Politics; Similarity (geometry); Political science; Sociology; Social science; History; Aesthetics; Law; Philosophy; Engineering; Archaeology; Computer science","score_opus":0.1700335627941907,"score_gpt":0.44300536854702993,"score_spread":0.2729718057528392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991275501","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12421353,0.023066433,0.0012854486,0.7083585,0.0014333002,0.0030945973,0.00054441026,0.0002920649,0.13771172],"genre_scores_gemma":[0.93971044,0.015086114,0.0002907466,0.04283234,0.0002940981,0.000017657578,0.0000067742926,0.00001878517,0.0017430175],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9904892,0.00061904243,0.0007300148,0.0014701982,0.004464507,0.002227038],"domain_scores_gemma":[0.99625295,0.0004811933,0.0006179125,0.00065307785,0.0007797171,0.0012151691],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":["sts"],"category_scores_codex":[0.0073719113,0.00040535477,0.000894771,0.00022713923,0.0024053187,0.0014040048,0.0022883096,0.000070822294,0.00078926847],"category_scores_gemma":[0.0018444685,0.0003313205,0.00020366343,0.0042532454,0.011908876,0.0029439668,0.0007713979,0.00037911485,0.00020746284],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000064241603,0.00009719628,0.0025177998,0.00010428546,0.000009621011,0.000009266061,0.0003675847,4.969544e-7,0.00044541416,0.044460155,0.9085165,0.04346522],"study_design_scores_gemma":[0.00044016563,0.00016465805,0.041866444,0.0002972649,0.000095017196,0.000041546173,0.0047895163,0.0015570441,0.00007220287,0.00006839163,0.9497967,0.00081109104],"about_ca_topic_score_codex":0.0019672874,"about_ca_topic_score_gemma":0.00005030923,"teacher_disagreement_score":0.8154969,"about_ca_system_score_codex":0.0010886218,"about_ca_system_score_gemma":0.0010542644,"threshold_uncertainty_score":0.9999139},"labels":[],"label_agreement":null},{"id":"W1991424569","doi":"10.1108/14777261211256963","title":"Using evaluation theory in priority setting and resource allocation","year":2012,"lang":"en","type":"article","venue":"Journal of Health Organization and Management","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; University of Toronto; Okanagan University College; Vancouver Coastal Health; Vancouver Coastal Health Research Institute; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"","keywords":"Management science; Context (archaeology); Process (computing); Computer science; Resource allocation; sort; Value (mathematics); Process management; Resource (disambiguation); Originality; Sociology; Economics; Business; Qualitative research","score_opus":0.19434294702859267,"score_gpt":0.5097530536520627,"score_spread":0.31541010662347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991424569","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91070265,0.002535213,0.077214524,0.0074891928,0.00039919972,0.00058145815,4.7413994e-7,0.000007694005,0.0010696027],"genre_scores_gemma":[0.99304175,0.0005742797,0.005184474,0.0010660824,0.000068517984,8.9728996e-7,0.0000020462696,0.00000516841,0.00005679486],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9973935,0.0007212076,0.0007465019,0.000096946016,0.0009126072,0.00012923004],"domain_scores_gemma":[0.998639,0.00013429014,0.0006765499,0.00009425233,0.00037306466,0.00008285791],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.028248953,0.00005808857,0.00013871872,0.0003589149,0.00015490894,0.00008364509,0.000074111456,0.00002407028,0.00012891578],"category_scores_gemma":[0.0007229337,0.00004514474,0.0000096588465,0.00055443624,0.000016144604,0.0005923463,0.000054441356,0.00007334199,0.0000030186395],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023350514,0.0001178626,0.2763366,0.00008064521,0.00001820301,5.395579e-7,0.007912126,0.0017092121,0.00007303007,0.026036223,0.0010375069,0.6866547],"study_design_scores_gemma":[0.0011829127,0.00006645657,0.95084745,0.00008584021,0.00003480589,0.000035556288,0.009031809,0.01625412,0.00004480436,0.004237474,0.01808043,0.00009836376],"about_ca_topic_score_codex":0.0000030410945,"about_ca_topic_score_gemma":0.0000040317213,"teacher_disagreement_score":0.68655634,"about_ca_system_score_codex":0.00016837195,"about_ca_system_score_gemma":0.00013147829,"threshold_uncertainty_score":0.97905797},"labels":[],"label_agreement":null},{"id":"W1992053221","doi":"10.1002/ev.325","title":"Enhancing disaster and emergency preparedness, response, and recovery through evaluation","year":2010,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Social Sciences and Humanities Research Council","funders":"","keywords":"Preparedness; Disaster response; Emergency management; Disaster preparedness; Emergency response; Process management; Evaluation methods; Disaster recovery; Disaster planning; Computer science; Business; Risk analysis (engineering); Computer security; Public relations; Political science; Medical emergency; Poison control; Human factors and ergonomics; Engineering; Medicine; Reliability engineering","score_opus":0.16373296269347223,"score_gpt":0.5114703559569701,"score_spread":0.34773739326349784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1992053221","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9752097,0.00038051026,0.0126752285,0.0017113662,0.0033245094,0.001658257,0.00001630038,0.00005184856,0.004972261],"genre_scores_gemma":[0.98703206,0.00014311355,0.006553541,0.00009989898,0.000386143,0.00055231544,0.000049258797,0.000019794079,0.005163873],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99584615,0.00063459453,0.0007423634,0.0006284172,0.0019391015,0.00020937104],"domain_scores_gemma":[0.9964079,0.0011067799,0.00033842106,0.00048125876,0.0015551397,0.00011046343],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.019232864,0.00016832522,0.00019940322,0.0002752845,0.00058824907,0.0002575804,0.0001401196,0.00012767207,0.0036773614],"category_scores_gemma":[0.010586427,0.00014369974,0.000077253026,0.0005825302,0.00005707318,0.0015291893,0.00005406828,0.00014328705,0.00005409091],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006838833,0.00010075947,0.007807197,0.000014282665,0.000049749196,6.299228e-8,0.010736519,0.0005569189,0.038565952,0.0010597986,0.016333222,0.92409164],"study_design_scores_gemma":[0.0050339997,0.00063246937,0.30664167,0.000050262213,0.00055872294,0.00002951039,0.005520883,0.26303568,0.005985218,0.2529367,0.15889345,0.000681449],"about_ca_topic_score_codex":0.00007801387,"about_ca_topic_score_gemma":0.0030419219,"teacher_disagreement_score":0.9234102,"about_ca_system_score_codex":0.00011710099,"about_ca_system_score_gemma":0.00076176564,"threshold_uncertainty_score":0.99774784},"labels":[],"label_agreement":null},{"id":"W1992090873","doi":"10.3138/cjpe.29.2.87","title":"The Utility of a Realist Evaluation Approach in Implementing and Evaluating Health Equity Policy","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Toronto; St. Michael's Hospital","funders":"","keywords":"Equity (law); Program evaluation; Public economics; Health policy; Program Design Language; Management science; Political science; Economics; Business; Economic growth; Public administration; Computer science; Health care","score_opus":0.6286769634684284,"score_gpt":0.6421045718362257,"score_spread":0.013427608367797328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1992090873","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96208906,0.0016334095,0.0048631146,0.00986119,0.00045335764,0.004005207,0.000013864914,0.00000830645,0.017072473],"genre_scores_gemma":[0.9949807,0.000019599667,0.004594288,0.00013960055,0.00014317875,0.00008673433,0.00001528573,0.0000073487413,0.0000132863315],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9874682,0.0049228254,0.0022742858,0.00030738642,0.004478708,0.00054859277],"domain_scores_gemma":[0.99288416,0.000848428,0.0020018464,0.0004067232,0.003500488,0.00035837048],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.21765892,0.00013000553,0.00034015058,0.0007187492,0.00054064416,0.00046250678,0.00047791196,0.00006504433,0.00020686092],"category_scores_gemma":[0.018293262,0.00008979254,0.00008997272,0.0011804741,0.00017821646,0.00045741443,0.000055653527,0.00025916638,0.0000019064586],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015028214,0.00002668929,0.03756957,0.000012698565,0.000010298685,6.2624586e-8,0.0018063241,0.00075915386,0.0000117788595,0.0019904247,0.00034051525,0.9574575],"study_design_scores_gemma":[0.0009926595,0.00037833233,0.29183453,0.00004303335,0.00003052947,0.00000984603,0.0023997598,0.66953063,0.000009318124,0.031975348,0.0027281488,0.00006784831],"about_ca_topic_score_codex":0.0060629505,"about_ca_topic_score_gemma":0.06229206,"teacher_disagreement_score":0.9573896,"about_ca_system_score_codex":0.000658036,"about_ca_system_score_gemma":0.012359833,"threshold_uncertainty_score":0.99323916},"labels":[],"label_agreement":null},{"id":"W1993394680","doi":"10.12927/hcpol.2008.19814","title":"Knowledge to Action: The Development of Training Strategies","year":2008,"lang":"en","type":"article","venue":"Healthcare policy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Ottawa Fertility Centre; Université de Montréal","funders":"","keywords":"Interim; Curriculum; Medical education; Action (physics); Training (meteorology); Psychology; Knowledge management; Computer science; Mathematics education; Pedagogy; Medicine; Political science","score_opus":0.7618975176201975,"score_gpt":0.6400045515209847,"score_spread":0.12189296609921285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993394680","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9065734,0.00015220004,0.0024703015,0.045963425,0.0003872617,0.0003277206,0.0000048201055,0.000035601734,0.04408524],"genre_scores_gemma":[0.99463165,0.000018934288,0.0022776884,0.0012058852,0.0002542411,0.00003367398,0.0000013127897,0.0000050786457,0.0015715539],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9979478,0.00019225308,0.0006141993,0.00018384549,0.00083443616,0.00022745132],"domain_scores_gemma":[0.99860394,0.00033072135,0.00014991114,0.0003316766,0.00044677957,0.00013698214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020795036,0.00008306851,0.0001656748,0.0002714527,0.00047979833,0.000042531505,0.00036008516,0.00003732868,0.0002378738],"category_scores_gemma":[0.00036530968,0.000049809092,0.00004239877,0.0010708407,0.000060263086,0.00018057734,0.00006106154,0.00010345084,0.00040302757],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019976354,0.000037854432,0.0038817793,0.000021342228,0.000008672572,4.7807146e-7,0.22426374,0.00019059528,0.00012901015,0.034565043,0.0041654315,0.7327161],"study_design_scores_gemma":[0.00027870043,0.0001467527,0.464507,0.000040297316,0.0000019500728,0.000024702887,0.07413138,0.00043535916,0.0010836275,0.0056871064,0.45349136,0.00017173307],"about_ca_topic_score_codex":0.00022387633,"about_ca_topic_score_gemma":0.0031583882,"teacher_disagreement_score":0.73254436,"about_ca_system_score_codex":0.00010692679,"about_ca_system_score_gemma":0.005814553,"threshold_uncertainty_score":0.99982154},"labels":[],"label_agreement":null},{"id":"W1993542572","doi":"10.1080/13632430068860","title":"Comparing School Improvement Programmes in England and Canada","year":2000,"lang":"en","type":"article","venue":"School Leadership and Management","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Work (physics); Quality management; New england; Quality (philosophy); Pedagogy; Political science; Sociology; Medical education; Medicine; Engineering; Operations management","score_opus":0.1522630993011123,"score_gpt":0.37860287193086417,"score_spread":0.22633977262975188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993542572","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9732037,0.00041196,0.000037740007,0.006714569,0.00012418636,0.00062940485,0.0000015240425,0.000021284292,0.018855603],"genre_scores_gemma":[0.9879884,0.00037899596,0.00036615398,0.0021309697,0.000047536716,0.00007439333,0.000003829937,0.000006265655,0.009003471],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9978158,0.0000836012,0.00043069577,0.00042962324,0.0008911111,0.00034919684],"domain_scores_gemma":[0.9993062,0.00006915384,0.00006552408,0.00027469697,0.00003932468,0.00024511092],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017882216,0.00014775094,0.00020094783,0.00016989536,0.00012748994,0.00035065433,0.00021805528,0.000031250216,0.0015383941],"category_scores_gemma":[0.00006499431,0.00011639519,0.000019199048,0.0002483445,0.00004487973,0.0002924065,0.00007854544,0.00015535888,0.00006929845],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057273115,0.00004547061,0.44545487,0.00006783149,0.000028175851,0.000015887734,0.00048543184,0.00015252807,0.0000071546774,0.00060252694,0.0048555047,0.54822737],"study_design_scores_gemma":[0.001897654,0.00008368143,0.6788189,0.000054299522,0.000014885974,0.0000024265244,0.007407046,0.0023793997,0.000020595464,0.00086106977,0.30824095,0.00021913441],"about_ca_topic_score_codex":0.041295663,"about_ca_topic_score_gemma":0.5228889,"teacher_disagreement_score":0.5480082,"about_ca_system_score_codex":0.00011859219,"about_ca_system_score_gemma":0.00012348326,"threshold_uncertainty_score":0.99937433},"labels":[],"label_agreement":null},{"id":"W1998312778","doi":"10.3138/cjpe.29.1.87","title":"Toward a Definition of Evaluation Within the Canadian Context: Who Knew This Would Be So Difficult?","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Environment and Climate Change Canada; Canadian Evaluation Society; University of Alberta","funders":"","keywords":"Scope (computer science); Presentation (obstetrics); Context (archaeology); Process (computing); Public relations; Psychology; Sociology; Computer science; Social psychology; Political science; History; Medicine","score_opus":0.40214964057962616,"score_gpt":0.47723035797279373,"score_spread":0.07508071739316757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998312778","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8880248,0.0019175094,0.0017628265,0.05618901,0.0035702928,0.005495005,0.000063613945,0.000024568824,0.042952396],"genre_scores_gemma":[0.9968018,0.000008582756,0.0010780579,0.0015976952,0.00022440203,0.00012061209,0.000042294247,0.00001539343,0.00011118078],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.991046,0.0019711903,0.0015937133,0.00028778997,0.0047044074,0.0003968919],"domain_scores_gemma":[0.98683476,0.00041912403,0.0016694326,0.000505216,0.0098079555,0.0007635057],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04370066,0.00020625287,0.0003957406,0.0009573403,0.0007037383,0.00077894336,0.0006544104,0.00026031447,0.003315985],"category_scores_gemma":[0.01223579,0.00013690375,0.000200939,0.0012587762,0.00031379948,0.0006886181,0.000014192629,0.0005574127,0.00008770836],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032460594,0.00004989979,0.010449235,0.000012851574,0.00007760853,0.0000025531235,0.011303892,0.00397962,0.00004529662,0.017406635,0.011627506,0.94501245],"study_design_scores_gemma":[0.0047617615,0.0021047462,0.16806246,0.00043451664,0.00092295575,0.00015396807,0.010337468,0.5363824,0.00044578296,0.11815404,0.1575697,0.0006702389],"about_ca_topic_score_codex":0.097979166,"about_ca_topic_score_gemma":0.8993084,"teacher_disagreement_score":0.9443422,"about_ca_system_score_codex":0.0011581569,"about_ca_system_score_gemma":0.021922711,"threshold_uncertainty_score":0.99759513},"labels":[],"label_agreement":null},{"id":"W1999716079","doi":"10.1002/ev.243","title":"Infusing evaluative thinking as process use: The case of the International Development Research Centre (IDRC)","year":2007,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Accountability; Process (computing); Political science; Sociology; Process management; Management; Business; Computer science","score_opus":0.45376368323160404,"score_gpt":0.6131986765418254,"score_spread":0.15943499331022132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1999716079","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97073287,0.000088618726,0.005401148,0.005605602,0.0018591895,0.0021244627,0.000007640155,0.000027014821,0.014153452],"genre_scores_gemma":[0.9925522,0.0000038376347,0.0021757549,0.00018869454,0.00022491481,0.000093993884,0.000016062926,0.00001182934,0.0047326833],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99184936,0.00079954765,0.0008792299,0.0003866346,0.0058032554,0.00028196335],"domain_scores_gemma":[0.9859741,0.003521078,0.00047735206,0.00048910244,0.00945406,0.00008435587],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06376707,0.00012256455,0.00013640529,0.00044212598,0.0014433279,0.00038755563,0.0006892894,0.00007581469,0.0008620387],"category_scores_gemma":[0.020717338,0.00007020439,0.00009717375,0.0019873292,0.00012331706,0.00072254357,0.00015155594,0.00025335525,0.000059135837],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021566892,0.00019928293,0.014877425,0.000009401295,0.0001178238,0.0000021175051,0.060796812,0.016938034,0.0005323885,0.006124012,0.016294807,0.88389224],"study_design_scores_gemma":[0.0045910636,0.00020652423,0.106915504,0.00024432348,0.00023473203,0.00024663637,0.1009031,0.28641787,0.034944553,0.25380877,0.21100812,0.0004788191],"about_ca_topic_score_codex":0.00032787875,"about_ca_topic_score_gemma":0.0063866493,"teacher_disagreement_score":0.88341343,"about_ca_system_score_codex":0.00071990327,"about_ca_system_score_gemma":0.003579946,"threshold_uncertainty_score":0.99985665},"labels":[],"label_agreement":null},{"id":"W1999945450","doi":"10.7202/1024929ar","title":"L’évaluation en classe","year":2014,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Humanities; Valuation (finance); Political science; Philosophy; Economics","score_opus":0.23742504993619337,"score_gpt":0.5178644741103188,"score_spread":0.2804394241741254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1999945450","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44652697,0.0012491973,0.24617083,0.21660823,0.020501183,0.0019538722,0.000038734343,0.00021263234,0.066738345],"genre_scores_gemma":[0.9221053,0.0006224239,0.012494945,0.0027339614,0.0016070983,0.00018588814,0.0004978839,0.00006036753,0.059692107],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9606199,0.03026996,0.001993558,0.0011961601,0.0052751834,0.0006451907],"domain_scores_gemma":[0.9883753,0.006835282,0.0010117745,0.0012628939,0.0022723947,0.00024236529],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.15286086,0.0004953324,0.00054885156,0.0007498668,0.00048182992,0.00076650654,0.0007569031,0.0005619439,0.014960784],"category_scores_gemma":[0.017251931,0.0004791046,0.0002654232,0.0015764788,0.00014339111,0.0024661662,0.00012024398,0.00062581623,0.0107133845],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041221065,0.0004685775,0.011177743,0.000062820916,0.000061738065,3.9888675e-7,0.103418775,0.018956704,0.0009889225,0.026814308,0.043978445,0.79403037],"study_design_scores_gemma":[0.0010502248,0.00023291366,0.45746192,0.00011914663,0.00017190403,0.000010978201,0.0024722777,0.29936686,0.00050097064,0.035172865,0.20299242,0.00044753228],"about_ca_topic_score_codex":0.00024095409,"about_ca_topic_score_gemma":0.0008471462,"teacher_disagreement_score":0.7935828,"about_ca_system_score_codex":0.0010289076,"about_ca_system_score_gemma":0.004071728,"threshold_uncertainty_score":0.99976605},"labels":[],"label_agreement":null},{"id":"W2000280390","doi":"10.1177/1075547005275427","title":"Achieving Buy-In","year":2005,"lang":"en","type":"article","venue":"Science Communication","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Knowledge transfer; Knowledge management; Process (computing); Matching (statistics); Body of knowledge; Business; Computer science; Medicine","score_opus":0.289795189439559,"score_gpt":0.5782053454331254,"score_spread":0.2884101559935664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2000280390","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8765421,0.0001785001,0.0007612031,0.014244797,0.00008590969,0.0001224001,4.0079092e-7,0.000024993687,0.10803972],"genre_scores_gemma":[0.98991287,0.00006992969,0.008718848,0.0005292862,0.000019879895,0.000010990945,0.0000010928898,0.0000020407276,0.0007350613],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9975535,0.00017468876,0.0004063362,0.00023432511,0.0014449696,0.00018614705],"domain_scores_gemma":[0.99789786,0.00036114056,0.0001394288,0.0012556994,0.0002869799,0.000058866513],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0142265195,0.0000527804,0.000082998755,0.00041876678,0.00036104347,0.00030108943,0.002102162,0.000020798037,0.0006582682],"category_scores_gemma":[0.0014750276,0.0000407431,0.00002287139,0.0020433315,0.0003055675,0.0018157425,0.00028552322,0.00012834447,0.0009587609],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006218219,0.0000981324,0.17474201,7.701773e-7,6.411741e-7,1.0189237e-7,0.00360283,0.0046409466,0.007995016,0.028322255,0.0009116069,0.7796795],"study_design_scores_gemma":[0.00023801743,0.000019460023,0.8540403,0.000018335246,0.0000010104319,0.0000020467717,0.0013991321,0.08217636,0.0014405247,0.006110212,0.054439303,0.00011527591],"about_ca_topic_score_codex":0.000021780752,"about_ca_topic_score_gemma":0.00037573377,"teacher_disagreement_score":0.7795642,"about_ca_system_score_codex":0.00015307932,"about_ca_system_score_gemma":0.00027317592,"threshold_uncertainty_score":0.9998191},"labels":[],"label_agreement":null},{"id":"W2000821194","doi":"10.1177/1098214009340580","title":"Toward Accurate Measurement of Participation","year":2009,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":86,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Conceptualization; Operationalization; Citizen journalism; Stakeholder; Field (mathematics); Participatory evaluation; Psychology; Sociology; Management science; Computer science; Epistemology; Political science; Public relations; Social science; Artificial intelligence; Engineering; Mathematics","score_opus":0.4707113104953488,"score_gpt":0.5611236037354239,"score_spread":0.0904122932400751,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2000821194","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9687301,0.00011325674,0.023991514,0.0044177147,0.0002842521,0.00016361472,9.294852e-7,0.0000036718122,0.0022949525],"genre_scores_gemma":[0.997949,0.00002591848,0.0016215859,0.00029512044,0.00008811981,0.0000025748463,9.071384e-7,0.0000026861821,0.0000140914435],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99210656,0.00072857545,0.0012656611,0.00012088566,0.0056584855,0.00011981544],"domain_scores_gemma":[0.99155825,0.00021921631,0.0022732755,0.00021740118,0.0056480416,0.00008381377],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022764243,0.00007913479,0.00029481115,0.00031337788,0.00004212512,0.00005270194,0.00023129226,0.000016949884,0.0006678664],"category_scores_gemma":[0.0038803685,0.000054786356,0.00011648862,0.00075172225,0.000063422376,0.00054921187,0.000009329701,0.00008661609,0.000031692336],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012537371,0.00012052605,0.0038210345,0.0000010150106,0.00002256329,5.35994e-7,0.0014296273,0.013686885,0.0063871103,0.00027914476,0.0008410622,0.97328514],"study_design_scores_gemma":[0.0016253154,0.004344353,0.8773189,0.00007562724,0.00019720322,0.000019647188,0.0033618144,0.07993228,0.010647767,0.020523945,0.0017755845,0.00017756462],"about_ca_topic_score_codex":0.00000507098,"about_ca_topic_score_gemma":0.0000050247854,"teacher_disagreement_score":0.9731076,"about_ca_system_score_codex":0.00015023707,"about_ca_system_score_gemma":0.000623695,"threshold_uncertainty_score":0.7889678},"labels":[],"label_agreement":null},{"id":"W2002129351","doi":"10.3138/jvme.28.1.3","title":"Professing Change","year":2001,"lang":"en","type":"review","venue":"Journal of Veterinary Medical Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medical education; Medicine; Psychology","score_opus":0.8180225295672611,"score_gpt":0.6993362880154632,"score_spread":0.11868624155179786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2002129351","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000150428,0.9882027,0.00014086318,0.0019698313,0.0073958472,0.00026769392,0.0000011664472,0.0000055419014,0.00186594],"genre_scores_gemma":[0.000084206295,0.9938295,0.00046758854,0.00072236813,0.0034802023,0.00003760976,0.000009827932,0.00001632348,0.001352407],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99274033,0.00095814245,0.0021377779,0.00021046177,0.0037723514,0.00018093894],"domain_scores_gemma":[0.99524564,0.0007109665,0.0025841843,0.00035093218,0.0007272681,0.00038098777],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009477899,0.00020513729,0.0011201972,0.0007533101,0.00009649751,0.00013903496,0.0010191951,0.00029907064,0.0070923525],"category_scores_gemma":[0.004772296,0.00012013081,0.00044148046,0.00090781844,0.00006333494,0.000668058,0.00009903286,0.0007482108,0.0002796475],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006991983,0.00019586615,0.000016278624,0.0005821357,0.000018107286,0.00002681557,0.00021522683,3.898641e-8,3.846376e-8,0.000035060842,0.011117731,0.9877857],"study_design_scores_gemma":[0.00011433528,0.0003547312,0.00009259436,0.012538191,0.00010709321,0.0027555237,0.00024684798,0.000029355399,1.6988604e-8,0.0002831284,0.9833606,0.00011758267],"about_ca_topic_score_codex":0.0000029969447,"about_ca_topic_score_gemma":0.0000012269752,"teacher_disagreement_score":0.9876681,"about_ca_system_score_codex":0.00022920486,"about_ca_system_score_gemma":0.009603887,"threshold_uncertainty_score":0.9960107},"labels":[],"label_agreement":null},{"id":"W2002747675","doi":"10.1177/1075547004267491","title":"New Evidence on Instrumental, Conceptual, and Symbolic Utilization of University Research in Government Agencies","year":2004,"lang":"en","type":"article","venue":"Science Communication","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":465,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Government (linguistics); The Symbolic; Conceptual framework; Sociology; Public relations; Political science; Psychology; Social science; Linguistics","score_opus":0.6781789006118617,"score_gpt":0.5680393100705534,"score_spread":0.11013959054130829,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2002747675","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9892183,0.00023001022,0.00044451407,0.002483821,0.000042016454,0.00021468925,0.0000016982956,0.0000063829666,0.0073585683],"genre_scores_gemma":[0.99670553,0.0013731776,0.0016806578,0.00006049419,0.0000036786428,0.0000015510548,7.606683e-7,0.0000016125917,0.00017252687],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99618393,0.00042551264,0.0002861025,0.00026643553,0.0026798656,0.00015816266],"domain_scores_gemma":[0.99788064,0.00079209363,0.00015230836,0.0007859009,0.00031136873,0.00007771138],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0111870235,0.000055401575,0.00009867051,0.00033613245,0.0003686054,0.000102385464,0.0012296026,0.000028237115,0.00008949516],"category_scores_gemma":[0.001457223,0.000047794718,0.000013282102,0.0025807621,0.001183931,0.0012813559,0.0004153363,0.00013837643,0.000031626158],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020740382,0.0002477929,0.1384046,0.000012684685,0.000004219347,0.0000010396303,0.034090918,0.0043159486,0.029906567,0.5459726,0.0004852541,0.24635099],"study_design_scores_gemma":[0.0011071268,0.00050294003,0.84483695,0.000521945,0.000003837556,0.0000021287315,0.081919625,0.0041902983,0.03499659,0.029206963,0.0025323564,0.00017921058],"about_ca_topic_score_codex":0.00039722145,"about_ca_topic_score_gemma":0.00039521942,"teacher_disagreement_score":0.7064324,"about_ca_system_score_codex":0.00068107015,"about_ca_system_score_gemma":0.0009360348,"threshold_uncertainty_score":0.43622434},"labels":[],"label_agreement":null},{"id":"W2002851593","doi":"10.1007/s10734-010-9344-4","title":"Faculties of education and institutional strategies for knowledge mobilization: an exploratory study","year":2010,"lang":"en","type":"article","venue":"Higher Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":81,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Mobilization; Higher education; Vision; Public relations; Exploratory research; Political science; Knowledge transfer; Sociology; Public administration; Social science; Knowledge management","score_opus":0.2600302038420381,"score_gpt":0.5367898028576558,"score_spread":0.27675959901561764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2002851593","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9901957,0.00015314347,0.0007941413,0.00024044269,0.003186441,0.0005537272,0.000006579915,0.000018191673,0.0048516407],"genre_scores_gemma":[0.9939804,0.000004282415,0.0020538233,0.000075523734,0.00033991612,0.0003856594,0.000055022017,0.000005756697,0.0030996364],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9987662,0.000100169804,0.0003862703,0.00026151972,0.00041022414,0.00007565283],"domain_scores_gemma":[0.9979912,0.0001601066,0.00018565745,0.00029708925,0.0012986559,0.000067285335],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012178819,0.0000902628,0.00011924618,0.00022309237,0.0001934964,0.00018317632,0.00018315783,0.00005178145,0.0005896696],"category_scores_gemma":[0.00012220201,0.00007229548,0.000023335202,0.00030715764,0.00009821501,0.0013810575,0.000022110255,0.00006559429,0.000021321786],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006655562,0.009095501,0.17258835,0.00008031991,0.000028196051,2.7541398e-8,0.07283342,0.0003096907,0.0113214115,0.5070885,0.011973607,0.2146144],"study_design_scores_gemma":[0.0005162371,0.00036642593,0.7265257,0.000015499394,0.00002822067,0.0000016349081,0.12912537,0.00076362886,0.00052082416,0.044880714,0.09706199,0.00019374753],"about_ca_topic_score_codex":0.000015166784,"about_ca_topic_score_gemma":0.00039916043,"teacher_disagreement_score":0.5539374,"about_ca_system_score_codex":0.000025759282,"about_ca_system_score_gemma":0.0028821537,"threshold_uncertainty_score":0.6456469},"labels":[],"label_agreement":null},{"id":"W2003107755","doi":"10.1080/14613800500042166","title":"Bridge over troubled waters: policy development for Canadian music in higher education","year":2005,"lang":"en","type":"article","venue":"Music Education Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Music education; The arts; Inclusion (mineral); Certification; Pedagogy; Sociology; Bridge (graph theory); Performing arts; Public relations; Political science; Library science; Visual arts; Social science; Art; Computer science","score_opus":0.5829400560954933,"score_gpt":0.5911762900500994,"score_spread":0.008236233954606154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2003107755","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87382257,0.00009192345,0.00003344582,0.07048557,0.0014576601,0.0012973709,0.000006708577,0.000016716514,0.052788008],"genre_scores_gemma":[0.90935785,0.000007696851,0.0017179275,0.0049248436,0.0013934711,0.0009561216,0.000087732944,0.000016795793,0.081537575],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99605936,0.00033046355,0.0006790485,0.00052405486,0.0017272079,0.00067984284],"domain_scores_gemma":[0.9971067,0.0004617959,0.00010177706,0.0005649171,0.001367376,0.0003974617],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0073408186,0.0001378755,0.00017320285,0.0028371622,0.00044748574,0.0004546751,0.0006404287,0.00010237652,0.012792407],"category_scores_gemma":[0.00073636795,0.000117734526,0.00005115912,0.0022299974,0.00006750688,0.00062522665,0.00006255166,0.0002465195,0.0014158918],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025350018,0.00045498376,0.02026758,0.000015909845,0.0000070345714,1.561499e-7,0.007315713,0.000077128,0.00012791532,0.015165983,0.39183974,0.5647025],"study_design_scores_gemma":[0.00028309546,0.000019433284,0.3826367,0.000020361007,0.0000010256231,6.8035024e-7,0.001026242,0.00023134847,0.0001124676,0.002393448,0.6131762,0.00009898383],"about_ca_topic_score_codex":0.034387633,"about_ca_topic_score_gemma":0.1696212,"teacher_disagreement_score":0.5646035,"about_ca_system_score_codex":0.002366481,"about_ca_system_score_gemma":0.032714307,"threshold_uncertainty_score":0.99936163},"labels":[],"label_agreement":null},{"id":"W2004772372","doi":"10.3138/cjpe.29.2.145","title":"Pawson, R. (2013). <i>The science of evaluation: A realist manifesto.</i>","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Ontario Tobacco Research Unit; University of Toronto","funders":"","keywords":"Manifesto; Philosophy; Epistemology; Sociology; Psychology; Political science; Law","score_opus":0.31751238103500456,"score_gpt":0.5079111319318299,"score_spread":0.19039875089682534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004772372","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91929597,0.0014031162,0.0041973265,0.026350671,0.0042339847,0.003914512,0.000015036355,0.000018947598,0.040570457],"genre_scores_gemma":[0.99700755,0.000010711163,0.0022111246,0.00028539516,0.0002938545,0.00006693462,0.000005627837,0.000008393479,0.00011042166],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9896608,0.0012605425,0.0013670324,0.0002767927,0.0070774932,0.00035734798],"domain_scores_gemma":[0.9842317,0.00048628793,0.001488773,0.00069040054,0.012625975,0.0004768387],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09991371,0.00013534862,0.00027149564,0.00082435407,0.00054188527,0.00050238887,0.0010893304,0.00006250703,0.0021748364],"category_scores_gemma":[0.011344653,0.00008640947,0.00013766943,0.0020356113,0.00067234086,0.0008952027,0.000025647629,0.00021639223,0.00007371929],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014914579,0.00004224728,0.0054545803,0.0000051808256,0.000016180891,0.0000011013177,0.0013149034,0.0077252192,0.00022252322,0.0046076025,0.01266062,0.9679349],"study_design_scores_gemma":[0.0023132197,0.0013751372,0.18477406,0.00012781528,0.00035475925,0.00020611942,0.002398261,0.55174744,0.0010519045,0.07609136,0.1792323,0.00032763678],"about_ca_topic_score_codex":0.0011407328,"about_ca_topic_score_gemma":0.015753442,"teacher_disagreement_score":0.96760726,"about_ca_system_score_codex":0.0004510296,"about_ca_system_score_gemma":0.012647062,"threshold_uncertainty_score":0.99873734},"labels":[],"label_agreement":null},{"id":"W2007329518","doi":"10.1111/j.1754-7121.2004.tb01871.x","title":"Comparison of Canadian master's programs in public administration, public management and public policy","year":2004,"lang":"en","type":"article","venue":"Canadian Public Administration","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Humanities; Administration (probate law); Public administration; Philosophy; Law","score_opus":0.30782713146082025,"score_gpt":0.4416387696497595,"score_spread":0.13381163818893926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2007329518","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5116517,0.0001490244,0.0006813145,0.4320217,0.00042065157,0.00160794,0.000117908065,0.00006474422,0.053285047],"genre_scores_gemma":[0.99618906,0.000035389075,0.0010492334,0.0010943309,0.00012726462,0.0001799245,0.0005343306,0.000026628304,0.0007638142],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9941822,0.0002905804,0.0017138249,0.0008343983,0.0016958981,0.0012830698],"domain_scores_gemma":[0.99466646,0.00009903486,0.00056806183,0.000879169,0.0010459091,0.0027413976],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0031772056,0.00035592914,0.0004920062,0.0077055055,0.00053435715,0.0028060307,0.0009958255,0.00028265527,0.00084463274],"category_scores_gemma":[0.0012469231,0.0003537998,0.00009523236,0.00659627,0.00032383672,0.002692894,0.00006885172,0.000316767,0.0001150394],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000065773925,0.0002053747,0.30111122,0.000021239332,0.00002895213,0.000020674597,0.0002989964,0.0000035496787,0.000004261171,0.6331425,0.0012583367,0.06389836],"study_design_scores_gemma":[0.0017213655,0.00076448615,0.21234645,0.00004327661,0.00001702093,0.00006383102,0.00877076,0.0013618935,0.00005529883,0.0139699,0.76022166,0.00066404],"about_ca_topic_score_codex":0.06446697,"about_ca_topic_score_gemma":0.9931485,"teacher_disagreement_score":0.92868155,"about_ca_system_score_codex":0.00155029,"about_ca_system_score_gemma":0.028216964,"threshold_uncertainty_score":0.9998914},"labels":[],"label_agreement":null},{"id":"W2007376202","doi":"10.1016/j.evalprogplan.2012.03.005","title":"The case for including reach as a key element of program theory","year":2012,"lang":"en","type":"article","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Agency of Canada; Ontario Stroke Network","funders":"","keywords":"Logic model; Equity (law); Key (lock); Element (criminal law); Computer science; Social equality; Health equity; Risk analysis (engineering); Management science; Engineering; Public relations; Business; Political science; Computer security; Economics; Public administration; Economic growth; Health care","score_opus":0.4328128632199853,"score_gpt":0.6179518607956844,"score_spread":0.18513899757569913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2007376202","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9701057,0.0038857753,0.0044717398,0.0013800616,0.00062773144,0.005127921,0.000008441798,0.000104448794,0.014288143],"genre_scores_gemma":[0.98899835,0.000022276194,0.009137263,0.00011396644,0.00012737124,0.0012563847,0.000022749757,0.000008412652,0.0003132301],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99690545,0.0006598327,0.00063257315,0.00021928403,0.0012632292,0.00031962423],"domain_scores_gemma":[0.9963437,0.0021846904,0.00039498828,0.0002754954,0.0006903793,0.000110767854],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.039268088,0.00012215158,0.00016642573,0.00011931053,0.0006882606,0.0002828895,0.00017983295,0.000053725173,0.00021606254],"category_scores_gemma":[0.0028993872,0.00007026498,0.00007056033,0.00033614735,0.00009083929,0.0003740043,0.000075538366,0.00009702111,0.000015746778],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007920876,0.000110839224,0.011203019,0.000009358755,0.000022426444,7.2987626e-7,0.0047865286,0.000092963426,0.00003217178,0.01214655,0.0007344173,0.9707818],"study_design_scores_gemma":[0.003006343,0.0020260902,0.022880092,0.00013179946,0.00026925205,0.00026973372,0.04296517,0.3424195,0.0009956572,0.06843732,0.51614153,0.00045749324],"about_ca_topic_score_codex":0.000008117062,"about_ca_topic_score_gemma":0.000010644364,"teacher_disagreement_score":0.9703243,"about_ca_system_score_codex":0.00003951332,"about_ca_system_score_gemma":0.00014624702,"threshold_uncertainty_score":0.9892757},"labels":[],"label_agreement":null},{"id":"W2008070236","doi":"10.1002/ev.299","title":"Reflections on the dilemmas of conducting environmental evaluations","year":2009,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact","funders":"","keywords":"Cognitive reframing; Multidisciplinary approach; Asset (computer security); Context (archaeology); Set (abstract data type); Face (sociological concept); Computer science; Management science; Theory of change; Work (physics); Sociology; Engineering ethics; Psychology; Social science; Social psychology; Economics; Engineering","score_opus":0.5676539202947379,"score_gpt":0.5954441216399692,"score_spread":0.027790201345231247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2008070236","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75038284,0.00029987976,0.037731193,0.043593157,0.0031011985,0.0056316517,0.00011168036,0.00016629962,0.15898208],"genre_scores_gemma":[0.9935433,0.00001929259,0.0015536534,0.00053680304,0.000249532,0.00019670125,0.00004855883,0.000008932285,0.0038432267],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9958905,0.0005305228,0.00074103504,0.00036842862,0.0022865906,0.0001828954],"domain_scores_gemma":[0.9964492,0.0019235753,0.00044422306,0.0006017363,0.000509823,0.000071463066],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009315129,0.00013803007,0.00017837211,0.00036024328,0.00085021916,0.00011173378,0.0002908323,0.00006704957,0.004187814],"category_scores_gemma":[0.0045145196,0.000094105395,0.00018958209,0.0008748849,0.000062322935,0.00038536347,0.00001603735,0.00013781937,0.00018981971],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000097881464,0.00047238785,0.0005505753,0.0000017789201,0.00006305515,5.5793507e-8,0.0030911956,0.024284005,0.031147126,0.05045737,0.03608853,0.85374606],"study_design_scores_gemma":[0.0045049335,0.002190218,0.1032492,0.000067977024,0.0005718948,0.000017972887,0.009199553,0.23834185,0.048867468,0.38882503,0.20354925,0.0006146566],"about_ca_topic_score_codex":0.00001898199,"about_ca_topic_score_gemma":0.000079488134,"teacher_disagreement_score":0.85313135,"about_ca_system_score_codex":0.00023667119,"about_ca_system_score_gemma":0.00042744016,"threshold_uncertainty_score":0.9967225},"labels":[],"label_agreement":null},{"id":"W2010270738","doi":"10.4102/aej.v2i1.98","title":"Reshaping development evaluation: Meeting the challenges of a changing context","year":2014,"lang":"en","type":"article","venue":"African Evaluation Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mastercard Foundation","funders":"","keywords":"Context (archaeology); Development (topology); Computer science; Process management; Engineering ethics; Engineering; Geography; Mathematics","score_opus":0.38877638053612223,"score_gpt":0.4856660053502125,"score_spread":0.09688962481409025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2010270738","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6776399,0.010358348,0.029515415,0.073608704,0.0029005287,0.0021175079,0.000002651113,0.000056548073,0.20380037],"genre_scores_gemma":[0.9974607,0.000043415544,0.0013559251,0.00047273946,0.00046039748,0.00006763692,0.0000016865778,0.000010718465,0.0001267617],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9868705,0.0032257547,0.0014217391,0.0003124728,0.007837792,0.00033174254],"domain_scores_gemma":[0.9917744,0.0017372809,0.0014435579,0.000460056,0.004466183,0.00011851247],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12736136,0.0001546578,0.00028186225,0.00056739256,0.00085834344,0.0002441061,0.0006980159,0.000050526414,0.0025399397],"category_scores_gemma":[0.009675578,0.00009471839,0.00011836848,0.0008323494,0.00011425223,0.00045046408,0.00010237815,0.00024435352,0.00012841422],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017014085,0.000021487047,0.00071525655,0.000003315747,0.000036388694,1.2472636e-7,0.020529287,0.0055293515,0.00013336001,0.006741958,0.0005655167,0.96570694],"study_design_scores_gemma":[0.0025143027,0.00023655352,0.036063556,0.00028166114,0.00017086508,0.00007038741,0.113269866,0.7195128,0.001740284,0.042607658,0.08317025,0.0003617979],"about_ca_topic_score_codex":0.0000024755639,"about_ca_topic_score_gemma":0.00006157227,"teacher_disagreement_score":0.96534514,"about_ca_system_score_codex":0.00023802537,"about_ca_system_score_gemma":0.0012079405,"threshold_uncertainty_score":0.99866635},"labels":[],"label_agreement":null},{"id":"W2011406769","doi":"10.1016/j.evalprogplan.2010.09.003","title":"Ten steps to making evaluation matter","year":2010,"lang":"en","type":"article","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":81,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital; University of Toronto","funders":"","keywords":"Program evaluation; Computer science; Program Design Language; Management science; Theory of change; Work (physics); Evaluation methods; Sustainability; Risk analysis (engineering); Process management; Software engineering; Engineering; Political science; Sociology; Business","score_opus":0.3049186399144428,"score_gpt":0.5971294410667453,"score_spread":0.29221080115230247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2011406769","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9389021,0.000116719566,0.001573088,0.0040807347,0.0010593917,0.0020919777,0.000003948901,0.00008768168,0.05208437],"genre_scores_gemma":[0.9842925,0.0000010373808,0.012710588,0.0016540763,0.00020954286,0.00049333513,0.00003578522,0.000012923937,0.0005901749],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9943448,0.00049507373,0.00060772046,0.0005349484,0.0037332524,0.0002842521],"domain_scores_gemma":[0.9974783,0.00038050683,0.0002373278,0.00044484762,0.0013045499,0.0001544366],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.023478607,0.00016350449,0.00018864653,0.00040236925,0.0003430694,0.0007978574,0.0002860999,0.000100780744,0.011462963],"category_scores_gemma":[0.0020255838,0.00012694833,0.000049528076,0.0006641402,0.000043307766,0.0005342768,0.00009222368,0.0002593825,0.0012650915],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021823053,0.00003531803,0.15183319,0.0000028632317,0.000008958987,3.5720572e-7,0.0019802356,0.0014014859,0.0004974504,0.00019851926,0.0055414625,0.8384783],"study_design_scores_gemma":[0.0007397526,0.00013293502,0.5727152,0.000040979492,0.00005357278,0.000011790155,0.0010893681,0.3467656,0.000098749406,0.004260594,0.073867515,0.00022389306],"about_ca_topic_score_codex":0.000005870003,"about_ca_topic_score_gemma":0.000045777764,"teacher_disagreement_score":0.83825445,"about_ca_system_score_codex":0.000045891316,"about_ca_system_score_gemma":0.00024236504,"threshold_uncertainty_score":0.99951255},"labels":[],"label_agreement":null},{"id":"W2011781980","doi":"10.1017/s000842391100076x","title":"A Focusing Tragedy: Public Policy and the Establishment of Afrocentric Education in Toronto","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Political Science","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Tragedy (event); Humanities; Political science; Extant taxon; Sociology; Art; Social science","score_opus":0.13133829112378453,"score_gpt":0.4452933463412808,"score_spread":0.3139550552174963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2011781980","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9382171,0.0003812358,0.00032006265,0.008877129,0.0003289014,0.00010956143,0.0000024172507,8.320281e-7,0.05176275],"genre_scores_gemma":[0.9986429,0.000010378447,0.00047503682,0.000707458,0.0000824,0.000001020759,4.7603276e-8,0.0000015548985,0.00007916408],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99782604,0.00014796207,0.0005458973,0.000119129996,0.00089888385,0.00046206123],"domain_scores_gemma":[0.9976703,0.00028735973,0.00021048078,0.000168368,0.00070257287,0.0009609204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008750551,0.0000540926,0.0001492735,0.00062307116,0.000153925,0.00022561855,0.00064245355,0.000022129458,0.00057314034],"category_scores_gemma":[0.007152755,0.000030871342,0.000036901016,0.0010607756,0.001001364,0.0011484022,0.000025627973,0.00009620789,0.0000028425125],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005709121,0.000019111449,0.031632844,0.0000012638645,0.0000010485921,0.0000011470383,0.0018098925,9.2567757e-7,0.000014500133,0.93034947,0.000069572205,0.036094535],"study_design_scores_gemma":[0.00044617333,0.00006878021,0.91935176,0.000025940566,0.0000050775143,0.000050903258,0.009125501,0.0004591754,0.00016804272,0.06925244,0.0009897763,0.000056407785],"about_ca_topic_score_codex":0.17413484,"about_ca_topic_score_gemma":0.1756727,"teacher_disagreement_score":0.8877189,"about_ca_system_score_codex":0.0010092357,"about_ca_system_score_gemma":0.024599507,"threshold_uncertainty_score":0.9809301},"labels":[],"label_agreement":null},{"id":"W2012973094","doi":"10.1007/s11205-007-9123-5","title":"Knowledge translation strategies in a community–university partnership: examining local Quality of Life (QoL)","year":2007,"lang":"en","type":"article","venue":"Social Indicators Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":27,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Northern British Columbia; University of Saskatchewan; Saskatoon City Hospital; McMaster University","funders":"Canadian Institutes of Health Research","keywords":"Participatory action research; Stakeholder; Quality of life (healthcare); General partnership; Public relations; Knowledge translation; Sociology; Community-based participatory research; Action research; Sustainability; Political science; Knowledge management; Medicine; Pedagogy; Nursing","score_opus":0.8037757856427898,"score_gpt":0.6511933081698433,"score_spread":0.1525824774729465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012973094","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9082463,0.000061977684,0.0026399605,0.00023548998,0.00003858875,0.00018100419,0.0000044584303,0.0000132420055,0.08857897],"genre_scores_gemma":[0.99951696,0.0000110251685,0.00008153677,0.000014100687,0.000050366085,0.0000019186675,0.000007084123,0.000005111705,0.00031188966],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9908232,0.0054411422,0.00071283884,0.00021497581,0.0024007848,0.00040704114],"domain_scores_gemma":[0.99267924,0.0062095476,0.00020708903,0.00027768378,0.0004796573,0.00014680768],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.06628665,0.00008136472,0.00026945316,0.0013608857,0.00066424016,0.00008415,0.0007462887,0.00017719278,0.00039717343],"category_scores_gemma":[0.001505444,0.00007658713,0.000066499706,0.003846874,0.00086501957,0.0004514205,0.00013243158,0.00092590385,0.00007080326],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00061025826,0.00073583744,0.4031157,0.000076602424,0.0000320692,0.0000032708276,0.20394892,0.00007380628,0.00061482645,0.056789506,0.00094240025,0.3330568],"study_design_scores_gemma":[0.00061430456,0.000095120646,0.6532112,0.000011189224,0.0000015765658,5.91594e-8,0.33817244,0.00027223892,0.0001749126,0.0041677956,0.0031997375,0.00007944157],"about_ca_topic_score_codex":0.00093695836,"about_ca_topic_score_gemma":0.012813932,"teacher_disagreement_score":0.33297738,"about_ca_system_score_codex":0.00022460982,"about_ca_system_score_gemma":0.001447323,"threshold_uncertainty_score":0.9614544},"labels":[],"label_agreement":null},{"id":"W2013250096","doi":"10.1002/ev.20007","title":"When one must go: The Canadian experience with strategic review and judging program value","year":2012,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Valuation (finance); Function (biology); Government (linguistics); Value (mathematics); Citizen journalism; Public relations; Process (computing); Value for money; Public administration; Business; Political science; Economics; Public economics; Computer science; Accounting; Law","score_opus":0.38211926976493,"score_gpt":0.524848788433648,"score_spread":0.14272951866871803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013250096","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5310917,0.04930536,0.008846051,0.10464218,0.0038329044,0.030395804,0.000064510925,0.00051046285,0.271311],"genre_scores_gemma":[0.9895501,0.000372417,0.0050799525,0.001238898,0.00021974616,0.0014519378,0.000027448306,0.000012605479,0.0020469066],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974876,0.00028447254,0.00036299377,0.00027355138,0.0012912492,0.00030010534],"domain_scores_gemma":[0.9982114,0.0002894883,0.00018674156,0.00039591195,0.00066985574,0.0002466147],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0075106025,0.000119651624,0.00016415729,0.00016297353,0.00089725514,0.00034020544,0.00019868347,0.00004593869,0.0012569275],"category_scores_gemma":[0.0005795008,0.000073465984,0.0000439995,0.00067489763,0.00007698065,0.00075787975,0.000016778446,0.00010517418,0.00007023394],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014444476,0.00011263824,0.014618085,0.000042452666,0.00004323125,5.1899615e-8,0.0050878134,0.00039331667,0.000027565133,0.008344883,0.010945407,0.9603701],"study_design_scores_gemma":[0.002063702,0.00063590537,0.19599095,0.00042303512,0.001104438,0.00004625676,0.00545183,0.08325389,0.00019627399,0.022606658,0.6875635,0.00066357065],"about_ca_topic_score_codex":0.008264406,"about_ca_topic_score_gemma":0.10604155,"teacher_disagreement_score":0.95970654,"about_ca_system_score_codex":0.00023403652,"about_ca_system_score_gemma":0.0010595373,"threshold_uncertainty_score":0.9996561},"labels":[],"label_agreement":null},{"id":"W2014034431","doi":"10.3138/cjpe.29.2.21","title":"Les défis de l’évaluation d'un programme d'intervention en contexte carcéral","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université du Québec à Trois-Rivières; Centre Jeunesse de Quebec","funders":"","keywords":"Prison; Valuation (finance); Government (linguistics); Psychology; Intervention (counseling); Public relations; Welfare economics; Political science; Business; Sociology; Applied psychology; Criminology; Economics; Finance; Psychiatry","score_opus":0.29812468333778513,"score_gpt":0.5076521920618863,"score_spread":0.20952750872410114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014034431","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93198735,0.00038223452,0.058638334,0.0030131429,0.001010433,0.0013903506,0.0000053379013,0.000025903619,0.0035469453],"genre_scores_gemma":[0.9843554,0.000007485693,0.014716613,0.00015746537,0.0003802183,0.00012446543,0.000026289601,0.000016108723,0.0002159829],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9914603,0.0039020374,0.0013026382,0.00026535912,0.0026047612,0.00046485887],"domain_scores_gemma":[0.99379027,0.000662523,0.0010219399,0.0003316745,0.003589748,0.0006038534],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06763887,0.00017148347,0.00030065456,0.0007434563,0.00034329822,0.0006582044,0.0005640265,0.00014783633,0.002534762],"category_scores_gemma":[0.012622556,0.00014023951,0.00028526262,0.0006534341,0.000109175504,0.00072126806,0.000016497463,0.0003028667,0.000093258735],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020143412,0.000056371187,0.03537898,0.0000054799757,0.00003018394,0.0000016651909,0.0023092725,0.0014761053,0.00006913379,0.0012333262,0.00054839754,0.95887095],"study_design_scores_gemma":[0.003488655,0.001895664,0.494542,0.00013206185,0.00026799794,0.00012138887,0.0025983602,0.33044395,0.00057877373,0.053858083,0.1117418,0.00033125895],"about_ca_topic_score_codex":0.0025259196,"about_ca_topic_score_gemma":0.023518635,"teacher_disagreement_score":0.95853966,"about_ca_system_score_codex":0.0009659827,"about_ca_system_score_gemma":0.0024539954,"threshold_uncertainty_score":0.9983771},"labels":[],"label_agreement":null},{"id":"W2014137215","doi":"10.1016/s0840-4704(10)60793-4","title":"Differentiating among Research, Evaluation and Measures to Assure Quality","year":2000,"lang":"en","type":"article","venue":"Healthcare Management Forum","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen Elizabeth II Health Sciences Centre","funders":"","keywords":"Generalizability theory; Causation; Quality (philosophy); Computer science; Process (computing); Key (lock); Process management; Risk analysis (engineering); Management science; Psychology; Medicine; Business; Computer security; Engineering; Political science","score_opus":0.517590888120203,"score_gpt":0.6212372567458465,"score_spread":0.10364636862564347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014137215","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90061975,0.00025169423,0.0007761944,0.04459513,0.000267492,0.0019645453,0.0000094501365,0.00006172428,0.051454034],"genre_scores_gemma":[0.99084574,0.0001230642,0.0006023415,0.0017399074,0.00006181696,0.00022728778,0.000013768814,0.00001166343,0.0063743987],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9896041,0.0022146634,0.00082608795,0.0006919754,0.006063229,0.00059990905],"domain_scores_gemma":[0.99749273,0.00043229456,0.00013595218,0.0007219762,0.0009371456,0.00027989535],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.031619098,0.00014620097,0.00024080653,0.000494282,0.0007699725,0.00043895273,0.00042202958,0.000068577276,0.0030533203],"category_scores_gemma":[0.000732397,0.000115801355,0.000054776523,0.0010860942,0.00006669124,0.00037861106,0.00021755951,0.00023348608,0.00050698576],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003394033,0.00003020168,0.15782341,0.000030394121,0.000014054458,7.791013e-7,0.0007720916,0.00019519501,0.0000040326527,0.0056174737,0.008625913,0.8268525],"study_design_scores_gemma":[0.0004541461,0.00012747518,0.8946637,0.000060694027,0.000011100693,4.2850974e-7,0.006258462,0.0076341415,0.000014711212,0.018401405,0.072220385,0.00015333579],"about_ca_topic_score_codex":0.0005565695,"about_ca_topic_score_gemma":0.004126152,"teacher_disagreement_score":0.8266992,"about_ca_system_score_codex":0.00017398404,"about_ca_system_score_gemma":0.00008189825,"threshold_uncertainty_score":0.99785805},"labels":[],"label_agreement":null},{"id":"W2014366393","doi":"10.1177/1356389003094006","title":"Evaluability Assessment: A Tool for Incorporating Evaluation in Social Change Programmes","year":2003,"lang":"en","type":"article","venue":"Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; University of Calgary","funders":"","keywords":"Behaviour change; Social change; Theory of change; Process management; Political science; Engineering ethics; Management science; Sociology; Public relations; Psychology; Engineering; Psychological intervention","score_opus":0.4539931329436821,"score_gpt":0.5881362452183663,"score_spread":0.13414311227468417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014366393","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9666018,0.00014199883,0.008847391,0.0023480614,0.0009464109,0.009916979,0.000018141756,0.000057110727,0.011122104],"genre_scores_gemma":[0.9837788,0.0000022154602,0.008671657,0.00028212252,0.00028671673,0.0067166216,0.00014313804,0.000017798486,0.00010098233],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9859606,0.0043205954,0.0015095995,0.00087435526,0.006894502,0.0004403371],"domain_scores_gemma":[0.9941632,0.0010792287,0.0007343861,0.0004998351,0.0034611674,0.00006217799],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11808656,0.00022942794,0.0003616562,0.00047265718,0.00048393814,0.0003664751,0.0003139536,0.00016008824,0.0024369794],"category_scores_gemma":[0.013360029,0.00019872378,0.00016141747,0.0014786106,0.00007076483,0.0013693722,0.00004091121,0.00018983333,0.000081349084],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005073347,0.00034721973,0.14789762,0.000021944626,0.000016173582,1.5099911e-7,0.0032805898,0.00228102,0.00026125592,0.020239754,0.00075291377,0.8248506],"study_design_scores_gemma":[0.0026764646,0.000147888,0.36203307,0.000015061472,0.000064256164,8.96538e-7,0.00092909427,0.4717394,0.00010413649,0.15933119,0.00274651,0.00021201151],"about_ca_topic_score_codex":0.000022984923,"about_ca_topic_score_gemma":0.00032365287,"teacher_disagreement_score":0.8246386,"about_ca_system_score_codex":0.0009796759,"about_ca_system_score_gemma":0.0018175447,"threshold_uncertainty_score":0.99847496},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"opus","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W2014453428","doi":"10.1097/00124645-200209000-00007","title":"Program Evaluation in Pediatric Education","year":2002,"lang":"en","type":"article","venue":"Journal for Nurses in Staff Development","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Hospital for Sick Children; Golder Associates (Canada)","funders":"","keywords":"Accountability; Participatory evaluation; Program evaluation; Nursing; Citizen journalism; Sick child; Process (computing); Medical education; Medicine; Process management; Psychology; Business; Political science; Computer science; Pediatrics","score_opus":0.25293065965254286,"score_gpt":0.5422232516733579,"score_spread":0.2892925920208151,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014453428","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97392106,0.0006011435,0.00025397592,0.0012415941,0.010177899,0.0022035474,0.0000013481529,0.000017372315,0.011582037],"genre_scores_gemma":[0.9700084,0.00026920956,0.016710063,0.00012866767,0.00032167137,0.0010337272,0.0000115278635,0.000013398282,0.0115033705],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99602646,0.00019785695,0.001161078,0.00027013005,0.0020596539,0.00028483832],"domain_scores_gemma":[0.99830323,0.00025711014,0.00038322856,0.00018411328,0.00077540707,0.00009692419],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0077012875,0.00012339924,0.00018692439,0.001001237,0.00016297564,0.00027195172,0.00034927257,0.000063790285,0.0015965566],"category_scores_gemma":[0.0012748288,0.000095716336,0.00005662949,0.0010651529,0.00001590777,0.00056632084,0.00002480216,0.00019297794,0.00015229922],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014649456,0.0007956617,0.061591968,0.000005436289,0.0000026546793,6.1904933e-7,0.0030291076,0.000769715,0.0000021923663,0.00009929463,0.021016732,0.912672],"study_design_scores_gemma":[0.0016566197,0.00024308637,0.28081942,0.000050986346,0.000013244148,0.000021971719,0.0037493494,0.036568407,0.000043368495,0.0073955534,0.669193,0.00024495504],"about_ca_topic_score_codex":0.0000015759899,"about_ca_topic_score_gemma":0.00012940596,"teacher_disagreement_score":0.912427,"about_ca_system_score_codex":0.00070361164,"about_ca_system_score_gemma":0.0011362233,"threshold_uncertainty_score":0.9993161},"labels":[],"label_agreement":null},{"id":"W2014719558","doi":"10.1016/j.childyouth.2008.11.001","title":"Brief and intensive family support program to prevent emergency placements: Lessons learned from a process evaluation","year":2008,"lang":"en","type":"article","venue":"Children and Youth Services Review","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; Université de Montréal","funders":"","keywords":"Process (computing); Psychology; Process management; Medical emergency; Medicine; Computer science; Engineering; Programming language","score_opus":0.246263387113279,"score_gpt":0.500102376527176,"score_spread":0.25383898941389704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014719558","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9515191,0.039157182,0.000034844194,0.0048931767,0.00016451,0.0029017113,0.00015532708,0.000047093763,0.0011270774],"genre_scores_gemma":[0.88011986,0.10973265,0.0002263046,0.008442327,0.00008334348,0.00028380295,0.000679659,0.000018337481,0.0004137128],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9963805,0.00027754542,0.00083567266,0.00072738726,0.0015386362,0.00024023638],"domain_scores_gemma":[0.99770373,0.000046250665,0.00037156048,0.00044583625,0.0011947477,0.00023789774],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0023152127,0.00023503524,0.00047557233,0.000112233334,0.00026122626,0.00010412701,0.00037137253,0.00005745501,0.0012945123],"category_scores_gemma":[0.00024246353,0.00016703822,0.000074251,0.0006125473,0.000043200365,0.00046169705,0.00017076857,0.0001224251,0.00016797576],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044967164,0.00027831094,0.079710566,0.0003651735,0.00010918892,0.0000011954842,0.020281801,0.000022579141,0.000015695476,0.00003031273,0.003040383,0.8960998],"study_design_scores_gemma":[0.0014350171,0.0006169289,0.9689087,0.0022941225,0.00054339867,0.000024775089,0.007284397,0.0023485117,0.000037627564,0.0014705111,0.014393853,0.0006421073],"about_ca_topic_score_codex":0.00021443224,"about_ca_topic_score_gemma":0.00013678115,"teacher_disagreement_score":0.89545774,"about_ca_system_score_codex":0.000023239072,"about_ca_system_score_gemma":0.00017078119,"threshold_uncertainty_score":0.9996184},"labels":[],"label_agreement":null},{"id":"W2014815450","doi":"10.1080/13561820903078157","title":"Training trainees, young activists, to conduct awareness campaigns about prevention of substance abuse among Lebanese/Armenian young people","year":2009,"lang":"en","type":"article","venue":"Journal of Interprofessional Care","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Armenian; Substance abuse; Psychology; Medical education; Political science; Medicine; Psychiatry","score_opus":0.15422098172521537,"score_gpt":0.4873518679039151,"score_spread":0.33313088617869974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014815450","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9916791,0.00023104849,0.0042165043,0.00045053934,0.0017874469,0.00027234099,0.000022279355,0.000011565064,0.0013292172],"genre_scores_gemma":[0.9970479,0.00003207665,0.0015180006,0.00016588192,0.00026623384,0.000009005333,0.00001272049,0.0000144740125,0.00093373563],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9947306,0.00042885073,0.0016105721,0.00031359863,0.0026107815,0.00030561924],"domain_scores_gemma":[0.9954617,0.00037453466,0.0014485797,0.00034472908,0.0021166713,0.000253769],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030634606,0.00023959462,0.00069094397,0.00058494916,0.00020951979,0.00012130442,0.000822259,0.00012127968,0.0008502721],"category_scores_gemma":[0.00036329747,0.00016617721,0.0003541586,0.00080288446,0.000058580157,0.0011037291,0.000021939042,0.00046123812,0.000013813769],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002174223,0.00036173422,0.36011028,0.00006271695,0.00009740017,0.000039397743,0.558354,0.002183413,0.023747046,0.00013464844,0.0027582822,0.04997686],"study_design_scores_gemma":[0.0011424397,0.00096817256,0.7750543,0.0017881728,0.00004384787,0.00011752066,0.21520628,0.00058026466,0.0036269627,0.00084420794,0.00033934956,0.00028850808],"about_ca_topic_score_codex":0.000019495774,"about_ca_topic_score_gemma":0.001703705,"teacher_disagreement_score":0.414944,"about_ca_system_score_codex":0.00025808168,"about_ca_system_score_gemma":0.00087421475,"threshold_uncertainty_score":0.9309883},"labels":[],"label_agreement":null},{"id":"W2015203864","doi":"10.12927/hcpol.2011.22132","title":"The Inside Story: Knowledge Translation Lessons from the Need to Know Team","year":2011,"lang":"en","type":"article","venue":"Healthcare policy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Manitoba; Manitoba Health","funders":"","keywords":"Knowledge translation; Health care; Sociology; Engineering ethics; Library science; Political science; Public relations; Knowledge management; Engineering; Law; Computer science","score_opus":0.5379846996749881,"score_gpt":0.5620614457758011,"score_spread":0.024076746100813007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015203864","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1045521,0.0029142823,0.0010864795,0.8266843,0.0013308132,0.0010830216,0.000091002585,0.00010234873,0.062155645],"genre_scores_gemma":[0.98895615,0.00023899622,0.00040707688,0.00793627,0.0006395434,0.00007703512,0.0000062551703,0.000013490346,0.0017252086],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99692994,0.0010425946,0.00048640597,0.00031680774,0.00086252246,0.00036171684],"domain_scores_gemma":[0.9959063,0.0023737827,0.00016776085,0.000883528,0.00043369105,0.00023491586],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0041381675,0.00013646307,0.0001723637,0.00016423385,0.0010630009,0.00015732615,0.00081215496,0.00007789491,0.00025032987],"category_scores_gemma":[0.0014233107,0.000068938825,0.00008756,0.0010379996,0.00008757781,0.00019898104,0.00007792815,0.00028416858,0.0017256299],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048738442,0.000034502078,0.007397968,0.0000024197166,0.000008927732,2.0206251e-7,0.06034672,0.000009620801,0.00003573695,0.037855186,0.07051479,0.8237452],"study_design_scores_gemma":[0.00021017918,0.00008577584,0.17060737,0.000019409514,0.0000050618864,9.98305e-7,0.007978368,0.0008083132,0.00009651083,0.016777748,0.80330867,0.00010161112],"about_ca_topic_score_codex":0.007191774,"about_ca_topic_score_gemma":0.03805534,"teacher_disagreement_score":0.884404,"about_ca_system_score_codex":0.00014810942,"about_ca_system_score_gemma":0.0013006933,"threshold_uncertainty_score":0.99941945},"labels":[],"label_agreement":null},{"id":"W2015742271","doi":"10.1016/s0277-9536(01)00247-7","title":"Evaluating the participatory process in a community-based heart health project","year":2002,"lang":"en","type":"article","venue":"Social Science & Medicine","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":114,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vancouver Coastal Health; University of Victoria; Ministry of Health","funders":"","keywords":"Participatory action research; Agency (philosophy); Fieldnotes; Public relations; Project team; Community-based participatory research; Citizen journalism; Community project; Population; Sociology; Psychology; Medical education; Business; Medicine; Political science; Knowledge management; Environmental health; Computer science","score_opus":0.701204145841031,"score_gpt":0.6632814748752291,"score_spread":0.03792267096580182,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015742271","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93031967,0.00010227734,0.000071821436,0.061251312,0.0002790977,0.00056043634,0.0000013335484,0.00002842516,0.0073856404],"genre_scores_gemma":[0.9862035,0.0000035149228,0.000040605708,0.013376956,0.00015939129,0.0000875699,0.0000010970155,0.0000044600874,0.00012291115],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99203646,0.0018740657,0.00073253777,0.00031058842,0.004522403,0.00052391796],"domain_scores_gemma":[0.99764806,0.0010449251,0.00030049344,0.00042542873,0.00046728522,0.00011378637],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.062040683,0.000112637514,0.00028666557,0.00033141565,0.0022374853,0.00011092631,0.0011149005,0.00003224736,0.0007887106],"category_scores_gemma":[0.0047217356,0.000060676728,0.000038796123,0.0044900645,0.0017074167,0.00037750934,0.0000565225,0.00046826023,0.00005804396],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043524535,0.00047054832,0.1457466,0.000047318765,0.000003802639,0.000001254186,0.6240122,0.001012003,0.0011390318,0.0014639036,0.018491099,0.20756876],"study_design_scores_gemma":[0.004942551,0.003823951,0.29725543,0.0004279847,0.000024046376,0.000007457931,0.18033025,0.46778008,0.0002845346,0.014764168,0.02976443,0.0005951241],"about_ca_topic_score_codex":0.00045790468,"about_ca_topic_score_gemma":0.00034862166,"teacher_disagreement_score":0.46676806,"about_ca_system_score_codex":0.00023398561,"about_ca_system_score_gemma":0.0014192039,"threshold_uncertainty_score":0.99906147},"labels":[],"label_agreement":null},{"id":"W2015789889","doi":"10.1007/s10459-012-9425-5","title":"Response to R. Ellaway","year":2012,"lang":"en","type":"letter","venue":"Advances in Health Sciences Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Medicine; Medical education; Psychology","score_opus":0.18171590779133415,"score_gpt":0.5861697159959158,"score_spread":0.40445380820458166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015789889","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020894038,0.008396832,0.0004962292,0.9631792,0.009487387,0.0009813415,0.000012551604,0.000033276698,0.015323782],"genre_scores_gemma":[0.014815062,0.0010830809,0.00787165,0.9605589,0.0024673163,0.0003129868,0.00003104193,0.000019909918,0.012840045],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99072737,0.0018085539,0.0016540714,0.0010585414,0.0037888405,0.0009626467],"domain_scores_gemma":[0.9942514,0.0031839604,0.0009948926,0.00088272337,0.0004119701,0.0002751095],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.029816035,0.00029178293,0.0004974169,0.0018442353,0.0004914041,0.0003229489,0.0016949188,0.00023702886,0.0015564124],"category_scores_gemma":[0.0031713839,0.00022558525,0.00007913154,0.003721639,0.00024914462,0.0018616483,0.00012187079,0.00080203585,0.0019563206],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027550119,0.00005016755,0.007317432,0.000042556767,6.583482e-7,4.960891e-7,0.0011394853,0.00073017157,0.0000022186855,0.00035359967,0.8260488,0.16428687],"study_design_scores_gemma":[0.000079431775,0.00023133907,0.006694736,0.00018296407,0.0000013885946,0.0000061289475,0.00080117054,0.00016348332,0.000007107433,0.007236087,0.9843411,0.0002550693],"about_ca_topic_score_codex":0.00017233194,"about_ca_topic_score_gemma":0.00026084553,"teacher_disagreement_score":0.1640318,"about_ca_system_score_codex":0.0007261051,"about_ca_system_score_gemma":0.007001012,"threshold_uncertainty_score":0.9993563},"labels":[],"label_agreement":null},{"id":"W2017203098","doi":"10.7202/1025741ar","title":"L’approche réaliste pour l’évaluation de programmes et la revue systématique","year":2014,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Humanities; Political science; Valuation (finance); Philosophy; Sociology; Economics","score_opus":0.1598021174624361,"score_gpt":0.49397242339533,"score_spread":0.3341703059328939,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017203098","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21872741,0.00072977756,0.47754833,0.23244162,0.003951454,0.0021637988,0.000027733031,0.00021990744,0.06418995],"genre_scores_gemma":[0.906995,0.0005322972,0.053602103,0.0026883166,0.0008214938,0.0005855731,0.0004688874,0.00007028354,0.03423602],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9543046,0.039051153,0.0018501783,0.0010718213,0.0030575355,0.00066470774],"domain_scores_gemma":[0.9887555,0.0066157943,0.0012194532,0.0010253952,0.0021451323,0.00023871599],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.17982362,0.00047615898,0.0005461247,0.0005575742,0.0003532655,0.0010684375,0.00065335614,0.0005874999,0.0023898024],"category_scores_gemma":[0.018097214,0.00046604997,0.00025293868,0.0012258413,0.00013710541,0.0018454236,0.000099063676,0.00067601574,0.0017702813],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055418746,0.00082947745,0.017135492,0.000395581,0.00009415628,0.0000011331504,0.2015523,0.026040161,0.0016206295,0.13120483,0.029514309,0.5915565],"study_design_scores_gemma":[0.0013860246,0.00023860982,0.31809068,0.00058327,0.0002590815,0.00007355487,0.0056117414,0.41203222,0.0007893332,0.0845308,0.17577791,0.0006267597],"about_ca_topic_score_codex":0.00024707647,"about_ca_topic_score_gemma":0.0005812879,"teacher_disagreement_score":0.6882676,"about_ca_system_score_codex":0.0008068647,"about_ca_system_score_gemma":0.006064754,"threshold_uncertainty_score":0.9999685},"labels":[],"label_agreement":null},{"id":"W2017595603","doi":"10.7202/003987ar","title":"Konstruktive Evaluation: Versuch eines Evaluationskonzepts für den Unterricht","year":2002,"lang":"fr","type":"article","venue":"Meta Journal des traducteurs","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Humanities; Philosophy","score_opus":0.34995795087401077,"score_gpt":0.48808725477185905,"score_spread":0.13812930389784828,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017595603","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23723419,0.6411769,0.012811597,0.052660804,0.020240756,0.0015303226,0.0001071073,0.000078248406,0.034160066],"genre_scores_gemma":[0.7481454,0.09569695,0.016807195,0.002261209,0.003177871,0.00020448858,0.000034835593,0.00013329127,0.13353874],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9835668,0.0048565674,0.0022164385,0.00087216566,0.0075094993,0.0009785043],"domain_scores_gemma":[0.9906308,0.0018583024,0.0011544587,0.0009061087,0.004735822,0.00071448716],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.020373747,0.0006602033,0.0010021104,0.0009976696,0.0015969536,0.0018083225,0.0014346587,0.00026239335,0.18709561],"category_scores_gemma":[0.0063505042,0.00051753083,0.0010186685,0.0026953726,0.000918073,0.0039185346,0.00011484866,0.0010487948,0.00679567],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046400706,0.000475408,0.0041205673,0.000024625728,0.0021043282,0.000031876472,0.0032771565,0.008860432,0.0001092949,0.0032007731,0.0448405,0.93290865],"study_design_scores_gemma":[0.004356377,0.0009907798,0.028495668,0.00027777994,0.013573716,0.0026508127,0.0030969055,0.25771835,0.0004015599,0.09546012,0.59183717,0.0011407638],"about_ca_topic_score_codex":0.00003583795,"about_ca_topic_score_gemma":0.00014490524,"teacher_disagreement_score":0.9317679,"about_ca_system_score_codex":0.00082956976,"about_ca_system_score_gemma":0.00095879403,"threshold_uncertainty_score":0.9997276},"labels":[],"label_agreement":null},{"id":"W2017680079","doi":"10.1002/ev.344","title":"Strategy evaluation: Experience at the International Development Research Centre","year":2010,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"International Development Research Centre","funders":"","keywords":"Corporation; Program evaluation; Strategic planning; Modalities; International development; Sociology; Management; Business; Public relations; Political science; Economics; Public administration; Social science","score_opus":0.5427282247833871,"score_gpt":0.6215806160734704,"score_spread":0.07885239129008326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017680079","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91039073,0.00014094659,0.0014902004,0.016930474,0.0060203075,0.0027575218,0.000012960522,0.00006168388,0.062195197],"genre_scores_gemma":[0.9515751,0.000011510159,0.0018905506,0.00021763319,0.0007345419,0.0011255036,0.00014056708,0.00001488827,0.04428971],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9894697,0.0006429789,0.00076087797,0.0006443333,0.008142579,0.00033953506],"domain_scores_gemma":[0.99081004,0.0016812054,0.00025631962,0.0007585415,0.0063509173,0.00014300107],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.037252042,0.0001469221,0.00013060197,0.000405758,0.0017441866,0.00062192057,0.0008644863,0.000106243184,0.03820798],"category_scores_gemma":[0.008411651,0.00010012754,0.00009906555,0.0010996154,0.00013935176,0.00076802645,0.0001624214,0.00031341743,0.0012144872],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005336565,0.000089406385,0.0049950867,0.0000011643777,0.000027037691,6.855896e-8,0.0040438185,0.0028557577,0.003933436,0.0022790388,0.08839645,0.8933254],"study_design_scores_gemma":[0.0012715538,0.000038290716,0.05281446,0.0000072867156,0.000028728715,0.0000061117084,0.0034192987,0.15311489,0.008417612,0.01147851,0.7692514,0.00015183043],"about_ca_topic_score_codex":0.00007421249,"about_ca_topic_score_gemma":0.0074876235,"teacher_disagreement_score":0.8931735,"about_ca_system_score_codex":0.00066953537,"about_ca_system_score_gemma":0.002814644,"threshold_uncertainty_score":0.99994093},"labels":[],"label_agreement":null},{"id":"W2018516961","doi":"10.1080/15423166.2013.812891","title":"Evaluation in Conflict Zones: Methodological and Ethical Challenges","year":2013,"lang":"en","type":"article","venue":"Journal of Peacebuilding & Development","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"International Development Research Centre","funders":"","keywords":"Field (mathematics); Peacebuilding; Politics; Engineering ethics; Sociology; Political science; Management science; Engineering; Public administration; Law","score_opus":0.620984892819336,"score_gpt":0.5573198522001579,"score_spread":0.0636650406191781,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2018516961","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9760818,0.0028936523,0.0059577567,0.012709365,0.00039489486,0.00027963778,1.1860949e-7,0.000006687855,0.0016760707],"genre_scores_gemma":[0.9098528,0.0013430369,0.08814403,0.0004908154,0.0000790658,0.00002192496,3.003509e-7,0.0000052719884,0.00006276925],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9930593,0.0017968942,0.0013752291,0.00024427316,0.0032935243,0.00023080532],"domain_scores_gemma":[0.9952993,0.0022807547,0.0006266243,0.00014952284,0.0014828746,0.00016093024],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.063689396,0.00012856966,0.00039598308,0.00049341796,0.00008953506,0.00017907946,0.00032039048,0.0001658426,0.0013026472],"category_scores_gemma":[0.008494343,0.00008165406,0.00005636614,0.00027439732,0.000058171678,0.0003417299,0.000098647324,0.0005459985,0.00006524096],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002590976,0.000064826134,0.009497483,0.000008252421,0.00003585606,0.0000051170314,0.0073380624,0.00049216615,0.0011479487,0.0019092837,0.0020767218,0.9773984],"study_design_scores_gemma":[0.001625248,0.00023349469,0.9142799,0.00015213773,0.000027720309,0.00010980763,0.0067244293,0.008416205,0.0008679258,0.02185745,0.045464937,0.0002407465],"about_ca_topic_score_codex":0.000004944347,"about_ca_topic_score_gemma":0.000025653728,"teacher_disagreement_score":0.97715765,"about_ca_system_score_codex":0.00021774703,"about_ca_system_score_gemma":0.000655606,"threshold_uncertainty_score":0.99985754},"labels":[],"label_agreement":null},{"id":"W2018648456","doi":"10.1023/a:1004066415147","title":"Performance indicators as conceptual technologies","year":2000,"lang":"en","type":"article","venue":"Higher Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":64,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Medical Association","funders":"","keywords":"Typology; Normative; Higher education; Sociology; Psychology; Epistemology; Political science; Anthropology; Philosophy","score_opus":0.10961919285035762,"score_gpt":0.46575735300886567,"score_spread":0.3561381601585081,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2018648456","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7695858,0.00015362429,0.0000024149158,0.0038029044,0.00066427194,0.000110586916,8.9702394e-7,0.00011347319,0.22556601],"genre_scores_gemma":[0.8806126,0.000102490994,0.00025709218,0.00076784263,0.00010418722,0.00005855612,0.000009028053,0.0000055993864,0.118082605],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99823374,0.00006254155,0.00034256067,0.00028379384,0.00091227586,0.00016509027],"domain_scores_gemma":[0.9991257,0.00010766208,0.00012123293,0.00046351622,0.00013246713,0.000049408347],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0007131957,0.00009803509,0.00011214597,0.0002858453,0.00016970989,0.00011417082,0.00046362472,0.00008523313,0.05792356],"category_scores_gemma":[0.000076269,0.00007284321,0.000036026224,0.00097288593,0.00015977,0.00052003737,0.000024615407,0.00011571511,0.011354665],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000118352655,0.00010422088,0.094764665,0.0000016472102,0.000004126466,1.064953e-7,0.0007404488,0.000054266595,0.000047328358,0.013939453,0.032749787,0.8575821],"study_design_scores_gemma":[0.00010531204,0.00005756773,0.2822735,0.000007413251,0.000003933548,0.0000021902326,0.0013240591,0.0000906076,0.0006109177,0.0037974985,0.71163046,0.00009651846],"about_ca_topic_score_codex":0.000010811295,"about_ca_topic_score_gemma":0.0000013080092,"teacher_disagreement_score":0.8574856,"about_ca_system_score_codex":0.00006420832,"about_ca_system_score_gemma":0.0004692344,"threshold_uncertainty_score":0.9894151},"labels":[],"label_agreement":null},{"id":"W2019371312","doi":"10.1016/j.evalprogplan.2013.05.004","title":"Defining, illustrating and reflecting on logic analysis with an example from a professional development program","year":2013,"lang":"en","type":"article","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sante Montreal; Université de Sherbrooke; Université de Montréal","funders":"Canadian Institutes of Health Research","keywords":"Logic model; Promotion (chess); Computer science; Intervention (counseling); Field (mathematics); Context (archaeology); Point (geometry); Management science; Risk analysis (engineering); Engineering ethics; Medicine; Engineering; Sociology; Nursing; Political science; Mathematics","score_opus":0.49624831202339564,"score_gpt":0.5912364724906018,"score_spread":0.0949881604672062,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019371312","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.994273,0.00016865315,0.0008172073,0.00023222664,0.000086831555,0.0013500255,0.0000013191712,0.00012748779,0.002943227],"genre_scores_gemma":[0.90576285,0.0000019644258,0.0927014,0.00027538958,0.00003952765,0.00081533974,0.00018400146,0.000008862922,0.00021068263],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.996027,0.00049740734,0.00059361296,0.00067036983,0.0019314156,0.00028020612],"domain_scores_gemma":[0.9979268,0.0006544198,0.00039650084,0.00025341706,0.000587863,0.00018103753],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005740801,0.00019970567,0.000277908,0.00034527227,0.0006695406,0.00094820064,0.00014710268,0.000085725114,0.0011674529],"category_scores_gemma":[0.00029894745,0.00012866578,0.000030184712,0.00090967386,0.00006660996,0.00061834085,0.00005507271,0.00021233695,0.000035877787],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042615073,0.0001490454,0.16162346,0.0000028649843,0.000082401966,6.959576e-7,0.006829983,0.0014481661,0.00001886832,0.00020484204,0.000069831076,0.8295272],"study_design_scores_gemma":[0.00083872105,0.0008426649,0.5419786,0.000079248675,0.00011461445,0.0000029181208,0.008555421,0.44370326,0.000051630843,0.0015495225,0.0020466945,0.00023671275],"about_ca_topic_score_codex":0.00026282723,"about_ca_topic_score_gemma":0.00034256073,"teacher_disagreement_score":0.8292905,"about_ca_system_score_codex":0.000043710446,"about_ca_system_score_gemma":0.000261167,"threshold_uncertainty_score":0.9997456},"labels":[],"label_agreement":null},{"id":"W2019919882","doi":"10.4102/aej.v1i1.43","title":"Participatory evaluation for development: Examining research-based knowledge from within the African context","year":2013,"lang":"en","type":"article","venue":"African Evaluation Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Popularity; Context (archaeology); Empowerment; Thematic analysis; Participatory development; Citizen journalism; Relevance (law); Participatory action research; Sociology; Participatory evaluation; Engineering ethics; Public relations; Political science; Psychology; Qualitative research; Social science; Geography; Social psychology; Engineering","score_opus":0.7823683775505966,"score_gpt":0.5926367515141084,"score_spread":0.1897316260364882,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019919882","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95740104,0.0007515679,0.014832169,0.010407873,0.0014795888,0.0034015172,0.000012259955,0.000036302576,0.011677712],"genre_scores_gemma":[0.9941351,0.0000021273318,0.0027614047,0.0004569166,0.00058928615,0.0015354201,0.000030068926,0.00002556122,0.00046415385],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9819538,0.006818193,0.001738928,0.000503451,0.008423112,0.00056252896],"domain_scores_gemma":[0.9779324,0.007085966,0.001124137,0.00072810036,0.01277552,0.00035386666],"candidate_categories":["metaresearch","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.12066077,0.00023291001,0.00032753905,0.0006523647,0.0019605528,0.0012849823,0.0011028897,0.00010021799,0.010879472],"category_scores_gemma":[0.018394537,0.0001449023,0.00012385128,0.001355238,0.0003959598,0.00096198136,0.00009409778,0.0005521887,0.0014513952],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010208658,0.0001633825,0.004085686,0.0000036233173,0.0000970951,3.0056012e-7,0.046739437,0.008097026,0.00077740994,0.0011615937,0.0241406,0.9146318],"study_design_scores_gemma":[0.0027094046,0.00028619546,0.08128133,0.00006316959,0.0001147366,0.000003535413,0.08024337,0.7484306,0.0011880425,0.052513756,0.032886628,0.00027919965],"about_ca_topic_score_codex":0.0000454212,"about_ca_topic_score_gemma":0.0003736922,"teacher_disagreement_score":0.91435254,"about_ca_system_score_codex":0.0008564671,"about_ca_system_score_gemma":0.00693292,"threshold_uncertainty_score":0.9997518},"labels":[],"label_agreement":null},{"id":"W2019936193","doi":"10.1177/0163278713475868","title":"Evidence for the Validity of Grouped Self-Assessments in Measuring the Outcomes of Educational Programs","year":2013,"lang":"en","type":"article","venue":"Evaluation & the Health Professions","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"University of Saskatchewan","keywords":"Psychology; Correlation; Self-assessment; Applied psychology; Clinical psychology; Social psychology; Mathematics","score_opus":0.7640554176157064,"score_gpt":0.6509811233514293,"score_spread":0.11307429426427706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019936193","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7293256,0.0005438737,0.002422104,0.25571376,0.001376498,0.010296625,0.0000075750477,0.0000142099,0.00029978435],"genre_scores_gemma":[0.99307495,0.000098877594,0.0014711501,0.0009809423,0.000063616106,0.0038129347,0.000007729868,0.000008016662,0.00048177288],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9907905,0.0037458057,0.0015136687,0.00028574237,0.003364509,0.00029977757],"domain_scores_gemma":[0.97741455,0.018273495,0.001305989,0.0009160389,0.0020253367,0.00006461882],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.048608102,0.00013040596,0.0002894218,0.00012990771,0.0008927021,0.000071694434,0.0010376497,0.00005248429,0.0010778154],"category_scores_gemma":[0.0065846033,0.000051717703,0.00012826323,0.00088621146,0.00012291205,0.00050836155,0.00014304658,0.00024353246,0.000049656897],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003754543,0.0005722886,0.84013325,0.000071666684,0.00005809484,4.7742614e-9,0.012804403,0.0010101346,0.00006463919,0.0055765067,0.005803326,0.13386814],"study_design_scores_gemma":[0.00051278505,0.00012202809,0.89800644,0.0001629812,0.00003427896,2.6855525e-7,0.006454256,0.06970942,0.00002539808,0.024571931,0.00034471307,0.000055519333],"about_ca_topic_score_codex":0.0003419926,"about_ca_topic_score_gemma":0.0005935377,"teacher_disagreement_score":0.2637494,"about_ca_system_score_codex":0.00021244213,"about_ca_system_score_gemma":0.0032525281,"threshold_uncertainty_score":0.9998353},"labels":[],"label_agreement":null},{"id":"W2020589415","doi":"10.1590/s1413-81232004000300006","title":"Health promotion evaluation, realist synthesis and participacion","year":2004,"lang":"pt","type":"article","venue":"Ciência & Saúde Coletiva","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Health promotion; MEDLINE; Promotion (chess); Medicine; Political science; Public health; Nursing","score_opus":0.22667373777812633,"score_gpt":0.4747177610787036,"score_spread":0.2480440233005773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2020589415","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7207528,0.0035146608,0.019242773,0.23194376,0.0026011863,0.005476763,0.00021101003,0.00020980893,0.016047252],"genre_scores_gemma":[0.9958855,0.0005737049,0.00052732317,0.0013409328,0.00022424312,0.00031482457,0.00003467463,0.000031261472,0.0010675302],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99162966,0.0015330922,0.0014635784,0.0010367756,0.0036198217,0.0007170791],"domain_scores_gemma":[0.99586946,0.0006185733,0.00088105624,0.00087737443,0.001215042,0.00053852616],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.014003495,0.00039285523,0.000683369,0.00038915616,0.0009507095,0.0005098076,0.00042666306,0.00020820177,0.003006811],"category_scores_gemma":[0.0037181994,0.00034403414,0.00013902568,0.001187033,0.0002655737,0.0007046457,0.00015363186,0.00030572462,0.0009365988],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023214163,0.0016357312,0.02041012,0.00023782536,0.00011801819,0.000009515357,0.012699081,0.004095216,0.0006844074,0.015437752,0.022392731,0.92204744],"study_design_scores_gemma":[0.008176101,0.0038642439,0.74248976,0.003334484,0.00070753804,0.00010772304,0.010597351,0.09141148,0.007925982,0.04512637,0.08395674,0.0023022185],"about_ca_topic_score_codex":0.00026434514,"about_ca_topic_score_gemma":0.0007862471,"teacher_disagreement_score":0.91974527,"about_ca_system_score_codex":0.0010399021,"about_ca_system_score_gemma":0.0031108437,"threshold_uncertainty_score":0.9999012},"labels":[],"label_agreement":null},{"id":"W2021958080","doi":"10.3917/es.031.0143","title":"L'introduction de la construction de sens dans l'implantation de politiques en éducation : apports et pistes de recherche","year":2013,"lang":"fr","type":"article","venue":"Education et sociétés","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Cégep Marie-Victorin","funders":"","keywords":"Humanities; Political science; Sociology; Philosophy","score_opus":0.3748860597684001,"score_gpt":0.6308946616460963,"score_spread":0.2560086018776962,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021958080","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6238848,0.00039316216,0.06501355,0.25701365,0.0071529117,0.0007213707,0.000023410217,0.00013049658,0.045666635],"genre_scores_gemma":[0.82768136,0.0052542277,0.10606086,0.005717016,0.003961831,0.00053779816,0.00034202728,0.000057200214,0.05038767],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98601365,0.011468963,0.00075830205,0.0005261155,0.00066385866,0.0005691333],"domain_scores_gemma":[0.99392796,0.0038425268,0.0005846964,0.00041573102,0.00091735146,0.00031175738],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.023692934,0.00026926462,0.0002570359,0.00029111214,0.00034107544,0.0007420171,0.00025473753,0.00063401036,0.013308302],"category_scores_gemma":[0.005895801,0.00029034892,0.00012721148,0.00051607355,0.00027118536,0.0018013355,0.000035117886,0.0008030734,0.0004886851],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000023353552,0.00081543037,0.055593092,0.00013063352,0.000077786106,9.771036e-7,0.14982715,0.0010631647,0.012919946,0.13246323,0.2185132,0.42857203],"study_design_scores_gemma":[0.0003782887,0.00009853191,0.30618927,0.00012393245,0.00013027877,0.00069437176,0.16010897,0.0062420317,0.00886815,0.39677665,0.11994104,0.00044848118],"about_ca_topic_score_codex":0.0044599944,"about_ca_topic_score_gemma":0.00021312604,"teacher_disagreement_score":0.42812356,"about_ca_system_score_codex":0.0068313833,"about_ca_system_score_gemma":0.020383393,"threshold_uncertainty_score":0.9999549},"labels":[],"label_agreement":null},{"id":"W2022040053","doi":"10.1177/0959353506067853","title":"Book Review: Participatory Research and Action: A Guide to Becoming a Researcher for Social Change","year":2006,"lang":"en","type":"article","venue":"Feminism & Psychology","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Participatory action research; Citizen journalism; Action (physics); Sociology; Action research; Psychology; Political science; Pedagogy; Anthropology","score_opus":0.868918886293883,"score_gpt":0.7243712130393111,"score_spread":0.14454767325457196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2022040053","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07599139,0.07988095,0.0044239564,0.6725886,0.0023430993,0.0072922907,0.00008982158,0.0001504201,0.15723945],"genre_scores_gemma":[0.27050716,0.009922877,0.006789392,0.42927507,0.0076140957,0.011648,0.00006887372,0.00011788328,0.26405665],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965212,0.0005640026,0.0006179908,0.0005919208,0.0011659281,0.00053897273],"domain_scores_gemma":[0.997635,0.0010219062,0.00011542346,0.00044645078,0.0006454182,0.00013579588],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0145634925,0.00010773032,0.00027671357,0.00034446208,0.00045090358,0.000093163704,0.00040228138,0.00011826506,0.0030381833],"category_scores_gemma":[0.0007454476,0.0000888011,0.000062311236,0.0006167169,0.00019514681,0.00021529652,0.00013340039,0.00023723647,0.0005319331],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000556862,0.00006455146,0.0006178974,0.00002331413,0.000004306125,0.0000018009639,0.0011787041,1.289213e-7,0.00020495312,0.0010510775,0.9553914,0.04140616],"study_design_scores_gemma":[0.000503549,0.00032254003,0.033904415,0.000046442216,0.0000051680126,0.0000057432926,0.000288668,0.0000613131,0.000059101796,0.008424849,0.95628417,0.0000940654],"about_ca_topic_score_codex":0.00004206511,"about_ca_topic_score_gemma":0.00012421852,"teacher_disagreement_score":0.24331355,"about_ca_system_score_codex":0.000071991824,"about_ca_system_score_gemma":0.00010791034,"threshold_uncertainty_score":0.9978732},"labels":[],"label_agreement":null},{"id":"W2025194027","doi":"10.1177/0193841x12458103","title":"Measuring Stakeholder Participation in Evaluation","year":2012,"lang":"en","type":"article","venue":"Evaluation Review","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières; Université Laval","funders":"","keywords":"Intraclass correlation; Reliability (semiconductor); Stakeholder; Sample (material); Convergent validity; Psychology; Generalizability theory; Sample size determination; Scale (ratio); Statistics; Applied psychology; Psychometrics; Clinical psychology; Mathematics; Economics; Developmental psychology; Geography","score_opus":0.8475988642781547,"score_gpt":0.6249450003263772,"score_spread":0.22265386395177744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2025194027","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6679611,0.187464,0.002532478,0.009724199,0.0025818646,0.008335941,0.000006760418,0.00008862073,0.121305004],"genre_scores_gemma":[0.99438477,0.0023743007,0.00033534778,0.0015767487,0.00014983848,0.0008956148,0.000044016375,0.000010488492,0.00022888386],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98644745,0.0035799912,0.0015105358,0.00038788392,0.0076792208,0.00039490336],"domain_scores_gemma":[0.9963818,0.00048631395,0.000517922,0.00065549224,0.0018209134,0.00013756091],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.104222745,0.00015728186,0.00033885756,0.00031055574,0.00010964375,0.00009458444,0.00027786006,0.000057266698,0.024950214],"category_scores_gemma":[0.011957306,0.00012115324,0.000092047856,0.0014593095,0.00002389697,0.0015652125,0.000044175038,0.00013966387,0.0027040427],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005376884,0.00017200192,0.08618295,0.000083770836,0.000008492564,7.5323506e-8,0.0007156972,0.0021308307,0.00006354203,0.0008978101,0.005772951,0.9039665],"study_design_scores_gemma":[0.0011915267,0.00003484978,0.8213325,0.0009253917,0.00022461775,0.0000026840094,0.00023044505,0.12060682,0.00017534448,0.0048244963,0.050149556,0.00030178123],"about_ca_topic_score_codex":0.000008936398,"about_ca_topic_score_gemma":0.00006749839,"teacher_disagreement_score":0.9036647,"about_ca_system_score_codex":0.00041595098,"about_ca_system_score_gemma":0.00045854147,"threshold_uncertainty_score":0.99807245},"labels":[],"label_agreement":null},{"id":"W2025382442","doi":"10.1136/bmj.327.7412.0-f","title":"Learning from indigenous people","year":2003,"lang":"en","type":"article","venue":"BMJ","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Indigenous; Life expectancy; History; Population; Ethnology; Geography; Media studies; Genealogy; Gender studies; Sociology; Demography","score_opus":0.19348164484052452,"score_gpt":0.48915792863467905,"score_spread":0.29567628379415456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2025382442","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8897691,0.00003960598,0.0021147637,0.0006653428,0.00037944524,0.00012755621,0.0000011644181,0.000024800622,0.10687825],"genre_scores_gemma":[0.9881802,0.0000072486096,0.0013204399,0.00034901046,0.00007654472,0.000012335576,0.000004062632,0.000004032389,0.010046077],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99820095,0.0002513268,0.0002930916,0.00017921788,0.0009445152,0.00013088601],"domain_scores_gemma":[0.99900705,0.00043965975,0.00012461457,0.00025708668,0.000118626,0.000052977495],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0029379749,0.000052980846,0.00010560593,0.000070499525,0.000166596,0.00012872969,0.00018536032,0.0000326651,0.010008165],"category_scores_gemma":[0.0016424943,0.00003878506,0.000039318824,0.00031691758,0.000010519619,0.00015313354,0.000021020916,0.00009554806,0.004548515],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007431429,0.000040664527,0.8980082,6.94194e-7,0.000010422027,0.0000029893974,0.010226228,0.0022705381,0.00023732841,0.0017115518,0.018702665,0.06878128],"study_design_scores_gemma":[0.00037862253,0.000082090824,0.57881135,0.0000049090136,0.000005486832,0.000004516515,0.0050520855,0.003693342,0.00063201075,0.012561682,0.3986225,0.00015141908],"about_ca_topic_score_codex":0.00007158352,"about_ca_topic_score_gemma":0.00022952825,"teacher_disagreement_score":0.37991986,"about_ca_system_score_codex":0.000020505651,"about_ca_system_score_gemma":0.00017673739,"threshold_uncertainty_score":0.99622655},"labels":[],"label_agreement":null},{"id":"W2026325511","doi":"10.3917/riges.301.0063","title":"La collaboration comme changement organisationnel : le cas d'Uniterra","year":2005,"lang":"fr","type":"article","venue":"Gestion","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Employment and Social Development Canada; HEC Montréal","funders":"","keywords":"Humanities; Political science; Art","score_opus":0.21533408757721442,"score_gpt":0.45843034441078867,"score_spread":0.24309625683357425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026325511","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24417,0.0018793065,0.035837553,0.69201016,0.002949325,0.00068952993,0.000054689186,0.00009654293,0.022312904],"genre_scores_gemma":[0.9637741,0.00046014963,0.0040185438,0.0019691833,0.000673624,0.00004271442,0.000096100266,0.00001532438,0.02895025],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969627,0.0007708482,0.00057268003,0.00032890987,0.001112419,0.00025240195],"domain_scores_gemma":[0.9981182,0.000399316,0.00027932416,0.00037011094,0.0007093765,0.0001236527],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.004092235,0.00016871224,0.00017034836,0.0002537838,0.00040502954,0.00047337316,0.00023706832,0.00021375994,0.0065808413],"category_scores_gemma":[0.00046369556,0.00016594266,0.000046204714,0.0009838701,0.00010519406,0.0013712919,0.00007191492,0.0002162447,0.0038574385],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028078366,0.00034710893,0.0030951004,0.00002004617,0.000018800267,0.0000025586999,0.017704869,0.010219068,0.00066631474,0.043036766,0.05975348,0.86510783],"study_design_scores_gemma":[0.0008568355,0.00013191182,0.04951332,0.000074058305,0.000031822714,0.00001734343,0.0063042324,0.090547666,0.0009207788,0.0028221866,0.8485665,0.00021337892],"about_ca_topic_score_codex":0.0002053923,"about_ca_topic_score_gemma":0.002128282,"teacher_disagreement_score":0.86489445,"about_ca_system_score_codex":0.0005559932,"about_ca_system_score_gemma":0.0006475768,"threshold_uncertainty_score":0.9969182},"labels":[],"label_agreement":null},{"id":"W2026932277","doi":"10.7202/900731ar","title":"Méthode d’évaluation pour l’amélioration desperformances dans l’enseignement postsecondaire","year":2009,"lang":"fr","type":"article","venue":"Revue des sciences de l éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.6727936110558197,"score_gpt":0.5444102415586829,"score_spread":0.1283833694971368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026932277","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80395776,0.0044770474,0.08653301,0.02519572,0.003685116,0.0007299895,0.000017785698,0.00008023006,0.07532334],"genre_scores_gemma":[0.92777747,0.001421166,0.054776333,0.0014429546,0.0006722633,0.000041747477,0.0000422771,0.000013277722,0.013812506],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9939758,0.0011850065,0.0012321499,0.0009044965,0.0018939638,0.00080854265],"domain_scores_gemma":[0.9969831,0.00044212997,0.000766714,0.0005835182,0.0009547177,0.00026981355],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.015689217,0.00035658124,0.00035771573,0.0006551154,0.0022404739,0.0012164471,0.00095752196,0.00022403807,0.0034257658],"category_scores_gemma":[0.0012251545,0.0003344637,0.00017846857,0.0026138134,0.0009909811,0.0036648682,0.000056067853,0.00026951957,0.0015590566],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003702102,0.0005821664,0.008593162,0.000098580684,0.000017566483,0.0000041192034,0.07801791,0.040223617,0.0084154215,0.059139963,0.0104163755,0.7944541],"study_design_scores_gemma":[0.0005618465,0.0013655265,0.17420827,0.00046682046,0.00009940323,0.00019122414,0.027537517,0.62688076,0.004320208,0.15529442,0.008470627,0.0006033904],"about_ca_topic_score_codex":0.00017029182,"about_ca_topic_score_gemma":0.00082191353,"teacher_disagreement_score":0.7938507,"about_ca_system_score_codex":0.0025139938,"about_ca_system_score_gemma":0.0043430873,"threshold_uncertainty_score":0.9999107},"labels":[],"label_agreement":null},{"id":"W2027649886","doi":"10.7202/1026400ar","title":"Strategic Decisions in Setting Up Child Rights Impact Assessments","year":2014,"lang":"en","type":"article","venue":"Revue générale de droit","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Scope (computer science); Process (computing); Psychology; Political science; Applied psychology; Business; Public relations; Computer science","score_opus":0.10119901637755277,"score_gpt":0.44525271918253523,"score_spread":0.3440537028049825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2027649886","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8331422,0.000023360224,0.0028041124,0.0005013646,0.00035504537,0.00022272117,0.000011953861,0.000037188252,0.16290201],"genre_scores_gemma":[0.99617845,0.000024132547,0.0017498563,0.0002730341,0.00020894282,0.000024726043,0.000023548488,0.000014381392,0.0015029415],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9965296,0.00040801434,0.0008694544,0.00053557265,0.0011366159,0.0005207468],"domain_scores_gemma":[0.9972958,0.0011792473,0.0003180016,0.00078343326,0.00018650168,0.00023699882],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.006103854,0.00016241695,0.00037577935,0.0004739773,0.00026047285,0.00037578793,0.000754444,0.00012527258,0.0015409093],"category_scores_gemma":[0.0007257658,0.00015782684,0.00018814909,0.00097392604,0.000040620063,0.0005481334,0.000094046576,0.0003583423,0.0010366256],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014797879,0.00061243615,0.66228724,0.000028434446,0.00008548698,0.00006575817,0.0028848732,0.03444104,0.0009736899,0.09148817,0.0058896802,0.20109524],"study_design_scores_gemma":[0.0010440998,0.00017415477,0.35998195,0.00016584578,0.000013275147,0.00006030018,0.0004885418,0.18462521,0.00014771173,0.4501992,0.0027851819,0.00031453496],"about_ca_topic_score_codex":0.000100191064,"about_ca_topic_score_gemma":0.00043949534,"teacher_disagreement_score":0.35871103,"about_ca_system_score_codex":0.00030782784,"about_ca_system_score_gemma":0.00020838312,"threshold_uncertainty_score":0.9997412},"labels":[],"label_agreement":null},{"id":"W2027849047","doi":"10.7202/1025739ar","title":"Dialogues entre théories spontanées et théories académiques de l’évaluation","year":2014,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Humanities; Philosophy","score_opus":0.15014967446998498,"score_gpt":0.47060124033660383,"score_spread":0.3204515658666188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2027849047","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.63532734,0.0019155954,0.13672724,0.17528065,0.010415626,0.0015182536,0.00008909847,0.00028511253,0.03844105],"genre_scores_gemma":[0.95368594,0.002617765,0.010391746,0.0034150442,0.0012835419,0.00022991486,0.001022377,0.00006180795,0.027291887],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.968468,0.024242083,0.001728175,0.001052362,0.0037961404,0.0007132485],"domain_scores_gemma":[0.9889807,0.006532661,0.0010921791,0.0009677569,0.0021889,0.00023782064],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.10689424,0.0005810635,0.00064021896,0.00061851746,0.00060660415,0.0012009026,0.0007168743,0.0005593508,0.0048984536],"category_scores_gemma":[0.016404046,0.0005419959,0.00026854232,0.0011609873,0.00027108518,0.0035537719,0.00013745432,0.00064704346,0.0020076523],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013275295,0.0005643381,0.09389413,0.000130114,0.00012278525,0.0000013278309,0.39768115,0.010590418,0.0013336769,0.16633952,0.028536176,0.30067363],"study_design_scores_gemma":[0.0010109213,0.00035948603,0.5955955,0.00026592377,0.00025360205,0.000019465668,0.009176171,0.059606347,0.0019953826,0.1780052,0.15305185,0.0006601431],"about_ca_topic_score_codex":0.0003639003,"about_ca_topic_score_gemma":0.0032162566,"teacher_disagreement_score":0.50170135,"about_ca_system_score_codex":0.0009930939,"about_ca_system_score_gemma":0.006034148,"threshold_uncertainty_score":0.99983597},"labels":[],"label_agreement":null},{"id":"W2028661836","doi":"10.14507/epaa.v11n2.2003","title":"Policymakers' Online Use of Academic Research","year":2003,"lang":"en","type":"article","venue":"Education Policy Analysis Archives","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Credibility; Public relations; Political science; Work (physics); Politics; Higher education; Exploratory research; Sample (material); Face (sociological concept); Quality (philosophy); Sociology; Principal (computer security); Social science","score_opus":0.5482865163427846,"score_gpt":0.6509797254309332,"score_spread":0.10269320908814861,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2028661836","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9470059,0.00018706614,0.0025474108,0.015338154,0.00015417852,0.00023630516,0.00005605259,0.000018006569,0.0344569],"genre_scores_gemma":[0.971928,0.00027219366,0.0046182587,0.0008487722,0.00020723596,0.000020711244,0.00004492633,0.0000075983867,0.022052296],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99470437,0.0018269964,0.00094557134,0.00040623802,0.0017898837,0.000326947],"domain_scores_gemma":[0.9943713,0.0035570066,0.00037850565,0.00091326435,0.0005723804,0.00020754844],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0039984947,0.00011844572,0.00033140625,0.005381115,0.00022564203,0.00012658838,0.00057024084,0.000060374117,0.0013291955],"category_scores_gemma":[0.012268954,0.00009186036,0.00026570816,0.008532973,0.00031027463,0.00046433017,0.000071551396,0.00034580275,0.00013495001],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029608673,0.00076218694,0.4093821,0.000009791004,0.0003832559,1.339062e-7,0.01199427,0.0052795885,0.0020917198,0.46124625,0.017274497,0.0915466],"study_design_scores_gemma":[0.00015872502,0.000049507686,0.6456248,0.000015134474,0.00011983482,0.0000016031956,0.0060167774,0.0053789504,0.0011777306,0.10135481,0.23994234,0.00015974433],"about_ca_topic_score_codex":0.00077561324,"about_ca_topic_score_gemma":0.0002735911,"teacher_disagreement_score":0.35989144,"about_ca_system_score_codex":0.00005339803,"about_ca_system_score_gemma":0.0028381776,"threshold_uncertainty_score":0.9995837},"labels":[],"label_agreement":null},{"id":"W2028776194","doi":"10.7202/1024966ar","title":"L’évaluation des dispositifs éducatifs","year":2014,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Humanities; Political science; Valuation (finance); Philosophy; Business","score_opus":0.20602175446442014,"score_gpt":0.4944309343703471,"score_spread":0.28840917990592696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2028776194","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5968993,0.0016721729,0.23683502,0.08350488,0.014409674,0.0014873502,0.00003838546,0.00016416937,0.064989045],"genre_scores_gemma":[0.90296763,0.0006115063,0.019728534,0.0019039776,0.0012216631,0.00021991924,0.000528133,0.00006636448,0.07275225],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.97168225,0.020245232,0.001870679,0.0011820794,0.004313818,0.00070593006],"domain_scores_gemma":[0.9895926,0.0050775832,0.0009424492,0.0013213841,0.0027665554,0.00029942513],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.11271913,0.00053861976,0.00056020456,0.0007218977,0.000809577,0.0009808054,0.0007690283,0.000436358,0.013504021],"category_scores_gemma":[0.014222648,0.00052021,0.00028122345,0.0018234018,0.00033797286,0.00277879,0.00011601223,0.00052341673,0.007873817],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031892116,0.00051780016,0.017075574,0.00008255585,0.00005313348,2.8090136e-7,0.13149816,0.009591917,0.0008786144,0.022283604,0.01593527,0.8020512],"study_design_scores_gemma":[0.0009630609,0.00027382746,0.6146614,0.00023626926,0.00022943385,0.000017553086,0.0033917867,0.18190676,0.00075968966,0.08455034,0.112446286,0.0005636228],"about_ca_topic_score_codex":0.00041575325,"about_ca_topic_score_gemma":0.0013565281,"teacher_disagreement_score":0.80148757,"about_ca_system_score_codex":0.0013365949,"about_ca_system_score_gemma":0.0043368014,"threshold_uncertainty_score":0.9997249},"labels":[],"label_agreement":null},{"id":"W2030410865","doi":"10.1111/j.1365-2753.2009.01165.x","title":"Knowledge transfer and the complex story of scurvy","year":2009,"lang":"en","type":"article","venue":"Journal of Evaluation in Clinical Practice","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; McGill University","funders":"","keywords":"Residence; Citation; Library science; Unit (ring theory); Knowledge transfer; Medicine; Sociology; Management; Psychology; Computer science","score_opus":0.5583617391089345,"score_gpt":0.6661655083178081,"score_spread":0.10780376920887358,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030410865","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7997489,0.0031520308,0.008361552,0.12749165,0.0017173159,0.00078196265,0.0000023131436,0.0000045227703,0.058739778],"genre_scores_gemma":[0.9954546,0.0004994205,0.0017547432,0.0019883616,0.00020277017,0.0000017378505,3.3799898e-7,0.0000024469462,0.00009555031],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98282665,0.010771347,0.0030651905,0.00017666169,0.0030533765,0.00010674596],"domain_scores_gemma":[0.9501701,0.04449107,0.001351504,0.00027624384,0.0036314414,0.000079660575],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.21180056,0.00007432432,0.00041737108,0.00021548064,0.00009132689,0.000070668604,0.00030455727,0.000073585405,0.0008477652],"category_scores_gemma":[0.11001108,0.00004038177,0.00016899902,0.00048110663,0.00023027301,0.0009934223,0.00001921443,0.0007008298,0.00003052939],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0031588261,0.0011940984,0.009274941,0.0000064445067,0.00007140154,0.0000032662458,0.004964478,0.0025260707,0.00009967893,0.015305508,0.015556951,0.9478383],"study_design_scores_gemma":[0.010484369,0.0009296881,0.780138,0.000056283818,0.00023490844,0.000057301022,0.003830428,0.06732363,0.000013716128,0.041151874,0.09568266,0.00009713869],"about_ca_topic_score_codex":0.0000022758934,"about_ca_topic_score_gemma":0.000017540502,"teacher_disagreement_score":0.9477412,"about_ca_system_score_codex":0.000043982367,"about_ca_system_score_gemma":0.00061437185,"threshold_uncertainty_score":0.9282434},"labels":[],"label_agreement":null},{"id":"W2030740562","doi":"10.1080/00048623.2001.10755139","title":"Working Towards Best Practice in Australian University Libraries: Reflections on a National Project","year":2001,"lang":"en","type":"article","venue":"Australian Academic & Research Libraries","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Sainte-Anne","funders":"","keywords":"Project commissioning; Library science; Best practice; Publishing; National library; Political science; Sociology; Engineering; Engineering management; Computer science","score_opus":0.6904710543448623,"score_gpt":0.6101898143526231,"score_spread":0.08028123999223924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030740562","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14421572,0.00014350061,0.00008956295,0.24345179,0.00078437594,0.0015650889,0.000059707312,0.00022524466,0.609465],"genre_scores_gemma":[0.73575485,0.00088397507,0.0033672387,0.0008966734,0.00047990444,0.000040303712,0.000037661477,0.0000271169,0.25851226],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99013275,0.0020058462,0.00081067765,0.00087319204,0.0052057314,0.0009718026],"domain_scores_gemma":[0.9944245,0.0037820544,0.00026556666,0.00052597123,0.00071334775,0.0002885398],"candidate_categories":["metaresearch","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.010126967,0.00025581004,0.0003138937,0.0023494298,0.0008443936,0.0011138598,0.0017183237,0.00043506932,0.002204007],"category_scores_gemma":[0.00946242,0.00022658055,0.00010720118,0.0074952412,0.0007172813,0.0068556927,0.00038682632,0.0028884425,0.00122567],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014654343,0.0005787426,0.03440804,0.000016952657,0.00008240431,0.00021146103,0.013179239,0.00080827397,0.00043418971,0.34736344,0.56143,0.040021855],"study_design_scores_gemma":[0.00057121355,0.00029838234,0.008858109,0.0001287846,0.0000065692234,0.000028436441,0.030089479,0.00015966872,0.0003003337,0.026814064,0.93250924,0.00023573064],"about_ca_topic_score_codex":0.00050841575,"about_ca_topic_score_gemma":0.00021960658,"teacher_disagreement_score":0.59153914,"about_ca_system_score_codex":0.00051897555,"about_ca_system_score_gemma":0.0041026226,"threshold_uncertainty_score":0.99992305},"labels":[],"label_agreement":null},{"id":"W203103160","doi":"","title":"How Ontario Spread Successful Practices across 5,000 Schools: By Building and Supporting Networks of Educators throughout the Province, Ontario Was Able to Develop a System Now Highly Regarded for Both Equity and Excellence","year":2013,"lang":"en","type":"article","venue":"Phi Delta Kappan","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Excellence; Public relations; Best practice; Sociology; Equity (law); Windsor; Pedagogy; Political science","score_opus":0.09736519881171954,"score_gpt":0.4442679409202967,"score_spread":0.3469027421085772,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W203103160","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98135537,0.0002937722,0.008672343,0.006298209,0.0004049858,0.0019599337,0.000026576876,0.00003606701,0.00095276686],"genre_scores_gemma":[0.98623806,0.000024393263,0.006800066,0.00037381126,0.000103953804,0.0003000619,0.000011721605,0.000020014893,0.006127916],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961325,0.00018475724,0.00096191745,0.000784705,0.0012566865,0.0006794345],"domain_scores_gemma":[0.9952538,0.0012551429,0.0016305968,0.00064386596,0.00094604015,0.0002705573],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0071221283,0.00029520903,0.00053967955,0.000093574716,0.0007800146,0.002322091,0.0009194276,0.00011996395,0.000092801056],"category_scores_gemma":[0.0014192568,0.00019149465,0.00005789231,0.0005221846,0.00013854717,0.002065297,0.0007543621,0.0003396611,0.000009647026],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025720746,0.00016641889,0.86505455,0.0002669311,0.00015344053,0.000002273383,0.02201077,0.00086773036,0.001043033,0.0010226346,0.055064622,0.054090366],"study_design_scores_gemma":[0.0036737141,0.0011782134,0.26143208,0.0010559045,0.000322767,0.00008583086,0.10472319,0.062149804,0.004937869,0.0031927023,0.5553022,0.0019457544],"about_ca_topic_score_codex":0.13458562,"about_ca_topic_score_gemma":0.532533,"teacher_disagreement_score":0.6036225,"about_ca_system_score_codex":0.00038430656,"about_ca_system_score_gemma":0.0016018759,"threshold_uncertainty_score":0.9987136},"labels":[],"label_agreement":null},{"id":"W2032319437","doi":"10.1017/s1744133106004026","title":"NICE's use of cost effectiveness as an exemplar of a deliberative process","year":2006,"lang":"en","type":"article","venue":"Health Economics Policy and Law","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Work & Health","funders":"","keywords":"Nice; Process (computing); Computer science; Process management; Psychology; Epistemology; Business; Philosophy","score_opus":0.2538145413590342,"score_gpt":0.5381795901443622,"score_spread":0.28436504878532803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032319437","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99401766,0.000050005354,0.00017280641,0.0009870129,0.000050383165,0.0003913251,0.00007944422,0.000005843357,0.0042454978],"genre_scores_gemma":[0.9976558,0.000092317605,0.00024504107,0.001806624,0.000059665254,0.000024048082,0.00001268976,0.000006229407,0.0000975941],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984803,0.00026935444,0.0006702175,0.0002380824,0.00016785886,0.00017416259],"domain_scores_gemma":[0.99816895,0.0007872294,0.0004749522,0.00024412847,0.00021491446,0.00010985018],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002293814,0.000090796864,0.0003361192,0.00015078946,0.00013533006,0.0000704377,0.00013586566,0.000049138238,0.000057979138],"category_scores_gemma":[0.00012716377,0.0000755734,0.000034034612,0.00017771745,0.00014890349,0.0006563534,0.000027088865,0.000058853846,0.000009665644],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018621406,0.000171443,0.014794175,0.000112814756,0.000011041065,1.7157039e-7,0.001655051,0.0067152116,0.000034220495,0.9627355,0.00013297572,0.013451226],"study_design_scores_gemma":[0.00417278,0.0023289034,0.3458792,0.00018092198,0.000019827308,0.000030042313,0.00146023,0.042767424,0.011730625,0.4642863,0.12656812,0.000575643],"about_ca_topic_score_codex":0.008763798,"about_ca_topic_score_gemma":0.0048979474,"teacher_disagreement_score":0.49844915,"about_ca_system_score_codex":0.00006385679,"about_ca_system_score_gemma":0.00083933974,"threshold_uncertainty_score":0.99783695},"labels":[],"label_agreement":null},{"id":"W2032895801","doi":"10.1080/1523908x.2013.829750","title":"Assessment practices in the policy and politics cycles: a contribution to reflexive governance for sustainable development?","year":2013,"lang":"en","type":"article","venue":"Journal of Environmental Policy & Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Canada Research Chairs","keywords":"Politics; Corporate governance; Audit; Relevance (law); Reflexivity; Evidence-based policy; State (computer science); Political science; Government (linguistics); Public administration; Public relations; Economics; Sociology; Accounting; Law; Social science","score_opus":0.1104233065189831,"score_gpt":0.5033562854669734,"score_spread":0.3929329789479903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032895801","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98409224,0.00016596896,0.0010927166,0.012169469,0.00003829428,0.0005374716,0.000009779173,0.000002432034,0.0018916168],"genre_scores_gemma":[0.99223393,0.000055790173,0.0033264314,0.0032490138,0.00037327193,0.00004118318,0.000003041987,0.0000073341307,0.0007099818],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.997297,0.00019657676,0.0008015533,0.00017792462,0.0011314033,0.0003955428],"domain_scores_gemma":[0.99709797,0.001211909,0.0012658725,0.00016633522,0.00011308707,0.00014483155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004121983,0.00013267342,0.00023415913,0.0003474341,0.00027444676,0.0003956548,0.00040703005,0.000049947634,0.000062668354],"category_scores_gemma":[0.002871628,0.00008560519,0.00005242615,0.00033116748,0.000051545136,0.0012674407,0.00010764346,0.00020374966,0.000020105923],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004668985,0.0013258156,0.63157314,0.00011163532,0.0002515625,0.00012834763,0.048355013,0.010239304,0.01136733,0.18893994,0.020404374,0.08683665],"study_design_scores_gemma":[0.0008096424,0.00030788934,0.8779528,0.000044137003,0.000009306665,0.000057869627,0.019876575,0.0005355788,0.00017512764,0.009276443,0.09083873,0.00011589561],"about_ca_topic_score_codex":0.00016688282,"about_ca_topic_score_gemma":0.00001018742,"teacher_disagreement_score":0.24637967,"about_ca_system_score_codex":0.0008150636,"about_ca_system_score_gemma":0.00054427155,"threshold_uncertainty_score":0.38153082},"labels":[],"label_agreement":null},{"id":"W203337933","doi":"10.15210/interfaces.v1i1.6284","title":"Metodologia interativa: um processo hermenêutico dialético.","year":2012,"lang":"pt","type":"article","venue":"LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Humanities; Philosophy; Sociology","score_opus":0.0948161759130375,"score_gpt":0.36517275688176243,"score_spread":0.27035658096872495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W203337933","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2582651,0.0063061547,0.02685655,0.13349256,0.021782754,0.0041226596,0.00036765684,0.0012507815,0.54755574],"genre_scores_gemma":[0.98816395,0.00028605893,0.002564011,0.0011397643,0.0018198157,0.0003825383,0.00014660685,0.00008905392,0.005408194],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.98815006,0.002233647,0.0023585272,0.0014371786,0.0037685847,0.0020519998],"domain_scores_gemma":[0.9923423,0.0015705109,0.001386669,0.0014705439,0.0017277749,0.0015022238],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007298254,0.0010225491,0.0011982359,0.0010961096,0.0016236745,0.0011600002,0.001969144,0.0010257923,0.0020261318],"category_scores_gemma":[0.0048127715,0.000857347,0.00055723643,0.0023280531,0.0000892131,0.002925312,0.00081710616,0.0014666648,0.00077445304],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005964288,0.0028994728,0.014475122,0.00023486733,0.00049395394,0.000079937694,0.017218053,0.00020522947,0.0030303323,0.9267324,0.01137263,0.022661552],"study_design_scores_gemma":[0.0017478903,0.00025245815,0.020194782,0.00025757976,0.00022691037,0.0007585382,0.0036757179,0.0036876013,0.0020870627,0.00073957624,0.96529454,0.0010773201],"about_ca_topic_score_codex":0.0000014177375,"about_ca_topic_score_gemma":0.000085812346,"teacher_disagreement_score":0.9539219,"about_ca_system_score_codex":0.001431555,"about_ca_system_score_gemma":0.0023064292,"threshold_uncertainty_score":0.9998769},"labels":[],"label_agreement":null},{"id":"W2033749959","doi":"10.1002/ev.1190","title":"Evaluative inquiry in university‐school professional learning partnerships","year":2000,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Professional learning community; Professional development; Pedagogy; Psychology; Sociology","score_opus":0.37815566276918305,"score_gpt":0.5350127287443462,"score_spread":0.1568570659751632,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2033749959","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9267965,0.00014984483,0.002481498,0.0049139014,0.0015029907,0.0021973248,0.000007968982,0.00011750545,0.061832476],"genre_scores_gemma":[0.8720748,0.000051598465,0.001334831,0.0001586301,0.00032240388,0.0001090688,0.000079940124,0.0000134978645,0.12585524],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9950977,0.001463309,0.0005340239,0.0005073165,0.0021384237,0.00025923536],"domain_scores_gemma":[0.9973262,0.0011768168,0.00020252669,0.00028450377,0.00085402554,0.0001559027],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.011742452,0.00014234215,0.00020150297,0.000600313,0.000504633,0.00010643968,0.00026484876,0.000113055416,0.030804774],"category_scores_gemma":[0.0036946202,0.00012921577,0.000116816474,0.001591727,0.000051647403,0.0009103186,0.000024984824,0.00025963216,0.0011628204],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036242625,0.00017203318,0.019669218,0.0000036477877,0.000023309416,6.2109024e-7,0.0044609667,0.06219227,0.00012365,0.001126557,0.031151507,0.8807138],"study_design_scores_gemma":[0.0042204238,0.00021430434,0.1445049,0.000046875113,0.0000694911,0.0000034846937,0.0071971817,0.31166738,0.00012061693,0.014794509,0.51690453,0.0002562752],"about_ca_topic_score_codex":0.000049506736,"about_ca_topic_score_gemma":0.00070522435,"teacher_disagreement_score":0.8804575,"about_ca_system_score_codex":0.000529168,"about_ca_system_score_gemma":0.0015628077,"threshold_uncertainty_score":0.9996149},"labels":[],"label_agreement":null},{"id":"W2033993956","doi":"10.1177/1098214013478146","title":"The Practice of Evaluation in Public Sector Contexts","year":2013,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Accountability; Public sector; Citizen journalism; Perception; Diversity (politics); Reflection (computer programming); Sociology; Evaluation methods; Public relations; Public administration; Political science; Psychology; Law; Computer science; Engineering","score_opus":0.1817166479435985,"score_gpt":0.51942008015783,"score_spread":0.3377034322142315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2033993956","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97212,0.00043598315,0.0011405452,0.017486684,0.00055047934,0.0006908134,9.514484e-7,0.000002723555,0.007571862],"genre_scores_gemma":[0.9983479,0.00008907158,0.0009407014,0.00041278443,0.00009871848,0.00004284217,0.0000017484974,0.0000061286964,0.00006013187],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98749596,0.003961464,0.0016684426,0.00016980339,0.0065120957,0.00019225692],"domain_scores_gemma":[0.97932833,0.0047503426,0.0033365218,0.0003734613,0.012122161,0.000089158566],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06268525,0.000098610064,0.00029143182,0.00043930142,0.00011427155,0.00025047082,0.00037114418,0.00002844849,0.002327336],"category_scores_gemma":[0.032873448,0.00005761548,0.000102010235,0.0013538031,0.0002034815,0.0019695333,0.000033228793,0.00020410874,0.00011834496],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006828456,0.00009669466,0.011006985,8.342536e-7,0.000032473556,3.1818197e-7,0.0012923105,0.0025527477,0.0006450415,0.0005639796,0.0020630984,0.98167723],"study_design_scores_gemma":[0.002801644,0.0016322384,0.63223195,0.000057240315,0.00014998727,0.00007358374,0.026250636,0.2905151,0.00038661022,0.02760956,0.01809752,0.00019390104],"about_ca_topic_score_codex":0.00009459017,"about_ca_topic_score_gemma":0.000106536565,"teacher_disagreement_score":0.98148334,"about_ca_system_score_codex":0.000271745,"about_ca_system_score_gemma":0.001478455,"threshold_uncertainty_score":0.9985847},"labels":[],"label_agreement":null},{"id":"W2034211783","doi":"10.1177/1098214015578731","title":"Merging Developmental and Feminist Evaluation to Monitor and Evaluate Transformative Social Change","year":2015,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Transformative learning; Theory of change; Sociology; Social transformation; Social change; Monitoring and evaluation; Participatory evaluation; Program evaluation; Political science; Pedagogy; Social science; Public administration; Law","score_opus":0.3677671345545405,"score_gpt":0.5374349974415299,"score_spread":0.16966786288698937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034211783","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9906209,0.0001968032,0.0017134985,0.004661172,0.00035727108,0.00062530825,0.0000056199497,0.000005908513,0.0018134789],"genre_scores_gemma":[0.9946082,0.000024608471,0.0043730927,0.0006233861,0.00028034672,0.000057411846,0.000004205081,0.000009586924,0.000019168345],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99220496,0.0012557354,0.00094469794,0.0002393816,0.005139417,0.0002157785],"domain_scores_gemma":[0.995243,0.0003213944,0.00088919763,0.000095510295,0.0031651244,0.00028578535],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0361091,0.00015816375,0.000366566,0.00051963225,0.00025250917,0.00021573067,0.00016896486,0.000033693403,0.0001909915],"category_scores_gemma":[0.0020282117,0.0001214128,0.00005309286,0.0007771955,0.0001595601,0.001257684,0.000053221393,0.000139413,0.000036310776],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001647859,0.00002686885,0.0047893524,0.0000017755115,0.000032034717,5.922293e-7,0.054496527,0.00021518565,0.00025670003,0.000075000244,0.00048524406,0.9394559],"study_design_scores_gemma":[0.0073336973,0.0035089871,0.57467043,0.00012984598,0.0005970101,0.00029118257,0.1838822,0.210718,0.00092770724,0.010000648,0.007269978,0.0006703087],"about_ca_topic_score_codex":0.00002910627,"about_ca_topic_score_gemma":0.000025879377,"teacher_disagreement_score":0.9387856,"about_ca_system_score_codex":0.00040713567,"about_ca_system_score_gemma":0.0007350713,"threshold_uncertainty_score":0.9925285},"labels":[],"label_agreement":null},{"id":"W2034409422","doi":"10.1177/1098214008316655","title":"Cross-Disciplinarization: A New Talisman for Evaluation?","year":2008,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Cross disciplinary; Discipline; Field (mathematics); Engineering ethics; Face (sociological concept); Management science; Sociology; Interdisciplinarity; Computer science; Data science; Social science; Engineering","score_opus":0.2784832306773482,"score_gpt":0.5746443419319662,"score_spread":0.296161111254618,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034409422","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9142166,0.00018608893,0.07712578,0.0042868354,0.0010192038,0.000773086,0.000006413502,0.0000108085815,0.0023751978],"genre_scores_gemma":[0.98802143,0.000027241089,0.009464083,0.0004095201,0.00075621414,0.00003797961,0.00002224966,0.000014573466,0.0012467095],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99093884,0.0007187479,0.00154122,0.00029946747,0.0062841857,0.00021750951],"domain_scores_gemma":[0.9870718,0.00094527146,0.0022966063,0.0004118052,0.009064811,0.00020966772],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.023306796,0.00015399737,0.00039792486,0.00052014575,0.00040211825,0.00019233969,0.00045764088,0.000043096705,0.0038206666],"category_scores_gemma":[0.0067837834,0.00011593144,0.00024662254,0.0012631351,0.00023248154,0.0011876657,0.000038829898,0.00012997248,0.00009066455],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044467382,0.00017789096,0.06797379,0.0000031691068,0.000096904194,0.000002322555,0.0065493565,0.11399089,0.0004107434,0.0008017536,0.023995185,0.78555334],"study_design_scores_gemma":[0.0075156293,0.0024559938,0.47174972,0.000039662245,0.00030045718,0.00030630452,0.0027254412,0.44972783,0.00054305897,0.045573555,0.01869688,0.00036546827],"about_ca_topic_score_codex":0.00001476363,"about_ca_topic_score_gemma":0.00001845535,"teacher_disagreement_score":0.78518784,"about_ca_system_score_codex":0.0002781866,"about_ca_system_score_gemma":0.0036542148,"threshold_uncertainty_score":0.99709},"labels":[],"label_agreement":null},{"id":"W2035384693","doi":"10.17323/1995-459x.2007.2.68.77","title":"Two levels of Foresight in Canada","year":2007,"lang":"en","type":"article","venue":"Foresight-Russia","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Futures studies; Computer science; Artificial intelligence","score_opus":0.15586054730761428,"score_gpt":0.45445094231868693,"score_spread":0.29859039501107265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2035384693","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9047416,0.00018319878,0.004379748,0.00081870717,0.0006402342,0.00032280918,0.000032954686,0.000014034238,0.088866726],"genre_scores_gemma":[0.9958102,0.0000055426485,0.0014210473,0.00037678092,0.00007482872,0.0000073621254,0.0000044676262,0.000010889646,0.002288852],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99568146,0.00012203257,0.0011551515,0.0003503214,0.0022524188,0.00043859228],"domain_scores_gemma":[0.9978082,0.00088766735,0.00035169208,0.000566602,0.00022641837,0.00015939157],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004327583,0.00016223808,0.00034774805,0.00041185733,0.00008459867,0.000046731555,0.0006880858,0.000055861907,0.0046111043],"category_scores_gemma":[0.0003607841,0.00011155864,0.0000778379,0.001062781,0.000056501554,0.00034614198,0.00008001699,0.00015887961,0.00011507168],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016749806,0.00009046424,0.8563837,0.00001632209,0.000022763305,0.000059857564,0.001058263,0.0016185343,0.001127546,0.05725065,0.022733836,0.059470583],"study_design_scores_gemma":[0.0009287117,0.00005461825,0.94428265,0.000026436988,0.000005229755,0.000003705619,0.0005908542,0.0034353738,0.010023267,0.013708677,0.02676245,0.00017804063],"about_ca_topic_score_codex":0.28468978,"about_ca_topic_score_gemma":0.9694807,"teacher_disagreement_score":0.6847909,"about_ca_system_score_codex":0.0003583148,"about_ca_system_score_gemma":0.0022202532,"threshold_uncertainty_score":0.9962988},"labels":[],"label_agreement":null},{"id":"W2035673888","doi":"10.1007/s11414-007-9064-4","title":"Linking Data to Decision-Making: Applying Qualitative Data Analysis Methods and Software to Identify Mechanisms for Using Outcomes Data","year":2007,"lang":"en","type":"article","venue":"The Journal of Behavioral Health Services & Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; McGill University","funders":"National Institute of Mental Health","keywords":"Data collection; Qualitative property; Data quality; Grounded theory; Qualitative research; Quality (philosophy); Knowledge management; Data management; Computer science; Process management; Data science; Management science; Psychology; Medical education; Medicine; Operations management; Data mining; Engineering","score_opus":0.8177234514371169,"score_gpt":0.7842822188259571,"score_spread":0.03344123261115983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2035673888","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28003395,0.00039890112,0.7168969,0.001040156,0.00024890006,0.0009014646,0.0004704242,0.0000071020786,0.0000022221363],"genre_scores_gemma":[0.39726278,0.000041157153,0.6015234,0.0009486045,0.00009367438,0.0000045382367,0.00009622353,0.000016745562,0.00001287754],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9866284,0.003390199,0.0024363534,0.00090342714,0.0057996297,0.000841979],"domain_scores_gemma":[0.9649554,0.02412126,0.0013883207,0.0057901987,0.003031356,0.00071350107],"candidate_categories":["metaresearch","sts","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.31403497,0.00020541865,0.00082180573,0.0020846298,0.0013472015,0.0008042214,0.01087916,0.000087556604,0.00009605245],"category_scores_gemma":[0.00086303527,0.00012586465,0.000073921605,0.0042895195,0.00007129443,0.0023132565,0.008321818,0.0006381078,0.000014285702],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00071818335,0.00015697819,0.006767701,0.00009032407,0.00015687004,0.000006380634,0.07158439,0.00078058406,0.0004749999,0.000084206535,0.00036043135,0.91881895],"study_design_scores_gemma":[0.0011077098,0.0012140528,0.05043502,0.0010897971,0.0008739945,0.00004524281,0.744027,0.17110783,0.00010601785,0.022808429,0.0066908477,0.00049404125],"about_ca_topic_score_codex":0.0021514995,"about_ca_topic_score_gemma":0.016021643,"teacher_disagreement_score":0.9183249,"about_ca_system_score_codex":0.00021122322,"about_ca_system_score_gemma":0.00087302754,"threshold_uncertainty_score":0.9999529},"labels":[],"label_agreement":null},{"id":"W2036342338","doi":"10.1177/1356389003009002006","title":"Reducing Anxiety and Resistance in Policy and Programme Evaluations","year":2003,"lang":"en","type":"article","venue":"Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; Simon Fraser University","funders":"","keywords":"Resistance (ecology); Anxiety; Process (computing); Psychology; Political science; Public relations; Social psychology; Computer science; Ecology; Biology","score_opus":0.22745225598283272,"score_gpt":0.5341188055677645,"score_spread":0.3066665495849318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036342338","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.927227,0.0010863282,0.0010385077,0.004147313,0.00014918143,0.0009285228,0.0000025934112,0.00002116411,0.06539937],"genre_scores_gemma":[0.99166626,0.00011829271,0.006782691,0.00018928727,0.0000475874,0.00012254261,0.0000064512683,0.000006336754,0.0010605699],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9959349,0.000977838,0.00053481443,0.00043378127,0.0018923517,0.00022629551],"domain_scores_gemma":[0.9984055,0.0004563653,0.00017686235,0.00031201093,0.0005606918,0.00008853835],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.023249589,0.00010334754,0.00014634828,0.00039065175,0.00018826147,0.0002326783,0.00009531732,0.00004665985,0.00046502936],"category_scores_gemma":[0.011726447,0.00008681909,0.000021624217,0.0010704515,0.000068462,0.0005294187,0.000026549782,0.00009917357,0.00003563167],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030684703,0.00010939215,0.18504576,0.000014617118,0.0000105489435,3.8667824e-7,0.007324254,0.0013976722,0.000811402,0.11043094,0.0011023094,0.693722],"study_design_scores_gemma":[0.0017183833,0.000046485035,0.6733787,0.00004436907,0.000026264246,0.000007946299,0.0016144798,0.06652263,0.00025334777,0.23145357,0.024710108,0.00022369546],"about_ca_topic_score_codex":0.00005519082,"about_ca_topic_score_gemma":0.0011273858,"teacher_disagreement_score":0.6934983,"about_ca_system_score_codex":0.00018341784,"about_ca_system_score_gemma":0.0006529009,"threshold_uncertainty_score":0.9965982},"labels":[],"label_agreement":null},{"id":"W2036501454","doi":"10.1177/1075547007305166","title":"Social Epistemology","year":2007,"lang":"en","type":"article","venue":"Science Communication","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Addiction and Mental Health","funders":"","keywords":"Social epistemology; Context (archaeology); Epistemology; Knowledge transfer; Variety (cybernetics); Social exchange theory; Epistemology of Wikipedia; Sociology; Process (computing); Psychology; Knowledge management; Social science; Computer science; Philosophy","score_opus":0.3751242082186892,"score_gpt":0.6042134133778434,"score_spread":0.2290892051591542,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036501454","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.65020746,0.00007271052,0.011663443,0.0130587295,0.00028393403,0.00015109913,6.2681374e-7,0.000049125643,0.32451284],"genre_scores_gemma":[0.99522126,0.000008012775,0.0029848511,0.0005571335,0.000033090135,0.0000035627193,0.000001971019,0.000002075738,0.0011880655],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9973781,0.00015505945,0.00042572428,0.00022330039,0.0015824955,0.00023531137],"domain_scores_gemma":[0.9975951,0.00056304893,0.00020917816,0.00087017426,0.0006958107,0.00006669665],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02974081,0.000051513027,0.00008875361,0.00033391215,0.0010387728,0.00019300648,0.0020093098,0.00003534433,0.00045194622],"category_scores_gemma":[0.0013178556,0.000039612405,0.000032645275,0.0018671791,0.0008790833,0.0007212849,0.00028527845,0.00011318121,0.0007062627],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002129433,0.000083576786,0.05834562,0.0000011512993,0.0000022166894,5.098036e-7,0.005408189,0.000037321337,0.009084639,0.42463163,0.004522442,0.49786142],"study_design_scores_gemma":[0.00021503364,0.00003647794,0.83698434,0.0000031604884,0.0000023157136,0.0000066788234,0.0026417805,0.0033771275,0.0029110154,0.08697087,0.06673138,0.00011983226],"about_ca_topic_score_codex":0.000015613456,"about_ca_topic_score_gemma":0.000108688844,"teacher_disagreement_score":0.7786387,"about_ca_system_score_codex":0.000107574866,"about_ca_system_score_gemma":0.00026656743,"threshold_uncertainty_score":0.999086},"labels":[],"label_agreement":null},{"id":"W2036568768","doi":"10.3821/145.2.cpj55c","title":"Professionals You Can Trust: Pharmacists Top the List Again in Ipsos Reid Survey","year":2012,"lang":"en","type":"article","venue":"Canadian Pharmacists Journal / Revue des Pharmaciens du Canada","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Family medicine","score_opus":0.21862582067413466,"score_gpt":0.451898377953977,"score_spread":0.23327255727984236,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036568768","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9834132,0.0012469401,0.0000450724,0.0020682814,0.007390868,0.00078364805,0.0008824369,0.000022482534,0.004147035],"genre_scores_gemma":[0.9802682,0.0011973759,0.000059531973,0.010484072,0.0014484817,0.00006374849,0.00007138804,0.000056494337,0.006350735],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99012333,0.0024979725,0.0018590981,0.00064895186,0.0028007287,0.0020698973],"domain_scores_gemma":[0.99235594,0.0013562511,0.0008031552,0.00073523587,0.0014484425,0.0033009432],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02007923,0.000564482,0.00065037666,0.00093717163,0.0017720214,0.00070432376,0.0023998402,0.00011578053,0.008899968],"category_scores_gemma":[0.002700597,0.00041396602,0.00022999333,0.0027895335,0.00031791342,0.001300939,0.0001517486,0.0015367471,0.00010424284],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002522514,0.00024507561,0.49203295,0.00005796054,0.00016104865,0.0070713474,0.009156287,0.0022184781,0.00069983274,0.00018823387,0.31536782,0.17254871],"study_design_scores_gemma":[0.008486332,0.00010770918,0.036109224,0.00009721101,0.0002003196,0.20776013,0.0006717721,0.033435374,0.005656652,0.00081529265,0.70376545,0.002894526],"about_ca_topic_score_codex":0.036994833,"about_ca_topic_score_gemma":0.3793106,"teacher_disagreement_score":0.45592374,"about_ca_system_score_codex":0.0036134738,"about_ca_system_score_gemma":0.0102476645,"threshold_uncertainty_score":0.9998312},"labels":[],"label_agreement":null},{"id":"W2036892132","doi":"10.1046/j.1466-7657.2000.00033.x","title":"Developing a programme‐review process for a baccalaureate nursing programme in Jordan","year":2000,"lang":"en","type":"article","venue":"International Nursing Review","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Windsor; Process (computing); Nursing; Inclusion (mineral); Maturity (psychological); Medicine; Medical education; Professional development; Political science; Sociology","score_opus":0.3258281283630685,"score_gpt":0.5763535823321086,"score_spread":0.25052545396904013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036892132","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014042001,0.47207257,0.008983113,0.41229653,0.0026640948,0.01360155,0.000042542124,0.00027959942,0.07601799],"genre_scores_gemma":[0.2964447,0.55658877,0.070157796,0.054931857,0.0013314994,0.0077820863,0.00062509417,0.00020891018,0.0119293025],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99568135,0.00018696474,0.0013963247,0.00057902734,0.0016720959,0.00048423384],"domain_scores_gemma":[0.99799794,0.00030103422,0.00036834163,0.00033200378,0.00087655435,0.00012411528],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005172697,0.00023357621,0.00056018925,0.00021373568,0.00012169807,0.00022973403,0.0008618119,0.000052939035,0.002534],"category_scores_gemma":[0.0019359781,0.00017821608,0.00021776768,0.0011388282,0.000095586394,0.00058851735,0.000012564081,0.00017267832,0.00027182544],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020078538,0.0001884541,0.000534366,0.0007832147,0.000011576668,0.0000017397285,0.00020942288,0.000020695765,7.512092e-7,0.0026856773,0.004184708,0.9913593],"study_design_scores_gemma":[0.0008192197,0.00012259139,0.0021134273,0.22618255,0.00008364853,0.00009544383,0.00017571474,0.0058395765,0.000026428403,0.03857592,0.7254971,0.0004683429],"about_ca_topic_score_codex":0.0000057428065,"about_ca_topic_score_gemma":0.000024443249,"teacher_disagreement_score":0.990891,"about_ca_system_score_codex":0.0005251628,"about_ca_system_score_gemma":0.000526601,"threshold_uncertainty_score":0.9983778},"labels":[],"label_agreement":null},{"id":"W2036952487","doi":"10.1186/cc5605","title":"Multicentre evaluation of the impact of the introduction of outreach services in the United Kingdom","year":2007,"lang":"en","type":"article","venue":"Critical Care","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Outreach; Family medicine; Medical emergency; Economic growth","score_opus":0.2634259280700664,"score_gpt":0.5651211959106154,"score_spread":0.301695267840549,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036952487","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9960079,0.00007039544,0.000044325196,0.002306148,0.00023215367,0.00030572168,0.000013652015,0.0000020298285,0.0010176607],"genre_scores_gemma":[0.999789,8.063535e-7,0.00003056633,0.00008977576,0.000070502334,0.0000035454937,0.000006544254,0.000002590388,0.000006655441],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9962569,0.00080696354,0.0005255356,0.00013732084,0.002151645,0.000121672354],"domain_scores_gemma":[0.99598616,0.0010243776,0.00017888717,0.0005693752,0.00222072,0.000020451158],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007137438,0.00006739047,0.0001300362,0.00011914472,0.000074347845,0.000024641648,0.00056464714,0.000049381255,0.00031956003],"category_scores_gemma":[0.0033553685,0.000026558197,0.00012940101,0.0011862546,0.00018102676,0.00012403494,0.000065603475,0.00013129023,0.0000030113838],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013167203,0.00034062142,0.8930334,0.00013024308,0.000020881822,2.0735847e-7,0.04213999,0.017766213,0.0042663817,0.009198387,0.000514286,0.032457747],"study_design_scores_gemma":[0.00039361676,0.00005152919,0.93431777,0.000034980127,0.00005114622,9.81811e-7,0.03950016,0.019813541,0.004001264,0.0016300508,0.0001703745,0.000034615357],"about_ca_topic_score_codex":0.00050668785,"about_ca_topic_score_gemma":0.0006988437,"teacher_disagreement_score":0.04128437,"about_ca_system_score_codex":0.00008336982,"about_ca_system_score_gemma":0.00015474507,"threshold_uncertainty_score":0.4016932},"labels":[],"label_agreement":null},{"id":"W2037599414","doi":"10.1111/capa.12103","title":"What metrics? On the utility of measuring the performance of policy research: An illustrative case and alternative from Employment and Social Development Canada","year":2015,"lang":"en","type":"article","venue":"Canadian Public Administration","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa; Institute on Governance","funders":"","keywords":"Government (linguistics); Task (project management); Object (grammar); Performance measurement; Focus (optics); Computer science; Research Object; State (computer science); Policy development; Public policy; Management science; Operations research; Public economics; Econometrics; Economics; Sociology; Engineering; Political science; Public administration; Artificial intelligence; Regional science; Economic growth; Management","score_opus":0.6470003141615459,"score_gpt":0.4995877186147932,"score_spread":0.14741259554675273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037599414","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96995455,0.000038244125,0.0000132826735,0.028773004,0.00011026083,0.00027728305,0.000056833098,0.0000017218217,0.00077483064],"genre_scores_gemma":[0.999461,0.000010390465,0.000041124153,0.0002949133,0.000065125045,0.000020522328,0.000014518807,0.0000035487633,0.000088835855],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99696386,0.000583665,0.00042289088,0.00023603004,0.001581875,0.0002116815],"domain_scores_gemma":[0.9972369,0.0008061992,0.00022130196,0.00025584298,0.0011771214,0.00030261144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0060951314,0.00009210308,0.0001347941,0.0002859987,0.000582212,0.00034812358,0.0002890359,0.0000411112,0.00008626018],"category_scores_gemma":[0.0014815144,0.0000550513,0.000011941208,0.0006598191,0.00029099715,0.00069596723,0.0000443587,0.00016128663,0.0000010566621],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032219474,0.00026042116,0.12584081,0.00003709673,0.00026646443,0.000088450375,0.14672908,0.00004018459,0.000076093114,0.12580903,0.012559654,0.58797055],"study_design_scores_gemma":[0.0013074134,0.0013855515,0.34346572,0.00007108044,0.000025503507,0.0000847474,0.49919596,0.054505087,0.012349956,0.0053612557,0.08174032,0.0005074193],"about_ca_topic_score_codex":0.41181022,"about_ca_topic_score_gemma":0.9860116,"teacher_disagreement_score":0.5874631,"about_ca_system_score_codex":0.0004242572,"about_ca_system_score_gemma":0.017250631,"threshold_uncertainty_score":0.98832065},"labels":[],"label_agreement":null},{"id":"W2038633574","doi":"10.1002/ev.1171","title":"Translating evaluation findings into “policy language”","year":2000,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Affect (linguistics); Welfare; Order (exchange); Policy learning; Policy analysis; Program evaluation; Language policy; Computer science; Management science; Political science; Public administration; Sociology; Pedagogy; Economics; Machine learning; Law; Finance","score_opus":0.19760218499848886,"score_gpt":0.5590826968278899,"score_spread":0.36148051182940105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2038633574","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8476119,0.0007453475,0.01511153,0.01480731,0.0011529359,0.0038299651,0.000023426293,0.00024352386,0.116474055],"genre_scores_gemma":[0.9772639,0.00003327219,0.005804547,0.00039311696,0.00081355945,0.00061485526,0.00016282816,0.00002466972,0.014889245],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9942243,0.00056245556,0.0008258471,0.0005654122,0.0035335342,0.00028844117],"domain_scores_gemma":[0.99728805,0.0006400135,0.00018390776,0.0005170975,0.0012292553,0.00014170454],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.015486436,0.00018394327,0.00022291872,0.0006725255,0.00070887734,0.0003290183,0.00030582485,0.00011663148,0.02525264],"category_scores_gemma":[0.004425323,0.00016225078,0.00019058483,0.0018048945,0.00003870415,0.0009614254,0.000012515551,0.00012511032,0.0009265425],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037213762,0.000042509666,0.00051013293,0.0000029625887,0.000016715243,3.2888373e-8,0.0065389206,0.012104154,0.0009759983,0.00044260567,0.0049649104,0.97436386],"study_design_scores_gemma":[0.0036857175,0.00017313921,0.017084036,0.000028352011,0.00021319283,0.000005516265,0.00175896,0.783249,0.0018582558,0.057034962,0.13459492,0.00031394477],"about_ca_topic_score_codex":0.0005207291,"about_ca_topic_score_gemma":0.0013140815,"teacher_disagreement_score":0.9740499,"about_ca_system_score_codex":0.0006330734,"about_ca_system_score_gemma":0.001744748,"threshold_uncertainty_score":0.99985135},"labels":[],"label_agreement":null},{"id":"W2038634373","doi":"10.1080/02255189.2003.9668898","title":"Issues of Participation in a University-NGO, North-South Partnership: Internationalizing a CED Program","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Development Studies/Revue canadienne d études du développement","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"General partnership; Political science; Public relations; Public administration; Government (linguistics); Context (archaeology); Work (physics); Economic growth; Sociology; Engineering; Geography; Economics","score_opus":0.2548865904375898,"score_gpt":0.41448711665643856,"score_spread":0.15960052621884874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2038634373","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.994468,0.0003058656,0.00007435299,0.003028901,0.00040484074,0.00036246394,0.0000067904966,0.00000563481,0.0013431619],"genre_scores_gemma":[0.99479055,0.00012965177,0.0043370547,0.0001645535,0.000039330087,0.000017339655,0.00000725601,0.000011684067,0.0005025779],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99679023,0.00030517436,0.0014850481,0.0003078651,0.00054184016,0.0005698522],"domain_scores_gemma":[0.9965621,0.00022613506,0.0008282816,0.00022324974,0.0015417616,0.0006184442],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039126785,0.00022285013,0.00053923397,0.0013809314,0.00024275098,0.00007198045,0.0005752316,0.000054205375,0.0005378755],"category_scores_gemma":[0.001537139,0.00020481687,0.0001021468,0.0013166725,0.00012052174,0.00033753135,0.00003526071,0.00018094528,0.000018040833],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051975378,0.00013283663,0.8624333,0.000044969445,0.00036513363,0.00018626761,0.09598971,0.0019175956,0.000008697689,0.009323977,0.001328824,0.028216707],"study_design_scores_gemma":[0.0017654063,0.00031700608,0.6215414,0.0003805693,0.00005630394,0.00002767338,0.045015857,0.00019692765,0.00023843779,0.000720173,0.3293242,0.00041606952],"about_ca_topic_score_codex":0.0010521957,"about_ca_topic_score_gemma":0.65822303,"teacher_disagreement_score":0.65717083,"about_ca_system_score_codex":0.0020637857,"about_ca_system_score_gemma":0.004257236,"threshold_uncertainty_score":0.83521897},"labels":[],"label_agreement":null},{"id":"W2039105877","doi":"10.1258/135581903322405126","title":"Linkage and exchange at the organizational level: A model of collaboration between research and policy","year":2003,"lang":"en","type":"article","venue":"Journal of Health Services Research & Policy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":66,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Centre for Addiction and Mental Health; Ministry of Health and Long Term Care","funders":"","keywords":"Linkage (software); Business; Knowledge management; Process management; Computer science; Genetics; Biology","score_opus":0.555921094673004,"score_gpt":0.6432288882677196,"score_spread":0.08730779359471563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2039105877","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9116006,0.0021373613,0.00022481183,0.08340847,0.000037580576,0.00046684023,0.00007811982,0.0000030459846,0.0020431986],"genre_scores_gemma":[0.9926664,0.0034364082,0.0006212209,0.000915569,0.00038155442,0.000006060546,0.0000044009867,0.00001267482,0.0019557145],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9901794,0.002764536,0.0011898952,0.00023099297,0.0051102573,0.00052491605],"domain_scores_gemma":[0.9883901,0.002608873,0.0006771896,0.00035881667,0.0075913463,0.0003737045],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.047669783,0.00010181621,0.0003449231,0.001969296,0.0010328614,0.00031330468,0.00057255983,0.00008810975,0.00020160663],"category_scores_gemma":[0.0025413176,0.000062001345,0.000029552995,0.004553671,0.0003471877,0.00059503585,0.00031481904,0.000546081,0.000017994977],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006093619,0.0006886556,0.46193746,0.0018079324,0.0002138018,0.0000070117435,0.19428553,0.0028928972,0.0045503397,0.17584765,0.024108374,0.13305098],"study_design_scores_gemma":[0.004207433,0.0036221384,0.44573513,0.00057978136,0.000015134065,0.00010609336,0.05213647,0.027218392,0.0026629395,0.3873365,0.076029666,0.0003503272],"about_ca_topic_score_codex":0.0010056007,"about_ca_topic_score_gemma":0.0013260858,"teacher_disagreement_score":0.21148884,"about_ca_system_score_codex":0.00047346606,"about_ca_system_score_gemma":0.008161931,"threshold_uncertainty_score":0.99746084},"labels":[],"label_agreement":null},{"id":"W2039506919","doi":"10.1016/j.evalprogplan.2012.07.002","title":"An evaluability assessment of a West Africa based Non-Governmental Organization's (NGO) progressive evaluation strategy","year":2012,"lang":"en","type":"article","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Canadian Institutes of Health Research","keywords":"Context (archaeology); Political science; Public relations; Program evaluation; Intervention (counseling); Impact evaluation; Politics; Humanitarian aid; Business; Public administration; Medicine; Nursing","score_opus":0.23215564390695925,"score_gpt":0.5669080049354714,"score_spread":0.3347523610285122,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2039506919","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98028946,0.0004892429,0.0046555665,0.00025860645,0.00035895428,0.0032288276,0.000027023572,0.000078960955,0.010613374],"genre_scores_gemma":[0.98932546,0.0000033449137,0.009561073,0.000087319066,0.00013947081,0.00049896515,0.00033450025,0.000020866333,0.000029015318],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98968023,0.0018295194,0.0010187231,0.00057340803,0.0064841686,0.00041395152],"domain_scores_gemma":[0.9947002,0.00052666356,0.00088683306,0.0006146839,0.0029840067,0.0002876341],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.030502586,0.0002643553,0.00035839117,0.0002801448,0.00038154094,0.000389297,0.00033864396,0.00014103919,0.0071990374],"category_scores_gemma":[0.0016888924,0.00021352601,0.00006910591,0.0012182867,0.00014761506,0.0015758025,0.00006604373,0.00019522816,0.000031290594],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037062684,0.00094701047,0.67515045,0.00002243725,0.000031868996,2.694271e-7,0.0024401622,0.012871628,0.0008576104,0.00028429052,0.00025951458,0.3070977],"study_design_scores_gemma":[0.0010715642,0.00043285196,0.5015212,0.000033138633,0.0001058489,0.0000025056895,0.0030628094,0.49267736,0.00035323776,0.00026896445,0.00031712544,0.00015338331],"about_ca_topic_score_codex":0.000012759247,"about_ca_topic_score_gemma":0.000006431415,"teacher_disagreement_score":0.47980574,"about_ca_system_score_codex":0.00044793016,"about_ca_system_score_gemma":0.0012858761,"threshold_uncertainty_score":0.9983016},"labels":[],"label_agreement":null},{"id":"W2039620387","doi":"10.1016/s0840-4704(10)60432-2","title":"Adventures in Research Land: <i>Another Glance “Through the Looking Glass” to See What Constitutes Research</i>","year":2001,"lang":"en","type":"article","venue":"Healthcare Management Forum","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Epistemology; Perspective (graphical); Harm; Quality (philosophy); Subject (documents); Adventure; Rule of thumb; Psychology; Sociology; Computer science; Social psychology; Artificial intelligence; Philosophy","score_opus":0.4623521493289002,"score_gpt":0.5924743503318438,"score_spread":0.13012220100294364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2039620387","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09139803,0.004495575,0.0022528484,0.7458233,0.0020067992,0.004501982,0.000012696193,0.0001039478,0.14940478],"genre_scores_gemma":[0.962453,0.0041299886,0.0006861393,0.018784141,0.00018856228,0.00043992177,0.000008309937,0.000022431946,0.013287511],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9904026,0.0017502367,0.0007937059,0.0007820574,0.004960243,0.00131117],"domain_scores_gemma":[0.99634266,0.0014611783,0.000116232455,0.0012298117,0.00070776185,0.00014233864],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.021309104,0.0001773697,0.00026907597,0.0008005271,0.0010321642,0.0010442355,0.0014495323,0.00008777761,0.0007495007],"category_scores_gemma":[0.0005293212,0.000114390714,0.00006917761,0.0036496841,0.0002674861,0.00099886,0.0008221225,0.0007054793,0.0017451377],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002951062,0.0001735643,0.2091227,0.000089376124,0.0000305746,0.000119337856,0.006086676,0.0016076168,0.000008534178,0.14927907,0.24237153,0.3908159],"study_design_scores_gemma":[0.00048497354,0.00013953206,0.01977269,0.0002851001,0.0000017478205,0.0000044824587,0.029718935,0.00057897146,0.000021705944,0.039206,0.90965384,0.00013202755],"about_ca_topic_score_codex":0.001633009,"about_ca_topic_score_gemma":0.022999102,"teacher_disagreement_score":0.87105495,"about_ca_system_score_codex":0.00033315917,"about_ca_system_score_gemma":0.00018751102,"threshold_uncertainty_score":0.9999928},"labels":[],"label_agreement":null},{"id":"W204142434","doi":"10.55016/ojs/ajer.v53i2.55263","title":"Policy Trends and Tensions in Accountability for Educational Management and Services in Canada","year":2007,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":54,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Accountability; Educational research; Public administration; Educational administration; Political science; Sociology; Psychology; Pedagogy; Higher education; Law","score_opus":0.24591616521862245,"score_gpt":0.5873597965113111,"score_spread":0.3414436312926886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W204142434","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9148965,0.000204338,0.0000021969117,0.07308969,0.00013736004,0.00012675744,0.000003963991,5.849256e-8,0.011539121],"genre_scores_gemma":[0.9920667,0.0001003352,0.00048077203,0.00036429358,0.00015077824,0.0000147828905,0.0000051422094,0.0000035424603,0.0068136603],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99734,0.00013480685,0.000696412,0.00019699597,0.0013654736,0.0002662997],"domain_scores_gemma":[0.9756118,0.023081673,0.00015551964,0.00015003516,0.0008303183,0.0001706532],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0077459305,0.00006709511,0.00014725469,0.0015246455,0.00012383252,0.00009105834,0.000297026,0.00002673146,0.0018828782],"category_scores_gemma":[0.00345782,0.00005121915,0.000022027436,0.001247095,0.00006909191,0.00036899585,0.00007353527,0.00018833448,0.000005404464],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008106223,0.00012643532,0.9639939,0.000018360215,0.000008062089,2.1696309e-7,0.0006931292,0.00005263378,0.000012757972,0.015588876,0.002499729,0.016924823],"study_design_scores_gemma":[0.0004248807,0.000035339282,0.9702019,0.00003720302,0.0000023645296,0.00001492937,0.0039529223,0.00035869313,0.000006064319,0.01673127,0.0081876,0.000046822883],"about_ca_topic_score_codex":0.41324797,"about_ca_topic_score_gemma":0.97377473,"teacher_disagreement_score":0.5605268,"about_ca_system_score_codex":0.0006389002,"about_ca_system_score_gemma":0.00497255,"threshold_uncertainty_score":0.9990295},"labels":[],"label_agreement":null},{"id":"W2043024755","doi":"10.1007/s11092-013-9184-8","title":"The journey from rhetoric to reality: participatory evaluation in a development context","year":2014,"lang":"en","type":"article","venue":"Educational Assessment Evaluation and Accountability","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":34,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Citizen journalism; Context (archaeology); Situated; Stakeholder; Sociology; Warrant; Rhetoric; Participatory action research; International development; Participatory evaluation; Engineering ethics; Conceptual framework; Epistemology; Political science; Social science; Public relations; Computer science; Engineering; Geography; Business","score_opus":0.3829268271012413,"score_gpt":0.5696211298539817,"score_spread":0.1866943027527404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2043024755","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9576222,0.00016670157,0.0012117317,0.03237257,0.0012076437,0.001470756,0.000009139568,0.000014152411,0.0059251143],"genre_scores_gemma":[0.99576014,0.000011691701,0.0008188507,0.0015095009,0.00027354847,0.00131592,0.00009406466,0.000009037915,0.00020725321],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9888198,0.002964711,0.0014746445,0.00069775386,0.005707079,0.00033606304],"domain_scores_gemma":[0.99110264,0.004836776,0.0004337771,0.00076210406,0.0026408662,0.00022386728],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.06747412,0.00021229907,0.00027989378,0.00023177454,0.00062161084,0.00066653313,0.00046428415,0.00007634415,0.0042337417],"category_scores_gemma":[0.008169542,0.0001473888,0.000055764463,0.0007548869,0.000099476136,0.0006588169,0.00012311428,0.00021942226,0.0002591008],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040770276,0.000305767,0.40191945,0.0000035498238,0.000019876607,1.4093768e-8,0.004641605,0.0012461955,0.00007665333,0.0071702255,0.0038153937,0.5807605],"study_design_scores_gemma":[0.00071416755,0.000030691954,0.80325055,0.000017410002,0.000023568862,3.2552109e-7,0.003767718,0.07966953,0.000035998553,0.052238986,0.06009216,0.00015888282],"about_ca_topic_score_codex":0.00030530157,"about_ca_topic_score_gemma":0.006621468,"teacher_disagreement_score":0.58060163,"about_ca_system_score_codex":0.0013693512,"about_ca_system_score_gemma":0.003834401,"threshold_uncertainty_score":0.9966765},"labels":[],"label_agreement":null},{"id":"W2043068352","doi":"10.1111/j.1524-4733.2010.00747.x","title":"Conditionally Funded Field Evaluations: PATHs Coverage with Evidence Development Program for Ontario","year":2010,"lang":"en","type":"article","venue":"Value in Health","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McMaster University; St. Joseph’s Healthcare Hamilton; Programs for Assessment of Technology in Health Research Institute","funders":"","keywords":"Field (mathematics); Data science; Computer science; Mathematics","score_opus":0.34842160670139555,"score_gpt":0.5381083385528902,"score_spread":0.18968673185149465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2043068352","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97512865,0.00006492715,0.010704194,0.00881839,0.0006602845,0.0029348542,0.00000931538,0.000049179154,0.0016301872],"genre_scores_gemma":[0.92396253,0.000015344993,0.07163932,0.0022378569,0.000059134585,0.0008961983,0.000028954459,0.000008383986,0.0011522877],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9963334,0.0002147348,0.0009839463,0.00042923223,0.0017131163,0.00032555853],"domain_scores_gemma":[0.99553746,0.0029824341,0.00036944737,0.00039320756,0.00056927133,0.00014820052],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010772634,0.00013138702,0.00023264159,0.00022058382,0.00029527498,0.00018847057,0.0003550909,0.00007092844,0.0021182832],"category_scores_gemma":[0.002044435,0.00009557,0.00004243393,0.00041667582,0.000038147427,0.0004412933,0.000035209167,0.00029652353,0.000098074655],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031115056,0.0007011216,0.47577655,0.0001022514,0.000023709672,0.000002921974,0.007921266,0.019759588,0.000069350055,0.017819902,0.0055880323,0.47192416],"study_design_scores_gemma":[0.0016683406,0.0015865468,0.82163817,0.00032989742,0.0000061564983,0.000008792685,0.00026581637,0.022472907,0.00023578605,0.029065434,0.12243057,0.000291587],"about_ca_topic_score_codex":0.0060016755,"about_ca_topic_score_gemma":0.13695493,"teacher_disagreement_score":0.47163257,"about_ca_system_score_codex":0.0003429317,"about_ca_system_score_gemma":0.0075503094,"threshold_uncertainty_score":0.9987939},"labels":[],"label_agreement":null},{"id":"W2043777716","doi":"10.3138/cjpe.29.1.36","title":"Supporting Knowledge Translation Through Evaluation: Evaluator as Knowledge Broker","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"McMaster University; Queen's University","funders":"","keywords":"Knowledge translation; Context (archaeology); Knowledge management; Computer science; History","score_opus":0.4946854783565933,"score_gpt":0.5959329823406669,"score_spread":0.10124750398407362,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2043777716","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6728983,0.010307306,0.019333895,0.0070667393,0.008343509,0.007601594,0.00001829282,0.00009115905,0.2743392],"genre_scores_gemma":[0.99219674,0.000015020231,0.0056251124,0.0002702803,0.00094635424,0.00021655628,0.000048190017,0.000033164277,0.0006486035],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98792875,0.003570183,0.0024330136,0.0005339553,0.0048655192,0.0006685862],"domain_scores_gemma":[0.9837446,0.0011667992,0.0016682688,0.00064738863,0.01200564,0.0007672675],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.07480533,0.0003111415,0.00053230993,0.0009844174,0.00058571313,0.00076042814,0.0008366985,0.00022395722,0.012596377],"category_scores_gemma":[0.014309654,0.00025693356,0.00035523635,0.0016892706,0.00017572739,0.0018474521,0.00002174334,0.00042150606,0.0012681882],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002283637,0.000101648606,0.0040514097,0.00001140184,0.000045874916,0.0000011308707,0.0072878283,0.0020152899,0.000083278275,0.0012598572,0.007003614,0.97811586],"study_design_scores_gemma":[0.0030289828,0.001147647,0.013149817,0.00011747747,0.00045390197,0.000080298465,0.0021614511,0.4814937,0.00031977752,0.05012747,0.44753796,0.00038150788],"about_ca_topic_score_codex":0.00026302162,"about_ca_topic_score_gemma":0.0144968135,"teacher_disagreement_score":0.9777343,"about_ca_system_score_codex":0.00092792994,"about_ca_system_score_gemma":0.015243008,"threshold_uncertainty_score":0.9999883},"labels":[],"label_agreement":null},{"id":"W2044475865","doi":"10.1258/1355819041403187","title":"Using questionnaires in qualitative interviews","year":2004,"lang":"en","type":"letter","venue":"Journal of Health Services Research & Policy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"","keywords":"Qualitative research; Psychology; Sociology; Nursing; Medicine; Social science","score_opus":0.7161355538467001,"score_gpt":0.7374352068787502,"score_spread":0.02129965303205006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2044475865","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013285278,0.0044766483,0.0003004449,0.9797966,0.0006753042,0.00053943635,0.00002509057,0.0000067161586,0.0008944966],"genre_scores_gemma":[0.07647625,0.0033924654,0.0031500538,0.9069159,0.0085748015,0.000023395018,0.00002503851,0.00006569206,0.0013763913],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9708574,0.013876102,0.004408397,0.00046818025,0.009238764,0.0011511852],"domain_scores_gemma":[0.9873475,0.0033764977,0.003465249,0.0007046972,0.0048024706,0.0003035941],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.08179068,0.00029410847,0.0012200119,0.0071227015,0.00035179063,0.00058781164,0.0023085899,0.0004118544,0.00055974245],"category_scores_gemma":[0.0019495293,0.00020264758,0.00028891955,0.0035781334,0.00019798036,0.0011297666,0.00031421505,0.004931331,0.00019187883],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017726744,0.00031158567,0.0010828745,0.0025503703,0.00010496007,0.00034134326,0.31916445,0.0019509662,0.000020230127,0.0010811118,0.5852006,0.08801426],"study_design_scores_gemma":[0.0011723106,0.0009818228,0.0028510885,0.0076861028,0.0000064535607,0.00013391806,0.041847665,0.0015906252,0.000010546069,0.12411101,0.8193212,0.0002872282],"about_ca_topic_score_codex":0.018021774,"about_ca_topic_score_gemma":0.003076726,"teacher_disagreement_score":0.27731678,"about_ca_system_score_codex":0.003813748,"about_ca_system_score_gemma":0.019624893,"threshold_uncertainty_score":0.99736434},"labels":[],"label_agreement":null},{"id":"W2045099471","doi":"10.1177/136548020000300106","title":"Learning, for a Change: School Improvement as Capacity Building","year":2000,"lang":"en","type":"article","venue":"Improving Schools","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Effi; Student achievement; Mathematics education; Set (abstract data type); Political science; Pedagogy; Sociology; Academic achievement; Public relations; Psychology; Computer science","score_opus":0.16352429064606971,"score_gpt":0.4580711998673282,"score_spread":0.2945469092212585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2045099471","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9860574,0.00005963899,0.0042397133,0.0023863378,0.00046811884,0.0013415271,0.000010848012,0.00014710691,0.0052893185],"genre_scores_gemma":[0.9707869,0.000021329572,0.007684049,0.0020718926,0.0006275451,0.0006134021,0.0000065266545,0.000026373356,0.018161941],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99633175,0.00014644687,0.0007419752,0.0006912102,0.001537631,0.00055097253],"domain_scores_gemma":[0.9979258,0.00036174938,0.00030799245,0.000618063,0.0004645139,0.000321866],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.005065156,0.00023033735,0.0003001133,0.00023653601,0.0005623035,0.0008433564,0.0006982189,0.00011690293,0.0090657035],"category_scores_gemma":[0.0038653768,0.00018404078,0.00018619893,0.0004804649,0.000039134124,0.001212782,0.00008112512,0.00045309312,0.002618994],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006569895,0.000049982864,0.009876881,0.000015509413,0.000016401926,9.613997e-7,0.00037324495,0.0003546026,0.014954768,0.0004995561,0.0030236198,0.97076875],"study_design_scores_gemma":[0.006034671,0.004306935,0.07405236,0.00018214213,0.0001076788,0.00003188955,0.0030756015,0.13948373,0.029905738,0.042491432,0.6986215,0.0017062997],"about_ca_topic_score_codex":0.0002958118,"about_ca_topic_score_gemma":0.000029524092,"teacher_disagreement_score":0.96906245,"about_ca_system_score_codex":0.00019640924,"about_ca_system_score_gemma":0.0003319611,"threshold_uncertainty_score":0.99815756},"labels":[],"label_agreement":null},{"id":"W2045890611","doi":"10.1007/s11205-007-9121-7","title":"A Comprehensive Action Plan Information System: A Tool for Tracking and Mapping Quality of Life Action Implementation and Planning","year":2007,"lang":"en","type":"article","venue":"Social Indicators Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Saskatoon City Hospital; University of Saskatchewan","funders":"","keywords":"Action plan; Process management; Action (physics); Compendium; Process (computing); Quality (philosophy); Participatory action research; Knowledge management; Public relations; Computer science; Business; Sociology; Political science; Management","score_opus":0.7288333779549295,"score_gpt":0.6653042651503156,"score_spread":0.06352911280461393,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2045890611","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9820679,0.000025586587,0.01659953,0.0002109627,0.00012485925,0.0006313155,0.000023724097,0.00001641777,0.00029973403],"genre_scores_gemma":[0.9994381,0.000009281461,0.0002953244,0.00004008179,0.0001371156,0.000036888774,0.0000312704,0.0000038591734,0.0000080894815],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9968389,0.00039126578,0.0007843666,0.0001701756,0.001574321,0.0002409605],"domain_scores_gemma":[0.99718505,0.0014263785,0.0004841968,0.000086329754,0.0007427338,0.00007531566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014984533,0.000069692825,0.0001903475,0.00094873173,0.0007439186,0.0002212013,0.000103735234,0.00009810411,0.00002539202],"category_scores_gemma":[0.0008346382,0.00006238558,0.000035591333,0.0007666359,0.000114688715,0.0009817199,0.000055511013,0.00017929186,0.0000042264664],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000643887,0.000023847215,0.39537483,0.000558042,0.000051640734,2.0211104e-7,0.051483758,0.000015580166,0.004150084,0.0058632656,0.0008144526,0.5410204],"study_design_scores_gemma":[0.00068077183,0.000073749354,0.7355771,0.000017963659,0.0000032624916,6.259636e-7,0.25977728,0.0005760266,0.00068047654,0.00035006157,0.0022013274,0.0000613371],"about_ca_topic_score_codex":0.0001273323,"about_ca_topic_score_gemma":0.000054335673,"teacher_disagreement_score":0.54095906,"about_ca_system_score_codex":0.000154264,"about_ca_system_score_gemma":0.00020645525,"threshold_uncertainty_score":0.57216954},"labels":[],"label_agreement":null},{"id":"W2045934399","doi":"10.1016/s1098-3015(10)69128-0","title":"PMC30 GUIDELINES FOR BUDGET IMPACT ANALYSIS IN CANADA","year":2007,"lang":"en","type":"article","venue":"Value in Health","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Business","score_opus":0.4295872366019313,"score_gpt":0.5961427506262914,"score_spread":0.16655551402436009,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2045934399","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9776376,0.00035091612,0.009002554,0.011616675,0.00037165728,0.00042301367,0.00004091772,0.0000069647836,0.00054969423],"genre_scores_gemma":[0.99225473,0.00005552203,0.0042840904,0.0031183185,0.000067210734,0.000010997193,0.00001340479,0.0000049855507,0.00019072929],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9962626,0.0002057288,0.0015656333,0.00030394152,0.001217987,0.00044410743],"domain_scores_gemma":[0.9971571,0.0015863435,0.00029285668,0.0003543333,0.00043688287,0.00017247825],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021484036,0.000098357166,0.00037485856,0.0008636789,0.00006650589,0.0000391477,0.00030725868,0.000032507935,0.00037492462],"category_scores_gemma":[0.0023460276,0.000070514565,0.000098653305,0.002870448,0.000010441812,0.0001327186,0.000023296798,0.000097105956,0.000012326651],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002321882,0.000016453598,0.6912045,0.00000593971,0.0000104610335,0.000001449816,0.00022995172,0.27412364,0.0000019256966,0.00018105155,0.008911373,0.025290046],"study_design_scores_gemma":[0.0003459486,0.000053979405,0.62880635,0.000012656796,0.0000042333995,5.6728595e-7,0.000870469,0.3585579,0.000011416444,0.0014765704,0.009786264,0.00007366994],"about_ca_topic_score_codex":0.96581537,"about_ca_topic_score_gemma":0.9910357,"teacher_disagreement_score":0.08443427,"about_ca_system_score_codex":0.0014963644,"about_ca_system_score_gemma":0.0063417484,"threshold_uncertainty_score":0.99929136},"labels":[],"label_agreement":null},{"id":"W2047839773","doi":"10.7202/1025740ar","title":"Arrimer théorie et pratique dans les programmes de troisième cycle en évaluation des interventions","year":2014,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Humanities; Political science; Valuation (finance); Philosophy; Economics","score_opus":0.19141541909476045,"score_gpt":0.5227753891063259,"score_spread":0.3313599700115655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047839773","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39552224,0.00071507954,0.53147364,0.05369723,0.0022242812,0.0013618318,0.00003058143,0.00013595003,0.014839193],"genre_scores_gemma":[0.9370333,0.0006586643,0.04244448,0.00075071136,0.0005340252,0.0005649951,0.0005492397,0.000061296974,0.017403303],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9642232,0.029627312,0.0018653098,0.0009468169,0.0026896293,0.0006477051],"domain_scores_gemma":[0.99190617,0.004070109,0.001031207,0.0008777805,0.0018795438,0.00023521771],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.10772773,0.00047532257,0.00048777997,0.0005782938,0.0006877125,0.0009163571,0.00064265786,0.00046890054,0.0039320695],"category_scores_gemma":[0.014265525,0.00045459226,0.00042965493,0.0012043996,0.000264451,0.0023764458,0.00011124765,0.0006334667,0.00089599617],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042389725,0.0010513745,0.051932756,0.0001986222,0.00012121007,4.819758e-7,0.25626698,0.03113094,0.0018720032,0.060346425,0.004010342,0.59302646],"study_design_scores_gemma":[0.0011513492,0.00051052746,0.6428559,0.00055609626,0.00035260047,0.000021261798,0.012882567,0.1894119,0.0014516587,0.12677516,0.023493191,0.00053782004],"about_ca_topic_score_codex":0.0010179458,"about_ca_topic_score_gemma":0.009174242,"teacher_disagreement_score":0.59248865,"about_ca_system_score_codex":0.0013833022,"about_ca_system_score_gemma":0.004895128,"threshold_uncertainty_score":0.9998819},"labels":[],"label_agreement":null},{"id":"W2049117895","doi":"10.1111/j.1559-8918.2010.00034.x","title":"They just don't get it: Strategies, tools, and best practices for explaining ethnography to stakeholders","year":2010,"lang":"en","type":"article","venue":"Ethnographic Praxis in Industry Conference Proceedings","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Workers Compensation Board of British Columbia","funders":"","keywords":"Ethnography; Service (business); Work (physics); Sociology; Praxis; Management; Political science; Business; Engineering; Law","score_opus":0.573950686292359,"score_gpt":0.512382726664855,"score_spread":0.061567959627504054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2049117895","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9616724,0.000043269418,0.0004358272,0.0141518535,0.00064636726,0.0011910149,0.00005618982,0.00008267328,0.02172036],"genre_scores_gemma":[0.9918215,0.000101769736,0.005849898,0.0010186962,0.0001952119,0.00055990706,0.000012605641,0.00002819701,0.0004121823],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9950206,0.00008350406,0.0011726444,0.0011885401,0.0017417287,0.00079296133],"domain_scores_gemma":[0.9948435,0.0015342269,0.0011222166,0.0004756307,0.001583657,0.00044077227],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.010535156,0.000444559,0.00052408,0.0016240806,0.00055316,0.0028705108,0.0013120386,0.00091293524,0.00055270444],"category_scores_gemma":[0.007695758,0.0003749501,0.00012112504,0.0024709161,0.00041344383,0.004407406,0.0002607875,0.0026711833,0.000017254917],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003516347,0.00046146545,0.59587306,0.00014585275,0.00009143334,0.000005934605,0.08535293,0.000061109466,0.010929616,0.039304778,0.010666765,0.25675544],"study_design_scores_gemma":[0.001978121,0.0011409487,0.04099675,0.00037762884,0.00006498759,0.000028299057,0.7463296,0.0034849828,0.0008049947,0.021579854,0.18205167,0.0011621845],"about_ca_topic_score_codex":0.00046516059,"about_ca_topic_score_gemma":0.005482368,"teacher_disagreement_score":0.66097665,"about_ca_system_score_codex":0.000026136011,"about_ca_system_score_gemma":0.00077269383,"threshold_uncertainty_score":0.99987024},"labels":[],"label_agreement":null},{"id":"W2051474802","doi":"10.7202/1024932ar","title":"Evaluation des apprentissages dans le contexte québécois","year":2014,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa; Université du Québec à Trois-Rivières","funders":"","keywords":"Humanities; Political science; Art","score_opus":0.18734299810483757,"score_gpt":0.4864640542908412,"score_spread":0.29912105618600365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2051474802","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.56657904,0.0031191146,0.33204368,0.032679632,0.007504351,0.0015965211,0.000028706358,0.00011332806,0.05633565],"genre_scores_gemma":[0.9603033,0.00044405693,0.0045786025,0.0006484139,0.0005625754,0.00028912388,0.00033127327,0.00004794805,0.03279472],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9572464,0.033151165,0.0016602838,0.0010957528,0.006271281,0.0005750714],"domain_scores_gemma":[0.9903684,0.0031850708,0.0009299898,0.0010718284,0.0042328318,0.0002118822],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.18400061,0.00043617556,0.00047940444,0.00048839767,0.0009983887,0.000707834,0.000656445,0.0003449367,0.007743268],"category_scores_gemma":[0.01661988,0.00042894916,0.00023797527,0.0012320492,0.00043011416,0.0026363921,0.000094098665,0.00037917745,0.0026991675],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001811665,0.00041705996,0.008194917,0.00004607167,0.000074565374,1.6139974e-7,0.12830664,0.012511875,0.0013614543,0.01827572,0.006239611,0.8245538],"study_design_scores_gemma":[0.0015657392,0.00020316776,0.55103457,0.00018170255,0.000347219,0.0000122338515,0.010485693,0.30535975,0.0013197766,0.06216159,0.066874,0.00045453946],"about_ca_topic_score_codex":0.003548502,"about_ca_topic_score_gemma":0.021310043,"teacher_disagreement_score":0.82409924,"about_ca_system_score_codex":0.0012972197,"about_ca_system_score_gemma":0.007435607,"threshold_uncertainty_score":0.99981624},"labels":[],"label_agreement":null},{"id":"W2051483991","doi":"10.1108/09578230010310975","title":"Guilty or not: the impact and effects of site‐based management on schools","year":2000,"lang":"en","type":"article","venue":"Journal of Educational Administration","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Workload; Competition (biology); Flexibility (engineering); Work (physics); Political science; Public relations; Business; Economics; Management; Engineering","score_opus":0.11250105986133785,"score_gpt":0.5161779364692537,"score_spread":0.40367687660791585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2051483991","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9799694,0.000042976146,0.0000981169,0.01648229,0.00018567189,0.00017994407,0.0000057351835,0.0000011139929,0.0030347526],"genre_scores_gemma":[0.9963238,0.000037032238,0.0010243184,0.000585346,0.0001676808,0.0000068079166,0.000004265253,0.0000030008362,0.0018477086],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9978742,0.00015499699,0.00061370083,0.00010575261,0.0011754696,0.00007586356],"domain_scores_gemma":[0.99729013,0.0015685952,0.00050807104,0.00019794112,0.00035625306,0.00007898015],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017684523,0.00008097274,0.00013613973,0.00015649723,0.00010365534,0.00012717374,0.00021896555,0.000026882788,0.003553938],"category_scores_gemma":[0.0006571407,0.000039362887,0.00008443161,0.00027901513,0.00003832142,0.00021757852,0.0000068825725,0.0001100982,0.00006279081],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0129792625,0.0059573706,0.12609617,0.00022421681,0.0005417558,0.000030491643,0.00293577,0.06091222,0.0040049446,0.026504995,0.18391469,0.5758981],"study_design_scores_gemma":[0.0008268821,0.0013954708,0.9834628,0.0001122275,0.000036686033,0.000038320894,0.0002462494,0.0036967695,0.0022193212,0.004244163,0.0036424042,0.00007867998],"about_ca_topic_score_codex":0.0000027073716,"about_ca_topic_score_gemma":0.0000056846907,"teacher_disagreement_score":0.8573667,"about_ca_system_score_codex":0.0000566708,"about_ca_system_score_gemma":0.0008234351,"threshold_uncertainty_score":0.99735695},"labels":[],"label_agreement":null},{"id":"W2052280380","doi":"10.1177/1356389012461192","title":"The ethical sensitivity of evaluators: A qualitative study using a vignette design","year":2012,"lang":"en","type":"article","venue":"Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université Laval","funders":"Government of Canada","keywords":"Vignette; Context (archaeology); Psychology; Qualitative research; Quality (philosophy); Social psychology; Engineering ethics; Sociology; Epistemology; Social science","score_opus":0.6117213930755443,"score_gpt":0.6475090385779075,"score_spread":0.03578764550236324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052280380","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9256657,0.00016237266,0.07076379,0.0009906868,0.00050821685,0.0014389176,0.0000026990028,0.000013440878,0.00045423085],"genre_scores_gemma":[0.99742955,0.0000028832744,0.0021185281,0.00016852886,0.00013904557,0.000068692025,0.000002031403,0.000008013604,0.00006275527],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9546191,0.035233486,0.0011530494,0.0003522681,0.00827651,0.00036556702],"domain_scores_gemma":[0.9850491,0.011283144,0.0008137304,0.0005737742,0.0021894267,0.000090818816],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.264315,0.00013162196,0.00024042251,0.00015138397,0.00043682638,0.00011775502,0.0002201448,0.0001013989,0.00053209614],"category_scores_gemma":[0.020995993,0.00007855737,0.00008456729,0.0007916494,0.00013649817,0.000511099,0.00007839686,0.0002643565,0.00016195008],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00054340134,0.0013875549,0.034663957,0.000008863947,0.00025465735,8.335158e-7,0.6717294,0.033953384,0.014572494,0.004389659,0.0052730865,0.2332227],"study_design_scores_gemma":[0.0009668425,0.00029974763,0.07285091,0.000014271665,0.00016026449,0.0000035077499,0.10266712,0.81044865,0.0012905382,0.010842168,0.00029554914,0.00016043612],"about_ca_topic_score_codex":0.000051071587,"about_ca_topic_score_gemma":0.000060513295,"teacher_disagreement_score":0.7764953,"about_ca_system_score_codex":0.00018336471,"about_ca_system_score_gemma":0.00060078927,"threshold_uncertainty_score":0.98725057},"labels":[],"label_agreement":null},{"id":"W2053130407","doi":"10.5430/ijba.v4n6p1","title":"Executive Guidelines for Evaluating Consultants","year":2013,"lang":"en","type":"article","venue":"International Journal of Business Administration","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Not for profit; Business; Profit (economics); Executive information system; Executive summary; Corporate title; Public relations; Marketing; Accounting; Information system; Knowledge management; Corporate governance; Management information systems; Computer science; Economics; Finance; Political science","score_opus":0.4921721356986198,"score_gpt":0.5987638587504672,"score_spread":0.10659172305184744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2053130407","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6463941,0.000112117035,0.2715819,0.071304806,0.006190406,0.00068378967,0.000041913798,0.000017718643,0.0036732862],"genre_scores_gemma":[0.9735112,0.000027021773,0.023777809,0.0009081544,0.00071280403,0.0000260808,0.000017973585,0.0000072052676,0.0010117491],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.995724,0.00008636379,0.0015482084,0.00016110223,0.0023671025,0.000113197864],"domain_scores_gemma":[0.94329685,0.000840004,0.0014000593,0.00012937648,0.054264534,0.00006916498],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0035920166,0.000106157924,0.00020641522,0.00030617617,0.00008051375,0.0005550518,0.00061264914,0.00005079388,0.0011685888],"category_scores_gemma":[0.021234663,0.000074654105,0.00009167988,0.00039070737,0.000044501856,0.0014485744,0.000032725995,0.000074736105,0.00008926044],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008485735,0.00042334947,0.016356109,0.000014911688,0.0002871897,0.00001685365,0.0008107728,0.008241204,0.028364139,0.009798987,0.13509543,0.79974246],"study_design_scores_gemma":[0.009517303,0.0019510608,0.39989337,0.00050022313,0.00014043765,0.00082847907,0.006973261,0.3035461,0.017970948,0.1613539,0.09649882,0.00082610047],"about_ca_topic_score_codex":0.000008249485,"about_ca_topic_score_gemma":0.00001169097,"teacher_disagreement_score":0.7989164,"about_ca_system_score_codex":0.000075296004,"about_ca_system_score_gemma":0.001086841,"threshold_uncertainty_score":0.9997445},"labels":[],"label_agreement":null},{"id":"W2053227498","doi":"10.1080/13632430120074437","title":"Building Change Capacity Within Secondary Schools Through Goal-driven and Living Organisations","year":2001,"lang":"en","type":"article","venue":"School Leadership and Management","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Restructuring; Organizational change; Government (linguistics); Sociology; Public relations; Theory of change; Qualitative research; Political science; Pedagogy; Social science","score_opus":0.3405425916178175,"score_gpt":0.42192219964630473,"score_spread":0.0813796080284872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2053227498","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91982996,0.0007590555,0.018456353,0.031883217,0.0007512607,0.0014442364,0.00001167573,0.00017855014,0.026685694],"genre_scores_gemma":[0.97417796,0.000523778,0.017092431,0.0051129367,0.00018545057,0.0000847596,0.00000270981,0.000014142122,0.0028058407],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9976481,0.00017835668,0.00044467382,0.0005354825,0.0008656616,0.0003277214],"domain_scores_gemma":[0.998954,0.00017967224,0.00017424725,0.000388199,0.0001111866,0.00019267378],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0022238242,0.00018682893,0.0002106003,0.00023905975,0.0004939881,0.0005847243,0.00028377777,0.00006923585,0.0013634152],"category_scores_gemma":[0.00031037524,0.00015411343,0.00004099601,0.00052157074,0.00009522921,0.0014973911,0.00021396422,0.00031812818,0.00023124692],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008260537,0.0002838764,0.4970568,0.0004367286,0.0003348637,0.00005247733,0.04976977,0.00032673593,0.0010259261,0.19003768,0.02887396,0.23171856],"study_design_scores_gemma":[0.0013653417,0.00017755997,0.7396882,0.00037493874,0.00011215799,0.000040650164,0.09991939,0.0038906387,0.00012552875,0.028845876,0.12475807,0.0007016222],"about_ca_topic_score_codex":0.00007934307,"about_ca_topic_score_gemma":0.00022230633,"teacher_disagreement_score":0.24263142,"about_ca_system_score_codex":0.00007893158,"about_ca_system_score_gemma":0.00004836364,"threshold_uncertainty_score":0.99954945},"labels":[],"label_agreement":null},{"id":"W2053476798","doi":"10.1016/j.obhdp.2009.11.007","title":"What types of advice do decision-makers prefer?","year":2010,"lang":"en","type":"article","venue":"Organizational Behavior and Human Decision Processes","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":158,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University; University of Ottawa","funders":"","keywords":"Advice (programming); Situational ethics; Psychology; Decision maker; Perspective (graphical); Autonomy; Interpersonal communication; Decision analysis; Social psychology; Management science; Applied psychology; Computer science; Political science; Engineering; Artificial intelligence","score_opus":0.05479233121572701,"score_gpt":0.4294093933916098,"score_spread":0.37461706217588275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2053476798","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9959916,0.00033196522,0.0010544609,0.00016710251,0.00078765425,0.00025999243,0.000023148174,0.00004915467,0.0013349334],"genre_scores_gemma":[0.9937312,0.0002438065,0.0044408133,0.00014495596,0.00009569023,0.000021521999,0.000032536904,0.000024990455,0.0012644724],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9958792,0.000041853233,0.00094925286,0.0005734662,0.0023689708,0.00018729949],"domain_scores_gemma":[0.9937398,0.0017014695,0.00038337978,0.0005341902,0.0034699524,0.0001711947],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015029006,0.00020618206,0.00031897632,0.0004394329,0.0004308307,0.0008085694,0.00067220494,0.0001508702,0.016638098],"category_scores_gemma":[0.0034535073,0.00015113565,0.00005063038,0.0013928601,0.00019007125,0.0016594578,0.00020764426,0.00020846243,0.00023142058],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014004677,0.00080638024,0.7151518,0.0000515618,0.000025219148,0.000007017143,0.0019525491,0.00013855487,0.0116682565,0.030141193,0.0076807155,0.2322367],"study_design_scores_gemma":[0.001777648,0.00030946246,0.81451017,0.00026262985,0.00012766659,0.00006620827,0.0025451707,0.00013688792,0.00866717,0.1348003,0.036139198,0.0006575148],"about_ca_topic_score_codex":0.000004820073,"about_ca_topic_score_gemma":0.00019907209,"teacher_disagreement_score":0.23157918,"about_ca_system_score_codex":0.000016308,"about_ca_system_score_gemma":0.00044432902,"threshold_uncertainty_score":0.9842608},"labels":[],"label_agreement":null},{"id":"W2053545578","doi":"10.7202/1005775ar","title":"Entre mesure, science et politique : construction et analyse d’un réseau international de copublications dans le domaine de l’éducation","year":2011,"lang":"fr","type":"article","venue":"Nouvelles perspectives en sciences sociales","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.18527747369761752,"score_gpt":0.5004955617796112,"score_spread":0.3152180880819937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2053545578","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6357936,0.0006579013,0.07705277,0.090142004,0.0020194706,0.0004181966,0.00013746932,0.00010034089,0.19367822],"genre_scores_gemma":[0.9361266,0.0011564754,0.059848867,0.0007834539,0.00028279662,0.000045473666,0.000013711598,0.000014133057,0.0017284976],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.99296004,0.0022257918,0.00076152687,0.0010539843,0.0022286256,0.0007700327],"domain_scores_gemma":[0.995633,0.001196855,0.0006533518,0.0004309226,0.0017516357,0.00033423185],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["sts"],"category_scores_codex":[0.021247705,0.00030054906,0.00031779066,0.0010353257,0.0023695265,0.001047823,0.0019793904,0.00019768001,0.0029240842],"category_scores_gemma":[0.003937955,0.00028488046,0.00020990716,0.0033135181,0.010011782,0.0034494465,0.00029666987,0.00039204233,0.00009512773],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000011149795,0.00037996334,0.040863674,0.0000035772257,0.000038488786,0.0000011820423,0.2937455,0.00019798652,0.0016785316,0.6589277,0.0003698083,0.0037824672],"study_design_scores_gemma":[0.00036775414,0.000118211436,0.16660625,0.00003750802,0.000041477368,0.00006117232,0.66409457,0.0061954856,0.0033440788,0.1571633,0.0016713537,0.00029882535],"about_ca_topic_score_codex":0.0062214974,"about_ca_topic_score_gemma":0.004819843,"teacher_disagreement_score":0.50176436,"about_ca_system_score_codex":0.0039414833,"about_ca_system_score_gemma":0.036880706,"threshold_uncertainty_score":0.9999892},"labels":[],"label_agreement":null},{"id":"W2054174565","doi":"10.14507/epaa.v8n30.2000","title":"Performance Models in Higher Education","year":2000,"lang":"en","type":"article","venue":"Education Policy Analysis Archives","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Governmentality; Accountability; Ideology; Sociology; Context (archaeology); State (computer science); Higher education; Public administration; Field (mathematics); Set (abstract data type); Public relations; Political science; Politics; Law","score_opus":0.18268149238160303,"score_gpt":0.497219501610406,"score_spread":0.314538009228803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054174565","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5952603,0.00010177385,0.00009212591,0.010984092,0.00015989828,0.00011349007,0.0000031527647,0.00001675863,0.39326835],"genre_scores_gemma":[0.8434811,0.0002486291,0.0008655199,0.0019516272,0.00032907212,0.00008523111,0.00004717397,0.0000064675655,0.15298517],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99749696,0.00029938068,0.0007219239,0.0004312392,0.00080932066,0.00024118234],"domain_scores_gemma":[0.99862075,0.0002701975,0.00018627227,0.00068291544,0.00010603445,0.00013383152],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00089662126,0.00014327318,0.00026634985,0.0025362482,0.0001575516,0.00017930029,0.0005193199,0.00004008445,0.01896594],"category_scores_gemma":[0.000082872095,0.00011699343,0.0001723787,0.004466787,0.00007442217,0.0008836306,0.000027026797,0.00012665996,0.00070025324],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020957696,0.00048060968,0.10547887,0.000004094056,0.00005327838,3.554419e-8,0.003427485,0.065949365,0.000025910334,0.025148382,0.00241982,0.79699117],"study_design_scores_gemma":[0.000106602645,0.000016865486,0.78687423,0.0000117421505,0.000052032956,6.2145966e-7,0.00047155312,0.09954786,0.000023008255,0.05230367,0.060443036,0.00014877677],"about_ca_topic_score_codex":0.0004111943,"about_ca_topic_score_gemma":0.00014078883,"teacher_disagreement_score":0.7968424,"about_ca_system_score_codex":0.00007918571,"about_ca_system_score_gemma":0.0019500135,"threshold_uncertainty_score":0.98193085},"labels":[],"label_agreement":null},{"id":"W2054415360","doi":"10.1016/j.stueduc.2009.12.005","title":"Evaluation for learning: A cross-case analysis of evaluator strategies","year":2009,"lang":"en","type":"article","venue":"Studies In Educational Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; Queen's University","funders":"","keywords":"Process (computing); Citizen journalism; Participatory evaluation; Reflection (computer programming); Program evaluation; Knowledge management; Computer science; Process management; Psychology; Sociology; Political science; Engineering","score_opus":0.5328970254040822,"score_gpt":0.6892803130688502,"score_spread":0.15638328766476794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054415360","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98623157,0.0017120772,0.0014552473,0.0024583836,0.0008283548,0.0016688873,0.000020584144,0.000013817066,0.005611094],"genre_scores_gemma":[0.99653715,0.000054177184,0.0018888186,0.00012286224,0.00017058777,0.00071421976,0.00015989166,0.0000068117624,0.00034550353],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9903953,0.0014148242,0.0015687029,0.00062754896,0.0057373648,0.00025624124],"domain_scores_gemma":[0.9808043,0.0034310853,0.00088383415,0.0004614738,0.014362555,0.00005672436],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.056533244,0.00019898811,0.0005395718,0.0015798666,0.00032877302,0.0001655678,0.0003002257,0.000085629385,0.0021487398],"category_scores_gemma":[0.031728927,0.00016688208,0.00025476728,0.0034186912,0.00018824189,0.0009230479,0.000034226574,0.0001304046,0.000026486005],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011313563,0.0004764412,0.04781553,0.000016731386,0.0007925123,5.1811134e-7,0.011775674,0.7467484,0.0002182783,0.016260853,0.0011622185,0.17461969],"study_design_scores_gemma":[0.00095994014,0.00019682974,0.32015836,0.000015960462,0.0011750015,0.000004327582,0.014451356,0.5031605,0.00003943631,0.15947911,0.00022643532,0.00013280404],"about_ca_topic_score_codex":0.000017732236,"about_ca_topic_score_gemma":0.0003115428,"teacher_disagreement_score":0.27234283,"about_ca_system_score_codex":0.00073066616,"about_ca_system_score_gemma":0.0029080468,"threshold_uncertainty_score":0.99876344},"labels":[],"label_agreement":null},{"id":"W2054501882","doi":"10.1016/s0308-521x(03)00124-0","title":"Expanding the use of impact assessment and evaluation in agricultural research and development","year":2003,"lang":"en","type":"article","venue":"Agricultural Systems","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":44,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Consortium of International Agricultural Research Centers","keywords":"Impact assessment; Computer science; Agriculture; Affect (linguistics); Evaluation methods; Management science; Risk analysis (engineering); Psychology; Political science; Business; Economics; Engineering","score_opus":0.5719115469701419,"score_gpt":0.5629656648672771,"score_spread":0.008945882102864844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054501882","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99705625,0.00041023042,0.00002381096,0.0002188147,0.00018621149,0.0008684001,0.000001909878,0.0000054517477,0.0012289417],"genre_scores_gemma":[0.9991491,0.000033168966,0.00024021027,0.0000046436257,0.000027020795,0.000107856315,0.000008722392,0.0000024811986,0.00042678908],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99489456,0.0014112282,0.0006949275,0.00030420598,0.0024400984,0.0002549903],"domain_scores_gemma":[0.9971634,0.0013262709,0.00022613847,0.00018429704,0.0010189967,0.00008091055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012191752,0.00012786286,0.00023437272,0.00015374948,0.00029562425,0.0005458757,0.00016248878,0.000058115387,0.00006557567],"category_scores_gemma":[0.00054387265,0.000048022215,0.000026928277,0.000839232,0.00007852892,0.0006620924,0.00006911471,0.00017215594,0.000010735997],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018235261,0.0001330275,0.9465024,0.000032767442,0.00006479418,0.0000012248125,0.007949144,0.00618911,0.011633501,0.0051190103,0.0047280435,0.017628752],"study_design_scores_gemma":[0.00036870455,0.000077049655,0.98038733,0.00005655507,0.000004320064,0.00002365359,0.015591918,0.0012655379,0.00029188703,0.000108777516,0.0017322588,0.00009202287],"about_ca_topic_score_codex":0.00024271713,"about_ca_topic_score_gemma":0.00023352589,"teacher_disagreement_score":0.033884924,"about_ca_system_score_codex":0.00031096474,"about_ca_system_score_gemma":0.00018987685,"threshold_uncertainty_score":0.5263892},"labels":[],"label_agreement":null},{"id":"W2054894396","doi":"10.1080/00220388.2010.514331","title":"Against Excessive Rhetoric in Impact Assessment: Overstating the Case for Randomised Controlled Experiments","year":2011,"lang":"en","type":"article","venue":"The Journal of Development Studies","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trent University","funders":"Link Foundation","keywords":"Causation; Causal inference; Argument (complex analysis); Impact evaluation; Impact assessment; Rhetoric; Inference; Randomized experiment; Psychology; Epistemology; Political science; Economics; Medicine; Law; Econometrics; Philosophy","score_opus":0.36281506576399253,"score_gpt":0.5344587604187655,"score_spread":0.17164369465477297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054894396","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99180144,0.0013153394,0.0024193542,0.0005656975,0.00061866007,0.001089441,0.0000012949952,0.000003884992,0.0021848658],"genre_scores_gemma":[0.9959008,0.00036632337,0.0031032087,0.00024606733,0.00005849118,0.00010064477,3.1582266e-7,0.000007146122,0.00021701951],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99635905,0.0006928478,0.0015581251,0.00012222992,0.0010208206,0.00024691346],"domain_scores_gemma":[0.9916626,0.0055154394,0.0016261566,0.00019325314,0.0009487904,0.0000537552],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018462673,0.0001770498,0.0006216397,0.0002296471,0.00063022145,0.00007418837,0.0005003406,0.000024714016,0.00011693779],"category_scores_gemma":[0.0023051258,0.0000663891,0.00018417403,0.00035439874,0.00009065377,0.0003786774,0.00010908536,0.00017560144,0.0000061416595],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.03350866,0.00083252846,0.048870735,0.000042451164,0.005402812,0.00038651074,0.80525964,0.0030234458,0.001025649,0.00065178133,0.014265874,0.08672989],"study_design_scores_gemma":[0.23799911,0.0010968884,0.113135196,0.00037383917,0.00039507198,0.0004938009,0.62355345,0.0077007287,0.0033010233,0.009018997,0.0022131668,0.0007187216],"about_ca_topic_score_codex":0.000007078101,"about_ca_topic_score_gemma":0.00004289518,"teacher_disagreement_score":0.20449045,"about_ca_system_score_codex":0.00031020594,"about_ca_system_score_gemma":0.0006180442,"threshold_uncertainty_score":0.6398831},"labels":[],"label_agreement":null},{"id":"W2055924906","doi":"10.5465/ambpp.2014.15896abstract","title":"A Crowd-Based Evaluation Model in a Business School Setting","year":2014,"lang":"en","type":"article","venue":"Academy of Management Proceedings","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Homophily; Writ; Attribution; Business ethics; Economic Justice; Social psychology; Psychology; Welfare; Interpersonal communication; Public relations; Sociology; Political science; Economics; Microeconomics","score_opus":0.1334656939451006,"score_gpt":0.47096993998574993,"score_spread":0.3375042460406493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055924906","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86689526,0.000034536723,0.013720431,0.017584156,0.00007470875,0.0011949675,0.0000014511894,0.000058670255,0.100435816],"genre_scores_gemma":[0.9878788,0.00001500604,0.00907642,0.002028462,0.000044050445,0.00013727797,0.0000022247903,0.000011008283,0.0008067414],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99535793,0.000059443853,0.000881214,0.0004922469,0.0029407742,0.00026836895],"domain_scores_gemma":[0.9986305,0.00014768407,0.00049324636,0.00012425595,0.0005283219,0.000075954515],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017063545,0.00015189788,0.00024424942,0.0008205873,0.00008778089,0.00014752863,0.0006831194,0.00009342272,0.00037487998],"category_scores_gemma":[0.0015318532,0.00012823906,0.00005445736,0.0015903196,0.000048349935,0.0009648158,0.00014870486,0.00017951027,0.00010891971],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001921942,0.00031438936,0.11291263,0.0004647663,0.00004551311,2.8635256e-7,0.0009420813,0.2710438,0.0019817962,0.09339797,0.028263008,0.49044156],"study_design_scores_gemma":[0.0011211338,0.000017929668,0.16792123,0.000103793594,0.000026051315,1.979931e-7,0.00029662473,0.7982789,0.00047682595,0.027056,0.0045740367,0.000127225],"about_ca_topic_score_codex":0.0000037252546,"about_ca_topic_score_gemma":0.0000014012966,"teacher_disagreement_score":0.52723515,"about_ca_system_score_codex":0.00010701038,"about_ca_system_score_gemma":0.000077040495,"threshold_uncertainty_score":0.5913918},"labels":[],"label_agreement":null},{"id":"W2055999462","doi":"10.1002/ev.392","title":"Internal evaluation a quarter‐century later: A conversation with Arnold J. Love","year":2011,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Conversation; Evaluation methods; Perspective (graphical); Association (psychology); Quarter (Canadian coin); Sociology; Psychology; Computer science; Artificial intelligence; History; Engineering","score_opus":0.2229234698309984,"score_gpt":0.4641575431803136,"score_spread":0.2412340733493152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055999462","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61333275,0.0005666818,0.20704406,0.0053913626,0.0062610894,0.009201546,0.000067196524,0.00030261884,0.15783268],"genre_scores_gemma":[0.99253136,0.000027642174,0.004075015,0.00021342552,0.00027601336,0.00032219975,0.00012036023,0.000022049002,0.0024119085],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99443346,0.0005540317,0.00078275666,0.000625641,0.0033279655,0.0002761534],"domain_scores_gemma":[0.9953578,0.00037370253,0.0005801295,0.00056597247,0.002970226,0.00015216986],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.009713752,0.00021947257,0.00024041109,0.00060544466,0.00021571667,0.00023610325,0.00030207416,0.000115095885,0.011453785],"category_scores_gemma":[0.0012237728,0.00016908732,0.0001462317,0.00087113434,0.000056685167,0.0012670308,0.000026319685,0.0001389492,0.0009926495],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012857944,0.00048879173,0.025123613,0.00001552443,0.00024173464,5.3248465e-7,0.036016207,0.0030458206,0.0008227548,0.0018053349,0.038029734,0.89312416],"study_design_scores_gemma":[0.009654631,0.0013650034,0.17335416,0.00008060967,0.0007345598,0.000025682375,0.0073559466,0.7264556,0.0037076194,0.03146711,0.04524055,0.00055850414],"about_ca_topic_score_codex":0.00023813077,"about_ca_topic_score_gemma":0.0007713031,"teacher_disagreement_score":0.89256567,"about_ca_system_score_codex":0.00046724858,"about_ca_system_score_gemma":0.001016102,"threshold_uncertainty_score":0.9997852},"labels":[],"label_agreement":null},{"id":"W2056018441","doi":"10.7202/1024962ar","title":"L’évaluation des apprentissages en contexte scolaire","year":2014,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Humanities; Political science; Valuation (finance); Philosophy; Economics","score_opus":0.1784532418022111,"score_gpt":0.48308834907843934,"score_spread":0.3046351072762282,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056018441","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5577309,0.002050824,0.35832325,0.040353466,0.009773321,0.001621685,0.000032649503,0.00015625013,0.029957613],"genre_scores_gemma":[0.92708856,0.00063523155,0.013517853,0.0010048549,0.0009038909,0.00021649577,0.00037026248,0.000055156554,0.056207705],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9662279,0.026022973,0.0017915535,0.0011174714,0.0042118714,0.0006282178],"domain_scores_gemma":[0.989402,0.0060761212,0.0009267977,0.0010673865,0.0022941404,0.00023355136],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.12515797,0.0005030799,0.0005691275,0.000615531,0.0008059311,0.0009078811,0.0007271639,0.00046848762,0.010297119],"category_scores_gemma":[0.016489593,0.00048704207,0.00026133689,0.0013998528,0.0003255915,0.0027708733,0.00012545551,0.0005141344,0.005148754],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031637577,0.0003343406,0.016356967,0.00008836793,0.000058074602,2.9655746e-7,0.1246254,0.009071196,0.00097578764,0.010204541,0.009992333,0.8282611],"study_design_scores_gemma":[0.0013781138,0.0002927009,0.667206,0.00034816907,0.00023341285,0.000015380843,0.004471697,0.1856689,0.0010131947,0.049381483,0.08945477,0.0005362],"about_ca_topic_score_codex":0.00021260857,"about_ca_topic_score_gemma":0.0009412158,"teacher_disagreement_score":0.8277249,"about_ca_system_score_codex":0.000842402,"about_ca_system_score_gemma":0.0029085805,"threshold_uncertainty_score":0.9997581},"labels":[],"label_agreement":null},{"id":"W2056130547","doi":"10.7202/018965ar","title":"L’évaluation de l’enseignement des sciences infirmières en milieu clinique : des compétences à développer, plutôt que des comportements à prioriser","year":2008,"lang":"fr","type":"article","venue":"Revue des sciences de l éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Humanities; Sociology; Psychology; Philosophy","score_opus":0.703465493990269,"score_gpt":0.5519743203126145,"score_spread":0.15149117367765452,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056130547","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94075006,0.0084741935,0.03233546,0.0026538917,0.0019001082,0.0009514774,0.000020253257,0.00009379297,0.012820742],"genre_scores_gemma":[0.7173665,0.0104616005,0.26845205,0.0005684285,0.00033145476,0.0001354141,0.000018088313,0.000021427632,0.0026450085],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9895507,0.002574132,0.0019976438,0.0014090943,0.0029247622,0.0015436489],"domain_scores_gemma":[0.9945742,0.0018243983,0.0010119857,0.00061470905,0.0015019148,0.00047282985],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["sts"],"category_scores_codex":[0.026010964,0.0005819216,0.00064914516,0.0009675092,0.009393386,0.0010680718,0.0019845122,0.00031134897,0.0016277774],"category_scores_gemma":[0.0032119474,0.0005207902,0.00026659758,0.004122491,0.020468991,0.0036921534,0.00028437714,0.00038967378,0.00044852917],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037352387,0.0007564541,0.64569306,0.000315581,0.000047572463,0.000012445326,0.17012197,0.025627442,0.0014026087,0.0042887153,0.0027894164,0.14890738],"study_design_scores_gemma":[0.000652962,0.0013219983,0.6425869,0.0011825301,0.000103114384,0.00043153306,0.035499394,0.129698,0.002807051,0.18051283,0.004428553,0.0007751431],"about_ca_topic_score_codex":0.0045606312,"about_ca_topic_score_gemma":0.008949245,"teacher_disagreement_score":0.2361166,"about_ca_system_score_codex":0.0038162712,"about_ca_system_score_gemma":0.0109759625,"threshold_uncertainty_score":0.9999689},"labels":[],"label_agreement":null},{"id":"W2058481312","doi":"10.7202/1025738ar","title":"L’évaluation entre « technicité » et « théorisation » ?","year":2014,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Humanities; Philosophy; Valuation (finance); Political science; Economics","score_opus":0.17794043406139376,"score_gpt":0.49301892040833134,"score_spread":0.3150784863469376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2058481312","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23995838,0.0009222943,0.42010674,0.21414891,0.013839218,0.002589836,0.000048057926,0.00031429777,0.10807228],"genre_scores_gemma":[0.944726,0.0008483378,0.013251384,0.0035514827,0.00093406765,0.0002472757,0.00084852264,0.00006722171,0.035525717],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9692954,0.02140412,0.0020745164,0.0012449708,0.0053599835,0.0006210014],"domain_scores_gemma":[0.99040055,0.0045199073,0.001284618,0.0012412498,0.0023463278,0.00020731766],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.12161459,0.00053780456,0.00054855656,0.000869217,0.00047828408,0.0008099346,0.00067615206,0.00055367884,0.011499058],"category_scores_gemma":[0.012618272,0.0005222458,0.00026810897,0.0017588051,0.00014038505,0.0028649576,0.00012015853,0.0006545238,0.005524882],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048514325,0.00057763566,0.011620057,0.000069185386,0.000061918996,3.6962015e-7,0.08047336,0.03382023,0.001947393,0.08842236,0.030861909,0.7520971],"study_design_scores_gemma":[0.0014616159,0.00031887568,0.39119536,0.00021879622,0.00023521509,0.000015870564,0.0031936073,0.320845,0.0011548466,0.08469608,0.19602261,0.0006420933],"about_ca_topic_score_codex":0.00023195302,"about_ca_topic_score_gemma":0.0008772644,"teacher_disagreement_score":0.75145495,"about_ca_system_score_codex":0.0010406339,"about_ca_system_score_gemma":0.0040249815,"threshold_uncertainty_score":0.9997229},"labels":[],"label_agreement":null},{"id":"W2058952363","doi":"10.1007/s11116-009-9233-9","title":"Articulating the activity-based paradigm: Reflections on the contributions of Ryuichi Kitamura","year":2009,"lang":"en","type":"article","venue":"Transportation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Sociology; Computer science","score_opus":0.23446963219885014,"score_gpt":0.5100919716142781,"score_spread":0.27562233941542796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2058952363","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92283005,0.000007623924,0.033584353,0.03979439,0.00010890137,0.000338946,0.000032360407,0.000026326641,0.0032770673],"genre_scores_gemma":[0.9986225,0.0000021910485,0.00014209152,0.0010822348,0.00002989039,0.000023690614,0.000017008722,0.0000025925253,0.00007781648],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.998296,0.00019238844,0.0003888221,0.00014779349,0.00085655454,0.00011844828],"domain_scores_gemma":[0.99801326,0.0011453137,0.00024534817,0.00033653443,0.0002307512,0.000028771843],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001940472,0.000075203025,0.00010847867,0.0000785992,0.00041741543,0.00005652369,0.00016886479,0.000032800002,0.00032894395],"category_scores_gemma":[0.0002650153,0.00003730571,0.00009656209,0.00070091174,0.000060448914,0.00016574067,7.0709785e-7,0.00013637131,0.000046209505],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029882204,0.0005896017,0.009779374,0.0000059785552,0.000045655543,0.000001493711,0.0065015825,0.21380767,0.058104005,0.6638877,0.002038615,0.044939496],"study_design_scores_gemma":[0.00043241333,0.00021575482,0.915074,0.000020080124,0.000037379094,3.207859e-7,0.00057497766,0.027105585,0.023562158,0.03044653,0.0024454924,0.000085314634],"about_ca_topic_score_codex":0.000019709973,"about_ca_topic_score_gemma":0.0001766893,"teacher_disagreement_score":0.9052946,"about_ca_system_score_codex":0.000026092543,"about_ca_system_score_gemma":0.00012055042,"threshold_uncertainty_score":0.36017057},"labels":[],"label_agreement":null},{"id":"W205902208","doi":"10.3138/cjpe.17.003","title":"The Inclusion of Stakeholders in Evaluation: Benefits and Drawbacks","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Stakeholder; Inclusion (mineral); Foundation (evidence); Process (computing); Empirical research; Evaluation methods; Business; Process management; Management science; Knowledge management; Psychology; Computer science; Public relations; Political science; Economics; Social psychology; Engineering","score_opus":0.5130399514960976,"score_gpt":0.5057613927462337,"score_spread":0.007278558749863939,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W205902208","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9803259,0.00886872,0.000044557295,0.005906369,0.00052697444,0.0011872357,0.0000038738667,0.0000024912663,0.003133922],"genre_scores_gemma":[0.99912757,0.00019186761,0.00043481757,0.00008095465,0.000059917576,0.000037310023,0.0000025166855,0.0000054508273,0.00005957952],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99444216,0.0008265634,0.0010833027,0.00016094056,0.0032664787,0.00022056785],"domain_scores_gemma":[0.99520004,0.0005001989,0.0007545359,0.00026126558,0.0030418106,0.00024214291],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03181007,0.00009510297,0.00019059368,0.00056602183,0.00044960904,0.00023232038,0.00039405163,0.000066685716,0.0014652563],"category_scores_gemma":[0.004038637,0.000062309475,0.000064369,0.0008690623,0.00015786412,0.0005074066,0.000040873187,0.00017527182,0.0000114971435],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000075408116,0.000022595688,0.019686252,0.0000017975298,0.000007899321,7.959297e-7,0.0028092396,0.0040381323,0.0000123763875,0.00033094443,0.0008548091,0.97222763],"study_design_scores_gemma":[0.0031207262,0.000817812,0.2605093,0.0001705843,0.00011479041,0.000042324482,0.0056449273,0.6653348,0.00012428105,0.02141505,0.042499896,0.00020549064],"about_ca_topic_score_codex":0.00034148546,"about_ca_topic_score_gemma":0.041564018,"teacher_disagreement_score":0.9720221,"about_ca_system_score_codex":0.0003028049,"about_ca_system_score_gemma":0.0015919841,"threshold_uncertainty_score":0.9994475},"labels":[],"label_agreement":null},{"id":"W2060998986","doi":"10.1177/1098214006287990","title":"Developing a Stakeholder-Driven Anticipated Timeline of Impact for Evaluation of Social Programs","year":2006,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Timeline; Stakeholder; Stakeholder engagement; Stakeholder analysis; Program evaluation; Process (computing); Process management; Computer science; Management science; Public relations; Business; Political science; Engineering; Geography","score_opus":0.47865420615752025,"score_gpt":0.5785712379293496,"score_spread":0.09991703177182937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2060998986","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9750329,0.00006220213,0.023281967,0.00054291636,0.00015083069,0.0007138599,0.000012302985,0.0000041292283,0.00019886985],"genre_scores_gemma":[0.99098086,0.000004071643,0.008737455,0.000024588204,0.00016325204,0.000024024748,0.000039240298,0.000010516149,0.000015975616],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9915067,0.0010452102,0.0019206788,0.00017679506,0.0051600276,0.00019057855],"domain_scores_gemma":[0.98145366,0.00047792355,0.0042222543,0.00017658323,0.013625381,0.000044217726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.028006349,0.00013172964,0.0005466081,0.00052132254,0.00012835425,0.000042784985,0.00025583315,0.000041653977,0.0003828456],"category_scores_gemma":[0.002031491,0.000095023126,0.00025459388,0.0012270785,0.0001685483,0.00042526668,0.000026498827,0.00008671324,0.0000034508635],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004521639,0.00036109058,0.047313873,0.000015322712,0.00016487931,2.3594384e-7,0.0025454697,0.07432165,0.007035482,0.00059364265,0.00057103887,0.86662513],"study_design_scores_gemma":[0.0042958404,0.0022164392,0.4510524,0.000093024064,0.000552861,0.000010034279,0.0024288946,0.5255904,0.0034334825,0.009895286,0.00025708653,0.00017426064],"about_ca_topic_score_codex":0.00005968901,"about_ca_topic_score_gemma":0.000038966522,"teacher_disagreement_score":0.8664509,"about_ca_system_score_codex":0.00032186395,"about_ca_system_score_gemma":0.0021784722,"threshold_uncertainty_score":0.9706498},"labels":[],"label_agreement":null},{"id":"W2062384087","doi":"10.1016/j.evalprogplan.2011.03.002","title":"A mixed method study of propensity for participatory evaluation","year":2011,"lang":"en","type":"article","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Citizen journalism; Propensity score matching; Scale (ratio); Process (computing); Psychology; Knowledge management; Applied psychology; Computer science; Medicine","score_opus":0.8458672483737865,"score_gpt":0.6543483092023503,"score_spread":0.19151893917143614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2062384087","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98349255,0.00015892062,0.008262446,0.00005572904,0.0003238225,0.0049026324,0.0000031629386,0.000037649672,0.0027630744],"genre_scores_gemma":[0.97790164,0.0000012011816,0.020407889,0.000047931604,0.000033916796,0.0015127353,0.0000169321,0.0000079596875,0.00006977913],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99427074,0.0017957109,0.0008057665,0.00037987877,0.0025516471,0.00019625352],"domain_scores_gemma":[0.9962728,0.0005649206,0.00049844425,0.00034226204,0.0022351202,0.00008645032],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04538593,0.00012778369,0.00028524618,0.0002298639,0.00021929012,0.00009292434,0.00018600003,0.00005897514,0.00075644633],"category_scores_gemma":[0.002632177,0.00009517243,0.000053595366,0.00042215947,0.000040725892,0.00035448183,0.000052367614,0.00007971295,0.000011547537],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017503482,0.00059558684,0.13429753,0.000010127766,0.00004336273,1.6539981e-7,0.028027378,0.0008729799,0.00008278973,0.00023882219,0.00027918007,0.83537704],"study_design_scores_gemma":[0.0023541749,0.0013152732,0.4832361,0.000021588305,0.00022036552,0.0000014239666,0.014702472,0.49182227,0.00048218778,0.004931452,0.00078801205,0.00012468101],"about_ca_topic_score_codex":0.00002919366,"about_ca_topic_score_gemma":0.000060278577,"teacher_disagreement_score":0.83525234,"about_ca_system_score_codex":0.00003547519,"about_ca_system_score_gemma":0.0002761592,"threshold_uncertainty_score":0.9829761},"labels":[],"label_agreement":null},{"id":"W2062641650","doi":"10.1016/j.jcjd.2013.03.092","title":"Qualitative Evaluation of The Ontario School Food and Beverage Policy (P/PM 150): Multiple Stakeholder Perspectives","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Diabetes","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Focus group; Cafeteria; Thematic analysis; Stakeholder; Christian ministry; Medicine; Qualitative research; Medical education; Public relations; Marketing; Political science; Business; Sociology; Social science","score_opus":0.2531735498023525,"score_gpt":0.4376354587938161,"score_spread":0.18446190899146359,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2062641650","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9929313,0.00060229964,0.0000145199765,0.0042219507,0.00018067656,0.00027880547,0.000019960484,0.0000010793541,0.0017494059],"genre_scores_gemma":[0.9989361,0.0000023055675,0.00024875253,0.000268563,0.00008473752,0.000008275597,5.9727245e-7,0.0000055273363,0.00044510892],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99703866,0.00070137135,0.0005749594,0.00013938278,0.001330854,0.00021478809],"domain_scores_gemma":[0.995531,0.00065074983,0.0005587991,0.00024279304,0.002637442,0.00037917506],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0056231576,0.00010057426,0.00022229587,0.00044754107,0.00018816655,0.0002133341,0.0003715874,0.000045131645,0.0032301263],"category_scores_gemma":[0.0067013856,0.000061432474,0.000094801995,0.00041079972,0.00018378427,0.00074421655,0.000020674686,0.00020595576,0.0000217469],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017551287,0.00002340851,0.8676077,0.0000041177695,0.00009510625,9.6547666e-8,0.115246266,0.0005297967,0.0003874464,0.00061214395,0.0038184305,0.011673708],"study_design_scores_gemma":[0.0007228968,0.00017459654,0.92691785,0.000039674283,0.000026870512,8.9641026e-7,0.051640168,0.00074687926,0.00043135145,0.018471446,0.0007457983,0.00008159165],"about_ca_topic_score_codex":0.017215572,"about_ca_topic_score_gemma":0.39165172,"teacher_disagreement_score":0.37443614,"about_ca_system_score_codex":0.0005381549,"about_ca_system_score_gemma":0.0062816585,"threshold_uncertainty_score":0.9993518},"labels":[],"label_agreement":null},{"id":"W2063290014","doi":"10.1177/1098214012464426","title":"Improving Program Results Through the Use of Predictive Operational Performance Indicators","year":2013,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Employment and Social Development Canada; Carleton University","funders":"","keywords":"Accountability; Context (archaeology); Performance indicator; Program evaluation; Process management; Quality (philosophy); Computer science; Risk analysis (engineering); Term (time); Operations management; Environmental economics; Business; Engineering; Marketing; Economics; Political science; Public administration","score_opus":0.1859485882753664,"score_gpt":0.471487866355326,"score_spread":0.2855392780799596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063290014","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9917656,0.00003234569,0.0037504886,0.0026396515,0.00026787614,0.0006962406,0.0000074979316,0.000006514174,0.0008337753],"genre_scores_gemma":[0.9884297,0.000035141427,0.010901447,0.00035183175,0.00013397021,0.000053229025,0.000006847192,0.000006287286,0.00008151281],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99375075,0.00078341673,0.0013920763,0.00017833758,0.0037432348,0.00015215827],"domain_scores_gemma":[0.9920714,0.0011549816,0.0027179765,0.0003344838,0.0036561033,0.00006507713],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007876904,0.00010793762,0.0002530985,0.00026584635,0.00017495704,0.00023050507,0.00039019893,0.000028125589,0.00046987322],"category_scores_gemma":[0.004184056,0.00005809321,0.000103965474,0.0011644142,0.00035204558,0.0024634404,0.00004899225,0.00020851442,0.000049033075],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000139515,0.00010553405,0.019569164,0.0000017014543,0.000041867326,1.3238049e-7,0.002950251,0.036148403,0.00021982669,0.00006828856,0.0030057437,0.93774956],"study_design_scores_gemma":[0.00089162536,0.0025731148,0.48575088,0.000036836635,0.00007080796,0.000019537018,0.0035522669,0.4999062,0.0006189755,0.00045218258,0.006026628,0.000100932484],"about_ca_topic_score_codex":0.00010486869,"about_ca_topic_score_gemma":0.0000065964937,"teacher_disagreement_score":0.93764865,"about_ca_system_score_codex":0.00010478024,"about_ca_system_score_gemma":0.0008794796,"threshold_uncertainty_score":0.51447827},"labels":[],"label_agreement":null},{"id":"W2063651347","doi":"10.1017/s104909651000137x","title":"How to Persuade Government Officials to Grant Interviews and Share Information for Your Research","year":2010,"lang":"en","type":"article","venue":"PS Political Science & Politics","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"American Political Science Association","keywords":"Government (linguistics); Politics; Political science; Public administration; Public relations; Law","score_opus":0.44642924118873273,"score_gpt":0.5818590763511748,"score_spread":0.1354298351624421,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063651347","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88206923,0.000005393889,0.00719746,0.09706777,0.00078069285,0.0012122956,0.00032752525,0.000027089704,0.011312526],"genre_scores_gemma":[0.98698217,0.0000012700863,0.0044852807,0.0068711955,0.0003129265,0.000112285976,0.0000037326363,0.0000067139404,0.0012244501],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.992319,0.00010508426,0.00062910066,0.00048361707,0.0048670005,0.0015962002],"domain_scores_gemma":[0.9949482,0.0008710601,0.000085054744,0.00061945256,0.0017035805,0.0017726289],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.013895613,0.00015717055,0.0002454736,0.0004498503,0.00074543175,0.0021426303,0.0011828068,0.000077972545,0.0002244223],"category_scores_gemma":[0.02646319,0.00011277155,0.00006879535,0.0009739778,0.0006112966,0.0013483246,0.00056501525,0.00027938053,0.0003700468],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010450098,0.000042015392,0.0015345704,0.000013054516,0.0000016722797,1.9636518e-7,0.003177353,0.000005068187,0.0035610371,0.96942025,0.002623229,0.019611074],"study_design_scores_gemma":[0.00054933806,0.0008894556,0.0686062,0.000053121716,0.000013355254,0.000013729742,0.029724592,0.010598378,0.01886777,0.10235507,0.7678348,0.000494203],"about_ca_topic_score_codex":0.00013763022,"about_ca_topic_score_gemma":0.00015750073,"teacher_disagreement_score":0.8670652,"about_ca_system_score_codex":0.00045201575,"about_ca_system_score_gemma":0.00077095727,"threshold_uncertainty_score":0.99889326},"labels":[],"label_agreement":null},{"id":"W2063748659","doi":"10.1016/s1098-2140(00)00090-4","title":"Planning for community-based evaluation","year":2000,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Centre for Global Health Research","funders":"","keywords":"Management science; Program evaluation; Set (abstract data type); Unit (ring theory); Process (computing); Conflict resolution; Evaluation methods; Process management; Computer science; Psychology; Sociology; Political science; Business; Engineering; Mathematics education","score_opus":0.355370496696108,"score_gpt":0.5926022913441982,"score_spread":0.2372317946480902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063748659","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97119504,0.0000836268,0.021226972,0.0020041321,0.00029903871,0.0005212631,0.0000054459224,0.000007950127,0.0046565332],"genre_scores_gemma":[0.9918718,0.0000048603206,0.006567748,0.0011978636,0.00017642937,0.000042391548,0.000026928317,0.000009950096,0.00010203072],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9909324,0.003138678,0.0011117165,0.00014423732,0.0044991253,0.00017383517],"domain_scores_gemma":[0.99139667,0.002398506,0.0012933873,0.00038363825,0.004428474,0.00009931434],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.062370263,0.000115685485,0.00031484058,0.00041459184,0.0003348171,0.0001538117,0.00040411297,0.000030891046,0.0047241133],"category_scores_gemma":[0.0032913194,0.00008755118,0.0001753835,0.000762441,0.00011680328,0.000566063,0.000009255357,0.0002414249,0.0000750351],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021897495,0.000075713375,0.0026774323,0.0000016634191,0.000018585042,1.6175443e-7,0.0011870371,0.19519553,0.00016251094,0.000024981127,0.0018481534,0.7985893],"study_design_scores_gemma":[0.003456121,0.0024610232,0.05898298,0.000072969604,0.0002517479,0.00001941933,0.0047213444,0.8889052,0.00042753326,0.015081334,0.025429545,0.00019076462],"about_ca_topic_score_codex":0.0000148748995,"about_ca_topic_score_gemma":0.000009231274,"teacher_disagreement_score":0.7983985,"about_ca_system_score_codex":0.00022742034,"about_ca_system_score_gemma":0.0011802013,"threshold_uncertainty_score":0.9961857},"labels":[],"label_agreement":null},{"id":"W2064093721","doi":"10.2202/1548-923x.1023","title":"Evaluation Framework for Nursing Education Programs: Application of the CIPP Model","year":2004,"lang":"en","type":"article","venue":"International Journal of Nursing Education Scholarship","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"York University","funders":"","keywords":"Nursing; Medicine; Public health; Nurse education; Medical education","score_opus":0.3703801059193039,"score_gpt":0.6129295372095647,"score_spread":0.24254943129026074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064093721","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4880178,0.00058776047,0.46935976,0.028139886,0.009848145,0.0011574641,0.000010013045,0.000014423994,0.0028647599],"genre_scores_gemma":[0.9505927,0.000015671721,0.048013613,0.00046690463,0.0006928294,0.00008677663,0.00002283081,0.000013276227,0.000095405536],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99350095,0.00031741467,0.0013065937,0.00026699377,0.004449251,0.00015881163],"domain_scores_gemma":[0.98397374,0.00030577835,0.002176396,0.00045540574,0.012982985,0.00010572295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008897969,0.00014479882,0.00020960454,0.00057270576,0.00019280575,0.00036214007,0.0013350444,0.00013089894,0.000045715835],"category_scores_gemma":[0.0057654288,0.00010741858,0.00026086267,0.00066776545,0.00015294355,0.0013441797,0.000019639561,0.00034806196,0.000014401629],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000090457,0.0021440974,0.0042408756,0.000004353172,0.0000375886,1.699961e-8,0.0029888724,0.01840489,0.00092914724,0.07334161,0.0006081671,0.89720994],"study_design_scores_gemma":[0.00067679404,0.00009321839,0.022020502,0.0014025525,0.00013734844,0.00005195684,0.003221026,0.013184713,0.0023029621,0.9559509,0.0008325137,0.0001254832],"about_ca_topic_score_codex":0.0000040594778,"about_ca_topic_score_gemma":0.0000036147667,"teacher_disagreement_score":0.8970844,"about_ca_system_score_codex":0.001649142,"about_ca_system_score_gemma":0.008216595,"threshold_uncertainty_score":0.9974059},"labels":[],"label_agreement":null},{"id":"W2064361885","doi":"10.1177/003172171309500310","title":"How Ontario Spread Successful Practices across 5,000 Schools","year":2013,"lang":"en","type":"article","venue":"Phi Delta Kappan","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mathematics education; Sociology; Pedagogy; Psychology","score_opus":0.22822636466045945,"score_gpt":0.48431351788187754,"score_spread":0.25608715322141806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064361885","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96101826,0.00008759681,0.00067396904,0.01924116,0.0006253984,0.0005168801,0.000019826806,0.00007356601,0.017743317],"genre_scores_gemma":[0.9618816,0.000019534777,0.0013630204,0.001072443,0.00023524817,0.0001225369,0.000019598476,0.000015336802,0.03527068],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956173,0.00022801578,0.00060973107,0.00064483203,0.0023583076,0.0005418453],"domain_scores_gemma":[0.99617684,0.0006664004,0.0009418493,0.0010288028,0.0009028904,0.00028321298],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003235388,0.00023472126,0.0003277845,0.00014897277,0.00041583733,0.0038876384,0.001214356,0.00011317553,0.012701376],"category_scores_gemma":[0.0022149708,0.0001658566,0.00012230712,0.0006174489,0.000090585694,0.00466549,0.00024820896,0.00042648194,0.0055010193],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003545889,0.00016635703,0.8022772,0.000007953436,0.000049516497,0.0000050876206,0.0039975066,0.00016176006,0.0005668209,0.00063242385,0.065349884,0.12675004],"study_design_scores_gemma":[0.0007636432,0.00012983098,0.40041,0.000021008751,0.00001930156,0.000014537651,0.007514973,0.004700256,0.000712773,0.0075616045,0.5777679,0.0003841744],"about_ca_topic_score_codex":0.034037866,"about_ca_topic_score_gemma":0.12518014,"teacher_disagreement_score":0.51241803,"about_ca_system_score_codex":0.00015955503,"about_ca_system_score_gemma":0.0003963815,"threshold_uncertainty_score":0.9971464},"labels":[],"label_agreement":null},{"id":"W2064567041","doi":"10.1606/1044-3894.63","title":"The Deconstruction of Professional Knowledge: Accountability without Authority","year":2002,"lang":"en","type":"article","venue":"Families in Society The Journal of Contemporary Social Services","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Accountability; Dialogic; Deconstruction (building); Public relations; Sociology; TRACE (psycholinguistics); Political science; Pedagogy; Law; Engineering","score_opus":0.1342275317147083,"score_gpt":0.4529898925400492,"score_spread":0.3187623608253409,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064567041","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98362267,0.003206489,0.0000495389,0.0039676894,0.0015795105,0.00021544471,0.000009134295,0.00000657213,0.007342924],"genre_scores_gemma":[0.99812406,0.0006280783,0.00012766564,0.00026329164,0.00027743535,0.000004225452,8.752201e-7,0.0000057508537,0.0005686338],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9954159,0.0011882276,0.0014664985,0.0001330877,0.0016211348,0.00017511245],"domain_scores_gemma":[0.99478155,0.0021033254,0.0015866549,0.00027154956,0.0012113556,0.000045574405],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014552306,0.00013588232,0.0003787234,0.000054214175,0.00080518477,0.00010238498,0.0011691316,0.00012974849,0.00018265774],"category_scores_gemma":[0.00017437644,0.00006631557,0.00032330677,0.0006993003,0.00058211223,0.00096616044,0.00015437895,0.00049570994,0.000011844231],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027493277,0.00035900366,0.7787819,0.000078766265,0.0001270834,3.1592575e-7,0.15183602,0.000049969214,0.0002550575,0.00086307543,0.017723443,0.049650468],"study_design_scores_gemma":[0.0013994575,0.00014123795,0.5229264,0.00012362952,0.00003375243,0.000009956239,0.37964574,0.010159076,0.00017577302,0.016089113,0.06912065,0.00017522035],"about_ca_topic_score_codex":0.00009648996,"about_ca_topic_score_gemma":0.00053921074,"teacher_disagreement_score":0.25585544,"about_ca_system_score_codex":0.00009997953,"about_ca_system_score_gemma":0.0003660948,"threshold_uncertainty_score":0.6192912},"labels":[],"label_agreement":null},{"id":"W2066532482","doi":"10.1590/s1413-81232012000300016","title":"Parâmetros e paradigmas em meta-avaliação: uma revisão exploratória e reflexiva","year":2012,"lang":"pt","type":"article","venue":"Ciência & Saúde Coletiva","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Philosophy","score_opus":0.40206759375564977,"score_gpt":0.4858091665761613,"score_spread":0.08374157282051153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2066532482","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.57818705,0.10030459,0.037965693,0.038665872,0.037235487,0.0124345105,0.0013345313,0.0014661851,0.1924061],"genre_scores_gemma":[0.9515056,0.0010559473,0.0015571874,0.0048270677,0.001619622,0.00051220524,0.000081848186,0.00012579761,0.038714726],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9846658,0.0026925185,0.0030851883,0.0016562032,0.005670253,0.0022300018],"domain_scores_gemma":[0.9904595,0.0019420149,0.0017388342,0.0031052353,0.0012762917,0.0014781306],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.015819324,0.0012151592,0.0024331345,0.00079424,0.0010897387,0.0011888944,0.0022698285,0.00059231505,0.05188942],"category_scores_gemma":[0.0030715058,0.00094145664,0.0014981509,0.0033241685,0.00035623717,0.0029245324,0.00067189906,0.0010597755,0.027902761],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008507946,0.0026859432,0.07434675,0.00030158594,0.0041277427,0.00006451051,0.02051168,0.00035434583,0.002906642,0.02742959,0.63785434,0.22856607],"study_design_scores_gemma":[0.0017517817,0.0005444769,0.04558473,0.00018812143,0.0028058586,0.000034681798,0.005898337,0.0024307908,0.003153476,0.0014639724,0.9345279,0.0016159222],"about_ca_topic_score_codex":0.000030359757,"about_ca_topic_score_gemma":0.000055021963,"teacher_disagreement_score":0.37331855,"about_ca_system_score_codex":0.0006321811,"about_ca_system_score_gemma":0.0010165835,"threshold_uncertainty_score":0.99984795},"labels":[],"label_agreement":null},{"id":"W2066945648","doi":"10.1002/ev.315","title":"Knowledge translation: Implications for evaluation","year":2009,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institutes of Health Research","funders":"","keywords":"Knowledge translation; Computer science; Knowledge management; Field (mathematics); Translation (biology); Sustainability","score_opus":0.5370852562015647,"score_gpt":0.6053385358954619,"score_spread":0.06825327969389727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2066945648","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024740197,0.0029711446,0.79366606,0.05993576,0.0038833464,0.016123056,0.00019025935,0.00039587516,0.09809429],"genre_scores_gemma":[0.9679669,0.00005481833,0.020185275,0.00053759094,0.0011858479,0.0031942655,0.00073627225,0.000027752021,0.0061112624],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99596775,0.00040230624,0.0010093215,0.00069385814,0.0016165207,0.00031026494],"domain_scores_gemma":[0.9918218,0.0019598578,0.00039619816,0.000698105,0.0049603456,0.00016366558],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.015362313,0.00021100276,0.0002687965,0.0006156423,0.0009147095,0.00032058152,0.0003619714,0.00014666481,0.001384666],"category_scores_gemma":[0.004748076,0.00019146148,0.00030834554,0.001474273,0.000031131935,0.0009602904,0.000009574584,0.000090978116,0.00016938997],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056097317,0.00014006207,0.00022805786,0.0000027104884,0.000017781096,2.254718e-9,0.00070717616,0.0040647923,0.00074062834,0.0083224485,0.04093262,0.9447876],"study_design_scores_gemma":[0.004305592,0.00031401013,0.05412227,0.0000121403355,0.00029988188,0.000002486509,0.00021093886,0.38600978,0.0005475296,0.2717831,0.28216392,0.00022834691],"about_ca_topic_score_codex":0.000008872319,"about_ca_topic_score_gemma":0.0003081708,"teacher_disagreement_score":0.9445593,"about_ca_system_score_codex":0.0004359178,"about_ca_system_score_gemma":0.001680196,"threshold_uncertainty_score":0.9995282},"labels":[],"label_agreement":null},{"id":"W2067449005","doi":"10.1002/ev.326","title":"Real‐time evaluation in humanitarian emergencies","year":2010,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Social Sciences and Humanities Research Council","funders":"","keywords":"Formative assessment; Credibility; Evaluation methods; Program evaluation; Field (mathematics); Emergency management; Process management; Computer science; Monitoring and evaluation; Risk analysis (engineering); Political science; Business; Psychology; Engineering; Public administration","score_opus":0.23693256838441462,"score_gpt":0.526100458986193,"score_spread":0.28916789060177833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2067449005","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9112027,0.000050018385,0.0015300631,0.0025357888,0.003859328,0.0028195567,0.00001626215,0.00010384174,0.077882424],"genre_scores_gemma":[0.9831802,0.000030389698,0.0045473333,0.00008297061,0.0006410053,0.0009268737,0.00018749232,0.000023607397,0.010380094],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99451846,0.00049047306,0.0009112529,0.0005576141,0.003247,0.00027518996],"domain_scores_gemma":[0.9958813,0.0007165552,0.00032337313,0.0006398227,0.0023267057,0.00011225195],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.024730623,0.00016679899,0.00022405921,0.0008356414,0.0004360841,0.000225463,0.0003461498,0.00014403694,0.02111136],"category_scores_gemma":[0.007601687,0.00014939815,0.00013542143,0.0013498528,0.000043472257,0.000930701,0.000033547472,0.0002025159,0.0009041436],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006143743,0.00024194793,0.00970449,0.0000038043308,0.000025481993,1.0096473e-7,0.0025765721,0.0067117508,0.03248901,0.006500219,0.037780326,0.90390486],"study_design_scores_gemma":[0.0022908766,0.00014543645,0.20895372,0.000010120862,0.00011585243,0.0000026306896,0.0006367078,0.61596113,0.0016407167,0.09887509,0.071104,0.00026370623],"about_ca_topic_score_codex":0.0005338709,"about_ca_topic_score_gemma":0.0154734785,"teacher_disagreement_score":0.90364116,"about_ca_system_score_codex":0.0002848825,"about_ca_system_score_gemma":0.0014098817,"threshold_uncertainty_score":0.99987376},"labels":[],"label_agreement":null},{"id":"W2068298920","doi":"10.1111/j.1754-7121.2009.00070_1.x","title":"Policy analytical capacity and evidence‐based policy‐making: Lessons from Canada","year":2009,"lang":"en","type":"article","venue":"Canadian Public Administration","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":524,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Policy making; Political science; Government (linguistics); Order (exchange); Public administration; Welfare economics; Policy analysis; Humanities; Economics; Philosophy; Finance","score_opus":0.3480418204072303,"score_gpt":0.49782447582658046,"score_spread":0.14978265541935015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2068298920","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24083309,0.000038804985,0.0007269546,0.7516578,0.0001247319,0.00016612739,0.00011850605,0.000018764873,0.0063152537],"genre_scores_gemma":[0.9765114,0.000005603116,0.0003203772,0.022321926,0.0003523451,0.0000067386227,0.000043415686,0.0000053353497,0.00043282265],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99715674,0.00019601716,0.00051023514,0.00045916872,0.0012313905,0.00044644688],"domain_scores_gemma":[0.9973442,0.0005056598,0.00018393171,0.00050690415,0.00044143377,0.0010178604],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011692748,0.00016202853,0.00020929806,0.00065878127,0.00039230075,0.000840639,0.00041448793,0.00011113429,0.0006022605],"category_scores_gemma":[0.0064473376,0.00014537816,0.000044327036,0.0012654541,0.00009774936,0.00084362697,0.000012965963,0.00016816295,0.000022194872],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021594618,0.00003921888,0.03782581,0.0000038782305,0.00001700157,0.000025941144,0.00013888632,0.000032759,0.00006368592,0.8423034,0.020283777,0.09924406],"study_design_scores_gemma":[0.00043626616,0.00024139258,0.7013828,0.00005294602,0.00001908792,0.000016631644,0.00040653956,0.055231385,0.00015727303,0.030905426,0.21070404,0.0004461766],"about_ca_topic_score_codex":0.7075905,"about_ca_topic_score_gemma":0.9965984,"teacher_disagreement_score":0.81139797,"about_ca_system_score_codex":0.0011229354,"about_ca_system_score_gemma":0.058259573,"threshold_uncertainty_score":0.94707924},"labels":[],"label_agreement":null},{"id":"W2069583597","doi":"10.1111/j.1741-1130.2006.00063.x","title":"Implementation of Goal Attainment Scaling in Community Intellectual Disability Services","year":2006,"lang":"en","type":"article","venue":"Journal of Policy and Practice in Intellectual Disabilities","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Learning Partnership","funders":"","keywords":"Goal Attainment Scaling; Intellectual disability; Context (archaeology); Set (abstract data type); Psychology; Process (computing); Perception; Scale (ratio); Quality (philosophy); Applied psychology; Value (mathematics); Process management; Medical education; Business; Computer science; Medicine; Rehabilitation; Psychiatry","score_opus":0.1305197222061774,"score_gpt":0.5232507001278847,"score_spread":0.39273097792170725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2069583597","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9919038,0.0002280128,0.00017831732,0.0036158548,0.00011910471,0.00017705376,0.000012739465,0.0000033082456,0.0037618536],"genre_scores_gemma":[0.9989755,0.00020714717,0.00036499248,0.00023462593,0.00014551228,0.000005932915,0.0000027481053,0.0000063287657,0.00005717641],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9934714,0.0029098652,0.0021010216,0.00016233281,0.0011159524,0.00023942655],"domain_scores_gemma":[0.8580794,0.14016837,0.00087715377,0.00029989754,0.00050526194,0.000069966416],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.015242736,0.00015708712,0.00043741913,0.00046739914,0.00012531338,0.00015622165,0.00040552765,0.00007419218,0.0010747868],"category_scores_gemma":[0.09114967,0.00011953351,0.00010522993,0.0008488382,0.00049571675,0.0014646781,0.00015162495,0.0005613135,0.000008855362],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015743569,0.0017330751,0.2419279,0.00019586741,0.000045430505,0.0000019273489,0.6783322,0.0033298545,0.0005080043,0.005282906,0.00070891913,0.06635953],"study_design_scores_gemma":[0.0008617698,0.00064326107,0.07079029,0.000094930925,0.000018764027,0.00005163226,0.8921178,0.00087175245,0.00094555353,0.029776054,0.0036952791,0.00013292485],"about_ca_topic_score_codex":0.013669385,"about_ca_topic_score_gemma":0.011924085,"teacher_disagreement_score":0.21378556,"about_ca_system_score_codex":0.00037562902,"about_ca_system_score_gemma":0.00035915634,"threshold_uncertainty_score":0.99983835},"labels":[],"label_agreement":null},{"id":"W2070045380","doi":"10.1300/j104v37n01_03","title":"Adapting Dominant Classifications to Particular Contexts","year":2003,"lang":"en","type":"article","venue":"Cataloging & Classification Quarterly","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Perspective (graphical); Context (archaeology); Computer science; Adaptation (eye); Process (computing); Work (physics); Generalization; Ethnic group; Interface (matter); Dewey Decimal Classification; Sociology; Knowledge management; Data science; World Wide Web; Epistemology; Artificial intelligence; Geography; Psychology; Engineering; Anthropology; Library classification; Archaeology","score_opus":0.22208588809522636,"score_gpt":0.4558080156071547,"score_spread":0.23372212751192836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070045380","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54893726,0.00019285081,0.40665272,0.01453083,0.0015739411,0.0014030982,0.00004186618,0.0002591614,0.02640826],"genre_scores_gemma":[0.99244153,0.0000037791538,0.003750596,0.00082062633,0.000074081814,0.00027444592,0.000050758386,0.000020900972,0.00256329],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99546826,0.0005726146,0.0012145098,0.00084399583,0.0014223396,0.00047827172],"domain_scores_gemma":[0.9961131,0.000820552,0.000476854,0.0014205938,0.0008238229,0.00034506657],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0054648076,0.00023951322,0.0003339807,0.0004228786,0.0005690305,0.0005563445,0.000684962,0.00010591977,0.00065334083],"category_scores_gemma":[0.0023012897,0.00019541726,0.00014087302,0.0013275122,0.00011603718,0.000645555,0.000019556444,0.00020056241,0.005441914],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049728267,0.0004524427,0.028811922,0.000014798569,0.000056560133,0.000008042819,0.013828833,0.00064259866,0.103164,0.5272822,0.023851087,0.30183783],"study_design_scores_gemma":[0.0012753963,0.0005229102,0.29085553,0.00006352665,0.00006248451,0.000037452508,0.027279658,0.02101715,0.0053648497,0.015844472,0.63675565,0.000920926],"about_ca_topic_score_codex":0.0000113903925,"about_ca_topic_score_gemma":0.00006650055,"teacher_disagreement_score":0.61290455,"about_ca_system_score_codex":0.00017766235,"about_ca_system_score_gemma":0.00033800883,"threshold_uncertainty_score":0.9953325},"labels":[],"label_agreement":null},{"id":"W2070142512","doi":"10.1016/s0308-521x(03)00123-9","title":"Using evaluation to enhance institutional learning and change: recent experiences with agricultural research and development","year":2003,"lang":"en","type":"article","venue":"Agricultural Systems","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":105,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Consortium of International Agricultural Research Centers","keywords":"Agriculture; Food security; Accountability; Agricultural communication; Poverty; Work (physics); Business; Political science; Economic growth; Economics; Engineering","score_opus":0.5128791513176436,"score_gpt":0.5431027004990195,"score_spread":0.03022354918137593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070142512","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9948067,0.00095062767,0.0002487627,0.00031279455,0.0003245243,0.00094112125,5.879741e-7,0.00001706973,0.0023977787],"genre_scores_gemma":[0.997582,0.00004036514,0.0011565497,0.000016427088,0.00010953069,0.0004503953,0.000007224653,0.0000029991393,0.00063448393],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9946343,0.0006556155,0.0004250322,0.000496996,0.0034551562,0.00033293277],"domain_scores_gemma":[0.9969473,0.00020749653,0.00014927644,0.00009656471,0.0024171302,0.00018226047],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0075663235,0.00015125176,0.00019320614,0.00013633126,0.0010767026,0.0005842366,0.0001356345,0.00005548695,0.00012531046],"category_scores_gemma":[0.0007094488,0.00007144977,0.000010374977,0.0009987698,0.000097403245,0.0008737958,0.00007409234,0.00015621736,0.000050139257],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023741409,0.00045880565,0.1643259,0.00017146702,0.00021924125,0.000015982665,0.4008276,0.015234768,0.045794882,0.01125972,0.003915649,0.3575386],"study_design_scores_gemma":[0.0006398799,0.00050654914,0.45190486,0.0003201975,0.000013687655,0.00027533178,0.44209725,0.0020647433,0.0051458236,0.0000429754,0.09638792,0.0006007674],"about_ca_topic_score_codex":0.00007493794,"about_ca_topic_score_gemma":0.0001596147,"teacher_disagreement_score":0.35693783,"about_ca_system_score_codex":0.0003231156,"about_ca_system_score_gemma":0.00023055341,"threshold_uncertainty_score":0.8281235},"labels":[],"label_agreement":null},{"id":"W2070292114","doi":"10.1002/ev.393","title":"Internal evaluation, historically speaking","year":2011,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Advancing Health Outcomes; University of British Columbia","funders":"","keywords":"Context (archaeology); Conservatism; Speculation; Government (linguistics); Function (biology); Evaluation methods; Internal validity; Political science; Public administration; Sociology; Public relations; Law; Business; History","score_opus":0.45966699897342617,"score_gpt":0.5336734648069541,"score_spread":0.07400646583352793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070292114","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08032717,0.0007554456,0.3456487,0.0020103045,0.011211468,0.004128161,0.000017113476,0.00026957344,0.55563205],"genre_scores_gemma":[0.96903145,0.000018073748,0.018405825,0.0002803786,0.00068460876,0.00054735306,0.00004555079,0.000023926166,0.0109628355],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9941237,0.0005208685,0.0008935625,0.0005509414,0.0036650556,0.00024587102],"domain_scores_gemma":[0.9943635,0.0005012636,0.00046783258,0.00057144905,0.003943295,0.00015264572],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01812725,0.00016361428,0.00020834751,0.0005522726,0.00042340692,0.00016272158,0.00042750023,0.00008961283,0.020662947],"category_scores_gemma":[0.007109472,0.00013786968,0.00019061229,0.0009179246,0.000037804002,0.0008693263,0.000042727825,0.00011707883,0.00067341403],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006994035,0.000106494765,0.0047185146,0.0000017700013,0.000031867366,8.036219e-8,0.0028740086,0.00064233865,0.00019893453,0.0023458034,0.038618345,0.9503919],"study_design_scores_gemma":[0.0030791464,0.0003135103,0.116277464,0.000024925645,0.0003393954,0.000010531442,0.0007121035,0.36990052,0.0012607474,0.16594063,0.3417998,0.0003412171],"about_ca_topic_score_codex":0.00036491107,"about_ca_topic_score_gemma":0.00091064576,"teacher_disagreement_score":0.9500507,"about_ca_system_score_codex":0.00080362195,"about_ca_system_score_gemma":0.0012487881,"threshold_uncertainty_score":0.9802323},"labels":[],"label_agreement":null},{"id":"W2070523591","doi":"10.1016/j.jenvman.2007.03.028","title":"Implementation of resource management plans: Identifying keys to success","year":2007,"lang":"en","type":"article","venue":"Journal of Environmental Management","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":45,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Social Sciences and Humanities Research Council of Canada; Government of the United Kingdom","keywords":"Plan (archaeology); Process management; Business; Process (computing); Resource (disambiguation); Quality (philosophy); Best practice; Environmental resource management; Operations management; Environmental planning; Computer science; Engineering; Geography; Political science","score_opus":0.08570874368535014,"score_gpt":0.46330122198744494,"score_spread":0.3775924783020948,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070523591","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9396833,0.00010511571,0.036217395,0.00067832106,0.0005192811,0.0006052709,0.000015101921,0.00000726421,0.022168944],"genre_scores_gemma":[0.9890302,0.0001382435,0.008312949,0.00051922706,0.00008304512,0.0000057392285,0.0000040988552,0.000012815169,0.0018937289],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9944005,0.00010578076,0.0017531231,0.00027316512,0.003170864,0.0002965409],"domain_scores_gemma":[0.99819195,0.00013051127,0.0010540782,0.00040415704,0.00004196914,0.000177361],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007803107,0.00016334749,0.00028868963,0.00092129706,0.000111239875,0.000105922736,0.0008052577,0.000031705462,0.0024311864],"category_scores_gemma":[0.0000132662035,0.00013236725,0.00016747249,0.0004621468,0.00004513892,0.0005010706,0.00036635692,0.00011319744,0.00017379363],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034398702,0.00047007835,0.17583184,0.00007604268,0.00038258504,0.00016800678,0.002102776,0.0030173466,0.0026963132,0.0032394428,0.010434407,0.80123717],"study_design_scores_gemma":[0.0013113727,0.00030971412,0.87190986,0.000064909145,0.00009488215,0.000014715385,0.037200056,0.000029388853,0.004053073,0.0009970525,0.083852395,0.00016258037],"about_ca_topic_score_codex":0.0000065868417,"about_ca_topic_score_gemma":0.000032220614,"teacher_disagreement_score":0.8010746,"about_ca_system_score_codex":0.00027589593,"about_ca_system_score_gemma":0.000010156773,"threshold_uncertainty_score":0.99848074},"labels":[],"label_agreement":null},{"id":"W2071060665","doi":"10.1111/j.1754-7121.2004.tb01187.x","title":"Acting on values: An ethical dead end for public servants","year":2004,"lang":"en","type":"article","venue":"Canadian Public Administration","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Ethical values; Value (mathematics); Civil servants; Political science; Sociology; Philosophy; Humanities; Law; Mathematics","score_opus":0.3566819678438881,"score_gpt":0.5013855914661595,"score_spread":0.14470362362227135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071060665","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5460195,0.000010304028,0.014226276,0.41772375,0.0012443108,0.00088423985,0.00015342639,0.00009730654,0.01964088],"genre_scores_gemma":[0.9885812,0.0000016421733,0.0019148947,0.0082135135,0.00029642181,0.00007669523,0.0002373384,0.000015809032,0.0006625066],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968631,0.00019492206,0.00058433705,0.00053590705,0.0012860697,0.0005356235],"domain_scores_gemma":[0.9968063,0.0005192937,0.00022298149,0.00055613363,0.00081185455,0.001083408],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0051464285,0.00016427833,0.00018038778,0.00053635373,0.0007348556,0.0014333185,0.00057276693,0.0003004568,0.0013301667],"category_scores_gemma":[0.0052331206,0.00014522346,0.00007907443,0.0006474646,0.00007879008,0.0014630733,0.000013842062,0.0003393659,0.00026618096],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040026815,0.00014622607,0.00432572,0.00000916041,0.000021141173,0.00000988754,0.00081037765,0.000085179636,0.00009633031,0.80397063,0.007050437,0.1834349],"study_design_scores_gemma":[0.0017791584,0.0017383992,0.016162539,0.000029338951,0.000015225297,0.00002950587,0.004505244,0.011630317,0.00083442003,0.078981556,0.88370466,0.00058961665],"about_ca_topic_score_codex":0.0005152389,"about_ca_topic_score_gemma":0.39247462,"teacher_disagreement_score":0.87665427,"about_ca_system_score_codex":0.00056313357,"about_ca_system_score_gemma":0.010159568,"threshold_uncertainty_score":0.9996033},"labels":[],"label_agreement":null},{"id":"W2071368667","doi":"10.3138/cjpe.29.2.128","title":"Pertinence de la recension réaliste des écrits pour l'analyse des évaluations de programmes complexes : l'exemple du suivi dans la communauté en santé mentale","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Université du Québec à Montréal","funders":"","keywords":"Relevance (law); Sociology; Humanities; Philosophy; Political science","score_opus":0.17300183107063663,"score_gpt":0.4822728331215107,"score_spread":0.3092710020508741,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071368667","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.977158,0.00045776306,0.017090153,0.0018479306,0.00013392296,0.00069734745,0.000014509417,0.000028090768,0.0025722487],"genre_scores_gemma":[0.9540495,0.00009759481,0.045279708,0.00018227499,0.00015074783,0.00009942266,0.00004436614,0.00002158215,0.000074768155],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98976254,0.006535487,0.0010659554,0.0002707756,0.0017602461,0.0006049715],"domain_scores_gemma":[0.9929226,0.0026798067,0.000684012,0.00041074745,0.0025553901,0.0007474227],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.047947854,0.00022138316,0.0003387129,0.0006150966,0.00094313355,0.0009169192,0.0007625128,0.00013637899,0.0008361263],"category_scores_gemma":[0.015348297,0.000181409,0.00020978307,0.0008988248,0.000679148,0.0007580374,0.000043557666,0.00033198783,0.000036363785],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024785413,0.00017012101,0.34319475,0.000017038758,0.00005097424,0.000008028675,0.027511027,0.00441703,0.002464872,0.0006405029,0.0020497402,0.6194511],"study_design_scores_gemma":[0.0013423505,0.00051998836,0.67978364,0.00028672552,0.00027294017,0.00049263344,0.012671437,0.23844776,0.0010580502,0.045313496,0.019538973,0.00027202856],"about_ca_topic_score_codex":0.0054344814,"about_ca_topic_score_gemma":0.08687384,"teacher_disagreement_score":0.61917907,"about_ca_system_score_codex":0.0014317207,"about_ca_system_score_gemma":0.0058849086,"threshold_uncertainty_score":0.9997508},"labels":[],"label_agreement":null},{"id":"W2072719401","doi":"10.1007/s10833-005-5033-y","title":"Organizational Learning Capacity, Evaluative Inquiry and Readiness for Change in Schools: Views and Perceptions of Educators","year":2006,"lang":"en","type":"article","venue":"Journal of Educational Change","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":40,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Social Sciences and Humanities Research Council of Canada; Ministry of Science, ICT and Future Planning","keywords":"Perception; Psychology; Pedagogy; Organizational culture; Organizational change; Organizational learning; Sociology; Public relations; Political science; Management","score_opus":0.39523611309726936,"score_gpt":0.5359292414985574,"score_spread":0.140693128401288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2072719401","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98776203,0.0006982349,0.000107101616,0.010367125,0.0005017303,0.00030779184,0.000014343212,0.0000012788846,0.00024037343],"genre_scores_gemma":[0.9956772,0.00015194534,0.0022651574,0.00021726235,0.001374342,0.00006604455,0.000018975798,0.000008045987,0.00022107785],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99800855,0.0001981138,0.00073137484,0.00016149969,0.00078559556,0.00011487867],"domain_scores_gemma":[0.99665636,0.00093601877,0.0006859663,0.00008261037,0.0015620465,0.00007697937],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033657455,0.00009836604,0.0002543987,0.0006497195,0.000119119126,0.00006467725,0.00014440411,0.000052812655,0.00082921307],"category_scores_gemma":[0.0016951691,0.00007716843,0.000046722827,0.0005814926,0.0000941767,0.00070940645,0.000032847052,0.00015913937,0.0000068547547],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023783827,0.00019273485,0.9738244,0.00002386094,0.000009712668,7.8857916e-8,0.012664963,0.000026045198,0.00029636253,0.008694195,0.0014600384,0.0027838617],"study_design_scores_gemma":[0.0004759527,0.00013828807,0.9536245,0.000082061146,0.000018855771,0.00002644625,0.007177884,0.000559858,0.00003375111,0.036554605,0.0012232448,0.0000845789],"about_ca_topic_score_codex":0.000076890516,"about_ca_topic_score_gemma":0.00025078174,"teacher_disagreement_score":0.027860409,"about_ca_system_score_codex":0.000101468664,"about_ca_system_score_gemma":0.00042023323,"threshold_uncertainty_score":0.90793014},"labels":[],"label_agreement":null},{"id":"W2073540103","doi":"10.17645/pag.v2i2.23","title":"The Elements of Effective Program Design: A Two-Level Analysis","year":2014,"lang":"en","type":"article","venue":"Politics and Governance","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan; Simon Fraser University","funders":"","keywords":"Theme (computing); Management science; Program Design Language; Work (physics); Policy analysis; Focus (optics); Computer science; Engineering ethics; Political science; Engineering; Public administration; Software engineering","score_opus":0.13261986062841608,"score_gpt":0.4807879119799717,"score_spread":0.34816805135155565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2073540103","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83820087,0.00055458536,0.13589273,0.002930386,0.00036376034,0.0011710312,0.00010793547,0.000027513755,0.020751184],"genre_scores_gemma":[0.9942764,0.000066664055,0.0040789936,0.00017054156,0.000030410247,0.00004040356,8.956852e-7,0.0000026339642,0.0013330507],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99828964,0.00019310288,0.00034058117,0.00016744818,0.00083337986,0.00017585003],"domain_scores_gemma":[0.9977385,0.0013516776,0.0003121422,0.0002947238,0.00024712185,0.000055853856],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029941814,0.000068704976,0.00016532681,0.00003513864,0.00016282599,0.00011025681,0.00023575222,0.000016655682,0.000039576666],"category_scores_gemma":[0.0009719625,0.000038556176,0.00006559445,0.00042422244,0.00009949297,0.00008094537,0.0000543294,0.000047241327,0.0000134340635],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018309547,0.000084690975,0.16034143,0.0000056586705,0.00014436127,1.8570975e-7,0.00033933338,0.00064129767,0.00005293347,0.2663945,0.0008017898,0.5711755],"study_design_scores_gemma":[0.00039493584,0.00018088233,0.7907971,0.000006437634,0.00007682074,3.614875e-7,0.000065236985,0.13801266,0.0005236461,0.030028865,0.039839216,0.00007385348],"about_ca_topic_score_codex":0.00013533828,"about_ca_topic_score_gemma":0.0002093069,"teacher_disagreement_score":0.6304557,"about_ca_system_score_codex":0.000021615859,"about_ca_system_score_gemma":0.000044201613,"threshold_uncertainty_score":0.15722753},"labels":[],"label_agreement":null},{"id":"W2074732573","doi":"10.1016/j.evalprogplan.2015.01.004","title":"Application of an organizational evaluation capacity self-assessment instrument to different organizations: Similarities and lessons learned","year":2015,"lang":"en","type":"article","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":32,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École Nationale d'Administration Publique","funders":"Government of Canada; Australian Government","keywords":"Novelty; Capacity development; Knowledge management; Business; Organization development; Capacity building; Profit (economics); Government (linguistics); Organizational effectiveness; Organizational performance; Marketing; Computer science; Environmental resource management; Psychology; Economics; Economic growth; Social psychology","score_opus":0.35567815516756507,"score_gpt":0.5310432671149354,"score_spread":0.17536511194737037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2074732573","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97741085,0.00012578869,0.016286628,0.0030463033,0.00016375579,0.001944923,0.00001912981,0.00009615941,0.00090646994],"genre_scores_gemma":[0.97737163,0.00001644492,0.021476192,0.00021836895,0.000066080036,0.0005214966,0.00029278628,0.000015238782,0.00002178447],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99423933,0.00088552973,0.00072575506,0.00054049405,0.003419181,0.00018973957],"domain_scores_gemma":[0.99480313,0.00025531815,0.00037769592,0.00035851833,0.0039190003,0.00028634592],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010545119,0.00019085454,0.00027014373,0.00036523555,0.00030092188,0.00037088108,0.00020483349,0.000096040436,0.00027355267],"category_scores_gemma":[0.0015179603,0.0001596576,0.000020191173,0.001035152,0.00006395359,0.0006254192,0.00011103363,0.000123353,0.000011769442],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041543324,0.0004674122,0.25288638,0.000020608772,0.000045393695,1.4296701e-7,0.012134939,0.023071606,0.00048043556,0.0079214135,0.00024541543,0.7026847],"study_design_scores_gemma":[0.001179259,0.00038225538,0.2980562,0.000024799898,0.000086105036,0.0000043609516,0.0040004435,0.67874867,0.0003245047,0.015674723,0.0013482496,0.00017043953],"about_ca_topic_score_codex":0.000030446454,"about_ca_topic_score_gemma":0.000050913044,"teacher_disagreement_score":0.70251423,"about_ca_system_score_codex":0.00025625757,"about_ca_system_score_gemma":0.00074877834,"threshold_uncertainty_score":0.6510648},"labels":[],"label_agreement":null},{"id":"W2075327290","doi":"10.7202/1027402ar","title":"Les politiques d’évaluation en éducation. Et après?","year":2014,"lang":"fr","type":"article","venue":"Éducation et francophonie","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Valuation (finance); Christian ministry; Humanism; Context (archaeology); Sociology; Argument (complex analysis); Pedagogy; Political science; Law; History","score_opus":0.23258177180899464,"score_gpt":0.49539680455877777,"score_spread":0.26281503274978313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2075327290","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22459696,0.003022251,0.07874977,0.2594887,0.029551962,0.0012302649,0.00008137041,0.00023548011,0.40304324],"genre_scores_gemma":[0.9119292,0.0012567223,0.0066269403,0.008337014,0.0014673834,0.00019258673,0.00022429125,0.0000530027,0.06991289],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98928154,0.0054944633,0.0014143764,0.00091174815,0.002316137,0.00058174075],"domain_scores_gemma":[0.9918826,0.0039636884,0.00078723265,0.0011705192,0.0018985838,0.00029737465],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.023134276,0.00043879848,0.0004831826,0.00058046065,0.0004981392,0.0007568451,0.00076118816,0.00038660257,0.022086393],"category_scores_gemma":[0.006389089,0.00042408847,0.00022986735,0.0012035607,0.0002156832,0.0020464195,0.000107899636,0.0005700262,0.00877771],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028813636,0.00084401824,0.008269276,0.00011724304,0.000057545716,4.990643e-7,0.10332256,0.0038148048,0.00040942,0.27264982,0.13595232,0.47453368],"study_design_scores_gemma":[0.0007996379,0.00019694737,0.18886186,0.00017890194,0.00005153164,0.000012629584,0.00974487,0.02254679,0.00066467066,0.066769175,0.70966655,0.00050642184],"about_ca_topic_score_codex":0.0037992452,"about_ca_topic_score_gemma":0.002754358,"teacher_disagreement_score":0.6873322,"about_ca_system_score_codex":0.0011393314,"about_ca_system_score_gemma":0.0048102266,"threshold_uncertainty_score":0.99982107},"labels":[],"label_agreement":null},{"id":"W2075343951","doi":"10.1016/s0899-9007(00)00224-0","title":"A comment on “a glimpse into the process … ”","year":2000,"lang":"en","type":"letter","venue":"Nutrition","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Process (computing); Medicine; Computer science; Programming language","score_opus":0.15228503825388787,"score_gpt":0.47495840058509115,"score_spread":0.32267336233120325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2075343951","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013747674,0.00012335762,0.000050613773,0.9823945,0.000477847,0.00067202176,0.000022211556,0.00003823624,0.014846446],"genre_scores_gemma":[0.0110817915,0.00019356198,0.000069481626,0.98304963,0.0026258624,0.00041553035,0.00025747067,0.000016939857,0.0022897108],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99540293,0.00041478995,0.00053941476,0.00043807752,0.0029806772,0.00022409309],"domain_scores_gemma":[0.9978827,0.0007800164,0.00026178305,0.00073728483,0.00030302547,0.000035162946],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0017978289,0.00020576172,0.00024317643,0.0002575191,0.00031825717,0.0003877321,0.0008243992,0.0003183529,0.004675375],"category_scores_gemma":[0.00014017671,0.00011601941,0.0001369523,0.00046778217,0.00007375874,0.00018596598,0.000027037891,0.0009909138,0.0029332086],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028016499,0.000090891146,0.000017269533,0.000025034835,0.000006731083,0.0000066477014,0.00062796794,0.000027319262,9.870053e-7,0.000064608146,0.97117776,0.027926791],"study_design_scores_gemma":[0.00042583776,0.00017272335,0.00006981943,0.00013041419,0.000014340549,0.0000036198232,0.00020921904,0.0006899264,0.00006354094,0.02420207,0.9738682,0.0001503053],"about_ca_topic_score_codex":0.000017381086,"about_ca_topic_score_gemma":0.000011857923,"teacher_disagreement_score":0.027776485,"about_ca_system_score_codex":0.00012945049,"about_ca_system_score_gemma":0.000115403134,"threshold_uncertainty_score":0.99784315},"labels":[],"label_agreement":null},{"id":"W2075823939","doi":"10.7202/1024897ar","title":"L’impact de la formulation des items dans les questionnaires d’enquête","year":2014,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Humanities; Philosophy","score_opus":0.14876275789572607,"score_gpt":0.5231927955924353,"score_spread":0.3744300376967092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2075823939","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6372722,0.00047476732,0.33750695,0.007817037,0.0015628063,0.00046317003,0.000020265745,0.000081477054,0.014801324],"genre_scores_gemma":[0.98413587,0.00046883934,0.00753046,0.00026573346,0.0005883891,0.000104055594,0.00026926762,0.00003938612,0.0065979785],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9776969,0.01806285,0.0010931338,0.00059538434,0.0020854182,0.00046629907],"domain_scores_gemma":[0.99186885,0.0053147282,0.000686825,0.00063373614,0.0012902081,0.00020566708],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.075157024,0.0003547913,0.00032773442,0.00048878754,0.0006623143,0.0007674963,0.00040914022,0.00042145877,0.0031430465],"category_scores_gemma":[0.013043432,0.00031829928,0.0002249937,0.0009623624,0.00025247122,0.002090852,0.00005132689,0.00038925782,0.0006628677],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003779287,0.0003542761,0.35387477,0.000053597836,0.00004778677,3.1404474e-7,0.13229658,0.07254786,0.0023511532,0.020337531,0.00552268,0.41257566],"study_design_scores_gemma":[0.00050538086,0.00016706443,0.64690185,0.00015938499,0.00007774366,0.000017490442,0.001243711,0.30049482,0.000344661,0.034033295,0.015817204,0.00023741665],"about_ca_topic_score_codex":0.0015503321,"about_ca_topic_score_gemma":0.002398805,"teacher_disagreement_score":0.41233826,"about_ca_system_score_codex":0.0016198548,"about_ca_system_score_gemma":0.0026849655,"threshold_uncertainty_score":0.9999269},"labels":[],"label_agreement":null},{"id":"W2076797169","doi":"10.5539/ass.v9n17p291","title":"Scenarios of Thailand Secondary Education within B.E. 2570","year":2013,"lang":"en","type":"article","venue":"Asian Social Science","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Plan (archaeology); Quartile; Futures contract; Secondary education; Delphi method; Medical education; Political science; Psychology; Geography; Mathematics education; Business; Medicine; Computer science","score_opus":0.07182185003518107,"score_gpt":0.44133129239136804,"score_spread":0.369509442356187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2076797169","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.290803,0.000018756826,0.000176882,0.003457797,0.0007160018,0.00023030728,0.000002580746,0.000014602541,0.70458007],"genre_scores_gemma":[0.9951799,0.0000015682118,0.0009224224,0.0005664981,0.00011058819,0.000018820563,0.0000012503822,0.000002955854,0.0031960327],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99710476,0.00008455048,0.00043007726,0.00029598075,0.001881227,0.0002034102],"domain_scores_gemma":[0.99848205,0.000079487814,0.00031258896,0.0002582135,0.0007573879,0.00011026503],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0034057524,0.00007395756,0.00013973853,0.00021119375,0.00043871882,0.00029168758,0.0007889632,0.00004243582,0.0051598605],"category_scores_gemma":[0.00053716433,0.000053796226,0.000047979316,0.0015131108,0.0005971557,0.0013653132,0.00009037033,0.00010634877,0.0006889172],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027796464,0.000069985224,0.01681647,0.0000037689367,0.000002150372,8.357831e-8,0.009103776,0.000002473665,0.0033082904,0.022167346,0.009488319,0.9390346],"study_design_scores_gemma":[0.00019006027,0.000058001242,0.92034787,0.000010924566,0.0000038803487,0.0000020667558,0.017590104,0.0006829629,0.001819469,0.049365886,0.009787396,0.00014135575],"about_ca_topic_score_codex":0.00012216499,"about_ca_topic_score_gemma":0.000046810164,"teacher_disagreement_score":0.9388932,"about_ca_system_score_codex":0.000063562824,"about_ca_system_score_gemma":0.0023690558,"threshold_uncertainty_score":0.99574953},"labels":[],"label_agreement":null},{"id":"W2077312509","doi":"10.1002/crq.3890180304","title":"The role of interest‐based facilitation in designing accreditation standards: The Canadian experience","year":2001,"lang":"en","type":"article","venue":"Mediation Quarterly","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"123 Certification (Canada)","funders":"","keywords":"Accreditation; Certification; Mediation; Family mediation; Best practice; Empowerment; Process (computing); Facilitation; Engineering ethics; Public relations; Knowledge management; Blueprint; Psychology; Medical education; Political science; Process management; Computer science; Business; Engineering; Alternative dispute resolution; Medicine","score_opus":0.15337191574280512,"score_gpt":0.44677615576907415,"score_spread":0.293404240026269,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077312509","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.977578,0.00027597207,0.012764531,0.0066412846,0.0005030672,0.00044556998,0.000020733445,0.000013533449,0.0017573311],"genre_scores_gemma":[0.9993541,0.000008402392,0.00015677497,0.00026191838,0.000043398406,0.00008201304,0.000012392859,0.0000033510637,0.00007764365],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9972941,0.00044757538,0.00059534644,0.00016850093,0.0013138824,0.00018056031],"domain_scores_gemma":[0.9970677,0.0016053049,0.00026019488,0.00029669493,0.00070217147,0.000067956236],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006192422,0.0000745233,0.000095573465,0.00024665348,0.00033330117,0.00023434364,0.00038740542,0.00004346157,0.00033291016],"category_scores_gemma":[0.0017692705,0.000042286774,0.000035944944,0.0007106399,0.00009496661,0.00047657176,0.0000045993456,0.000102684346,0.000043826913],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000965249,0.00003200521,0.12632778,0.000002592231,0.0000060458674,0.0000011753189,0.10686755,0.0026509515,0.0013263277,0.0035219626,0.002090189,0.7570769],"study_design_scores_gemma":[0.0010597807,0.00055726024,0.3847597,0.000035326422,0.000006952036,0.0000016682528,0.1707102,0.25152156,0.0019809154,0.031697664,0.1574418,0.0002271811],"about_ca_topic_score_codex":0.0044075353,"about_ca_topic_score_gemma":0.34809208,"teacher_disagreement_score":0.7568497,"about_ca_system_score_codex":0.00023332624,"about_ca_system_score_gemma":0.0009484583,"threshold_uncertainty_score":0.66629046},"labels":[],"label_agreement":null},{"id":"W207771378","doi":"10.1007/978-94-007-2780-9_5","title":"Meeting Implementation Challenges","year":2012,"lang":"en","type":"book-chapter","venue":"SpringerBriefs in public health","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science","score_opus":0.5169040828152909,"score_gpt":0.5333717705477959,"score_spread":0.016467687732505065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W207771378","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00029831092,0.010126017,0.00019943644,0.04662678,0.001248271,0.0007354689,0.000025336014,0.000085308704,0.94065505],"genre_scores_gemma":[0.5428914,0.06677789,0.005099225,0.013907305,0.004020437,0.00027592087,0.00030240035,0.0003349718,0.36639047],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9931269,0.00031710078,0.0019844652,0.0007743084,0.0029136569,0.00088356266],"domain_scores_gemma":[0.99649954,0.0005482561,0.0012059803,0.00090789254,0.00038299643,0.00045532722],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.026529644,0.00034609376,0.00067423575,0.0010386705,0.00021310801,0.0002699403,0.00073315634,0.00024859203,0.009528549],"category_scores_gemma":[0.00046056783,0.00030612128,0.00014377444,0.00018719283,0.00007123894,0.0007289312,0.00027128248,0.0005961206,0.0012139473],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015092063,0.000022288728,0.0013184613,0.00003321831,0.000010647049,8.3725524e-7,0.0015564903,0.0000026164528,3.6079396e-7,0.33721736,0.0020153832,0.6578208],"study_design_scores_gemma":[0.00031071098,0.00006795767,0.013976448,0.000094347284,0.000003077257,0.0000034761172,0.00079245813,0.000056933313,0.0000019910358,0.02225113,0.9621684,0.000273065],"about_ca_topic_score_codex":0.00014606476,"about_ca_topic_score_gemma":0.0025778997,"teacher_disagreement_score":0.96015304,"about_ca_system_score_codex":0.00080904615,"about_ca_system_score_gemma":0.0020591049,"threshold_uncertainty_score":0.9999391},"labels":[],"label_agreement":null},{"id":"W2077784671","doi":"10.7202/009972ar","title":"L’évaluation participative de type empowerment : une stratégie pour le travail de rue","year":2005,"lang":"fr","type":"article","venue":"Service social","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.21781828543829523,"score_gpt":0.4899163054966697,"score_spread":0.27209802005837447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077784671","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8030328,0.00054410595,0.0016833858,0.1735895,0.00081203296,0.00030561705,0.000028444905,0.000038232123,0.019965904],"genre_scores_gemma":[0.96968275,0.00014348658,0.0047771255,0.0075655924,0.001570785,0.00002540666,0.000027342345,0.000022424136,0.016185101],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9959539,0.0009908137,0.0006665962,0.00039093808,0.0013259698,0.0006717442],"domain_scores_gemma":[0.9980757,0.000299116,0.000298354,0.00024262119,0.0008799941,0.00020420644],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.005134888,0.00022496405,0.00027990976,0.00009427733,0.0006034394,0.0002626673,0.00042412928,0.0002532773,0.006408404],"category_scores_gemma":[0.00017493154,0.00022953817,0.00012199047,0.0011528687,0.00010974065,0.00060863286,0.000069460875,0.00030241205,0.0030299174],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018591234,0.00095661904,0.004283844,0.00005005351,0.00012133161,0.000005526324,0.19125584,0.017796531,0.0031965892,0.010097238,0.029264815,0.7427857],"study_design_scores_gemma":[0.0029887476,0.0003815925,0.38932905,0.00008604293,0.00022892986,0.000008648796,0.071168505,0.31994483,0.0032423183,0.04232318,0.16963245,0.00066573394],"about_ca_topic_score_codex":0.0025248006,"about_ca_topic_score_gemma":0.014376575,"teacher_disagreement_score":0.74211997,"about_ca_system_score_codex":0.00063065544,"about_ca_system_score_gemma":0.006210086,"threshold_uncertainty_score":0.9994238},"labels":[],"label_agreement":null},{"id":"W2077911505","doi":"10.1080/09614520701337160","title":"Results-based management: friend or foe?","year":2007,"lang":"en","type":"article","venue":"Development in Practice","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Humber Polytechnic","funders":"","keywords":"Perspective (graphical); Work (physics); Point (geometry); Political science; Public relations; Sociology; Engineering ethics; Engineering; Computer science; Artificial intelligence","score_opus":0.24346306555366723,"score_gpt":0.5393384996383762,"score_spread":0.29587543408470895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077911505","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041632403,0.000051116072,0.03617745,0.008511413,0.0010019327,0.00063344237,0.000003843369,0.00007462798,0.91191375],"genre_scores_gemma":[0.7281064,0.00004829866,0.24437857,0.0057449644,0.00005556316,0.00004606202,0.000025527537,0.000015067667,0.02157956],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9953911,0.00020469961,0.0011942746,0.00047429276,0.0023689838,0.00036667567],"domain_scores_gemma":[0.994802,0.0038340257,0.00042281838,0.0004743546,0.0003620659,0.00010471849],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.025265643,0.00014090951,0.00015970343,0.00058825035,0.00016935266,0.00021562283,0.00051746925,0.00006336891,0.0010751126],"category_scores_gemma":[0.005012388,0.00010089487,0.000027029379,0.0016179231,0.000030685576,0.0010089832,0.00011107594,0.00018742168,0.0018905937],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0033610584,0.0007069036,0.0080076065,0.00001738811,0.00005993764,0.00045906153,0.0056826132,0.0007836764,0.000025765732,0.010877524,0.01865014,0.95136833],"study_design_scores_gemma":[0.0015357966,0.00004183099,0.052746717,0.000029729003,0.000008420146,0.0000069324947,0.004484465,0.00067414396,0.000760495,0.0002897765,0.93924767,0.00017401726],"about_ca_topic_score_codex":0.000010512069,"about_ca_topic_score_gemma":0.00032633924,"teacher_disagreement_score":0.9511943,"about_ca_system_score_codex":0.0002044611,"about_ca_system_score_gemma":0.00045311297,"threshold_uncertainty_score":0.99983805},"labels":[],"label_agreement":null},{"id":"W2077943567","doi":"10.1007/s12134-015-0425-1","title":"Knowledge Mobilization/Transfer and Immigration Policy: Forging Space for NGOs—the Case of CERIS—The Ontario Metropolis Centre","year":2015,"lang":"en","type":"article","venue":"Journal of International Migration and Integration / Revue de l integration et de la migration internationale","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Waterloo; York University; Toronto Metropolitan University","funders":"","keywords":"Immigration; Knowledge transfer; Settlement (finance); Government (linguistics); Political science; Public relations; Public administration; Immigration policy; Economic growth; Sociology; Business; Economics; Management","score_opus":0.08883022023495073,"score_gpt":0.4355564453671454,"score_spread":0.34672622513219464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077943567","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4794178,0.00032645225,0.46285465,0.05301946,0.00078366906,0.00062473427,0.00007234042,0.000019903619,0.0028809973],"genre_scores_gemma":[0.98548293,0.00057179737,0.007536304,0.0011652089,0.0006197709,0.000088739725,0.00011752955,0.000026450316,0.0043912516],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99557596,0.0010300182,0.0018700036,0.0003592685,0.00094365445,0.00022107732],"domain_scores_gemma":[0.9892558,0.0030070643,0.001297593,0.00030478643,0.0059365,0.00019824255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008562927,0.0003115632,0.0003988472,0.0010404752,0.00029853417,0.00092040474,0.000560525,0.0001816259,0.00018485005],"category_scores_gemma":[0.006925794,0.00020143701,0.00026430225,0.00067649013,0.00027680118,0.0018726107,0.00006220726,0.00049385877,0.0000052554933],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008159946,0.00053615146,0.037798792,0.000033139062,0.0003228712,0.000014502225,0.11534742,0.009114158,0.011191948,0.76981163,0.028670693,0.026342677],"study_design_scores_gemma":[0.003964654,0.0011498835,0.021945719,0.00042574052,0.00022662534,0.003841503,0.06357353,0.51462746,0.019391058,0.059138052,0.31111002,0.00060575816],"about_ca_topic_score_codex":0.007255411,"about_ca_topic_score_gemma":0.19906259,"teacher_disagreement_score":0.7106736,"about_ca_system_score_codex":0.00096046086,"about_ca_system_score_gemma":0.0014277601,"threshold_uncertainty_score":0.9993554},"labels":[],"label_agreement":null},{"id":"W2080636013","doi":"10.12927/cjnl.2014.23843","title":"Critical Appraisal through a New Lens","year":2014,"lang":"en","type":"article","venue":"Nursing leadership","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Lens (geology); Psychology; Nurse Administrator; Nursing; Sociology; MEDLINE; Political science; Medicine; Optics","score_opus":0.7227861547626216,"score_gpt":0.5601454549371083,"score_spread":0.16264069982551332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2080636013","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015751192,0.00025356252,0.343285,0.27470636,0.006178031,0.00015911799,0.0000018845386,0.00021075062,0.3594541],"genre_scores_gemma":[0.9839173,0.0000013625186,0.008442109,0.0037244125,0.0007055376,0.0000027576361,0.0000023211408,0.000012302133,0.0031918841],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969217,0.00033580026,0.00039087413,0.00039240345,0.0015563623,0.00040286157],"domain_scores_gemma":[0.9953446,0.0037473103,0.000077358476,0.0004922994,0.0001964343,0.00014200628],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0023869704,0.00012721612,0.00020092247,0.00010314397,0.00018925506,0.00032683535,0.00042559986,0.00009849972,0.0021212334],"category_scores_gemma":[0.009142194,0.000099862424,0.0000932084,0.00041127732,0.0002544963,0.00080350845,0.000013760881,0.0002222137,0.00240078],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006418953,0.00018058562,0.0030639698,0.000012330125,0.000008418767,0.0000015280308,0.024136141,0.00020196309,0.00042307732,0.30009323,0.29124928,0.38056532],"study_design_scores_gemma":[0.0014737695,0.00049607863,0.0329015,0.00029733212,0.000049192437,0.000040536423,0.026534569,0.025786959,0.0012148367,0.23613797,0.67444634,0.0006209205],"about_ca_topic_score_codex":0.000011296312,"about_ca_topic_score_gemma":0.000010776101,"teacher_disagreement_score":0.9681661,"about_ca_system_score_codex":0.00005088462,"about_ca_system_score_gemma":0.00019000511,"threshold_uncertainty_score":0.9992042},"labels":[],"label_agreement":null},{"id":"W2080665263","doi":"10.1007/bf03059639","title":"Voor ons is er maar één uitweg: de oplossing van het probleem","year":2007,"lang":"nl","type":"article","venue":"Kind & Adolescent Praktijk","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"World Federation of Science Journalists","funders":"","keywords":"Maar; Political science; Theology; Philosophy; Geology","score_opus":0.1408046764324589,"score_gpt":0.4612497021678766,"score_spread":0.32044502573541767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2080665263","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74372494,0.0032352228,0.06076097,0.035069976,0.0065783905,0.0043732775,0.00026587525,0.00043038416,0.14556096],"genre_scores_gemma":[0.95360327,0.0002882259,0.0048556435,0.009066491,0.000997753,0.000019864334,0.000025485493,0.0000789644,0.031064278],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9898424,0.000621076,0.0021155525,0.0014391873,0.004105919,0.0018758753],"domain_scores_gemma":[0.99521095,0.0005573037,0.0009923722,0.0015438929,0.0007775444,0.0009179481],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.012817515,0.00071616005,0.00076115003,0.0007231454,0.0010532815,0.0014824418,0.0014720751,0.00049463223,0.01973361],"category_scores_gemma":[0.0006503608,0.00061721116,0.00045492026,0.0015882772,0.00036968736,0.0012948471,0.0004505326,0.0011699117,0.011345082],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005101483,0.0029911888,0.41845694,0.00035188507,0.00021319708,0.00018093684,0.012392111,0.0007472736,0.0054069073,0.0028132051,0.18518932,0.37074688],"study_design_scores_gemma":[0.0022133803,0.0003504079,0.2612388,0.0010432856,0.00017118067,0.00006837013,0.0030030957,0.008448099,0.009480183,0.0016556735,0.71132314,0.001004355],"about_ca_topic_score_codex":0.00004871171,"about_ca_topic_score_gemma":0.00027198295,"teacher_disagreement_score":0.52613384,"about_ca_system_score_codex":0.00075014745,"about_ca_system_score_gemma":0.0017920968,"threshold_uncertainty_score":0.99962795},"labels":[],"label_agreement":null},{"id":"W2081322617","doi":"10.1177/1356389005058475","title":"Polity, Politics and Policy Evaluation in Belgium","year":2005,"lang":"en","type":"article","venue":"Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Polity; Parliament; Politics; Institutionalisation; Political science; Public administration; Corporate governance; Government (linguistics); Public policy; Phenomenon; Political economy; Comparative politics; Sociology; Economics; Law","score_opus":0.2900194241285808,"score_gpt":0.5822176039709627,"score_spread":0.2921981798423819,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081322617","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93253773,0.00023006277,0.0003182405,0.025774797,0.00023384675,0.00081376993,0.000006123882,0.000022901566,0.040062524],"genre_scores_gemma":[0.9966677,0.000028637007,0.00070711726,0.00120021,0.00047842346,0.000089654204,0.000029642202,0.000008666857,0.0007899657],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9928079,0.0010785771,0.0007931291,0.00043253944,0.0045818794,0.00030595172],"domain_scores_gemma":[0.9975584,0.00041874152,0.00022975243,0.0004467783,0.0012302184,0.00011608843],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02595729,0.0001358167,0.00018663077,0.00084719766,0.00015463437,0.00021234101,0.00023368275,0.0000913504,0.0032186336],"category_scores_gemma":[0.005280739,0.00011607637,0.000042125273,0.0010144262,0.000063985666,0.00089945574,0.000082722785,0.00013036659,0.0006668479],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014485392,0.00012323749,0.06395793,0.0000040253535,0.0000076192473,1.6569616e-7,0.0028277996,0.01213827,0.00038513597,0.031798914,0.002217567,0.88652486],"study_design_scores_gemma":[0.0010006714,0.00003545527,0.44723678,0.00000777492,0.000017563163,0.0000028971408,0.0003449154,0.45643333,0.00015790593,0.08832588,0.0063394806,0.00009735498],"about_ca_topic_score_codex":0.00017726302,"about_ca_topic_score_gemma":0.0007824812,"teacher_disagreement_score":0.8864275,"about_ca_system_score_codex":0.000746948,"about_ca_system_score_gemma":0.0012906517,"threshold_uncertainty_score":0.9976926},"labels":[],"label_agreement":null},{"id":"W2081401431","doi":"10.3928/01484834-20100331-01","title":"Contesting Our Taken-for-Granted Understanding of Student Evaluation: Insights from a Team of Institutional Ethnographers","year":2010,"lang":"en","type":"article","venue":"Journal of Nursing Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Excellence; Ethnography; Work (physics); Process (computing); Engineering ethics; Sociology; Nurse educator; Pedagogy; Nurse education; Medical education; Psychology; Medicine; Political science; Computer science","score_opus":0.49631814844364786,"score_gpt":0.5860610238057367,"score_spread":0.0897428753620888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081401431","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97350496,0.00022181722,0.016056804,0.0013702128,0.0060121235,0.0002635218,0.0000062236613,0.0000035985,0.0025607594],"genre_scores_gemma":[0.9898895,0.000006434616,0.009621677,0.000045551198,0.00039759142,0.000005114438,0.000008321577,0.0000049737064,0.000020834786],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9964145,0.00017802858,0.0011437996,0.00013623633,0.002038539,0.00008891181],"domain_scores_gemma":[0.9942373,0.00061580667,0.001826567,0.00019168088,0.0030527494,0.0000759211],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004094713,0.00008850742,0.0002621286,0.0005788448,0.00016264354,0.00007051912,0.00029865318,0.00006972655,0.000073176336],"category_scores_gemma":[0.0019217394,0.00006759302,0.00013927175,0.00058841595,0.0001134975,0.0005469679,0.000008003782,0.00021009365,0.0000013241176],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006473952,0.0051728007,0.16628599,0.00004901835,0.00033169272,4.306573e-7,0.110128164,0.0102133555,0.19804469,0.034744766,0.01900887,0.45537284],"study_design_scores_gemma":[0.003736177,0.0006774685,0.50991476,0.0018459255,0.0003777475,0.000044370187,0.27672067,0.029073874,0.005580358,0.17065519,0.0011111553,0.0002622877],"about_ca_topic_score_codex":0.000011816211,"about_ca_topic_score_gemma":0.00004237033,"teacher_disagreement_score":0.45511055,"about_ca_system_score_codex":0.00024546377,"about_ca_system_score_gemma":0.0022655597,"threshold_uncertainty_score":0.40190056},"labels":[],"label_agreement":null},{"id":"W2081551946","doi":"10.14507/epaa.v11n51.2003","title":"Educational Policy Reform and its Impact on Equity Work in Ontario: Global Challenges and Local Possibilities","year":2003,"lang":"en","type":"article","venue":"Education Policy Analysis Archives","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Western University","funders":"","keywords":"Restructuring; Equity (law); Public administration; Work (physics); Educational equity; Political science; Public policy; Local government; Government (linguistics); Sociology; Public economics; Economic growth; Economics; Social science; Law","score_opus":0.14829016703220738,"score_gpt":0.5252458321578913,"score_spread":0.37695566512568396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081551946","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87625796,0.0011650779,0.000051164192,0.016302064,0.00007804584,0.00014611804,0.000013955386,0.000007737524,0.10597787],"genre_scores_gemma":[0.99390644,0.00043283,0.0002805095,0.0005779595,0.00013418327,0.000036971225,0.000020455163,0.000004765813,0.004605916],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99741834,0.00042920667,0.0005805399,0.0005222881,0.000736496,0.00031310992],"domain_scores_gemma":[0.99833107,0.0006835032,0.00022169063,0.0003918683,0.00011211612,0.00025976554],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015414393,0.00020420724,0.00034882704,0.0015802399,0.00017577481,0.00019771596,0.00024610836,0.000054638003,0.00063370226],"category_scores_gemma":[0.0010923567,0.00014637706,0.00014173152,0.0017607446,0.0001767783,0.00038841448,0.00008540696,0.00016301889,0.00003504495],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000810681,0.00042964684,0.27740762,0.000008485451,0.00015151755,1.2442901e-7,0.019558262,0.0008675932,0.0000047210337,0.5623931,0.00015035838,0.1389475],"study_design_scores_gemma":[0.00014289939,0.000056593395,0.79764825,0.000016038186,0.000029460994,0.000003078805,0.0045769783,0.00039938354,0.000008544614,0.19633166,0.00066604355,0.000121049976],"about_ca_topic_score_codex":0.030578598,"about_ca_topic_score_gemma":0.10702383,"teacher_disagreement_score":0.52024066,"about_ca_system_score_codex":0.0009871861,"about_ca_system_score_gemma":0.0055102436,"threshold_uncertainty_score":0.9774936},"labels":[],"label_agreement":null},{"id":"W2081701430","doi":"10.3138/cjpe.29.1.62","title":"Assessing the Quality of Aboriginal Program Evaluations","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université Laval","funders":"","keywords":"Treasury; Popularity; Quality (philosophy); Context (archaeology); Government (linguistics); Program evaluation; Strengths and weaknesses; Corporate governance; Replicate; Business; Political science; Public administration; Psychology; Finance; Geography; Statistics","score_opus":0.5441703005540053,"score_gpt":0.6713453947850856,"score_spread":0.1271750942310803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081701430","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97209966,0.00031010687,0.008894664,0.0053995093,0.0012740468,0.001951466,0.0000056940157,0.000016952055,0.010047918],"genre_scores_gemma":[0.98893946,0.0000050339804,0.010430857,0.00015178813,0.00026907373,0.000115135685,0.000010135984,0.00000908745,0.00006944371],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9904861,0.0028566509,0.001828106,0.00021410797,0.0043084575,0.00030658382],"domain_scores_gemma":[0.9886031,0.0011304843,0.0019521005,0.0005300196,0.007432273,0.0003520031],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.071635656,0.00013753271,0.00033564895,0.00053151516,0.00040941144,0.00084167527,0.00077615504,0.00008141744,0.0014301499],"category_scores_gemma":[0.009443286,0.00008536712,0.00021772092,0.0012379902,0.00026507955,0.0010719385,0.0000105603185,0.00028323123,0.000041650314],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000058553255,0.00007095182,0.045118,0.000005480016,0.000024198984,2.4565028e-7,0.0007468679,0.0025363949,0.0000763465,0.0031776682,0.00087601866,0.94736195],"study_design_scores_gemma":[0.0010424993,0.0006837851,0.71918356,0.00006230642,0.00015732835,0.00001821178,0.0021339988,0.13614297,0.00015909324,0.024139095,0.11611635,0.0001608],"about_ca_topic_score_codex":0.0008393119,"about_ca_topic_score_gemma":0.012815612,"teacher_disagreement_score":0.9472012,"about_ca_system_score_codex":0.00027066653,"about_ca_system_score_gemma":0.008181978,"threshold_uncertainty_score":0.9994827},"labels":[],"label_agreement":null},{"id":"W2081929183","doi":"10.3138/cjpe.29.2.48","title":"Think Positively! And Make a Difference Through Evaluation","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Obligation; Punishment (psychology); Theme (computing); Accountability; Reinforcement; Psychology; Social psychology; Epistemology; Computer science; Political science; Law; Philosophy","score_opus":0.37937904172344933,"score_gpt":0.5354819516833826,"score_spread":0.1561029099599333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081929183","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9751555,0.0007254456,0.008023181,0.0041012145,0.0008663202,0.0013767516,0.0000056929543,0.0000111674135,0.009734743],"genre_scores_gemma":[0.9938131,0.000015164867,0.0053049154,0.00047344924,0.00020133716,0.000040659423,0.000010256865,0.000008770637,0.0001323776],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99398226,0.0013833162,0.00084569765,0.00026312695,0.0032588663,0.00026673256],"domain_scores_gemma":[0.9937254,0.00042909873,0.0007310844,0.0002885477,0.004448332,0.00037753992],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.026156405,0.00014264004,0.0002583504,0.00041681025,0.00029752773,0.0005839048,0.00035510003,0.00009251741,0.0011795682],"category_scores_gemma":[0.0060253507,0.00010658927,0.00008640065,0.0005356559,0.00013250991,0.00060677255,0.000016392629,0.0002102,0.00004642053],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011387634,0.000021582024,0.014522768,0.000002868024,0.000017250037,8.596913e-7,0.0029339392,0.00045319955,0.000071333,0.0019004485,0.0004294713,0.9796349],"study_design_scores_gemma":[0.0015823615,0.0007910879,0.5868156,0.000073620045,0.00018787675,0.00007166901,0.0015902997,0.29542643,0.000103734186,0.09681657,0.016343882,0.00019683535],"about_ca_topic_score_codex":0.00041622252,"about_ca_topic_score_gemma":0.0112039475,"teacher_disagreement_score":0.97943807,"about_ca_system_score_codex":0.00030348395,"about_ca_system_score_gemma":0.0030664832,"threshold_uncertainty_score":0.9997335},"labels":[],"label_agreement":null},{"id":"W2082427028","doi":"10.1332/174426406778881737","title":"Affecting policy and practice: issues involved in developing an Argument Catalogue","year":2006,"lang":"en","type":"article","venue":"Evidence & Policy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Argument (complex analysis); Codebook; Order (exchange); Computer science; Argument map; Epistemology; Data science; Artificial intelligence; Philosophy; Medicine","score_opus":0.2746668582311512,"score_gpt":0.5651246503110933,"score_spread":0.29045779207994205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082427028","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9198569,0.0009585044,0.00049209845,0.07542171,0.00011265665,0.00034192266,0.0000032774396,0.00004900492,0.0027639093],"genre_scores_gemma":[0.9881641,0.00044634033,0.006167784,0.0035452023,0.0008164838,0.000029859975,0.000009123772,0.000011662412,0.00080944464],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9963635,0.00071904314,0.00072248414,0.0005146744,0.0012553951,0.00042487343],"domain_scores_gemma":[0.9960792,0.0026664997,0.00033675475,0.00048049496,0.0003174842,0.00011957],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008324747,0.00018240049,0.00025966496,0.0008727282,0.00023706422,0.0005765316,0.00043871533,0.00007677498,0.00006410933],"category_scores_gemma":[0.018804282,0.00014807424,0.000035721452,0.0017457049,0.00010072394,0.0034332965,0.00018565108,0.0001634908,0.00016678675],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016025099,0.00033041122,0.56258017,0.000073088166,0.000021409323,0.000040610143,0.025504462,0.0019459327,0.006035769,0.22213766,0.0056200246,0.17555021],"study_design_scores_gemma":[0.0006478919,0.00022096017,0.8866582,0.0003973919,0.000011488095,0.000052827738,0.008518341,0.0031839695,0.002818716,0.038911212,0.058039285,0.0005397161],"about_ca_topic_score_codex":0.038449503,"about_ca_topic_score_gemma":0.012501948,"teacher_disagreement_score":0.32407802,"about_ca_system_score_codex":0.00042077567,"about_ca_system_score_gemma":0.0012833053,"threshold_uncertainty_score":0.98946077},"labels":[],"label_agreement":null},{"id":"W2082546237","doi":"10.7202/051269ar","title":"La relation entre le contexte de l'évaluation du rendement et l'indulgence de l'évaluateur","year":2005,"lang":"fr","type":"article","venue":"Relations industrielles","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.14348326845550793,"score_gpt":0.41783557589080644,"score_spread":0.2743523074352985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082546237","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5666664,0.0047799638,0.1076375,0.21301818,0.0009992738,0.00092813594,0.00006421503,0.00013313735,0.10577316],"genre_scores_gemma":[0.9315127,0.0017023095,0.010263212,0.0010824635,0.00047653416,0.00007752971,0.00008015791,0.00003230714,0.054772753],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99212056,0.0035541977,0.0013304227,0.00061830675,0.0017801618,0.00059637305],"domain_scores_gemma":[0.9952582,0.0025882674,0.00066306524,0.0005981705,0.00060656655,0.00028574537],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.017051984,0.0003338501,0.00031399817,0.00040293986,0.0009682754,0.00044414686,0.00047922824,0.0008243571,0.008595476],"category_scores_gemma":[0.0033308037,0.00034384525,0.00018538669,0.0012266542,0.00032102191,0.0017256333,0.00013266134,0.0011084019,0.0024260548],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028806198,0.00035004676,0.068691984,0.0000029164291,0.00006478889,0.0000050557,0.013587832,0.24100073,0.00016220211,0.08399679,0.054858103,0.53725076],"study_design_scores_gemma":[0.0012017869,0.00008331818,0.06586929,0.00016196595,0.00010929693,0.000053216518,0.0057075634,0.32334659,0.0005754301,0.008257584,0.59432554,0.00030840855],"about_ca_topic_score_codex":0.00034623596,"about_ca_topic_score_gemma":0.00031815533,"teacher_disagreement_score":0.53946745,"about_ca_system_score_codex":0.0010578489,"about_ca_system_score_gemma":0.006589829,"threshold_uncertainty_score":0.99990135},"labels":[],"label_agreement":null},{"id":"W2083111387","doi":"10.1016/j.evalprogplan.2011.03.003","title":"Using hybrid models to support the development of organizational evaluation capacity: A case narrative","year":2011,"lang":"en","type":"article","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Work (physics); Narrative; Process management; Program evaluation; Public sector; Internal validity; Knowledge management; Management science; Computer science; Business; Engineering; Political science; Medicine","score_opus":0.7330308143647964,"score_gpt":0.5574659762554713,"score_spread":0.1755648381093251,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2083111387","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9571189,0.000052649197,0.036403045,0.0001176911,0.0001828547,0.0016010578,0.000007241902,0.000025623302,0.004490922],"genre_scores_gemma":[0.9384346,5.9446955e-7,0.06112309,0.00015082194,0.00003294305,0.00017485418,0.0000365796,0.000009047701,0.00003749268],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99520135,0.0006533752,0.0008209157,0.00035176528,0.0027867998,0.0001857706],"domain_scores_gemma":[0.9963752,0.00022756819,0.0003947084,0.00026067902,0.0026332417,0.00010858296],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.018810706,0.00014475312,0.00018639516,0.00026654193,0.00058048667,0.00014137004,0.00019838475,0.000042790296,0.0023885674],"category_scores_gemma":[0.0008508524,0.000098320976,0.00003334891,0.00072249357,0.00007100003,0.00050605723,0.000081839105,0.000099394674,0.000024177878],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007015831,0.00016635303,0.010114551,0.000009677096,0.00007141515,0.000005276227,0.36690208,0.027883612,0.00029180347,0.0010992592,0.00038343124,0.5930024],"study_design_scores_gemma":[0.00063645444,0.00020447727,0.006628038,0.00003822394,0.00008181721,0.0001580963,0.026910532,0.9519537,0.0015251327,0.011172365,0.0005079522,0.00018317963],"about_ca_topic_score_codex":0.00002184543,"about_ca_topic_score_gemma":0.00007142494,"teacher_disagreement_score":0.9240701,"about_ca_system_score_codex":0.00010544101,"about_ca_system_score_gemma":0.001057443,"threshold_uncertainty_score":0.9985234},"labels":[],"label_agreement":null},{"id":"W2083375559","doi":"10.7202/031922ar","title":"Les causes de l’isolement professionnel des directions d’établissement d’enseignement","year":2007,"lang":"fr","type":"article","venue":"Revue des sciences de l éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Political science; Humanities; Philosophy","score_opus":0.7230253220908784,"score_gpt":0.5864955802259844,"score_spread":0.13652974186489408,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2083375559","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8517755,0.006460867,0.09404367,0.007791353,0.0050794515,0.0007332864,0.000016949172,0.00007884505,0.03402003],"genre_scores_gemma":[0.9295301,0.0019521608,0.050050803,0.00053105265,0.00051513885,0.00011254138,0.000011532635,0.000017855393,0.017278824],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9946514,0.0007379217,0.0011460829,0.00076172967,0.0015392633,0.0011636341],"domain_scores_gemma":[0.99679357,0.00087512896,0.00054247316,0.000504389,0.00086924963,0.0004151643],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02092366,0.00030369297,0.00028253754,0.0006834175,0.0041424404,0.0007191753,0.00080165226,0.00017880237,0.0049595274],"category_scores_gemma":[0.0014593881,0.0002701332,0.00015171118,0.0025773814,0.0018432084,0.0013098097,0.00016208754,0.00027145594,0.000391292],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004097292,0.0016175186,0.1335152,0.00035584517,0.000056764402,0.0000109909215,0.13902558,0.0059365085,0.0051051253,0.07132142,0.0077405185,0.6352736],"study_design_scores_gemma":[0.00068007654,0.001037445,0.52286994,0.001615931,0.0001831707,0.00020755951,0.20742753,0.030764457,0.011550901,0.07049726,0.15230475,0.0008609647],"about_ca_topic_score_codex":0.0035003833,"about_ca_topic_score_gemma":0.015441745,"teacher_disagreement_score":0.6344126,"about_ca_system_score_codex":0.0064505395,"about_ca_system_score_gemma":0.0024364567,"threshold_uncertainty_score":0.9999751},"labels":[],"label_agreement":null},{"id":"W2083643374","doi":"10.1177/1741143208095793","title":"Manitoba Superintendents","year":2008,"lang":"en","type":"article","venue":"Educational Management Administration & Leadership","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Manitoba; Research Manitoba","funders":"","keywords":"Leadership style; Diversity (politics); Servant leadership; Qualitative research; Pedagogy; Educational leadership; Leadership; Public relations; Sociology; Psychology; Political science; Social science","score_opus":0.545364325289118,"score_gpt":0.48238470568333097,"score_spread":0.06297961960578707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2083643374","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5635034,0.00011724762,0.00424867,0.12213564,0.0030495701,0.0009435158,0.000013930503,0.00013108757,0.30585694],"genre_scores_gemma":[0.9223907,0.000022358778,0.0018419698,0.0022292736,0.00031891407,0.000103925864,0.00008663406,0.000010988248,0.07299525],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9961377,0.0001528082,0.0006674715,0.0004972061,0.0022603066,0.0002845461],"domain_scores_gemma":[0.99844366,0.00031994254,0.00019884025,0.0005214562,0.0003637869,0.00015232232],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0013391671,0.00017109969,0.00014995685,0.00036392303,0.00040378715,0.00022256844,0.0006280534,0.000052791213,0.010668965],"category_scores_gemma":[0.00029836,0.00015375952,0.0001035692,0.00063770957,0.00014046527,0.00071597856,0.000052493946,0.00012845654,0.0058911876],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017209812,0.0012805741,0.3313095,0.00006103741,0.00014150565,0.000039284274,0.0035098374,0.00026759348,0.00008938196,0.3442714,0.2991565,0.019701295],"study_design_scores_gemma":[0.000489855,0.00011149423,0.8568371,0.000015819629,0.00001704162,0.000057996516,0.016105304,0.00041583955,0.0001765145,0.014382195,0.11111086,0.00027999558],"about_ca_topic_score_codex":0.000006797035,"about_ca_topic_score_gemma":0.00008174845,"teacher_disagreement_score":0.5255276,"about_ca_system_score_codex":0.00012571608,"about_ca_system_score_gemma":0.00038241953,"threshold_uncertainty_score":0.9948828},"labels":[],"label_agreement":null},{"id":"W2084255127","doi":"10.1002/yd.216","title":"Using evaluation to improve program quality based on the BELL model","year":2007,"lang":"en","type":"article","venue":"New Directions for Youth Development","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bell (Canada)","funders":"","keywords":"Program evaluation; Process (computing); Computer science; Process management; Business; Political science","score_opus":0.5993267681160669,"score_gpt":0.5823467472478094,"score_spread":0.01698002086825745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084255127","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2761507,0.000009682472,0.70612985,0.0018514846,0.0009553715,0.0032541705,0.000018098704,0.00010086064,0.0115297865],"genre_scores_gemma":[0.8363537,4.5706813e-7,0.1593027,0.0012897302,0.00010305679,0.00032838326,0.000022377435,0.000014161979,0.0025854378],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99592125,0.0001443,0.00081743277,0.00046927514,0.0022831808,0.00036453552],"domain_scores_gemma":[0.99742633,0.0007123158,0.00023732879,0.000497612,0.00094441086,0.00018197992],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0211298,0.00016151881,0.000165654,0.0003427644,0.00085490424,0.00021342431,0.00031550226,0.00006482789,0.00024404308],"category_scores_gemma":[0.0017544371,0.00010490041,0.0001015099,0.00094410795,0.000022261314,0.00018839339,0.000049961014,0.00010508645,0.00010408484],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011603211,0.00020652711,0.0010835953,0.0000029322748,0.000016699803,3.955993e-8,0.004186475,0.094863005,0.0003111237,0.00073634216,0.0012938685,0.89718336],"study_design_scores_gemma":[0.00088668097,0.00014273557,0.019993972,0.000025340772,0.000037198206,2.3368337e-7,0.0022137347,0.93184763,0.006562229,0.0017558355,0.03625675,0.00027765718],"about_ca_topic_score_codex":0.000055436994,"about_ca_topic_score_gemma":0.0004687308,"teacher_disagreement_score":0.8969057,"about_ca_system_score_codex":0.00054438476,"about_ca_system_score_gemma":0.0017219211,"threshold_uncertainty_score":0.73232096},"labels":[],"label_agreement":null},{"id":"W208579925","doi":"","title":"Health Action Theatre by Seniors: Community Development and Education with Groups of Diverse Languages and Cultures.","year":2002,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Facilitator; Participatory action research; Action (physics); Citizen journalism; Health care; Oppression; Public relations; Literacy; Health literacy; Sociology; Variety (cybernetics); Nursing; Pedagogy; Psychology; Medicine; Political science; Social psychology; Computer science","score_opus":0.14171339054055376,"score_gpt":0.47823031049161335,"score_spread":0.3365169199510596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W208579925","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9875742,0.00031237848,0.00023483748,0.001823444,0.000028258331,0.00011826303,0.0000037100579,0.000010861379,0.00989404],"genre_scores_gemma":[0.9947805,0.00015896847,0.0021054351,0.0004331851,0.000008306224,0.000004753252,0.000011051779,0.0000019203708,0.0024959273],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9990658,0.00017202442,0.00018537634,0.00009748215,0.00041410883,0.00006520222],"domain_scores_gemma":[0.9994793,0.00010895174,0.00011947734,0.00013950357,0.00009469088,0.000058087717],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009689543,0.00005728044,0.00010334986,0.000060416027,0.00023260189,0.00005215187,0.00007341459,0.00002038119,0.0004117012],"category_scores_gemma":[0.000022837825,0.0000327675,0.000006656053,0.00013797086,0.000047651254,0.0002450639,0.000033163764,0.000074531374,0.000011398077],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010724812,0.00016398735,0.06883085,0.000017861239,0.000008453405,4.2612115e-8,0.016545122,0.0000037686884,0.00011441913,0.00017499339,0.039280504,0.87484926],"study_design_scores_gemma":[0.0012635767,0.00047720515,0.5616787,0.000079699756,0.000012378381,0.000025413063,0.32164854,0.0010575067,0.002885175,0.00054815796,0.11004055,0.00028308193],"about_ca_topic_score_codex":0.0003641762,"about_ca_topic_score_gemma":0.0013130947,"teacher_disagreement_score":0.8745662,"about_ca_system_score_codex":0.000027125921,"about_ca_system_score_gemma":0.000062100466,"threshold_uncertainty_score":0.45078394},"labels":[],"label_agreement":null},{"id":"W2086956653","doi":"10.1111/j.1741-1130.2008.00197.x","title":"Utility of Logic Models to Plan Quality of Life Outcome Evaluations","year":2009,"lang":"en","type":"article","venue":"Journal of Policy and Practice in Intellectual Disabilities","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Surrey Place Centre","funders":"","keywords":"Logic model; Agency (philosophy); Service (business); Process management; Plan (archaeology); Service delivery framework; Quality (philosophy); Outcome (game theory); Computer science; Quality of life (healthcare); Management science; Knowledge management; Risk analysis (engineering); Operations management; Business; Nursing; Medicine; Engineering; Marketing; Sociology","score_opus":0.6912627560750403,"score_gpt":0.6255451003056898,"score_spread":0.06571765576935051,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086956653","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94990623,0.0002219793,0.0039213244,0.017620547,0.00011404531,0.00018049876,0.000026942922,0.0000028447441,0.028005602],"genre_scores_gemma":[0.9965121,0.00012172418,0.0015293562,0.0015341035,0.00007981853,0.0000016029549,5.126778e-7,0.0000025571076,0.00021819692],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9940058,0.0016878786,0.002467229,0.00015805651,0.0015221104,0.00015889916],"domain_scores_gemma":[0.8723067,0.12381869,0.0014727447,0.00040868198,0.0017925263,0.0002006797],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017996298,0.00011419868,0.000559565,0.0005336122,0.000056590154,0.000062195366,0.0003531284,0.000067694586,0.0010294804],"category_scores_gemma":[0.5350102,0.00007919663,0.00013672607,0.00073257025,0.00021806535,0.00114099,0.000053628824,0.0002489723,0.000009774313],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0070874454,0.0024488447,0.045651376,0.00013160634,0.0001247294,9.839895e-7,0.62965065,0.025399007,0.00080476445,0.20315796,0.0071359267,0.07840667],"study_design_scores_gemma":[0.0010013469,0.0019811082,0.09000109,0.00007431438,0.000044507997,0.000031548254,0.3807218,0.007565599,0.0003157906,0.51551193,0.0025412312,0.0002097493],"about_ca_topic_score_codex":0.00033020086,"about_ca_topic_score_gemma":0.0001665184,"teacher_disagreement_score":0.5170139,"about_ca_system_score_codex":0.00005150218,"about_ca_system_score_gemma":0.00080766244,"threshold_uncertainty_score":0.9998837},"labels":[],"label_agreement":null},{"id":"W2087913318","doi":"10.1353/cpr.0.0004","title":"Inspiring Knowledge Mobilization Through a Communications Policy: The Case of a Community University Research Alliance","year":2007,"lang":"en","type":"article","venue":"Progress in community health partnerships","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Centre for Addiction and Mental Health","funders":"","keywords":"Alliance; Empowerment; Participatory action research; Stakeholder; Mental health; Public relations; Community mobilization; Community-based participatory research; Knowledge management; Citizen journalism; Bridge (graph theory); Political science; Sociology; Psychology; Medicine; Computer science","score_opus":0.7993981571009401,"score_gpt":0.6700554823389523,"score_spread":0.1293426747619878,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087913318","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94055027,0.0032095448,0.002185583,0.029654698,0.00011343261,0.0015055111,0.000022976441,0.00007150972,0.022686489],"genre_scores_gemma":[0.99655086,0.0005520982,0.002229742,0.0004452398,0.000030186975,0.000025318486,0.000018533401,0.000012246166,0.00013575707],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9630936,0.033741105,0.001246539,0.00019551288,0.0010151863,0.0007081067],"domain_scores_gemma":[0.9753471,0.018270493,0.00058470684,0.004163206,0.0014544242,0.00018008582],"candidate_categories":["metaresearch","sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.10848028,0.00015738497,0.00036219246,0.000540324,0.0047462718,0.00010286288,0.0037891888,0.00012672723,0.000028153134],"category_scores_gemma":[0.0035510072,0.00012598603,0.000074998716,0.005374237,0.0020228063,0.0005571032,0.0017638931,0.0032767393,0.000033465487],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020987519,0.0030213688,0.3037305,0.00031997365,0.000026533495,0.000013135001,0.2843894,0.0001520182,0.0000049638384,0.17318052,0.0013414354,0.23361027],"study_design_scores_gemma":[0.0021893082,0.0009220865,0.2038574,0.0006270627,0.000012487371,0.000104413426,0.55175835,0.010757061,0.00018518114,0.039836984,0.18933779,0.00041185966],"about_ca_topic_score_codex":0.013052693,"about_ca_topic_score_gemma":0.32056504,"teacher_disagreement_score":0.30751234,"about_ca_system_score_codex":0.00077494443,"about_ca_system_score_gemma":0.0015807975,"threshold_uncertainty_score":0.9990227},"labels":[],"label_agreement":null},{"id":"W2088547373","doi":"10.1258/1355819054308576","title":"Systematically reviewing qualitative and quantitative evidence to inform management and policy-making in the health field","year":2005,"lang":"en","type":"review","venue":"Journal of Health Services Research & Policy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1384,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Service Delivery and Organisation Programme; Canadian Health Services Research Foundation","keywords":"Management science; Qualitative research; Narrative; Thematic analysis; Computer science; Systematic review; Psychological intervention; Knowledge management; Data science; Sociology; MEDLINE; Medicine; Political science; Social science; Nursing; Economics","score_opus":0.7490632737818417,"score_gpt":0.7650935679213311,"score_spread":0.01603029413948942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2088547373","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005489775,0.9038398,0.00019285223,0.09249664,0.000053515756,0.0024084016,0.00000840733,0.0000031279699,0.000942338],"genre_scores_gemma":[0.001025162,0.98112816,0.0034723273,0.013823597,0.00030679128,0.0000919478,0.0000011037217,0.000014949382,0.0001359434],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9741814,0.013238759,0.0053713955,0.00046232753,0.0057722717,0.0009738437],"domain_scores_gemma":[0.97279984,0.020990716,0.0035124565,0.00071737566,0.0014581624,0.0005214397],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.14367896,0.00031603588,0.002344802,0.0043151644,0.00065036066,0.000851533,0.0017085364,0.000107041196,0.00003540324],"category_scores_gemma":[0.0058091353,0.00016727656,0.00018977634,0.005296538,0.000091945614,0.001002008,0.0005587741,0.0012515385,0.00005563728],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002204947,0.00002600142,0.000009851327,0.03772283,0.00003504739,0.0000042829865,0.08474569,0.0000046891523,3.498952e-9,0.01339564,0.0007633883,0.8632705],"study_design_scores_gemma":[0.00017383814,0.0015249003,0.00031088368,0.15332043,0.000018166866,0.00009258556,0.07202397,0.00014062785,6.300476e-9,0.0027990337,0.76945823,0.0001373482],"about_ca_topic_score_codex":0.0012671998,"about_ca_topic_score_gemma":0.00104022,"teacher_disagreement_score":0.8631332,"about_ca_system_score_codex":0.0012209862,"about_ca_system_score_gemma":0.0052947565,"threshold_uncertainty_score":0.9392671},"labels":[],"label_agreement":null},{"id":"W2089532943","doi":"10.1177/1477878506064723","title":"Book Review: Evidence-Based Practice in Education","year":2006,"lang":"en","type":"article","venue":"Theory and Research in Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Engineering ethics; Sociology; Pedagogy; Psychology; Engineering","score_opus":0.26466898268151334,"score_gpt":0.6349895069017699,"score_spread":0.3703205242202566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2089532943","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06168528,0.7645255,0.000112074915,0.12401313,0.0007465852,0.0014022964,0.0000010354955,0.00001392778,0.047500186],"genre_scores_gemma":[0.7885041,0.13730668,0.00079397013,0.03747069,0.00055019895,0.00083242037,0.000032678323,0.000015193797,0.034494042],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99265534,0.00488541,0.0005242471,0.00033092452,0.0013824919,0.00022160441],"domain_scores_gemma":[0.9905638,0.008019312,0.00013414213,0.0003921012,0.0008270267,0.00006359101],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05246404,0.000071140545,0.0001260143,0.0007562038,0.00013002717,0.00014791448,0.00027037415,0.000049874343,0.0015330573],"category_scores_gemma":[0.011792908,0.000053621865,0.000020473253,0.0014983763,0.0001342313,0.0014320053,0.00003661815,0.00030450654,0.00022699028],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018939248,0.001033341,0.0053620916,0.00015806255,0.0000011894193,7.1298297e-7,0.0006905992,0.000098887234,0.00014492395,0.0495843,0.38792092,0.5548156],"study_design_scores_gemma":[0.0001794404,0.0000737127,0.038217075,0.0021605436,0.0000040696245,0.000003995648,0.0037948408,0.00028346543,0.00020945397,0.13670732,0.8182667,0.00009941458],"about_ca_topic_score_codex":0.00024111918,"about_ca_topic_score_gemma":0.000055903303,"teacher_disagreement_score":0.72681886,"about_ca_system_score_codex":0.00019284057,"about_ca_system_score_gemma":0.0035364206,"threshold_uncertainty_score":0.9993797},"labels":[],"label_agreement":null},{"id":"W2089680994","doi":"10.1017/s0008423912000984","title":"Policy Work in Multi-Level States: Institutional Autonomy and Task Allocation among Canadian Policy Analysts","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Political Science","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Autonomy; Work (physics); Government (linguistics); Political science; Public administration; Principal (computer security); Public policy; Public economics; Policy analysis; Distribution (mathematics); Economics; Computer science; Law","score_opus":0.1942261877820189,"score_gpt":0.4646403145276306,"score_spread":0.2704141267456117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2089680994","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97960085,0.00007227311,0.0015008295,0.015155355,0.00036286534,0.000114897026,0.000039120023,0.0000024928747,0.003151316],"genre_scores_gemma":[0.9960538,0.0000035255584,0.0013202738,0.0020863707,0.00027272286,0.0000025987476,0.0000020938887,0.0000040818945,0.00025452382],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9964783,0.00013301634,0.00072051364,0.00021652202,0.0010657015,0.0013859471],"domain_scores_gemma":[0.99304247,0.00020801551,0.00018547723,0.00021441709,0.0006841414,0.005665459],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00683438,0.00012463624,0.00021175013,0.003591635,0.00047041275,0.0004048837,0.00069809105,0.000068801695,0.00020349176],"category_scores_gemma":[0.006057909,0.00009831235,0.000049805443,0.0034957516,0.0013361389,0.0018756173,0.000031753647,0.00025146277,0.00005510203],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000002214548,0.000015285932,0.692602,0.0000014020234,0.0000037495329,0.000009451312,0.0018983084,0.0005632416,0.000012702172,0.29754812,0.00012822634,0.007215315],"study_design_scores_gemma":[0.00023182739,0.000022614839,0.98908156,0.000029980412,0.000004096946,0.00004156417,0.0007463366,0.0030463364,0.000018531893,0.0031327244,0.003527892,0.000116545736],"about_ca_topic_score_codex":0.70580715,"about_ca_topic_score_gemma":0.8568187,"teacher_disagreement_score":0.29647955,"about_ca_system_score_codex":0.003984357,"about_ca_system_score_gemma":0.056958634,"threshold_uncertainty_score":0.9998392},"labels":[],"label_agreement":null},{"id":"W2090535596","doi":"10.1016/j.respe.2013.03.037","title":"Pragmatisme et réalisme pour l’évaluation des interventions de santé publique","year":2013,"lang":"fr","type":"review","venue":"Revue d Épidémiologie et de Santé Publique","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":25,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; Université de Montréal","funders":"","keywords":"Psychological intervention; Context (archaeology); Fidelity; Psychology; Public health; Management science; Medicine; Nursing; Computer science; Engineering","score_opus":0.3284066098860767,"score_gpt":0.5351979809226327,"score_spread":0.20679137103655604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2090535596","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014029278,0.60648507,0.29200262,0.035723913,0.003340478,0.0065105204,0.0006869966,0.0006250157,0.040596098],"genre_scores_gemma":[0.0123826135,0.889987,0.07294196,0.006187424,0.0013029303,0.003031947,0.0011751808,0.00018541269,0.012805548],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.96050984,0.02757968,0.0055320067,0.0022576025,0.0018172368,0.0023036383],"domain_scores_gemma":[0.97482955,0.014552497,0.004139571,0.0025698484,0.0029749882,0.000933557],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"category_scores_codex":[0.07029368,0.0016073803,0.0035520266,0.001989256,0.00070686865,0.0030036562,0.003729055,0.0022739384,0.01751389],"category_scores_gemma":[0.0501255,0.0013161078,0.0026772493,0.0028519176,0.00070786424,0.004725274,0.0011962634,0.0031916797,0.0034952697],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001934529,0.0006105676,0.0078064487,0.006423716,0.00035385997,0.000038336028,0.0021661029,0.0012035453,0.000037811784,0.08660801,0.027906625,0.86682564],"study_design_scores_gemma":[0.0010386037,0.0007743867,0.06524334,0.021710686,0.0008020888,0.0009893145,0.0012215403,0.023950912,0.000029397006,0.15246736,0.72971857,0.0020538098],"about_ca_topic_score_codex":0.00090056896,"about_ca_topic_score_gemma":0.001121366,"teacher_disagreement_score":0.86477184,"about_ca_system_score_codex":0.00375389,"about_ca_system_score_gemma":0.024802485,"threshold_uncertainty_score":0.9996674},"labels":[],"label_agreement":null},{"id":"W2091267703","doi":"10.1111/j.1467-9620.2005.00594.x","title":"Toward an Evaluation Habit of Mind: Mapping the Journey","year":2005,"lang":"en","type":"article","venue":"Teachers College Record The Voice of Scholarship in Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Mindset; Context (archaeology); Meaning (existential); Habit; Psychology; Epistemology; Principal (computer security); Meaning-making; Publication; Cognition; Sociology; Pedagogy; Social psychology; Political science; Computer science","score_opus":0.35309932199417465,"score_gpt":0.48526479680984064,"score_spread":0.13216547481566598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2091267703","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9798701,0.000459639,0.00011764519,0.012425062,0.0006981014,0.0007975637,0.00000525857,0.0000069642224,0.005619671],"genre_scores_gemma":[0.99468863,0.00005400211,0.00368275,0.00030963405,0.00022719626,0.00009571421,0.0000071626205,0.000010527411,0.0009243959],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9941204,0.00213053,0.0011318186,0.0003101893,0.0021055127,0.0002015278],"domain_scores_gemma":[0.99598444,0.0011115482,0.00091678894,0.00083438953,0.0010817557,0.00007110558],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.035429467,0.00014015728,0.00024203234,0.0004806711,0.0001962761,0.000121211815,0.0011543444,0.00010295773,0.0009563007],"category_scores_gemma":[0.0037637851,0.00008420928,0.00010050298,0.0015855876,0.00013175941,0.0014487403,0.00005626843,0.00045578543,0.00009732409],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053021995,0.00043955795,0.10790067,0.0000082351635,0.00001730603,4.1979284e-8,0.025900483,0.0012187032,0.0011111367,0.00087938196,0.001155412,0.861316],"study_design_scores_gemma":[0.000791895,0.00015411919,0.81520325,0.00015384582,0.000058247908,0.0000073414626,0.10404365,0.026107663,0.0018193406,0.015951967,0.035500154,0.00020852241],"about_ca_topic_score_codex":0.00012440978,"about_ca_topic_score_gemma":0.0010204609,"teacher_disagreement_score":0.8611075,"about_ca_system_score_codex":0.00035678924,"about_ca_system_score_gemma":0.0016871475,"threshold_uncertainty_score":0.99995697},"labels":[],"label_agreement":null},{"id":"W2091274395","doi":"10.1177/105756770201200130","title":"Book Review: Harmonization in Forensic Expertise: An Inquiry Into the Desirability of and Opportunities for International Standards.","year":2002,"lang":"en","type":"article","venue":"International Criminal Justice Review","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Government of Ontario","funders":"","keywords":"Harmonization; Forensic science; Engineering ethics; Political science; Psychology; Law; Criminology; Sociology; Medicine; Engineering; Philosophy; Veterinary medicine","score_opus":0.508653172114449,"score_gpt":0.5367581659919508,"score_spread":0.02810499387750176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2091274395","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0058405143,0.9195662,0.013199377,0.056233734,0.0015032107,0.0013717593,0.000074719435,0.000019055731,0.0021914165],"genre_scores_gemma":[0.042189345,0.9156526,0.001183855,0.03972044,0.00023897142,0.00020689065,0.000060080303,0.00001190708,0.0007359208],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962157,0.00032433346,0.0012108972,0.0003361676,0.0017815059,0.00013139083],"domain_scores_gemma":[0.9956664,0.0007451044,0.00049799646,0.0003502626,0.0026681996,0.000072076946],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006136614,0.00014586558,0.00034536418,0.00015867905,0.0000909478,0.00009062901,0.0006927982,0.000036619986,0.0033842702],"category_scores_gemma":[0.005998137,0.0000966876,0.000100322235,0.00017543876,0.00019595468,0.00091837597,0.00010627735,0.00010551513,0.0000092923865],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004455186,0.00011713209,0.00027146278,0.0029556924,0.0000240061,0.0000025384015,0.0033526726,0.00003440616,0.000014238661,0.0020061526,0.18634123,0.8048359],"study_design_scores_gemma":[0.00043102304,0.00014987134,0.00096909434,0.0049774763,0.00031502775,0.000019629853,0.0032488815,0.03528215,0.000059893326,0.00074201263,0.95362824,0.00017670121],"about_ca_topic_score_codex":0.00001116903,"about_ca_topic_score_gemma":0.000024154273,"teacher_disagreement_score":0.80465925,"about_ca_system_score_codex":0.00016916155,"about_ca_system_score_gemma":0.00011928046,"threshold_uncertainty_score":0.99752676},"labels":[],"label_agreement":null},{"id":"W2092754277","doi":"10.1177/1049732305284080","title":"The Politics of Developing Research Methods","year":2005,"lang":"en","type":"editorial","venue":"Qualitative Health Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Politics; Psychology; Sociology; Political science; Law","score_opus":0.934498547462301,"score_gpt":0.8566156616393253,"score_spread":0.07788288582297564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2092754277","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020575667,0.015340225,0.013083893,0.14807552,0.79215556,0.0036185405,0.0005119544,0.0000491551,0.026959375],"genre_scores_gemma":[0.00026619574,0.0113158915,0.09049813,0.0003242246,0.77851695,0.0006189938,0.00014062486,0.000102541904,0.11821645],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.6117638,0.30054888,0.0076250634,0.0024392088,0.07243682,0.005186261],"domain_scores_gemma":[0.40499187,0.54722464,0.0013223344,0.0023297041,0.043492697,0.0006387368],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6495502,0.00028354797,0.0009978254,0.0021373725,0.0043007787,0.0006702277,0.003576166,0.0006056601,0.00035744443],"category_scores_gemma":[0.29645085,0.00017091965,0.00018447303,0.0053001265,0.0024690335,0.00028152496,0.0010242582,0.0059004696,0.0008225533],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046493333,0.000034141398,0.0000033167614,0.00013211879,0.000025108668,3.7660664e-7,0.035790965,0.0000028992572,0.0000020568975,0.05433946,0.8057071,0.103916],"study_design_scores_gemma":[0.00023250237,0.000467549,0.000048041493,0.00019508436,0.0000013251206,1.8458199e-7,0.07738056,0.0002122875,0.000044777826,0.116034135,0.8052563,0.00012726561],"about_ca_topic_score_codex":0.0011223684,"about_ca_topic_score_gemma":0.00089980237,"teacher_disagreement_score":0.35309938,"about_ca_system_score_codex":0.0023872438,"about_ca_system_score_gemma":0.041721135,"threshold_uncertainty_score":0.9999554},"labels":[],"label_agreement":null},{"id":"W2093062308","doi":"10.1177/1356389012442445","title":"A socio-political framework for evaluability assessment of participatory evaluations of partnerships: Making sense of the power differentials in programs that involve the state and civil society","year":2012,"lang":"en","type":"article","venue":"Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; University of Ottawa","funders":"","keywords":"General partnership; Citizen journalism; Participatory evaluation; Politics; Public relations; Civil society; Participatory action research; Power (physics); State (computer science); Political science; Public administration; Sociology; Computer science","score_opus":0.5679951806189625,"score_gpt":0.5888862518149395,"score_spread":0.020891071195976996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2093062308","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.985726,0.00019095182,0.009451217,0.0017517401,0.00030689852,0.002307969,0.000027476279,0.0000050911863,0.00023265649],"genre_scores_gemma":[0.996661,0.0000067858236,0.0026688022,0.00014159708,0.000036528752,0.00045059464,0.0000073354904,0.000009496822,0.000017823168],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99113566,0.0030960995,0.0012758508,0.00030565483,0.003780151,0.00040659108],"domain_scores_gemma":[0.9924256,0.0043313988,0.0009870699,0.0007152928,0.001469915,0.00007070656],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.047197003,0.00015518868,0.0003871417,0.00007841457,0.00016912995,0.00004924174,0.0002737185,0.00011591106,0.0004916904],"category_scores_gemma":[0.005120374,0.000087166256,0.00025866248,0.0004930697,0.00052802195,0.00033359128,0.00014065468,0.00019942789,0.0000017277173],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039265975,0.0004748185,0.9385109,0.000071084694,0.00006529143,7.200268e-9,0.019447044,0.0006740426,0.0004842955,0.03284596,0.00009421614,0.0072930665],"study_design_scores_gemma":[0.0006107047,0.00010268879,0.7568241,0.0001066052,0.00015584391,2.9394604e-7,0.008235553,0.10450143,0.0009003061,0.12844557,0.000035672394,0.000081244514],"about_ca_topic_score_codex":0.0000116285655,"about_ca_topic_score_gemma":0.00011421087,"teacher_disagreement_score":0.18168682,"about_ca_system_score_codex":0.0002152437,"about_ca_system_score_gemma":0.0007585249,"threshold_uncertainty_score":0.98111117},"labels":[],"label_agreement":null},{"id":"W2093407124","doi":"10.1016/j.evalprogplan.2010.08.002","title":"Participatory evaluation and process use within a social aid organization for at-risk families and youth","year":2010,"lang":"en","type":"article","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Citizen journalism; Participatory action research; Process (computing); Participatory evaluation; Theme (computing); Sociology; Participant observation; Empirical research; Public relations; Psychology; Political science; Social science; Computer science","score_opus":0.34576509372296227,"score_gpt":0.5476790976864736,"score_spread":0.20191400396351133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2093407124","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99662656,0.00017549687,0.0006008223,0.00029330928,0.0002746687,0.0017332189,0.00003093022,0.00007546806,0.00018953363],"genre_scores_gemma":[0.99730426,0.000017628363,0.001884491,0.00013555802,0.00012159678,0.0002484496,0.00021172283,0.000016220896,0.000060057595],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968404,0.00041561818,0.00051737926,0.00042178185,0.0016059319,0.0001988892],"domain_scores_gemma":[0.99713737,0.00044320436,0.0004466407,0.00015560449,0.0017046666,0.00011249724],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013310392,0.00016137544,0.00019751054,0.0001988414,0.0009905681,0.0006955895,0.000090849586,0.00013261581,0.00019757594],"category_scores_gemma":[0.0054175328,0.00013069631,0.000022534425,0.00042495114,0.00015698744,0.0008182363,0.000056340887,0.00016583301,0.0000061498413],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010899403,0.0000567005,0.59748423,0.000024874762,0.000025111676,8.9342144e-8,0.07449862,0.00064254797,0.0002679749,0.00038375097,0.0001572382,0.32634988],"study_design_scores_gemma":[0.0025252402,0.0002387971,0.47087482,0.00003278838,0.00029092032,0.000006512073,0.018224714,0.501808,0.00038505468,0.0040667616,0.0012797643,0.00026666193],"about_ca_topic_score_codex":0.000013109172,"about_ca_topic_score_gemma":0.00009879449,"teacher_disagreement_score":0.5011654,"about_ca_system_score_codex":0.000033610282,"about_ca_system_score_gemma":0.00021759997,"threshold_uncertainty_score":0.7618749},"labels":[],"label_agreement":null},{"id":"W2093433911","doi":"10.1332/174426410x535846","title":"Correlates of consulting research evidence among policy analysts in government ministries: a cross-sectional survey","year":2010,"lang":"en","type":"article","venue":"Evidence & Policy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université du Québec à Montréal; Université TÉLUQ; McMaster University; École Nationale d'Administration Publique; Université Laval","funders":"Canada Research Chairs","keywords":"Predictive power; Cross-sectional study; Relevance (law); Government (linguistics); Psychology; Survey research; Power (physics); Political science; Applied psychology; Medicine","score_opus":0.49555548149098944,"score_gpt":0.6255825139166528,"score_spread":0.13002703242566332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2093433911","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9958244,0.00017350192,0.000059287184,0.0016263966,0.00031451703,0.00037617903,0.000046060428,0.000016797705,0.0015628622],"genre_scores_gemma":[0.99646753,0.00017091876,0.00018274783,0.00013783702,0.00034106214,0.000052053067,0.000003300502,0.0000125626175,0.002631974],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98902744,0.0015184282,0.0017531512,0.0007750505,0.00624409,0.00068183924],"domain_scores_gemma":[0.97008806,0.025150241,0.0008210645,0.0012176149,0.0024283018,0.0002947102],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.044409245,0.00021156143,0.00042399336,0.0010769989,0.00035831134,0.00060704304,0.0015101058,0.00020084938,0.0011277406],"category_scores_gemma":[0.20993158,0.00017328365,0.0001347285,0.0057434924,0.0011745101,0.0018075313,0.00045879884,0.0008837138,0.00032094668],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012360241,0.00006264372,0.99136704,0.000013355242,0.000009249601,0.0000028531847,0.0012684558,0.00045885053,0.0019306575,0.0020520475,0.00036558523,0.0023456442],"study_design_scores_gemma":[0.00028607374,0.00012578427,0.9897126,0.00023036289,0.0000022661852,0.0000070611336,0.00056285976,0.00572453,0.0010761726,0.0017833519,0.0003281603,0.00016075482],"about_ca_topic_score_codex":0.018263623,"about_ca_topic_score_gemma":0.012378131,"teacher_disagreement_score":0.16552234,"about_ca_system_score_codex":0.00053094164,"about_ca_system_score_gemma":0.003761555,"threshold_uncertainty_score":0.99978536},"labels":[],"label_agreement":null},{"id":"W2093491439","doi":"10.1037/1082-989x.7.1.126","title":"The role of qualitative research in psychological journals.","year":2002,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":183,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"PsycINFO; Qualitative research; Qualitative analysis; Psychology; Content analysis; Applied psychology; Social psychology; MEDLINE; Social science; Sociology","score_opus":0.9375029604873701,"score_gpt":0.8324841901757505,"score_spread":0.10501877031161966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2093491439","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50292,0.0072844955,0.017661711,0.021316176,0.0008823148,0.0006068209,0.000005238865,0.000033845365,0.44928944],"genre_scores_gemma":[0.9168964,0.00074873446,0.080959834,0.00033712183,0.00007302813,0.000056732246,1.9364079e-7,0.000004920134,0.00092303375],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9704429,0.02457314,0.0013574505,0.00058196485,0.0025336088,0.0005109739],"domain_scores_gemma":[0.9730021,0.025203196,0.0002902099,0.00074874086,0.0006247978,0.00013099024],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12530676,0.00011892806,0.00034813493,0.00036046666,0.00028038124,0.00016704907,0.0013761608,0.00017204358,0.0073454836],"category_scores_gemma":[0.015197282,0.000054971217,0.00014088675,0.002592566,0.0006824816,0.00016050425,0.00013593676,0.0009031989,0.0005211517],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000738244,0.0004253943,0.0032949324,5.34131e-7,0.000005033755,0.0000021725252,0.0034991915,0.0000127130725,0.0013213303,0.02033557,0.0023585174,0.9686708],"study_design_scores_gemma":[0.0004234338,0.00059199013,0.09659927,0.000012834333,0.0000016088486,0.000010713997,0.01230831,0.0026390464,0.00027371864,0.83308357,0.0539583,0.000097227006],"about_ca_topic_score_codex":0.000004991409,"about_ca_topic_score_gemma":0.0000053681483,"teacher_disagreement_score":0.9685736,"about_ca_system_score_codex":0.00003620322,"about_ca_system_score_gemma":0.000008418303,"threshold_uncertainty_score":0.9935619},"labels":[],"label_agreement":null},{"id":"W2094453063","doi":"10.1007/s00003-014-0897-5","title":"Science into policy; improving uptake and adoption of research: outcomes and conclusions","year":2014,"lang":"de","type":"article","venue":"Journal of Consumer Protection and Food Safety","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Nuclear Safety Commission; Canadian Food Inspection Agency","funders":"","keywords":"Science policy; Psychology; Political science; Public administration","score_opus":0.1685392461029831,"score_gpt":0.4675757979327029,"score_spread":0.2990365518297198,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2094453063","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96305066,0.0051682037,0.017164227,0.012036587,0.0010098418,0.000752026,0.000011898376,0.00001007964,0.0007964965],"genre_scores_gemma":[0.9948071,0.0031128328,0.0016664858,0.00013159795,0.00014931288,0.0000036818203,2.771159e-7,0.0000072869093,0.00012137891],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99552673,0.0006427313,0.0012319763,0.00031663716,0.002003838,0.00027809318],"domain_scores_gemma":[0.99569273,0.0007307473,0.0009990771,0.00024832808,0.0019881697,0.00034096604],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02241775,0.00015949155,0.00045817715,0.0017973091,0.001215537,0.00033080424,0.00024324775,0.00012278031,0.000048855793],"category_scores_gemma":[0.0048774164,0.00011252669,0.00007104368,0.0013409527,0.0016560709,0.0009282308,0.00032271264,0.00058754004,0.000006864341],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036774113,0.000107725835,0.020203386,0.00013701728,0.00008686241,6.639671e-7,0.0038716784,0.000026080615,0.010058647,0.01480255,0.000038516795,0.95029914],"study_design_scores_gemma":[0.007015191,0.009848902,0.7858928,0.00080002117,0.0002257979,0.00026755733,0.012589989,0.030997653,0.0020947407,0.023382315,0.12633672,0.00054829766],"about_ca_topic_score_codex":0.00008682894,"about_ca_topic_score_gemma":0.000054570966,"teacher_disagreement_score":0.94975084,"about_ca_system_score_codex":0.00010488073,"about_ca_system_score_gemma":0.0013834721,"threshold_uncertainty_score":0.934905},"labels":[],"label_agreement":null},{"id":"W2094647050","doi":"10.7202/1024965ar","title":"L’implication des détenteurs d’enjeux (stakeholders) au sein de la démarche d’évaluation de programme: problème et/ou solution ?","year":2014,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Humanities; Philosophy; Physics","score_opus":0.4473959198716816,"score_gpt":0.5297977442965724,"score_spread":0.08240182442489086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2094647050","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31820548,0.0005321912,0.56533766,0.1021939,0.0014925003,0.0019573898,0.000021124519,0.00019190482,0.010067849],"genre_scores_gemma":[0.93818504,0.00061870087,0.049551677,0.0013507835,0.00061905524,0.00082097476,0.0007343955,0.00008601267,0.00803334],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.95469004,0.037082873,0.0019037443,0.0013382339,0.0037028275,0.0012822604],"domain_scores_gemma":[0.98960304,0.0050049233,0.0012947307,0.0011106763,0.0025761772,0.00041046462],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.18356486,0.00057578075,0.00050274644,0.0007504568,0.0008881546,0.0011168991,0.0007364791,0.00068157853,0.0012141785],"category_scores_gemma":[0.018270733,0.00058908394,0.0002922806,0.0015947566,0.00050489226,0.002558246,0.00012099736,0.0008355211,0.00092098414],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00007829505,0.0009888776,0.03572078,0.00020937517,0.000075539945,5.07399e-7,0.10739989,0.020709757,0.008650501,0.05041939,0.007368581,0.7683785],"study_design_scores_gemma":[0.0014456443,0.0003259253,0.5735787,0.0002766576,0.00024288589,0.000045564513,0.003711646,0.27699795,0.0017326969,0.09533352,0.04578635,0.0005224689],"about_ca_topic_score_codex":0.0012439393,"about_ca_topic_score_gemma":0.0017737441,"teacher_disagreement_score":0.76785606,"about_ca_system_score_codex":0.0041956594,"about_ca_system_score_gemma":0.013585659,"threshold_uncertainty_score":0.99992},"labels":[],"label_agreement":null},{"id":"W2094920704","doi":"10.1016/j.evalprogplan.2010.11.007","title":"Short-term consultancy and collaborative evaluation in a post-conflict and humanitarian setting: Lessons from Afghanistan","year":2010,"lang":"en","type":"article","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Centre Hospitalier de l’Université de Montréal","funders":"","keywords":"Process (computing); Strengths and weaknesses; Process management; Public relations; Term (time); sort; Political science; Business; Psychology; Computer science; Social psychology","score_opus":0.18804525281371393,"score_gpt":0.5408853601456034,"score_spread":0.3528401073318895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2094920704","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9912779,0.001509821,0.00006527945,0.0017423226,0.00025606208,0.0016669439,0.000049367125,0.000045137593,0.0033872204],"genre_scores_gemma":[0.99600524,0.00005615314,0.0031246692,0.00018239277,0.000075464704,0.00027406463,0.00021615431,0.0000110140345,0.000054852764],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99615824,0.00067874684,0.0006253584,0.0006247525,0.0016772307,0.00023566555],"domain_scores_gemma":[0.9970481,0.0009365062,0.00023840554,0.00026081805,0.001368118,0.00014809144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011804117,0.00020131104,0.0002648125,0.00031286944,0.00040038745,0.0008665975,0.00013525273,0.0001419049,0.0006133667],"category_scores_gemma":[0.0024300923,0.00017156205,0.000020700627,0.00048482357,0.000162244,0.0006111698,0.00007184489,0.0003256256,0.000010226072],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006651537,0.00006053898,0.21372412,0.000004898342,0.000021336307,0.0000023836276,0.015969185,0.000037579422,0.0026058548,0.0010001888,0.000115171075,0.76639223],"study_design_scores_gemma":[0.0017090262,0.00019855858,0.8477937,0.00006325771,0.00007480658,0.000007862734,0.008365591,0.13279374,0.00011394758,0.0039225807,0.0047213277,0.00023558585],"about_ca_topic_score_codex":0.00004734802,"about_ca_topic_score_gemma":0.0014738961,"teacher_disagreement_score":0.7661566,"about_ca_system_score_codex":0.00004159484,"about_ca_system_score_gemma":0.00042573735,"threshold_uncertainty_score":0.835662},"labels":[],"label_agreement":null},{"id":"W2095348549","doi":"10.1332/174426410x524866","title":"Issues in conducting and disseminating brief reviews of evidence","year":2010,"lang":"en","type":"article","venue":"Evidence & Policy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":87,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"RMIT University; Government of Canada","keywords":"Scope (computer science); Systematic review; Management science; Sample (material); Process (computing); Inclusion (mineral); Dissemination; Engineering ethics; Psychology; Political science; MEDLINE; Computer science; Engineering; Social psychology","score_opus":0.6913111467050981,"score_gpt":0.6473704541238192,"score_spread":0.04394069258127886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095348549","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9805227,0.0039037098,0.000053674936,0.013784283,0.00018398273,0.00028336188,9.4385035e-7,0.000011622375,0.0012557231],"genre_scores_gemma":[0.9920931,0.0033683514,0.0023912978,0.0004542448,0.00021888068,0.000020859892,2.404413e-7,0.000005764476,0.0014472492],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99703765,0.0003546196,0.0010262941,0.00037986095,0.0009529521,0.00024859555],"domain_scores_gemma":[0.99519014,0.0033067807,0.0005348082,0.0005702669,0.0002977209,0.000100257595],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014207094,0.00012709679,0.0003824194,0.00035658857,0.00009714513,0.00016029394,0.000541991,0.00006014408,0.00087555626],"category_scores_gemma":[0.0759248,0.00008306971,0.00005649229,0.001117962,0.00018707839,0.0018254316,0.00017152843,0.00027474877,0.000084172105],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013095021,0.000030157364,0.41285273,0.00008142546,0.000002404803,0.0000019011158,0.00927082,0.000018497796,0.08480362,0.006200483,0.0018321025,0.48489276],"study_design_scores_gemma":[0.00049352454,0.00031242947,0.8481088,0.0061940737,0.000024020712,0.00005506532,0.004855383,0.006846761,0.03788946,0.019017827,0.07550552,0.0006971193],"about_ca_topic_score_codex":0.0011536562,"about_ca_topic_score_gemma":0.0007610927,"teacher_disagreement_score":0.48419562,"about_ca_system_score_codex":0.000026853111,"about_ca_system_score_gemma":0.00025002362,"threshold_uncertainty_score":0.9586727},"labels":[],"label_agreement":null},{"id":"W2096072880","doi":"10.7202/706562ar","title":"Pour une évaluation sensible à l’environnement des interventions : l’analyse de l’implantation","year":2005,"lang":"fr","type":"article","venue":"Service social","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.31980196490372814,"score_gpt":0.5136415366732641,"score_spread":0.19383957176953592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096072880","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7675052,0.00087026047,0.027069634,0.18143854,0.0008680574,0.00039728952,0.000072037474,0.000056072797,0.02172288],"genre_scores_gemma":[0.968306,0.00035681354,0.01452206,0.004217854,0.001472663,0.000037756654,0.00012350548,0.000022968423,0.010940386],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9959335,0.00084562466,0.00094679627,0.0004038774,0.0013631856,0.0005070209],"domain_scores_gemma":[0.99808294,0.00031524812,0.00044278946,0.00025820665,0.0007476107,0.00015322282],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0049039205,0.00022278859,0.00027888417,0.0002577751,0.001008812,0.00032666803,0.0003451894,0.00019299364,0.0134045],"category_scores_gemma":[0.00018537541,0.0002301435,0.00032469557,0.0013853578,0.0001274961,0.001006621,0.000108408865,0.00023500601,0.00498304],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052265932,0.00069185835,0.0071781175,0.00018645976,0.00016808404,0.0000039816373,0.034098778,0.019916078,0.0016569401,0.014197139,0.009145155,0.9127051],"study_design_scores_gemma":[0.0034557257,0.00021701626,0.41459054,0.00039537658,0.0009862336,0.000042814987,0.055795263,0.36085445,0.0016867255,0.088171415,0.07302635,0.00077809935],"about_ca_topic_score_codex":0.0020020916,"about_ca_topic_score_gemma":0.049469937,"teacher_disagreement_score":0.91192704,"about_ca_system_score_codex":0.0008713593,"about_ca_system_score_gemma":0.00089687103,"threshold_uncertainty_score":0.9957917},"labels":[],"label_agreement":null},{"id":"W2097302936","doi":"","title":"Ontario's Best Public Schools: 2009-2011","year":2012,"lang":"en","type":"preprint","venue":"RePEc: Research Papers in Economics","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mathematics education; Significant difference; Psychology; Preparatory school; Political science; Medical education; Pedagogy; Primary education; Medicine","score_opus":0.3190271172473413,"score_gpt":0.48816852434983693,"score_spread":0.16914140710249564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097302936","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5021667,0.00027129563,0.000015294207,0.00284013,0.001781318,0.0008680546,0.00005535264,0.0000292741,0.49197263],"genre_scores_gemma":[0.924274,0.0031517455,0.0012508334,0.00028238283,0.0005863964,0.00037479505,0.0000796937,0.00004899727,0.06995113],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9923727,0.00094777695,0.0016649322,0.0013976077,0.002261939,0.0013550253],"domain_scores_gemma":[0.99400675,0.0013126513,0.00053632713,0.0026754562,0.00083943846,0.0006293833],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.024430731,0.00039332107,0.0007532407,0.0015638068,0.0003325363,0.0013605539,0.0027324262,0.0006253814,0.02225801],"category_scores_gemma":[0.0024053538,0.0003496399,0.00029276323,0.00031559722,0.00027653496,0.0008592938,0.0025356335,0.0036720736,0.0038009163],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042881096,0.00031796598,0.31615785,0.000020360101,0.00005716604,0.000006572671,0.0008514671,0.0014474732,0.000011138968,0.0009180282,0.0029054587,0.6772637],"study_design_scores_gemma":[0.0006977122,0.00010568092,0.10722453,0.000097260716,0.000010203603,0.000009865475,0.0036092673,0.0059609558,0.000028992406,0.011138643,0.87046856,0.00064834236],"about_ca_topic_score_codex":0.003639438,"about_ca_topic_score_gemma":0.07756577,"teacher_disagreement_score":0.86756307,"about_ca_system_score_codex":0.0028809712,"about_ca_system_score_gemma":0.006202607,"threshold_uncertainty_score":0.9998956},"labels":[],"label_agreement":null},{"id":"W2097795869","doi":"","title":"IMPACT OF THE NOVA SCOTIA SCHOOL ACCREDITATION PROGRAM ON TEACHING AND STUDENT LEARNING: AN INITIAL STUDY","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Educational Administration and Policy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nova scotia; Accreditation; Nova (rocket); Student achievement; Medical education; Mathematics education; Academic achievement; Pedagogy; Psychology; Sociology; Medicine; Engineering","score_opus":0.2217868316452144,"score_gpt":0.5665266842348189,"score_spread":0.3447398525896045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097795869","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9928487,0.000013365153,0.0000037854418,0.0021707215,0.00025433803,0.00024630936,0.000007510421,0.0000012266061,0.004454055],"genre_scores_gemma":[0.9989867,0.0000013958354,0.000192045,0.00016426174,0.00037803032,0.0000031154495,0.0000035728312,0.000004247945,0.00026662654],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9982777,0.00043061006,0.00051890494,0.00011923695,0.00054269686,0.00011083652],"domain_scores_gemma":[0.99819684,0.00025369128,0.0004858588,0.00011574773,0.00049882743,0.00044900907],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0019297103,0.000087451815,0.0001234972,0.0004284449,0.00026173855,0.00022403715,0.00022924173,0.000032794884,0.0011287145],"category_scores_gemma":[0.002156874,0.00005531189,0.000052990275,0.00024435524,0.00009384407,0.00045992289,0.000009230291,0.00027031047,0.000009585471],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005453411,0.00057874754,0.96571416,0.0000017744677,0.00003305279,9.075202e-7,0.011464588,0.000058251157,0.000018331239,0.0050200126,0.0006546359,0.01640098],"study_design_scores_gemma":[0.0003322479,0.002769337,0.9895481,0.000012979515,0.000015251199,0.000043632906,0.0053395904,0.00004951727,0.000014040183,0.0014778879,0.00034287872,0.000054539378],"about_ca_topic_score_codex":0.0034147357,"about_ca_topic_score_gemma":0.0133786285,"teacher_disagreement_score":0.023833912,"about_ca_system_score_codex":0.000101617676,"about_ca_system_score_gemma":0.008943141,"threshold_uncertainty_score":0.9997844},"labels":[],"label_agreement":null},{"id":"W2097845821","doi":"10.1017/s0047279411000821","title":"The Discursive Turn in Policy Analysis and the Validation of Policy Stories","year":2012,"lang":"en","type":"article","venue":"Journal of Social Policy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Queen's University","keywords":"Narrative; Presentation (obstetrics); Context (archaeology); Narrative inquiry; Identification (biology); Strengths and weaknesses; Field (mathematics); Focus (optics); Key (lock); Sociology; Public relations; Political science; Linguistics; Computer science; Psychology; Social psychology; History; Medicine","score_opus":0.09848772467763912,"score_gpt":0.5212652790576524,"score_spread":0.4227775543800133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097845821","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87008995,0.00024569765,0.00024191989,0.12560114,0.0001670033,0.000106600004,0.000009632956,0.0000017107992,0.0035363282],"genre_scores_gemma":[0.995988,0.00024686058,0.000034647906,0.00041171093,0.0028027215,0.0000024185038,5.402288e-7,0.000003776218,0.00050933065],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99694127,0.0006524071,0.00084791216,0.00006595989,0.0012658173,0.00022665902],"domain_scores_gemma":[0.99684197,0.0011713887,0.0012327003,0.00015749744,0.00051557017,0.000080863916],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00791592,0.00008527378,0.00034354904,0.0010025357,0.00033546227,0.00015979036,0.00039782486,0.000050890314,0.00003499866],"category_scores_gemma":[0.00586326,0.00003834275,0.0002413176,0.0032201142,0.0004083934,0.0006004774,0.000074438976,0.00018464882,0.0000047494045],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045274044,0.00016216906,0.22592613,0.000007594049,0.00059733586,4.653202e-7,0.19832608,0.00055304624,0.00019259931,0.4659164,0.003731828,0.10413362],"study_design_scores_gemma":[0.00111292,0.000047095804,0.9199737,0.000005798927,0.00012852,0.0000047621897,0.01932419,0.00012745569,0.0002661186,0.0498295,0.009107886,0.00007209514],"about_ca_topic_score_codex":0.0020338667,"about_ca_topic_score_gemma":0.00034895865,"teacher_disagreement_score":0.6940475,"about_ca_system_score_codex":0.00019960813,"about_ca_system_score_gemma":0.0008664553,"threshold_uncertainty_score":0.7019294},"labels":[],"label_agreement":null},{"id":"W2098950772","doi":"10.1177/1049731511406552","title":"Promoting Evidence-Informed Practice in Child Welfare in Ontario","year":2011,"lang":"en","type":"article","venue":"Research on Social Work Practice","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Formative assessment; Feeling; Public relations; Welfare; Evidence-based practice; Psychology; Function (biology); Medical education; Political science; Medicine; Pedagogy; Social psychology; Alternative medicine","score_opus":0.6552859092548622,"score_gpt":0.6308419702331487,"score_spread":0.02444393902171349,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098950772","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15759474,0.00013399174,0.000008373412,0.11375365,0.00029224015,0.0011382358,9.2373386e-7,0.00003062072,0.7270472],"genre_scores_gemma":[0.9949689,0.00014605233,0.0013356541,0.00084691145,0.00012055941,0.00014420945,0.000002320658,0.0000157307,0.0024196494],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9864457,0.0047269478,0.001056777,0.0006612566,0.0062463037,0.00086300116],"domain_scores_gemma":[0.97801775,0.01911659,0.00052422774,0.00053996145,0.001628212,0.0001732833],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.061041113,0.00017415507,0.00031227438,0.00092429476,0.0011793561,0.0005294454,0.0009817152,0.00019499409,0.0061783665],"category_scores_gemma":[0.12232843,0.00014503115,0.00007967482,0.005526377,0.00015740973,0.005339515,0.0003127456,0.002748026,0.002180903],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0075095603,0.0032450743,0.09969146,0.00003762662,0.00006877642,0.00057476124,0.44075635,0.000071429306,0.0000071706127,0.03490039,0.010933801,0.4022036],"study_design_scores_gemma":[0.0007958307,0.00033546644,0.40572268,0.00031337698,0.000007824379,0.000014567618,0.05963375,0.00009219984,0.00003063496,0.0011890423,0.5316453,0.00021933208],"about_ca_topic_score_codex":0.020923804,"about_ca_topic_score_gemma":0.1200934,"teacher_disagreement_score":0.83737415,"about_ca_system_score_codex":0.0014632726,"about_ca_system_score_gemma":0.0018164027,"threshold_uncertainty_score":0.99955267},"labels":[],"label_agreement":null},{"id":"W2099038409","doi":"10.7202/1016856ar","title":"L’évaluation formative en contexte de renouveau pédagogique au primaire : analyse de pratiques au service de la réussite","year":2013,"lang":"fr","type":"article","venue":"Nouveaux cahiers de la recherche en éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Humanities; Political science; Art","score_opus":0.23324673933649556,"score_gpt":0.5075677920171348,"score_spread":0.2743210526806392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099038409","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7736979,0.00038367676,0.1370367,0.039675023,0.0005242187,0.0011256061,0.000020212032,0.00011786763,0.047418773],"genre_scores_gemma":[0.8390104,0.0016643363,0.13668893,0.006792522,0.0005915835,0.0006860058,0.00011393373,0.00006963715,0.014382642],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9433735,0.052220665,0.0012154928,0.00073911727,0.0013041894,0.001147015],"domain_scores_gemma":[0.9665696,0.029248018,0.000973826,0.0008967879,0.0016989849,0.00061275536],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.10168018,0.0005356996,0.0005787158,0.000532573,0.00070159027,0.00092633447,0.0009825622,0.0029086804,0.0013730393],"category_scores_gemma":[0.029088426,0.00051166705,0.000246057,0.0017813954,0.0005295582,0.0026680913,0.000117141506,0.0031335792,0.0006903275],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000066573055,0.00038090127,0.020371748,0.00015914909,0.00015704193,0.000003360728,0.8009557,0.0035169374,0.0066282563,0.0041270657,0.007426677,0.15620656],"study_design_scores_gemma":[0.0013959814,0.00032776996,0.35497168,0.0004434489,0.00037877937,0.00014485202,0.24607052,0.26881427,0.00953695,0.094156444,0.022922352,0.0008369485],"about_ca_topic_score_codex":0.008642984,"about_ca_topic_score_gemma":0.0061279302,"teacher_disagreement_score":0.5548852,"about_ca_system_score_codex":0.03151483,"about_ca_system_score_gemma":0.038569506,"threshold_uncertainty_score":0.9997335},"labels":[],"label_agreement":null},{"id":"W2100635587","doi":"10.1177/1049732303013006005","title":"A Review Committee's Guide for Evaluating Qualitative Proposals","year":2003,"lang":"en","type":"review","venue":"Qualitative Health Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":97,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Qualitative research; Checklist; Relevance (law); Qualitative analysis; Qualitative property; Psychology; Medical education; Medicine; Management science; Sociology; Computer science; Political science; Social science; Engineering","score_opus":0.9741940835152648,"score_gpt":0.8657494064839709,"score_spread":0.1084446770312939,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100635587","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.488477e-7,0.96020687,0.0034185182,0.010588101,0.00044040798,0.017572489,0.00065747934,0.000047317433,0.007068597],"genre_scores_gemma":[1.4757536e-7,0.9378986,0.024255095,0.0042536417,0.0001728017,0.009122597,0.00037890446,0.000111460904,0.023806764],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.7300787,0.23744872,0.010877944,0.0030036021,0.015705472,0.0028855891],"domain_scores_gemma":[0.8202291,0.1559056,0.004417483,0.0027109007,0.015714249,0.0010226694],"candidate_categories":["metaresearch","metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.5524664,0.000825034,0.0056434846,0.0017973318,0.0018566508,0.00050113077,0.0024497407,0.00038561318,0.0024021727],"category_scores_gemma":[0.13119063,0.00054789445,0.0012098401,0.00611956,0.00073329866,0.0005199872,0.00037269137,0.0022550917,0.0034654585],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000988084,0.000076413016,8.150192e-8,0.05168854,0.00006579686,4.3677505e-7,0.023938617,1.9394867e-7,2.296642e-8,0.0087039005,0.3503327,0.5651834],"study_design_scores_gemma":[0.00041942572,0.001434347,1.7010858e-7,0.060480326,0.00007575022,0.0000060990883,0.046671934,0.00006080657,1.0307266e-7,0.02623678,0.8641581,0.00045619317],"about_ca_topic_score_codex":0.0001478037,"about_ca_topic_score_gemma":0.00011829877,"teacher_disagreement_score":0.5647272,"about_ca_system_score_codex":0.0020364227,"about_ca_system_score_gemma":0.024297642,"threshold_uncertainty_score":0.99969727},"labels":[],"label_agreement":null},{"id":"W2101222132","doi":"10.7202/1010144ar","title":"Les approches et les stratégies gouvernementales de mise en oeuvre des politiques éducatives","year":2012,"lang":"fr","type":"article","venue":"Éducation et francophonie","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.18991555640996863,"score_gpt":0.4823340321692547,"score_spread":0.29241847575928603,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101222132","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84112924,0.024951523,0.0057934066,0.026267065,0.004428457,0.0005605658,0.00013132335,0.00012309202,0.0966153],"genre_scores_gemma":[0.9504522,0.0040865107,0.012134772,0.0012795398,0.00084279245,0.00018842808,0.000080925434,0.000046169698,0.030888641],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9941508,0.0022995553,0.00091761735,0.00055728876,0.0011965573,0.0008781686],"domain_scores_gemma":[0.9957537,0.0021142655,0.0005162496,0.0006031354,0.0006064519,0.00040620004],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.007527374,0.0004640328,0.0004232904,0.00033902697,0.0006826994,0.00055592554,0.00067448453,0.00033607436,0.010686484],"category_scores_gemma":[0.0015104089,0.00042295738,0.00021647738,0.0006810455,0.00082410185,0.0027692933,0.00013151788,0.0005205101,0.00097313436],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004229878,0.0018311344,0.19203623,0.00031707497,0.0001214461,9.706977e-7,0.45992106,0.00032794802,0.0009978706,0.122663185,0.028055862,0.1936849],"study_design_scores_gemma":[0.0004378804,0.00011856114,0.55446905,0.00027094432,0.00005069389,0.000020977053,0.21951328,0.00032506502,0.0036270057,0.014501116,0.20619538,0.0004700485],"about_ca_topic_score_codex":0.007099305,"about_ca_topic_score_gemma":0.0037774793,"teacher_disagreement_score":0.3624328,"about_ca_system_score_codex":0.0010346462,"about_ca_system_score_gemma":0.002419216,"threshold_uncertainty_score":0.9998222},"labels":[],"label_agreement":null},{"id":"W2101260272","doi":"10.1002/ev.313","title":"Policy implementation: Implications for evaluation","year":2009,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":96,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Douglas Mental Health University Institute","funders":"","keywords":"Accountability; Toolbox; Corporate governance; Context (archaeology); Process (computing); Government (linguistics); Sustainability; Political science; Public relations; Process management; Public administration; Sociology; Computer science; Business; Management; Economics","score_opus":0.3635462965884845,"score_gpt":0.6388161775626578,"score_spread":0.2752698809741734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101260272","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07374496,0.00069677946,0.60759455,0.23746827,0.0037387987,0.025750782,0.00051988964,0.0005055534,0.049980417],"genre_scores_gemma":[0.97384626,0.000045642548,0.013234507,0.0018462659,0.0017148161,0.0038943223,0.0011391685,0.000026240645,0.0042527984],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9954602,0.00034872463,0.0010618655,0.00067296816,0.0020919237,0.00036428488],"domain_scores_gemma":[0.992761,0.0009590209,0.0005403029,0.0007275004,0.0048364247,0.00017572414],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0135816615,0.00020770733,0.00024875384,0.00087736116,0.00097587414,0.0003909091,0.00037745922,0.00010767638,0.0018362255],"category_scores_gemma":[0.005147405,0.00019040937,0.00026938223,0.0017724562,0.000027515933,0.0010022811,0.000017921118,0.000075096264,0.00011029302],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040160245,0.00007711609,0.0007934293,0.0000017445924,0.000020099655,2.913662e-9,0.00038423736,0.002747438,0.0007377552,0.031873405,0.0545567,0.90876794],"study_design_scores_gemma":[0.005524888,0.00043213734,0.18522179,0.0000072370644,0.00026444555,0.0000036403565,0.00059999275,0.09917181,0.0010330003,0.56849855,0.13898616,0.0002563681],"about_ca_topic_score_codex":0.000066864566,"about_ca_topic_score_gemma":0.0005281173,"teacher_disagreement_score":0.9085115,"about_ca_system_score_codex":0.0007423776,"about_ca_system_score_gemma":0.003105188,"threshold_uncertainty_score":0.99907625},"labels":[],"label_agreement":null},{"id":"W2101387205","doi":"10.18438/b8dg8b","title":"Conducting Your Own Research: Something to Consider","year":2016,"lang":"en","type":"article","venue":"Evidence Based Library and Information Practice","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Data science","score_opus":0.6121189350941796,"score_gpt":0.560055832412034,"score_spread":0.052063102682145534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101387205","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061018065,0.00024123532,0.024445955,0.8628277,0.00058754935,0.0006715547,0.000015133926,0.00014185614,0.050050918],"genre_scores_gemma":[0.83971864,0.0003943007,0.021067668,0.13587743,0.00016212834,0.00005137601,0.000004178418,0.000008962868,0.0027153366],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9952157,0.001338807,0.00083032553,0.0002671744,0.0020557188,0.0002922576],"domain_scores_gemma":[0.9715258,0.026615743,0.00042219777,0.00050062535,0.000677278,0.00025835514],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["scholarly_communication","insufficient_payload"],"category_scores_codex":[0.017298123,0.00011358677,0.00015000081,0.0007520687,0.0004873484,0.0015315284,0.00042680884,0.00007119882,0.004343636],"category_scores_gemma":[0.07144056,0.0000675301,0.000035078956,0.0013459881,0.00011344469,0.32590333,0.0002564306,0.00026210654,0.002488758],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005510024,0.000043736065,0.0046434426,0.00003402969,0.000017142793,0.000004943571,0.0026840467,0.0003104071,0.0023273772,0.4481684,0.06470117,0.4765143],"study_design_scores_gemma":[0.0003650131,0.00017285913,0.0038066304,0.0002737345,0.0000059787208,0.000015760754,0.0064888014,0.0015103131,0.0066681895,0.0034449955,0.9770951,0.00015262584],"about_ca_topic_score_codex":0.000005200131,"about_ca_topic_score_gemma":1.0616197e-7,"teacher_disagreement_score":0.9123939,"about_ca_system_score_codex":0.00002390615,"about_ca_system_score_gemma":0.0006577794,"threshold_uncertainty_score":0.999505},"labels":[],"label_agreement":null},{"id":"W2101813690","doi":"10.1186/1478-4491-7-3","title":"Programme evaluation training for health professionals in francophone Africa: process, competence acquisition and use","year":2009,"lang":"en","type":"article","venue":"Human Resources for Health","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Montréal; Centre Hospitalier de l’Université de Montréal","funders":"Bill and Melinda Gates Foundation","keywords":"Competence (human resources); Medical education; Psychology; Program evaluation; Population; Nursing; Test (biology); Medicine; Environmental health","score_opus":0.39224083539978405,"score_gpt":0.5570035462460682,"score_spread":0.16476271084628413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101813690","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9640281,0.0009338041,0.0028659,0.02647753,0.00016348556,0.005252427,0.000049847644,0.000058791597,0.00017008037],"genre_scores_gemma":[0.9886364,0.000022698192,0.004823828,0.0054062842,0.0001458581,0.0006391522,0.00008342863,0.000012923872,0.00022944337],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99556786,0.00045879566,0.0011728029,0.0006024796,0.0015667641,0.00063127314],"domain_scores_gemma":[0.9974257,0.00074464857,0.0007622676,0.00028335289,0.0005410675,0.00024298746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016441852,0.00017904608,0.00047801554,0.00037867404,0.00087534514,0.00023547611,0.0002461377,0.000076295546,0.00008211389],"category_scores_gemma":[0.0006976306,0.00014178136,0.00006845876,0.0006382224,0.000061077684,0.00052129664,0.000019159103,0.000147065,0.000004544064],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00058864476,0.00077984104,0.011051791,0.00041786866,0.000013230025,4.1432463e-7,0.15777227,0.0009316033,0.000099603894,0.0034599078,0.012578883,0.8123059],"study_design_scores_gemma":[0.0071547143,0.0048982506,0.74744356,0.0008523661,0.000010762019,0.0000063996217,0.033906505,0.09704314,0.000021721919,0.06521318,0.042955793,0.0004936093],"about_ca_topic_score_codex":0.000029867711,"about_ca_topic_score_gemma":0.00044099524,"teacher_disagreement_score":0.81181234,"about_ca_system_score_codex":0.00021380669,"about_ca_system_score_gemma":0.000983844,"threshold_uncertainty_score":0.6732536},"labels":[],"label_agreement":null},{"id":"W2101892546","doi":"10.1002/ev.316","title":"Knowledge theories can inform evaluation practice: What can a complexity lens add?","year":2009,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":60,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Competence (human resources); Fidelity; Knowledge management; Computer science; Process (computing); Context (archaeology); Complex adaptive system; Paradigm shift; Psychology; Epistemology; Artificial intelligence; Social psychology","score_opus":0.37554862024845537,"score_gpt":0.565178999495196,"score_spread":0.18963037924674064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101892546","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20226106,0.0069217067,0.045617845,0.18890312,0.019849624,0.02303287,0.00030402813,0.0011128265,0.5119969],"genre_scores_gemma":[0.9877691,0.00027370782,0.0038435138,0.0023133783,0.0007249766,0.00058375765,0.0004694851,0.00002148346,0.004000544],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99270236,0.0010355408,0.0010938247,0.00065177,0.0041124267,0.00040408046],"domain_scores_gemma":[0.98911935,0.001797782,0.0007161945,0.0008224178,0.0073528606,0.00019139524],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.023628587,0.00028440726,0.00035859365,0.00066575164,0.001089137,0.001187649,0.00041385926,0.00015745181,0.0032407104],"category_scores_gemma":[0.014891838,0.00024237475,0.00021619398,0.0017383805,0.00010671814,0.0042701135,0.000040687206,0.000217217,0.00023391297],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000118689684,0.00020985205,0.00020764252,0.0000036382814,0.00004033529,6.504539e-8,0.0074647125,0.0023225325,0.00009852554,0.023697067,0.02615753,0.9396794],"study_design_scores_gemma":[0.0042050118,0.00073179265,0.03972557,0.00007056997,0.0005773504,0.0000177249,0.013632263,0.29093575,0.0007459727,0.33321208,0.31564128,0.0005046349],"about_ca_topic_score_codex":0.00014934556,"about_ca_topic_score_gemma":0.0075420365,"teacher_disagreement_score":0.9391748,"about_ca_system_score_codex":0.0010515157,"about_ca_system_score_gemma":0.0035641717,"threshold_uncertainty_score":0.9998492},"labels":[],"label_agreement":null},{"id":"W2102186678","doi":"10.1111/j.1365-2648.2004.03239_2.x","title":"Using Social Theory: Thinking Through Research","year":2004,"lang":"en","type":"article","venue":"Journal of Advanced Nursing","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":57,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Northern British Columbia","funders":"","keywords":"Citation; Library science; Sociology; Computer science; Psychology","score_opus":0.5933039009506306,"score_gpt":0.6616892097516013,"score_spread":0.06838530880097071,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102186678","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79512525,0.0005906408,0.17798866,0.0077627245,0.0018718239,0.00013150547,9.863766e-7,0.000012662907,0.016515747],"genre_scores_gemma":[0.9231311,0.000027870685,0.0757962,0.00023077425,0.0006990342,4.2204692e-7,1.8389187e-7,0.000011268772,0.00010312232],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9945619,0.0005112158,0.0007964315,0.00017375353,0.0036314104,0.00032525364],"domain_scores_gemma":[0.99689555,0.00067323854,0.0006385185,0.00018163976,0.0015399277,0.00007111558],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014117543,0.00009496666,0.0002704868,0.00039541224,0.0008547179,0.0002778733,0.00056739384,0.0000619303,0.00018045185],"category_scores_gemma":[0.0013999409,0.00006775748,0.00014438185,0.0010582095,0.00021240284,0.0017976565,0.000038324222,0.0005615103,0.000027350856],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006505714,0.0003289763,0.00041014978,0.0000070829415,0.000039908988,0.000042268486,0.061882284,0.13229004,0.027120473,0.241029,0.0010028972,0.53519636],"study_design_scores_gemma":[0.0010161113,0.00018299176,0.0012119391,0.00027886502,0.000012313729,0.000096455624,0.030345917,0.0002879482,0.0041875876,0.957746,0.0045433845,0.0000904709],"about_ca_topic_score_codex":0.0000017928123,"about_ca_topic_score_gemma":0.0000016900598,"teacher_disagreement_score":0.716717,"about_ca_system_score_codex":0.0006121318,"about_ca_system_score_gemma":0.0006076158,"threshold_uncertainty_score":0.65738857},"labels":[],"label_agreement":null},{"id":"W2102447872","doi":"","title":"PART: An Attempt in Federal Performance-Based Budgeting","year":2012,"lang":"en","type":"article","venue":"˜The œinnovation journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Budget process; Appropriation; Government (linguistics); Normative; Accounting; Politics; Control (management); Accountability; Public administration; Economics; Business; Political science; Management; Law","score_opus":0.2561284105904764,"score_gpt":0.4656787438483344,"score_spread":0.209550333257858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102447872","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98419726,0.00002837413,0.005257746,0.0039014765,0.0012226272,0.000120006865,0.000001111773,0.000015809892,0.005255603],"genre_scores_gemma":[0.9947567,0.000004859652,0.0006568903,0.00255282,0.0011479096,0.000011021027,0.000007877381,0.000009296467,0.00085264334],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9963044,0.0004076,0.0011081577,0.00015638962,0.001637655,0.0003858118],"domain_scores_gemma":[0.9979868,0.0002613974,0.00059459667,0.00030942014,0.0007522256,0.00009558598],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01917988,0.00012610834,0.00015896399,0.0005480831,0.000667701,0.0005406449,0.00045541945,0.00005617467,0.0024019256],"category_scores_gemma":[0.00028752562,0.00007400124,0.000045757923,0.001908282,0.000049598002,0.0017231281,0.000032055796,0.00044897132,0.0003404292],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034747754,0.00007465162,0.84000325,0.0000020447437,0.0000042665006,6.421387e-7,0.0009319633,0.0033940636,0.0002939946,0.0007306078,0.00385285,0.15067694],"study_design_scores_gemma":[0.00107212,0.00012843512,0.8057037,0.000031936488,0.0000035464202,0.000055310888,0.0016547509,0.06908208,0.00038755042,0.001004052,0.120679975,0.00019654023],"about_ca_topic_score_codex":0.0000037447614,"about_ca_topic_score_gemma":0.0000316008,"teacher_disagreement_score":0.15048039,"about_ca_system_score_codex":0.000110812594,"about_ca_system_score_gemma":0.0003047202,"threshold_uncertainty_score":0.99851},"labels":[],"label_agreement":null},{"id":"W2102960304","doi":"10.1177/1098214012464037","title":"Arguments for a Common Set of Principles for Collaborative Inquiry in Evaluation","year":2013,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":113,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; Carleton University; University of Ottawa","funders":"","keywords":"Logic model; Set (abstract data type); Context (archaeology); Field (mathematics); Stakeholder; Program evaluation; Management science; Engineering ethics; Sociology; Computer science; Epistemology; Knowledge management; Public relations; Political science; Social science; Public administration; Engineering","score_opus":0.39253977170837995,"score_gpt":0.5662179449091042,"score_spread":0.1736781732007242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102960304","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98558354,0.00010209202,0.009325097,0.0017711198,0.00040965484,0.0024858536,0.000019871648,0.0000021983183,0.00030059542],"genre_scores_gemma":[0.9892596,0.000018280763,0.009960947,0.0001531373,0.00013121401,0.0004107251,0.000026212156,0.00000874278,0.000031140153],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.993849,0.0010684364,0.001714679,0.00020198018,0.0029942351,0.00017166209],"domain_scores_gemma":[0.98529494,0.00197222,0.003016125,0.00024871496,0.009396606,0.00007141837],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.029864952,0.00011819261,0.00047374985,0.00058552413,0.000069994974,0.00008531129,0.00028771613,0.000037085436,0.00050511287],"category_scores_gemma":[0.0061370325,0.00008853722,0.0001253126,0.0009930803,0.0001350084,0.00086500513,0.000024477664,0.00008149468,0.000011689032],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004938131,0.00019034835,0.04199456,0.000013982809,0.00008054135,9.910812e-8,0.011389159,0.051619925,0.002236897,0.0005150211,0.003115026,0.8883506],"study_design_scores_gemma":[0.005472619,0.0034739124,0.26173934,0.000110695095,0.00017055609,0.0000045470642,0.03310417,0.6547024,0.002050935,0.036493763,0.0024909147,0.00018615049],"about_ca_topic_score_codex":0.000023156561,"about_ca_topic_score_gemma":0.00007633395,"teacher_disagreement_score":0.88816446,"about_ca_system_score_codex":0.00029252126,"about_ca_system_score_gemma":0.0012717171,"threshold_uncertainty_score":0.9989582},"labels":[],"label_agreement":null},{"id":"W2103006552","doi":"10.1111/capa.12125","title":"Research use capacity in provincial governments","year":2015,"lang":"en","type":"article","venue":"Canadian Public Administration","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Public relations; Capacity building; Political science; Public administration; Public policy; Research policy; Business","score_opus":0.7072553219903148,"score_gpt":0.5270814467335905,"score_spread":0.18017387525672435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103006552","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93875533,0.000004555055,0.00012924924,0.026166791,0.00034278858,0.0003304923,0.000052092688,0.000010439126,0.03420825],"genre_scores_gemma":[0.9955281,7.924194e-7,0.0002311625,0.00043562448,0.000109161134,0.00003673704,0.00003059624,0.000005346256,0.0036224814],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99573356,0.0004903005,0.0004349195,0.00031901267,0.002605226,0.00041699],"domain_scores_gemma":[0.9974634,0.00024731449,0.00008818029,0.00038587165,0.0009481468,0.0008670746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010177467,0.00007787107,0.00010659416,0.0006346313,0.0001744895,0.0010054415,0.0004045339,0.00009945123,0.000659891],"category_scores_gemma":[0.006945946,0.00006977736,0.000022277536,0.0012454331,0.00009331187,0.0017494207,0.00002985918,0.00023723219,0.0005926127],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042381846,0.00012493241,0.6440813,0.0000028409033,0.000005578385,0.000036041703,0.00090837205,0.000014318553,0.000028720437,0.21324252,0.11515492,0.026358085],"study_design_scores_gemma":[0.000524788,0.00021736366,0.18887603,0.000005286485,0.0000010911173,0.000007716377,0.002737601,0.0050226785,0.000072673465,0.0072040944,0.795182,0.00014870995],"about_ca_topic_score_codex":0.0130472565,"about_ca_topic_score_gemma":0.9110378,"teacher_disagreement_score":0.8979905,"about_ca_system_score_codex":0.00163716,"about_ca_system_score_gemma":0.012668665,"threshold_uncertainty_score":0.99352497},"labels":[],"label_agreement":null},{"id":"W2106298922","doi":"10.7202/900281ar","title":"Le système québécois d’évaluation au niveau primaire : exploration des pénalisations possibles pour les étudiants des milieux défavorisés","year":2009,"lang":"fr","type":"article","venue":"Revue des sciences de l éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Political science; Humanities; Valuation (finance); Philosophy; Business","score_opus":0.591741984015275,"score_gpt":0.5040630577279763,"score_spread":0.08767892628729868,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106298922","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8637555,0.005189447,0.08632406,0.02574263,0.0014643435,0.0007051664,0.000027006803,0.0000994894,0.016692312],"genre_scores_gemma":[0.9564897,0.0028248008,0.03467867,0.00026918922,0.00068395946,0.0000831896,0.000055678236,0.000020122427,0.004894696],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9937181,0.0015353508,0.0012561026,0.0009680363,0.0016357561,0.0008866857],"domain_scores_gemma":[0.9957327,0.0007435794,0.0008022841,0.0006006303,0.0017846606,0.00033611164],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.010607153,0.00040030212,0.00042716105,0.0008513644,0.005186307,0.0011616247,0.00094998255,0.00025321826,0.0005465363],"category_scores_gemma":[0.0032842627,0.00039498456,0.0002164222,0.0035256671,0.00257857,0.0074536684,0.00006706137,0.00024146089,0.0005091614],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000028329796,0.0008696666,0.051967118,0.00023572269,0.000030667645,0.0000034406185,0.16613117,0.03431396,0.0031327058,0.07261678,0.0020773895,0.66859305],"study_design_scores_gemma":[0.0005471417,0.0006052294,0.42584634,0.0010032547,0.00011577123,0.00008954028,0.086808085,0.102102734,0.0013590811,0.379182,0.0017800471,0.00056074886],"about_ca_topic_score_codex":0.012894058,"about_ca_topic_score_gemma":0.072853036,"teacher_disagreement_score":0.6680323,"about_ca_system_score_codex":0.0046317554,"about_ca_system_score_gemma":0.018578224,"threshold_uncertainty_score":0.99987525},"labels":[],"label_agreement":null},{"id":"W2106726492","doi":"10.1016/j.jneb.2011.02.005","title":"Building Evaluation Capacity in Local Programs for Multisite Nutrition Education Interventions","year":2011,"lang":"en","type":"article","venue":"Journal of Nutrition Education and Behavior","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Compendium; Capacity building; Scope (computer science); Plan (archaeology); Program evaluation; Psychological intervention; Process management; Empowerment; Medical education; Work (physics); Monitoring and evaluation; Computer science; Engineering management; Business; Medicine; Engineering; Political science; Nursing; Geography; Public administration","score_opus":0.47637077761000074,"score_gpt":0.5342831789769521,"score_spread":0.05791240136695136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106726492","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97507644,0.0008175275,0.019235516,0.00059027283,0.001990735,0.0021151872,0.0000085515185,0.000009176174,0.00015658088],"genre_scores_gemma":[0.93960947,0.00012643436,0.05771563,0.000097995966,0.00030523606,0.002021501,0.00003516343,0.000008762318,0.00007983202],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9971895,0.00028845816,0.0012508851,0.00023600119,0.00088390475,0.00015120237],"domain_scores_gemma":[0.99588937,0.00012918917,0.0008826443,0.00017264395,0.0027864184,0.00013975421],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043633045,0.00012616368,0.00024212763,0.0009599473,0.00013376106,0.0001583958,0.0001993822,0.000104157494,0.0003893425],"category_scores_gemma":[0.00043349483,0.00011066416,0.00020397258,0.00054376613,0.000073789524,0.0012436305,0.00001612399,0.00017813325,0.000008156328],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054608307,0.026181348,0.02227937,0.00010784542,0.000006956583,2.2948532e-7,0.0012845639,0.000003517658,0.0007541831,0.0011103601,0.0015762985,0.94664073],"study_design_scores_gemma":[0.00604307,0.0013571656,0.8719741,0.0021982894,0.00047416548,0.00023501202,0.038479034,0.0027787138,0.003241246,0.04758546,0.025203198,0.0004305228],"about_ca_topic_score_codex":0.00004886767,"about_ca_topic_score_gemma":0.00016378851,"teacher_disagreement_score":0.9462102,"about_ca_system_score_codex":0.0002913127,"about_ca_system_score_gemma":0.0005111927,"threshold_uncertainty_score":0.45127535},"labels":[],"label_agreement":null},{"id":"W2107365024","doi":"10.1111/j.1571-9979.2003.tb00782.x","title":"Bringing Horses to Water? Overcoming Bad Relationships in the Pre-Negotiating Stage of Consensus Building","year":2003,"lang":"en","type":"article","venue":"Negotiation Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Appeal; Negotiation; Incentive; Public relations; Political science; Process (computing); Business; Economics; Law; Computer science","score_opus":0.18810384495929627,"score_gpt":0.45181518145445715,"score_spread":0.2637113364951609,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107365024","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9641128,0.000043783966,0.029656332,0.00169475,0.0005265485,0.00021979633,0.0000025533898,0.00000876629,0.0037346275],"genre_scores_gemma":[0.9926389,0.0000067418096,0.0065559074,0.0002125104,0.000104019025,0.0000056720855,8.757246e-7,0.0000081643675,0.00046725108],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9952337,0.0014530247,0.0011772799,0.00020850016,0.0016378443,0.00028964743],"domain_scores_gemma":[0.9965879,0.002135597,0.0004906558,0.00027900332,0.00041585372,0.00009100771],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017403359,0.00011599892,0.00019961751,0.0005483035,0.000519753,0.0004639999,0.0003704167,0.000053632495,0.0006169632],"category_scores_gemma":[0.007584512,0.00007100654,0.000076990946,0.00073891226,0.000027357644,0.00047277077,0.000034752433,0.00045366792,0.000037009948],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032525368,0.000055795495,0.44818735,0.000008197625,0.0000159459,0.0000068298973,0.025434423,0.49400476,0.009132286,0.015831342,0.00075042614,0.0065400973],"study_design_scores_gemma":[0.0021009508,0.00022856068,0.7673,0.00022008138,0.000034115423,0.0002641907,0.040068287,0.123850614,0.014826817,0.011451684,0.039164823,0.0004898432],"about_ca_topic_score_codex":0.000023655246,"about_ca_topic_score_gemma":0.000051028168,"teacher_disagreement_score":0.37015414,"about_ca_system_score_codex":0.00011326867,"about_ca_system_score_gemma":0.00018835536,"threshold_uncertainty_score":0.90799165},"labels":[],"label_agreement":null},{"id":"W2107647310","doi":"10.7202/706795ar","title":"L’intervention en situation de crise en protection de la jeunesse. Crise familiale ou crise organisationnelle?","year":2005,"lang":"fr","type":"article","venue":"Service social","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Political science; Humanities; Philosophy","score_opus":0.07044402744840594,"score_gpt":0.4244328233750205,"score_spread":0.35398879592661453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107647310","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84272385,0.00044730282,0.050774068,0.09892714,0.001682489,0.00094356574,0.00004766022,0.00015162323,0.004302312],"genre_scores_gemma":[0.9841473,0.00032142806,0.0025690559,0.0020946348,0.0034669293,0.00015628789,0.000056700595,0.000046642315,0.0071409843],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99320114,0.0031936646,0.0009782927,0.0005762287,0.001471782,0.00057886925],"domain_scores_gemma":[0.9973343,0.00061563286,0.00052421214,0.00034011624,0.0009914449,0.00019432209],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008697251,0.0003248486,0.00033174432,0.0002808769,0.0009459681,0.0005776834,0.0005614564,0.00063709525,0.0075976504],"category_scores_gemma":[0.0009460395,0.0003514475,0.00026191107,0.001124692,0.00010695353,0.0016972384,0.00014542496,0.0005871461,0.0025898023],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038891382,0.0016862646,0.0041690804,0.000440155,0.00013083075,0.000008930807,0.28269628,0.0076854043,0.011059631,0.006067797,0.014058995,0.67160773],"study_design_scores_gemma":[0.0060236105,0.00038759224,0.15559512,0.0003204035,0.00052319444,0.000056648023,0.1520309,0.3634914,0.0079620555,0.05376042,0.25861716,0.0012315263],"about_ca_topic_score_codex":0.0023449077,"about_ca_topic_score_gemma":0.005433306,"teacher_disagreement_score":0.6703762,"about_ca_system_score_codex":0.001458571,"about_ca_system_score_gemma":0.0010838537,"threshold_uncertainty_score":0.9998937},"labels":[],"label_agreement":null},{"id":"W2108092689","doi":"10.26522/brocked.v16i1.79","title":"From Performance-Based To Inquiry-Based Accountability","year":2007,"lang":"en","type":"article","venue":"Brock Education Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Institute for Christian Studies","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Accountability; Identity (music); Scale (ratio); Sociology; Empirical research; Epistemology; Survey research; Aesthetics; Political science; Philosophy; Geography; Law","score_opus":0.19738421389024086,"score_gpt":0.5154301629827893,"score_spread":0.31804594909254846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2108092689","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9217117,0.00003477775,0.06844338,0.00382937,0.004031044,0.0001968439,0.0000046283103,0.000023862305,0.0017243861],"genre_scores_gemma":[0.9791701,0.0000023134041,0.011053069,0.0067115524,0.002174985,0.000013849833,0.000015023131,0.000010681744,0.0008484604],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9960345,0.00017381435,0.001001528,0.00034176852,0.002127558,0.00032080832],"domain_scores_gemma":[0.99617517,0.00072850706,0.0004113384,0.0005538538,0.0015543718,0.0005767626],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.004673669,0.00015413204,0.00019395053,0.0005813153,0.00043873792,0.00051842036,0.00067044696,0.0000776354,0.009571737],"category_scores_gemma":[0.0015648119,0.00011816697,0.00011326224,0.0009432664,0.00004153086,0.0006292813,0.00003108374,0.00028993515,0.0015122531],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034875056,0.00042522894,0.33279103,0.0000055308633,0.000009464432,5.253289e-7,0.0025609517,0.008732012,0.0013076625,0.000021467982,0.10440635,0.54939103],"study_design_scores_gemma":[0.0005810055,0.00013938009,0.75384295,0.000042406646,0.000010821115,0.000007177415,0.0055658636,0.0028541454,0.0033736862,0.0009261143,0.23245732,0.00019913203],"about_ca_topic_score_codex":0.00003163065,"about_ca_topic_score_gemma":0.00007257403,"teacher_disagreement_score":0.5491919,"about_ca_system_score_codex":0.00034913642,"about_ca_system_score_gemma":0.0041030175,"threshold_uncertainty_score":0.9992652},"labels":[],"label_agreement":null},{"id":"W2108155649","doi":"10.1177/1049732309344612","title":"Strengths and Challenges in the Use of Interpretive Description: Reflections Arising From a Study of the Moral Experience of Health Professionals in Humanitarian Work","year":2009,"lang":"en","type":"article","venue":"Qualitative Health Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":533,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Interpretation (philosophy); Qualitative research; Engineering ethics; Context (archaeology); Epistemology; Strengths and weaknesses; Discipline; Sociology; Management science; Psychology; Social psychology; Social science; Computer science","score_opus":0.9440937988956182,"score_gpt":0.7470193126754651,"score_spread":0.1970744862201531,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2108155649","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9721007,0.0012684795,0.000064355736,0.025224507,0.00005691721,0.0011511869,0.000014084432,0.0000018080179,0.00011798802],"genre_scores_gemma":[0.99864054,0.00034728416,0.0006038705,0.00029881217,0.000008870548,0.00006822425,0.0000011108767,0.0000027447097,0.00002854947],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.97404176,0.021405715,0.0014544143,0.00034643078,0.00246538,0.00028629086],"domain_scores_gemma":[0.9842762,0.014009484,0.0005677862,0.00045112232,0.00064681127,0.000048601112],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0329422,0.00008190715,0.00037380232,0.0004659493,0.0002958218,0.000039880197,0.00043141237,0.000036217574,0.000032034422],"category_scores_gemma":[0.0074726883,0.000045406454,0.000028783721,0.0018523374,0.00029665878,0.00033855604,0.00010042543,0.00048235198,7.862784e-7],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011751338,0.0015774572,0.012011963,0.000019253608,0.0000040151153,1.7591258e-7,0.95396024,0.000025558375,0.000010101339,0.0041181934,0.00012143804,0.028034084],"study_design_scores_gemma":[0.00035857316,0.0009436284,0.38453102,0.0003644975,3.818982e-7,9.02968e-8,0.60669434,0.0001235954,0.0000069902903,0.006877849,0.00007592575,0.00002310489],"about_ca_topic_score_codex":0.004208372,"about_ca_topic_score_gemma":0.014259238,"teacher_disagreement_score":0.37251905,"about_ca_system_score_codex":0.00016377524,"about_ca_system_score_gemma":0.0007497794,"threshold_uncertainty_score":0.9957895},"labels":[],"label_agreement":null},{"id":"W2108704795","doi":"","title":"A Systematic Review and Analysis of Leading Practices in Canada with Reference to Key Initiatives Elsewhere","year":2002,"lang":"en","type":"review","venue":"Insights (Essays)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Key (lock); Political science; Computer science; Computer security","score_opus":0.3638534774319989,"score_gpt":0.5012476984949779,"score_spread":0.13739422106297894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2108704795","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007208768,0.97132146,0.00003398632,0.00010299485,0.000027737462,0.0014543688,0.000042990927,0.0000061319593,0.026938226],"genre_scores_gemma":[0.0044616344,0.9942699,0.00014266721,0.00030396366,0.000006309264,0.00024830765,0.000020956917,0.000014372604,0.0005318974],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9933474,0.0015148502,0.0023071154,0.0006736165,0.001931689,0.00022533625],"domain_scores_gemma":[0.99086666,0.0036146278,0.003961559,0.00088273745,0.00052514736,0.00014928068],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027338113,0.00037923155,0.004725465,0.0012532471,0.000075418364,0.00014685963,0.00074901135,0.0000978443,0.0006028561],"category_scores_gemma":[0.0028628442,0.00020166072,0.00014894635,0.0055619176,0.000044289376,0.00062535243,0.00010787152,0.00032870422,0.000058693717],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011166594,0.00010386257,0.0010441698,0.9204107,0.003014207,0.000075637145,0.0024130866,0.00009043008,1.521943e-7,0.0039709546,0.00048889796,0.06837674],"study_design_scores_gemma":[0.00019211574,0.00016330756,0.00036215814,0.66733307,0.019455627,0.000024831466,0.0015163756,0.00048096915,3.4069674e-7,0.00010031601,0.30956802,0.00080286415],"about_ca_topic_score_codex":0.037148535,"about_ca_topic_score_gemma":0.7664323,"teacher_disagreement_score":0.72928375,"about_ca_system_score_codex":0.00037128324,"about_ca_system_score_gemma":0.0020708162,"threshold_uncertainty_score":0.9692632},"labels":[],"label_agreement":null},{"id":"W2110460008","doi":"10.5539/gjhs.v7n3p105","title":"A Researcher’s Self-Reflection of the Facilitation and Evaluation of an Action Research Project Within the Swedish Social and Care Context","year":2014,"lang":"en","type":"article","venue":"Global Journal of Health Science","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"General partnership; Negotiation; Presumption; Power (physics); Context (archaeology); Action (physics); Public relations; Process (computing); Ranking (information retrieval); Facilitation; Sociology; Psychology; Political science; Computer science; Social science","score_opus":0.6746007377395924,"score_gpt":0.6802595762459721,"score_spread":0.005658838506379715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110460008","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99565834,0.00023540773,0.0001600051,0.0028823582,0.00026314735,0.0004319373,0.000004498313,0.00000190945,0.00036236938],"genre_scores_gemma":[0.99948746,0.000028740895,0.0003681184,0.000057733847,0.00004669603,0.0000040520554,2.5324212e-7,0.0000011581421,0.000005780955],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98919904,0.0030737408,0.0007417621,0.00018833793,0.006614856,0.00018226799],"domain_scores_gemma":[0.9921441,0.0003192556,0.00091071613,0.00018519486,0.006370032,0.00007066664],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.10079392,0.000052229785,0.00015646554,0.00021769987,0.000981077,0.00014719892,0.00047097515,0.000029847693,0.0000062799113],"category_scores_gemma":[0.0035144978,0.000026422813,0.000029820483,0.001765071,0.0007954521,0.00083027105,0.00008252352,0.00022689896,5.378786e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020798747,0.00009023806,0.06954185,0.00007546403,0.000009287783,5.9255605e-8,0.038956705,0.0005062227,0.0018757522,0.002933095,0.0006771645,0.8851262],"study_design_scores_gemma":[0.00069089315,0.001046721,0.85890085,0.000055162116,0.000010977769,0.00003328812,0.08266811,0.045454863,0.0005359849,0.010215566,0.00034891977,0.000038686943],"about_ca_topic_score_codex":0.0005040067,"about_ca_topic_score_gemma":0.0012806121,"teacher_disagreement_score":0.8850875,"about_ca_system_score_codex":0.00039202624,"about_ca_system_score_gemma":0.004805127,"threshold_uncertainty_score":0.9259219},"labels":[],"label_agreement":null},{"id":"W2111271717","doi":"10.7202/1025779ar","title":"Research From the Global South: The important role of context in international research activities","year":2014,"lang":"en","type":"article","venue":"McGill Journal of Education / Revue des sciences de l éducation de McGill","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Situated; Context (archaeology); Phenomenon; Field (mathematics); Sociology; Political science; Geography; Public relations; Epistemology; Archaeology","score_opus":0.7247718127755086,"score_gpt":0.6154165113504811,"score_spread":0.10935530142502747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111271717","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95304775,0.0005303771,0.00015550318,0.016161563,0.0016912038,0.00023143235,0.000053829517,0.0000042987645,0.028124027],"genre_scores_gemma":[0.9967675,0.00015975333,0.0015651492,0.0007153001,0.0003608229,0.000027829563,0.0000025438278,0.000006065478,0.0003949874],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99180305,0.0032331934,0.0012488466,0.00031660078,0.002988484,0.00040983534],"domain_scores_gemma":[0.98894346,0.006221341,0.0009730615,0.0005030793,0.0032176296,0.00014140535],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.058585577,0.00011473497,0.00022887661,0.0006449139,0.0014376056,0.00031820626,0.0025071946,0.00007651581,0.0005747856],"category_scores_gemma":[0.014101388,0.00006727987,0.000119266006,0.0025962286,0.0013730021,0.000843522,0.0001639218,0.00056198286,0.000034840068],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021566628,0.00087175786,0.43525034,0.000016088028,0.00005468389,0.0000013084396,0.047846198,0.004783609,0.0014433141,0.24721734,0.011060569,0.25123912],"study_design_scores_gemma":[0.0003135373,0.00028540145,0.25359112,0.00020660178,0.000011886269,0.000090791254,0.26892865,0.014925958,0.0011706563,0.31256422,0.14778215,0.00012902496],"about_ca_topic_score_codex":0.0011638964,"about_ca_topic_score_gemma":0.0020111583,"teacher_disagreement_score":0.2511101,"about_ca_system_score_codex":0.0014652426,"about_ca_system_score_gemma":0.0020681294,"threshold_uncertainty_score":0.9998624},"labels":[],"label_agreement":null},{"id":"W2111340440","doi":"10.1177/1356389009105883","title":"How Legitimate and Justified are Judgments in Program Evaluation?","year":2009,"lang":"en","type":"article","venue":"Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Value (mathematics); Function (biology); Psychology; Order (exchange); Social psychology; Computer science; Economics","score_opus":0.3428563984356187,"score_gpt":0.5551089461910942,"score_spread":0.21225254775547547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111340440","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96743304,0.00031164574,0.00037259585,0.016790414,0.0004258271,0.003843633,0.000005646445,0.000062554,0.010754623],"genre_scores_gemma":[0.9968715,0.000017643717,0.0013399652,0.0004808336,0.00008137139,0.00048497992,0.000049939594,0.000006013042,0.00066777045],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99333256,0.000764783,0.0005463072,0.0005169652,0.004592764,0.00024662632],"domain_scores_gemma":[0.9976911,0.00019499088,0.000366344,0.00042019758,0.0012411351,0.00008622392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018362312,0.0001523123,0.00022036525,0.00041134784,0.00015336122,0.0007103499,0.00022714165,0.000081333754,0.00084383297],"category_scores_gemma":[0.0026617073,0.0001226223,0.00004232702,0.00080525485,0.00003987708,0.0011248793,0.000031699383,0.00012487313,0.00011482002],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025109974,0.00015732454,0.013122111,0.000003075247,0.000004716643,6.298372e-7,0.00057983556,0.001941315,0.0003168528,0.0003987791,0.0018308804,0.98161936],"study_design_scores_gemma":[0.0013299375,0.00012363918,0.501936,0.000023513894,0.00003151119,0.00000167968,0.00080030423,0.4754462,0.00010094876,0.017744372,0.002347804,0.00011405372],"about_ca_topic_score_codex":0.000004404109,"about_ca_topic_score_gemma":0.000101090496,"teacher_disagreement_score":0.98150533,"about_ca_system_score_codex":0.00020674337,"about_ca_system_score_gemma":0.00027846888,"threshold_uncertainty_score":0.9239379},"labels":[],"label_agreement":null},{"id":"W2111622450","doi":"10.21432/t2002r","title":"Strategic Planning for Technological Innovation in Canadian Post Secondary Education","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Learning and Technology","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Strategic planning; Checklist; Schedule; Higher education; Institution; Educational technology; Technology integration; Information technology; Knowledge management; Process management; Engineering management; Pedagogy; Computer science; Business; Political science; Sociology; Engineering; Psychology; Marketing","score_opus":0.0942960210960043,"score_gpt":0.42700765300724797,"score_spread":0.33271163191124364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111622450","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9806342,0.0006123018,0.000308461,0.0155860735,0.00018384344,0.000097992546,0.0000031016186,0.000009319501,0.0025646763],"genre_scores_gemma":[0.99839795,0.000009139523,0.0012514647,0.00015692953,0.000028687018,0.000005949619,0.000005544508,0.000004811461,0.00013953488],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988729,0.000035559227,0.00052514166,0.0001395408,0.00015376994,0.00027311477],"domain_scores_gemma":[0.9986034,0.00008578379,0.00028415173,0.000083469036,0.0007628611,0.00018035647],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024242632,0.00007307816,0.0001623212,0.0044207596,0.00022029997,0.00010012625,0.00022602337,0.0002115834,0.000117868825],"category_scores_gemma":[0.0023739117,0.00006150939,0.00001872666,0.0016105896,0.00013841431,0.000171522,0.000006886151,0.000557644,0.0000068524637],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012945923,0.000017957802,0.46591866,0.000008900583,0.000011663701,0.000048440794,0.00064666884,0.002252836,0.0005878611,0.2395505,0.00021267004,0.2907309],"study_design_scores_gemma":[0.0019471436,0.0013869925,0.05434684,0.00024562833,0.000014552953,0.00088458916,0.06521139,0.0007438745,0.0005559107,0.5501356,0.3241572,0.00037023137],"about_ca_topic_score_codex":0.01696738,"about_ca_topic_score_gemma":0.43284538,"teacher_disagreement_score":0.415878,"about_ca_system_score_codex":0.00029145865,"about_ca_system_score_gemma":0.013428272,"threshold_uncertainty_score":0.9921647},"labels":[],"label_agreement":null},{"id":"W2112073464","doi":"10.7202/900108ar","title":"Besoin d’une approche systémique en évaluation","year":2009,"lang":"fr","type":"article","venue":"Revue des sciences de l éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Humanities; Valuation (finance); Political science; Philosophy; Economics","score_opus":0.6834314759832737,"score_gpt":0.5673113482833153,"score_spread":0.11612012769995839,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112073464","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.63729,0.004659025,0.14921233,0.07609883,0.0047114072,0.0009922171,0.000011085401,0.00010336568,0.12692173],"genre_scores_gemma":[0.92274565,0.00090320944,0.048797194,0.0012888282,0.00074510346,0.00004215711,0.000019200363,0.000009640907,0.02544905],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9948105,0.0014293898,0.00088714034,0.00075388147,0.0015156302,0.0006034365],"domain_scores_gemma":[0.9972885,0.0008196786,0.0004772519,0.0005161526,0.00067912403,0.00021927405],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.020124422,0.00024620476,0.0002985828,0.00047782506,0.0011014633,0.00083756103,0.00096123107,0.00022671552,0.0014263167],"category_scores_gemma":[0.002661062,0.00022669167,0.0001397544,0.0032385641,0.0008434063,0.00201106,0.0000478885,0.00025972928,0.0015373812],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016675409,0.00044590893,0.002903247,0.00012341692,0.000011647335,0.0000030929325,0.13070944,0.025022216,0.0029287955,0.100388214,0.009204354,0.728243],"study_design_scores_gemma":[0.00036943477,0.0008770538,0.062371235,0.0005677073,0.0000781337,0.00021890533,0.028309684,0.5231845,0.001156423,0.3490562,0.033313423,0.0004973272],"about_ca_topic_score_codex":0.0003135635,"about_ca_topic_score_gemma":0.00031492303,"teacher_disagreement_score":0.72774565,"about_ca_system_score_codex":0.0013289712,"about_ca_system_score_gemma":0.003073328,"threshold_uncertainty_score":0.9994865},"labels":[],"label_agreement":null},{"id":"W2112073558","doi":"10.12927/cjnl.2006.18047","title":"Evaluating Our RN Recruitment Plan","year":2006,"lang":"en","type":"article","venue":"Nursing leadership","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Ottawa Hospital","funders":"","keywords":"Economic shortage; Workforce; Workforce planning; Nursing; Plan (archaeology); Nursing shortage; Nursing staff; Business; Human resources; Psychology; Medicine; Nurse education; Political science; Geography; Government (linguistics)","score_opus":0.9101320233870559,"score_gpt":0.5999320468971601,"score_spread":0.31019997648989583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112073558","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62258464,0.00088426546,0.00952854,0.14363098,0.0050700842,0.0016192294,0.000012035507,0.00038198798,0.21628825],"genre_scores_gemma":[0.98194236,9.043156e-7,0.0042464696,0.0010264089,0.00044628876,0.00003292549,0.00001545322,0.0000139555,0.012275254],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99573123,0.0004179393,0.00060262956,0.00044307145,0.0023757208,0.00042940123],"domain_scores_gemma":[0.9985971,0.00035543856,0.00024166993,0.00048095777,0.000237527,0.000087328895],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0058030146,0.00015329914,0.00020377814,0.00024157981,0.00028448907,0.00032288657,0.00041640145,0.00012569957,0.00064275],"category_scores_gemma":[0.0004906049,0.000121166304,0.000095098956,0.00052162714,0.000053285337,0.0003135825,0.000014538319,0.00027915114,0.001393915],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010206625,0.0003430857,0.019954555,0.000013154925,0.000014234321,0.000005884333,0.006273309,0.0069533433,0.0038148705,0.006773981,0.11779255,0.837959],"study_design_scores_gemma":[0.0050261016,0.0013639041,0.40606308,0.0010025342,0.00014703746,0.00008577059,0.16717415,0.1604808,0.009967169,0.1525419,0.09446577,0.0016817879],"about_ca_topic_score_codex":0.000022017965,"about_ca_topic_score_gemma":0.000032947046,"teacher_disagreement_score":0.8362772,"about_ca_system_score_codex":0.0002241829,"about_ca_system_score_gemma":0.00019066437,"threshold_uncertainty_score":0.9993836},"labels":[],"label_agreement":null},{"id":"W2112238768","doi":"10.1136/jech.2004.031765","title":"Can scientists and policy makers work together?: Table 1","year":2005,"lang":"en","type":"review","venue":"Journal of Epidemiology & Community Health","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":395,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Government of Canada; University of Toronto; Public Health Agency of Canada; University of Ottawa","funders":"","keywords":"Incentive; Work (physics); General partnership; Accountability; Public relations; Science policy; Engineering ethics; Perception; Medicine; Political science; Public administration; Epistemology; Economics; Law","score_opus":0.630728599622718,"score_gpt":0.6526695250093589,"score_spread":0.02194092538664094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112238768","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00021749373,0.9734762,0.0002769264,0.0233729,0.00073872216,0.00034798044,0.000037221904,0.0000090991825,0.0015234762],"genre_scores_gemma":[0.0002070764,0.9850167,0.005263754,0.008053036,0.0005540162,0.000006660608,0.000017512803,0.000020950158,0.0008602933],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9676666,0.025237987,0.005040588,0.00035128923,0.0009384259,0.0007650607],"domain_scores_gemma":[0.9624819,0.027440628,0.0071014944,0.0015397714,0.0006698756,0.0007662968],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13477205,0.00037577303,0.004180781,0.0014438528,0.0010155457,0.00009662248,0.0019565327,0.0003748578,0.0003719518],"category_scores_gemma":[0.032744963,0.00023725952,0.0005096193,0.0018709261,0.00050308,0.00026059206,0.00042065937,0.0034053097,0.00006357951],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009434469,0.00006767316,0.0026722713,0.00037708564,0.000056947512,0.000001091838,0.000391131,0.000037680235,5.4555067e-9,0.001076312,0.035060976,0.96024936],"study_design_scores_gemma":[0.0002431821,0.0003179052,0.0027539027,0.0032673685,0.00006263758,0.0002679755,0.00033750958,0.000018398581,5.7096945e-9,0.0050210245,0.98755586,0.00015420523],"about_ca_topic_score_codex":0.00162788,"about_ca_topic_score_gemma":0.0033866975,"teacher_disagreement_score":0.96009517,"about_ca_system_score_codex":0.0011329117,"about_ca_system_score_gemma":0.009672734,"threshold_uncertainty_score":0.99889386},"labels":[],"label_agreement":null},{"id":"W2112574591","doi":"10.7202/1024593ar","title":"Le stage comme dispositif de transfert des compétences professionnelles d’enseignants haïtiens en formation initiale","year":2014,"lang":"fr","type":"article","venue":"Phronesis","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Humanities; Political science; Sociology; Philosophy","score_opus":0.21414116749563514,"score_gpt":0.4349309270976488,"score_spread":0.22078975960201366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112574591","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68625516,0.0008708426,0.2783258,0.016633341,0.0011564906,0.0005066076,0.00010558768,0.000073119954,0.016073043],"genre_scores_gemma":[0.98528033,0.0005679514,0.006485982,0.0010949018,0.000226471,0.000065413835,0.0000384193,0.000024084793,0.00621645],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9950258,0.0018141626,0.0008916562,0.0004183328,0.0012063422,0.00064368866],"domain_scores_gemma":[0.9970823,0.0015745148,0.0002522625,0.00045844214,0.00037406335,0.00025841934],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0047572353,0.00028676988,0.00043041902,0.00023142362,0.0012313888,0.0003461864,0.0006585741,0.00019337286,0.0020679878],"category_scores_gemma":[0.00038418674,0.00024212878,0.00016326115,0.0005572793,0.00050972047,0.001795023,0.000103568294,0.00023464597,0.0007604526],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021729915,0.00095020235,0.013350389,0.00048005334,0.00006272719,0.0000086512855,0.07436285,0.002211527,0.0029236,0.031199126,0.0048385644,0.869395],"study_design_scores_gemma":[0.0038549025,0.0010190395,0.17650373,0.0014846863,0.00021191043,0.00006373509,0.08895744,0.49226257,0.022742635,0.06869696,0.1428559,0.001346485],"about_ca_topic_score_codex":0.0008244286,"about_ca_topic_score_gemma":0.0020718295,"teacher_disagreement_score":0.86804855,"about_ca_system_score_codex":0.00016652499,"about_ca_system_score_gemma":0.0006854703,"threshold_uncertainty_score":0.99884427},"labels":[],"label_agreement":null},{"id":"W2112746316","doi":"","title":"Educational Quality and Accountability in Ontario: Past, Present, and Future","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Educational Administration and Policy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Accountability; Scale (ratio); Educational assessment; Quality (philosophy); Political science; Public administration; Quality assessment; Public relations; Sociology; Pedagogy; Geography","score_opus":0.1666889239092964,"score_gpt":0.519257219435984,"score_spread":0.3525682955266876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112746316","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8115441,0.00020438648,0.000009410359,0.1805117,0.00029835338,0.00008064362,0.000012917772,4.5238033e-7,0.0073380116],"genre_scores_gemma":[0.9946126,0.00001873058,0.00040622908,0.0012368364,0.001808929,0.0000024519904,0.000011860479,0.0000028378374,0.0018995253],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983611,0.000106369895,0.00075203134,0.00017097109,0.00044083616,0.00016865488],"domain_scores_gemma":[0.99764025,0.0008439633,0.00031912967,0.000114984956,0.00047062855,0.00061106053],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0034261656,0.000093051036,0.00015398179,0.0005534229,0.00016940317,0.0002465057,0.000120257195,0.00006548153,0.0019539506],"category_scores_gemma":[0.00046628926,0.00007834722,0.000027333987,0.00029098138,0.00015498162,0.0005062731,0.00000889885,0.00019167855,0.0000048126735],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035323126,0.00004160538,0.9274668,0.0000046149203,0.0000054550596,5.512994e-7,0.0026583483,0.0000017006284,0.000008441727,0.057002958,0.0030531299,0.009721092],"study_design_scores_gemma":[0.00022271898,0.000053871347,0.8619915,0.000007184369,0.000003102175,0.00009329285,0.0016054467,0.0000065772238,0.000004712812,0.03158531,0.10435864,0.00006760478],"about_ca_topic_score_codex":0.0592943,"about_ca_topic_score_gemma":0.7771057,"teacher_disagreement_score":0.7178114,"about_ca_system_score_codex":0.00026046872,"about_ca_system_score_gemma":0.01379604,"threshold_uncertainty_score":0.9989584},"labels":[],"label_agreement":null},{"id":"W2113515522","doi":"10.3138/cjpe.016.001","title":"Addressing Attribution through Contribution Analysis: Using Performance Measures Sensibly","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":342,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Government of Canada","funders":"","keywords":"Attribution; Accountability; Authorship attribution; Public relations; Administration (probate law); Psychology; Business; Political science; Social psychology; Computer science; Law; Artificial intelligence","score_opus":0.6796845234554371,"score_gpt":0.5702891541640307,"score_spread":0.10939536929140636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113515522","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8888697,0.00082637015,0.107565895,0.0007287594,0.0006935711,0.0006666715,0.000008013981,0.000013635787,0.00062737573],"genre_scores_gemma":[0.99560225,0.000048386515,0.0038184223,0.00013507526,0.0002826333,0.000016131764,0.000042168987,0.000008724095,0.00004621566],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.993841,0.0008973504,0.0013199361,0.00027050773,0.0032349837,0.0004362063],"domain_scores_gemma":[0.98958164,0.00015144452,0.001232262,0.00033769858,0.008321461,0.000375514],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.018551076,0.0001717153,0.00041818607,0.0012312278,0.0006017481,0.00065463595,0.00035469665,0.00013210381,0.001019635],"category_scores_gemma":[0.00228243,0.00013822787,0.00027456754,0.003573975,0.00011652338,0.0018451835,0.0000119093975,0.00026303317,0.000044166944],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057296238,0.0000558953,0.2139138,0.000003362315,0.00025842924,0.000012390333,0.0008444975,0.10988875,0.00038922628,0.00026829354,0.00036931163,0.67393875],"study_design_scores_gemma":[0.0013251012,0.00042452785,0.20916432,0.000098227654,0.0013315025,0.00017806873,0.00088060094,0.73570275,0.0007337685,0.0023098204,0.04758309,0.0002682058],"about_ca_topic_score_codex":0.0005635114,"about_ca_topic_score_gemma":0.010192095,"teacher_disagreement_score":0.67367053,"about_ca_system_score_codex":0.0009571845,"about_ca_system_score_gemma":0.0041317972,"threshold_uncertainty_score":0.99989355},"labels":[],"label_agreement":null},{"id":"W2113537253","doi":"10.46743/2160-3715/2003.1870","title":"Understanding Reliability and Validity in Qualitative Research","year":2015,"lang":"en","type":"article","venue":"The Qualitative Report","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5194,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Reliability (semiconductor); Qualitative research; Validity; Psychology; Triangulation; Perspective (graphical); Test (biology); Positivism; Test validity; Construct validity; Social psychology; Epistemology; Computer science; Sociology; Psychometrics; Mathematics; Artificial intelligence; Social science; Developmental psychology","score_opus":0.9638247936679258,"score_gpt":0.7706150627950911,"score_spread":0.19320973087283477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113537253","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92295194,0.000061439445,0.009572461,0.016095214,0.00021638894,0.00046983507,0.000006882644,0.00001982825,0.050606005],"genre_scores_gemma":[0.9959808,0.000011139273,0.0008066493,0.00010192012,0.0000396685,0.00004381664,0.000004089605,0.0000067400897,0.0030051556],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97192764,0.021346131,0.001274848,0.00062413316,0.004455629,0.00037159357],"domain_scores_gemma":[0.9701804,0.026477171,0.00043187937,0.00090236124,0.0018131818,0.0001950226],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.30819207,0.00011900184,0.00030049265,0.0002912848,0.00028407236,0.0001795511,0.00036187202,0.00006142782,0.00013895381],"category_scores_gemma":[0.05178552,0.00006799261,0.000048294147,0.0014444728,0.00088444183,0.0004983063,0.00020567527,0.0004337043,0.0001251255],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015474572,0.00007797162,0.011825984,0.0000071054906,0.000010559356,0.000029521294,0.8952657,0.00014656327,0.000021410695,0.082573205,0.009509596,0.00037764478],"study_design_scores_gemma":[0.00022220805,0.00012140685,0.0043554893,0.000009896335,0.0000018175191,0.000012995574,0.482209,0.000694068,0.000027260296,0.5100931,0.0021887838,0.000063964486],"about_ca_topic_score_codex":0.00043845412,"about_ca_topic_score_gemma":0.00036344441,"teacher_disagreement_score":0.42751992,"about_ca_system_score_codex":0.0005754951,"about_ca_system_score_gemma":0.0007012338,"threshold_uncertainty_score":0.9562017},"labels":[],"label_agreement":null},{"id":"W2113822265","doi":"10.22230/cjnser.2013v4n2a143","title":"Exploring the perspectives of International Nongovernmental Organizations (INGOs) on the use of program evaluation and impact assessment in their work","year":2013,"lang":"en","type":"article","venue":"Canadian journal of nonprofit and social economy research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Political science; Valuation (finance); Work (physics); Humanities; Management; Business; Accounting; Economics; Engineering; Philosophy","score_opus":0.5801046623752703,"score_gpt":0.527428974065241,"score_spread":0.05267568831002922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113822265","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98869675,0.00003966016,0.000009977284,0.009094667,0.00005734466,0.00054105883,0.000005746466,4.9013704e-7,0.0015543028],"genre_scores_gemma":[0.99966437,0.00004018971,0.000072505325,0.000039058916,0.00007401618,0.00005387138,0.0000010552939,0.000003994095,0.00005094046],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99820703,0.00043562328,0.00038972858,0.00009904112,0.0007243702,0.00014420057],"domain_scores_gemma":[0.99699503,0.0009534312,0.00022315359,0.000098301556,0.0016417834,0.000088314235],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006146373,0.000057078774,0.00013273643,0.00031974775,0.00026515906,0.00035450913,0.00026865694,0.000024602865,0.0009330458],"category_scores_gemma":[0.0007629328,0.000030288349,0.000041996034,0.00049474,0.00028914504,0.0006945606,0.00003566885,0.00027442107,0.0000025516251],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002302626,0.00005497144,0.85898226,0.0000029078512,0.00007608527,5.1446085e-7,0.039146896,0.0002839135,0.000044704888,0.0048056636,0.0011887364,0.095390335],"study_design_scores_gemma":[0.00025156554,0.00014311206,0.91791505,0.000022149852,0.000003852292,0.0000016183209,0.07499315,0.003808999,0.000036727582,0.0014454857,0.0013427542,0.00003552755],"about_ca_topic_score_codex":0.0014737075,"about_ca_topic_score_gemma":0.0030363323,"teacher_disagreement_score":0.09535481,"about_ca_system_score_codex":0.00037899605,"about_ca_system_score_gemma":0.0014680338,"threshold_uncertainty_score":0.9999802},"labels":[],"label_agreement":null},{"id":"W2115598025","doi":"10.7202/1006244ar","title":"Évaluation d’un partenariat dans le cadre de la mise en place de services intersectoriels pour des enfants victimes d’agressions sexuelles","year":2011,"lang":"fr","type":"article","venue":"Service social","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Université du Québec à Montréal","funders":"","keywords":"Humanities; Political science; Art","score_opus":0.10297610131486636,"score_gpt":0.4116412306681267,"score_spread":0.30866512935326035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115598025","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9542578,0.00053561793,0.0019394081,0.0063974718,0.0011277925,0.0003331796,0.00009057972,0.00009232926,0.03522585],"genre_scores_gemma":[0.9828171,0.00023198502,0.006952859,0.0015854028,0.00088263594,0.00005940344,0.000032528475,0.00004595095,0.007392093],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9933137,0.003486067,0.0007248989,0.0005686479,0.0011572542,0.0007494316],"domain_scores_gemma":[0.99696785,0.0012687166,0.00044666295,0.0003814063,0.00063689786,0.00029844083],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006636022,0.0003775524,0.00040589264,0.00017435417,0.0015043614,0.00037487393,0.0010108068,0.0005678925,0.008819962],"category_scores_gemma":[0.00022716145,0.0003506642,0.00019617766,0.0008498536,0.00027311977,0.0011306495,0.00028235986,0.00047613506,0.0006242268],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021565825,0.0006417521,0.09560449,0.00019379055,0.00019363945,0.00002391642,0.8164054,0.00070508674,0.004631296,0.002783978,0.0015517615,0.07704921],"study_design_scores_gemma":[0.0024469346,0.00015220324,0.33547264,0.00042189652,0.00033398473,0.000057301175,0.49999267,0.0740636,0.008607909,0.0654738,0.012235077,0.00074198906],"about_ca_topic_score_codex":0.012486231,"about_ca_topic_score_gemma":0.012312016,"teacher_disagreement_score":0.31641275,"about_ca_system_score_codex":0.00042077314,"about_ca_system_score_gemma":0.0025295406,"threshold_uncertainty_score":0.99989456},"labels":[],"label_agreement":null},{"id":"W2115682002","doi":"10.1111/j.1937-8327.1988.tb00019.x","title":"Evaluation Research: A Pragmatic, Program-Focused, Research Strategy for Decision-Makers","year":2008,"lang":"en","type":"article","venue":"Performance Improvement Quarterly","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Stakeholder; Management science; Plan (archaeology); Computer science; Process (computing); Knowledge management; Data collection; Resource (disambiguation); Process management; Sociology; Public relations; Business; Political science; Engineering","score_opus":0.5811322214091504,"score_gpt":0.5973990219782318,"score_spread":0.016266800569081363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115682002","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9751394,0.00015500684,0.0025919809,0.0012341581,0.0006690383,0.007862233,0.000027141381,0.00011579269,0.012205282],"genre_scores_gemma":[0.98309445,0.000100743106,0.0070449077,0.00011371789,0.00038619118,0.0060066474,0.000040816965,0.000041982206,0.0031705375],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97686094,0.0013346031,0.0018831766,0.0012516839,0.017074585,0.0015949912],"domain_scores_gemma":[0.9819587,0.0045547443,0.00040050803,0.0016002565,0.011120906,0.00036490758],"candidate_categories":["metaresearch","metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.090021536,0.00033696642,0.00046349785,0.0019937267,0.0025920758,0.00084128295,0.0015032091,0.00019221363,0.0016744534],"category_scores_gemma":[0.0041414406,0.0002542284,0.00020020528,0.0035058237,0.00056169956,0.0020949296,0.00011490729,0.0007532321,0.0015769522],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025674514,0.00049164373,0.00134312,0.000031606152,0.00003479792,0.0000016639217,0.0033226914,0.00047960758,0.0007343794,0.00055243063,0.021256926,0.9714944],"study_design_scores_gemma":[0.0058825985,0.02813497,0.02868363,0.00020568566,0.000051669816,0.000021534299,0.012372217,0.7898026,0.0013037173,0.041487575,0.091299705,0.0007541008],"about_ca_topic_score_codex":0.000053827636,"about_ca_topic_score_gemma":0.00017960607,"teacher_disagreement_score":0.97074026,"about_ca_system_score_codex":0.00067755836,"about_ca_system_score_gemma":0.0024796487,"threshold_uncertainty_score":0.999991},"labels":[],"label_agreement":null},{"id":"W2115711712","doi":"10.7202/900551ar","title":"Les orientations de la recherche en éducation dans les constituantes de l’Université du Québec","year":2009,"lang":"fr","type":"article","venue":"Revue des sciences de l éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université du Québec à Trois-Rivières; Université du Québec à Rimouski","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.8001690954422226,"score_gpt":0.5940486158248311,"score_spread":0.20612047961739144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115711712","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7739042,0.0017709851,0.09831859,0.035567157,0.0007007698,0.00024112349,0.000012074972,0.00005599123,0.08942912],"genre_scores_gemma":[0.935573,0.0021255224,0.054259546,0.00041783412,0.00026332244,0.00001757064,0.000011926288,0.000007426251,0.007323852],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99436504,0.0036496324,0.0004815183,0.00047416758,0.0005796134,0.000450012],"domain_scores_gemma":[0.99261963,0.006033202,0.00033596682,0.0003131559,0.00048382586,0.00021419674],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017176582,0.00019200658,0.0001865605,0.00035174456,0.001722944,0.0005826731,0.000797019,0.00031174693,0.0019980134],"category_scores_gemma":[0.009517435,0.00018917784,0.00010913125,0.0016253017,0.001757885,0.0012282417,0.00004126655,0.00039855426,0.00027307798],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000014547905,0.0004657306,0.16143206,0.000045488214,0.000014593156,0.0000042330557,0.44417927,0.0077649145,0.0047610467,0.10418951,0.0070141847,0.27011442],"study_design_scores_gemma":[0.0004128609,0.0004195222,0.49670252,0.00038640268,0.00014333715,0.00046454975,0.2230611,0.12559244,0.0025517608,0.08167559,0.06811677,0.0004731544],"about_ca_topic_score_codex":0.015191713,"about_ca_topic_score_gemma":0.023427777,"teacher_disagreement_score":0.33527046,"about_ca_system_score_codex":0.00835705,"about_ca_system_score_gemma":0.013466407,"threshold_uncertainty_score":0.9995767},"labels":[],"label_agreement":null},{"id":"W2115776235","doi":"10.3138/cjpe.0023.004","title":"Evaluation Capacity Building in the Schools: Administrator-Led and Teacher-Led Perspectives","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Capacity building; Sustainability; Capacity development; Process (computing); Process management; Business; Knowledge management; Computer science; Political science; Environmental resource management; Environmental science","score_opus":0.3996361563938446,"score_gpt":0.5246982158041983,"score_spread":0.1250620594103537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115776235","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9854289,0.0011366346,0.0002529405,0.009171236,0.00021724038,0.0013728151,0.000002145243,0.000005769785,0.002412277],"genre_scores_gemma":[0.99716765,0.000014569034,0.0023194188,0.00022213328,0.00019456883,0.000057013527,0.0000030726114,0.0000049661026,0.000016610828],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9924151,0.0024319736,0.0008886255,0.00026991926,0.0037086448,0.00028575066],"domain_scores_gemma":[0.99538875,0.00025034384,0.000607017,0.0002950518,0.0031627752,0.00029605237],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.062279426,0.00014709054,0.00023754401,0.0006950101,0.0002843963,0.0008050032,0.00047215234,0.0000934149,0.0008007645],"category_scores_gemma":[0.009834752,0.00009893366,0.00009211127,0.0009541929,0.00009059022,0.00093157904,0.000005628225,0.00044257264,0.0000121499215],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022594999,0.00010005707,0.024496809,0.0000016249887,0.000019823403,0.0000046227606,0.009449862,0.0006525071,0.00011272338,0.0017046955,0.00080275617,0.96263194],"study_design_scores_gemma":[0.0020577523,0.0010372606,0.7908895,0.000073413554,0.00018713968,0.00010187177,0.03170789,0.11587414,0.000047919355,0.053865302,0.0039549638,0.00020284687],"about_ca_topic_score_codex":0.0002570339,"about_ca_topic_score_gemma":0.011996215,"teacher_disagreement_score":0.9624291,"about_ca_system_score_codex":0.000737633,"about_ca_system_score_gemma":0.005078318,"threshold_uncertainty_score":0.99850583},"labels":[],"label_agreement":null},{"id":"W2116343005","doi":"10.1177/1356389012453289","title":"Towards an evidence base of theory-driven evaluations: Some questions for proponents of theory-driven evaluation","year":2012,"lang":"en","type":"article","venue":"Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; University of Toronto; St. Michael's Hospital","funders":"","keywords":"Management science; Causality (physics); Psychological intervention; Promotion (chess); Development theory; Theory of change; Computer science; Psychology; Engineering ethics; Sociology; Political science; Economics; Economic growth; Engineering","score_opus":0.37736500390818084,"score_gpt":0.5722308654359345,"score_spread":0.19486586152775365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116343005","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86966616,0.002029552,0.1168348,0.0011058884,0.0016350107,0.007055422,0.00014446375,0.00006180904,0.001466905],"genre_scores_gemma":[0.98666024,0.000067669265,0.01094041,0.00013643593,0.00034448164,0.0013627841,0.00022686628,0.000029100704,0.00023200815],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98019284,0.007960978,0.00206492,0.00069640414,0.00860393,0.0004809391],"domain_scores_gemma":[0.9846474,0.003484014,0.0016312294,0.0013083214,0.008709921,0.00021913562],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.104484,0.0002903029,0.0005167416,0.0007531174,0.00033891943,0.00010645154,0.00079106534,0.0001824574,0.0052380725],"category_scores_gemma":[0.035492517,0.00023197771,0.00025576373,0.0010116531,0.00024257696,0.0043167444,0.00010690806,0.00015412766,0.00014985878],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007164042,0.0014692893,0.025019761,0.00010589181,0.00017096882,6.8586544e-8,0.011802788,0.06610368,0.027999293,0.20627294,0.0009374373,0.6594015],"study_design_scores_gemma":[0.0018157351,0.00061341777,0.12930736,0.00021265754,0.0007162943,0.000001950991,0.0017059443,0.5733773,0.009243588,0.28253624,0.00019668233,0.0002728408],"about_ca_topic_score_codex":0.00002832712,"about_ca_topic_score_gemma":0.00004052329,"teacher_disagreement_score":0.6591286,"about_ca_system_score_codex":0.0004366177,"about_ca_system_score_gemma":0.0021589294,"threshold_uncertainty_score":0.9956713},"labels":[],"label_agreement":null},{"id":"W2116868899","doi":"10.7202/1027321ar","title":"Translating research findings into educational policy and practice: the virtues and vices of a metaphor","year":2014,"lang":"en","type":"article","venue":"Nouveaux cahiers de la recherche en éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Analogy; Parallels; Metaphor; Variety (cybernetics); Meaning (existential); Epistemology; Relation (database); Sociology; Task (project management); Psychology; Linguistics; Computer science; Management; Philosophy","score_opus":0.43502936636945005,"score_gpt":0.626329396386352,"score_spread":0.19130003001690193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116868899","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.824509,0.0004684801,0.0030005276,0.10447119,0.00010871859,0.00030711488,0.0000018920839,0.000011508188,0.06712156],"genre_scores_gemma":[0.9638867,0.0003244911,0.033797774,0.0006688129,0.00017423416,0.000053387572,0.0000035224646,0.000008876421,0.0010822258],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98502225,0.012977026,0.00042058813,0.00030146554,0.0010880753,0.0001906257],"domain_scores_gemma":[0.89063567,0.10788903,0.00022375204,0.00035548728,0.000789702,0.000106359315],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10536921,0.000093972354,0.00014856613,0.00038922712,0.0003681789,0.00027011038,0.00031811232,0.0002830581,0.00009233589],"category_scores_gemma":[0.12564552,0.000063750966,0.000032774882,0.0010204215,0.0005193036,0.0005465876,0.00004174416,0.0008096837,0.000015929576],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008006164,0.0001269768,0.0049267216,0.000047445417,0.000045005425,6.9832886e-8,0.5364739,0.00004879144,0.015671141,0.19277103,0.0011328709,0.24867602],"study_design_scores_gemma":[0.00059583876,0.00021596564,0.088261455,0.00006280858,0.00006318425,0.000040227267,0.184187,0.008296068,0.0032862877,0.63683987,0.077920265,0.0002310305],"about_ca_topic_score_codex":0.00031434197,"about_ca_topic_score_gemma":0.00012860347,"teacher_disagreement_score":0.44406885,"about_ca_system_score_codex":0.0005500514,"about_ca_system_score_gemma":0.0018430474,"threshold_uncertainty_score":0.92121065},"labels":[],"label_agreement":null},{"id":"W2117288619","doi":"10.1136/bmj.332.7548.983","title":"How should we rate research?","year":2006,"lang":"en","type":"editorial","venue":"BMJ","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Cornerstone; Research Assessment Exercise; Quality (philosophy); Institution; Higher education; Political science; Public relations; Shadow (psychology); Medical education; Business; Psychology; Economics; Medicine; Economic growth","score_opus":0.5504605934071498,"score_gpt":0.6254533397278883,"score_spread":0.07499274632073849,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117288619","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000030032967,0.00028331246,0.00020304206,0.044809174,0.8724074,0.0005289236,0.000108743036,0.000041297502,0.0815881],"genre_scores_gemma":[0.0002461136,0.00014152052,0.00023228176,0.000073169096,0.65511066,0.0000864435,0.000119302575,0.000020014986,0.34397048],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9839624,0.0015562063,0.000780799,0.00076656044,0.012424606,0.0005094242],"domain_scores_gemma":[0.9862767,0.008838572,0.00044452804,0.0013158566,0.0029891084,0.00013523008],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.03946779,0.00023644866,0.00044987112,0.00069924287,0.00031885074,0.001952149,0.0015250912,0.00071198354,0.0016008024],"category_scores_gemma":[0.021337708,0.00015923187,0.00017576387,0.0010482533,0.0001621751,0.00041545686,0.00029997836,0.0014083976,0.0033250253],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020993362,0.000022362763,0.00003531042,0.000009665557,0.000008222149,0.000009131075,0.000053583473,0.000029904444,0.000010122382,0.00021493791,0.9878118,0.011773972],"study_design_scores_gemma":[0.00029990647,0.00008150794,0.00014758323,0.000055170247,0.000007283503,4.0100548e-7,0.00019984611,0.00051367667,0.000030459736,0.009319829,0.9891374,0.00020694014],"about_ca_topic_score_codex":0.000074744166,"about_ca_topic_score_gemma":0.00039609184,"teacher_disagreement_score":0.2623824,"about_ca_system_score_codex":0.00017157484,"about_ca_system_score_gemma":0.002019323,"threshold_uncertainty_score":0.99931186},"labels":[],"label_agreement":null},{"id":"W2119001104","doi":"10.18357/ijcyfs41201311850","title":"THE GRANDE PRAIRIE PACT PROGRAM EVALUATION: DISCREPANCY BETWEEN MODEL EVALUATION PRACTICE AND CONSTRAINED REAL WORLD EVALUATION OF CRIME PREVENTION IN SMALL COMMUNITIES","year":2013,"lang":"en","type":"article","venue":"International Journal of Child Youth and Family Studies","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Mount Royal University; Concordia University; University of Calgary","funders":"","keywords":"Pact; Mental health; Recidivism; Officer; Confidentiality; Public relations; Criminal justice; Psychology; Political science; Medical education; Criminology; Medicine; Psychiatry; Law","score_opus":0.40526663393336354,"score_gpt":0.5389014322961405,"score_spread":0.13363479836277697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119001104","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9786467,0.00408709,0.00033224912,0.006665616,0.00035852302,0.0015383919,0.000017466975,0.000006725446,0.008347212],"genre_scores_gemma":[0.9965776,0.0017908753,0.0011516107,0.0001767497,0.00012120105,0.00012420761,0.00001968617,0.0000062656104,0.000031793767],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99309385,0.0015895386,0.0014062996,0.00017295677,0.0035876832,0.00014969427],"domain_scores_gemma":[0.98657364,0.0016466944,0.0014607453,0.00018988668,0.010066919,0.00006212055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025652131,0.00015817424,0.00033801765,0.0004258749,0.00024201244,0.00025667893,0.00035322743,0.000044751632,0.000026100124],"category_scores_gemma":[0.003876997,0.000098115044,0.00009109067,0.0002625019,0.00033300446,0.0011147427,0.000112384856,0.0002396907,0.0000013542594],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002954661,0.0002654353,0.107936814,0.000008876847,0.00070738513,4.0288734e-7,0.026245592,0.0023895248,0.000008587192,0.0013570676,0.0002960753,0.8604888],"study_design_scores_gemma":[0.0036974126,0.00035695467,0.7413158,0.00028596094,0.0006357297,0.00000996664,0.06977321,0.12268488,0.000016482407,0.06089427,0.00019345184,0.0001358664],"about_ca_topic_score_codex":0.00016196237,"about_ca_topic_score_gemma":0.00086603645,"teacher_disagreement_score":0.8603529,"about_ca_system_score_codex":0.00013966105,"about_ca_system_score_gemma":0.0004386307,"threshold_uncertainty_score":0.8890568},"labels":[],"label_agreement":null},{"id":"W2119756126","doi":"10.1080/09640560601156532","title":"Participatory evaluation of collaborative and integrated water management: Insights from the field","year":2007,"lang":"en","type":"article","venue":"Journal of Environmental Planning and Management","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":78,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Toronto and Region Conservation Authority; University of Guelph","funders":"Chartered Institution of Wastes Management","keywords":"General partnership; Stakeholder; Context (archaeology); Watershed management; Negotiation; Diversity (politics); Civil society; Citizen journalism; Environmental resource management; Sociology; Watershed; Knowledge management; Political science; Public relations; Environmental planning; Geography; Economics; Social science; Computer science; Politics","score_opus":0.11088296056796622,"score_gpt":0.4271492559888773,"score_spread":0.3162662954209111,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119756126","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.992119,0.0010965822,0.0016753805,0.00043768002,0.00016227517,0.00020387225,0.00000349804,0.0000016627674,0.004300006],"genre_scores_gemma":[0.99849725,0.00026087416,0.00063535845,0.00043211613,0.000029773933,0.0000032231712,0.0000033651518,0.000003023656,0.00013501405],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9978592,0.00016106394,0.00053477887,0.00011345241,0.001232842,0.000098669494],"domain_scores_gemma":[0.9991506,0.0003249261,0.0002886776,0.0001334921,0.000050816234,0.000051504143],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004509719,0.000083027604,0.00014115941,0.00013142482,0.00010637093,0.000059367096,0.00014546404,0.000026156113,0.00023523574],"category_scores_gemma":[0.000039178256,0.000041650525,0.000027586886,0.00009753078,0.00007045354,0.00022274714,0.00010553682,0.00008588378,0.0000062405825],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011249423,0.0005117841,0.15124829,0.00004098012,0.0012594981,0.00010004763,0.042161565,0.006690665,0.006115308,0.0023911393,0.014010181,0.7743456],"study_design_scores_gemma":[0.002082183,0.00035933132,0.8627597,0.00013695126,0.0003737812,0.0000046290843,0.07383195,0.0031568855,0.005741668,0.0063937297,0.04501962,0.00013955521],"about_ca_topic_score_codex":0.0000028520353,"about_ca_topic_score_gemma":0.000005934264,"teacher_disagreement_score":0.77420604,"about_ca_system_score_codex":0.000040298328,"about_ca_system_score_gemma":0.00000708335,"threshold_uncertainty_score":0.25756663},"labels":[],"label_agreement":null},{"id":"W2119940806","doi":"10.1111/1468-2419.00115","title":"Training evaluation: perspectives and evidence from Canada","year":2000,"lang":"en","type":"article","venue":"International Journal of Training and Development","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Perspective (graphical); Training (meteorology); Sociology; Management training; Psychology; Medical education; Public relations; Pedagogy; Political science; Management; Medicine; Computer science","score_opus":0.3853519311013413,"score_gpt":0.4920965181865723,"score_spread":0.10674458708523099,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119940806","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9906932,0.0019120178,0.00050269323,0.0043587657,0.00048409816,0.00004547436,0.0000029757166,0.0000031352681,0.0019975996],"genre_scores_gemma":[0.99026,0.00025512913,0.008678402,0.0003629967,0.00019468529,0.000002573436,0.0000014585297,0.0000031865254,0.00024153553],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9964012,0.00011588718,0.0006193933,0.00018128465,0.0025829163,0.00009934694],"domain_scores_gemma":[0.9978285,0.0007464931,0.00027470983,0.000066034845,0.0009727569,0.000111517],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0038699766,0.00008617532,0.00017090367,0.00013235457,0.00010671071,0.00022160515,0.00028557391,0.000022775228,0.0029804115],"category_scores_gemma":[0.000933151,0.00006387994,0.000022791794,0.00007924143,0.00004379963,0.00043846248,0.000026764346,0.0001138807,0.0000060473185],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039723283,0.000009131704,0.006895621,4.3409477e-7,0.000069110254,0.00001034612,0.052613266,0.000475526,0.00002500688,0.000028861727,0.0003478449,0.93948513],"study_design_scores_gemma":[0.0016906551,0.00010286521,0.78765285,0.00045581209,0.000029684055,0.00026661856,0.10359482,0.007941352,0.00018944722,0.002903913,0.09489297,0.00027901545],"about_ca_topic_score_codex":0.0026099768,"about_ca_topic_score_gemma":0.012043742,"teacher_disagreement_score":0.9392061,"about_ca_system_score_codex":0.00018030113,"about_ca_system_score_gemma":0.003030344,"threshold_uncertainty_score":0.997931},"labels":[],"label_agreement":null},{"id":"W2119978303","doi":"10.1016/j.evalprogplan.2015.09.006","title":"Utilization of internal evaluation results by community mental health organizations: Credibility in different forms","year":2015,"lang":"en","type":"article","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Mental Health Association; York University","funders":"","keywords":"Credibility; Respondent; Internal consistency; Objectivity (philosophy); Mental health; Internal validity; Psychology; Consistency (knowledge bases); Program evaluation; Applied psychology; Public relations; Medicine; Political science; Clinical psychology; Psychometrics; Computer science; Psychiatry","score_opus":0.4930127229246157,"score_gpt":0.6011227326634501,"score_spread":0.10811000973883439,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119978303","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9907198,0.00074906717,0.0022844137,0.001614751,0.000261619,0.0018467274,0.00005435333,0.000039096667,0.0024301955],"genre_scores_gemma":[0.99789155,0.00002586375,0.00062732736,0.00019432728,0.000023376908,0.00009374113,0.0010875455,0.0000075690327,0.000048703987],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99220973,0.0028369993,0.0013051865,0.0003183325,0.0031319081,0.00019784852],"domain_scores_gemma":[0.9965842,0.00040302458,0.0006942822,0.0003666224,0.0018007447,0.00015114587],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.040357396,0.00014950785,0.00028472464,0.00029622228,0.00023712561,0.00016624382,0.00024332324,0.00007190535,0.00019612476],"category_scores_gemma":[0.006709946,0.00011118082,0.000028906565,0.0009449307,0.000078791505,0.0005773301,0.00009738036,0.00022566186,0.000007678215],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026805667,0.00064111565,0.26822856,0.000018124088,0.00001563975,5.811271e-8,0.03143546,0.0037897602,0.00006288848,0.00012465121,0.008379355,0.68703634],"study_design_scores_gemma":[0.004113664,0.00071220647,0.23740253,0.00012887345,0.000015968862,0.0000024720646,0.014234103,0.7347408,0.00030536222,0.005175926,0.0030313672,0.00013675196],"about_ca_topic_score_codex":0.00019711425,"about_ca_topic_score_gemma":0.0002924238,"teacher_disagreement_score":0.730951,"about_ca_system_score_codex":0.00035729172,"about_ca_system_score_gemma":0.00060609065,"threshold_uncertainty_score":0.988154},"labels":[],"label_agreement":null},{"id":"W2120146990","doi":"10.7202/1021540ar","title":"L’évaluation d’un projet d’intervention par les pairs et le respect de ses principes d’action : le cas du GIAP","year":2014,"lang":"fr","type":"article","venue":"Drogues santé et société","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Humanities; Valuation (finance); Political science; Philosophy; Economics; Finance","score_opus":0.15969163385961302,"score_gpt":0.47839236624136994,"score_spread":0.3187007323817569,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120146990","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8504529,0.0013353348,0.0372599,0.035004873,0.0030022773,0.00092993036,0.000052993062,0.00023998885,0.07172178],"genre_scores_gemma":[0.9864203,0.0015796539,0.0043682796,0.0009126149,0.0006581854,0.00014394961,0.00015958118,0.00004723163,0.005710225],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9907327,0.004779585,0.0012281277,0.00079495367,0.0018701416,0.0005944629],"domain_scores_gemma":[0.99591166,0.001733199,0.00085257605,0.0006184049,0.0007098558,0.00017431949],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.022052797,0.0003977698,0.0005089191,0.00030183303,0.0009907854,0.00070567173,0.00051166245,0.00035303037,0.0027880126],"category_scores_gemma":[0.0025702382,0.0003756376,0.0004672147,0.0005634262,0.0003100996,0.001844102,0.00018833774,0.00050318567,0.00051759795],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011374484,0.000827684,0.028148046,0.00011583107,0.00010646327,0.0000045128645,0.011975093,0.0025341026,0.00090463244,0.030519357,0.0058724284,0.9188781],"study_design_scores_gemma":[0.0038646911,0.0009621958,0.447166,0.00048760057,0.0001993217,0.00007954312,0.060746413,0.17161778,0.013608468,0.059648026,0.24073426,0.00088571204],"about_ca_topic_score_codex":0.0024599668,"about_ca_topic_score_gemma":0.004477693,"teacher_disagreement_score":0.9179924,"about_ca_system_score_codex":0.00042432887,"about_ca_system_score_gemma":0.0010919813,"threshold_uncertainty_score":0.9998696},"labels":[],"label_agreement":null},{"id":"W2120292430","doi":"10.1177/1098214012440030","title":"A New Realistic Evaluation Analysis Method","year":2012,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":144,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Public Health Ontario; University of Toronto","funders":"Health Research Board","keywords":"Coding (social sciences); Computer science; Qualitative research; Qualitative analysis; Narrative; Management science; Context (archaeology); Evaluation methods; Data science; Psychology; Sociology; Social science; Engineering","score_opus":0.29742318158161135,"score_gpt":0.6135208376358036,"score_spread":0.3160976560541922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120292430","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2729564,0.00047320683,0.7160211,0.0023298915,0.0008939134,0.00034561535,0.0000034624757,0.00000912737,0.0069672633],"genre_scores_gemma":[0.9390099,0.000018102959,0.059850387,0.00033082452,0.0005459119,0.000008960162,0.000012333111,0.000007946536,0.00021565447],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98620427,0.0036090617,0.0014516233,0.00021308832,0.008253094,0.0002688432],"domain_scores_gemma":[0.9905058,0.0015396079,0.0026389742,0.00047343184,0.004504244,0.0003379342],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.08044642,0.00014157471,0.000533049,0.0013237938,0.00010950227,0.00014717273,0.00035287274,0.00003633859,0.009592068],"category_scores_gemma":[0.008161817,0.00010074926,0.00034325197,0.004146119,0.000052745836,0.0011957019,0.000031590032,0.00017001606,0.00015889762],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056471803,0.000053866766,0.039207507,5.0199844e-7,0.00028522318,2.033798e-7,0.0017722686,0.043084387,0.00016589371,0.00038730152,0.0038795734,0.9111068],"study_design_scores_gemma":[0.0010173871,0.00045864744,0.53329664,0.0000112399775,0.004213882,0.00004073945,0.0032798636,0.44310302,0.00015972738,0.009809973,0.004422669,0.00018623992],"about_ca_topic_score_codex":0.00011767673,"about_ca_topic_score_gemma":0.000052354808,"teacher_disagreement_score":0.91092056,"about_ca_system_score_codex":0.00037985574,"about_ca_system_score_gemma":0.0013892109,"threshold_uncertainty_score":0.9913133},"labels":[],"label_agreement":null},{"id":"W2120293388","doi":"10.1016/j.evalprogplan.2011.10.005","title":"Beyond resistance: Exploring health managers’ propensity for participatory evaluation in a developing country","year":2011,"lang":"en","type":"article","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Institut National de Santé Publique du Québec","keywords":"Citizen journalism; Meaning (existential); Psychological intervention; Public relations; Psychology; Process (computing); Action (physics); Resistance (ecology); Participatory action research; Business; Applied psychology; Sociology; Nursing; Medicine; Political science; Computer science","score_opus":0.7568210147087717,"score_gpt":0.5826741051646402,"score_spread":0.17414690954413148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120293388","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97734386,0.0017788289,0.00466296,0.0013879273,0.0006128196,0.0050259833,0.0000064355595,0.00008984059,0.009091334],"genre_scores_gemma":[0.9793312,0.000052859945,0.016998896,0.000713687,0.000059309896,0.0026575143,0.00005907764,0.000013020316,0.0001144284],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99525946,0.0008515934,0.00086889055,0.00046961496,0.0021693076,0.0003811512],"domain_scores_gemma":[0.9979927,0.000324366,0.00041123808,0.00028026718,0.00087848614,0.00011293994],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03916711,0.00016064003,0.0002902786,0.00035095974,0.00038888323,0.00021312406,0.00018441898,0.00006157802,0.00025560957],"category_scores_gemma":[0.0014244951,0.00013760687,0.000037693517,0.0006935929,0.000055265205,0.00086777034,0.000050247436,0.00013037183,0.000016212955],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023622379,0.00011335445,0.12188656,0.00007828859,0.000023887414,0.0000011743373,0.036335923,0.00068206195,0.000013213575,0.0057008145,0.0014956153,0.8334329],"study_design_scores_gemma":[0.00286399,0.00030320045,0.74789673,0.00037997734,0.0000570779,0.0000024657247,0.011675962,0.18033531,0.00015853786,0.031468444,0.024457958,0.00040035992],"about_ca_topic_score_codex":0.00002798001,"about_ca_topic_score_gemma":0.00043585256,"teacher_disagreement_score":0.83303255,"about_ca_system_score_codex":0.00028180622,"about_ca_system_score_gemma":0.0008899471,"threshold_uncertainty_score":0.98937964},"labels":[],"label_agreement":null},{"id":"W2121899445","doi":"","title":"A Book Review: Anfara, V. A., & Mertz, N. T. (Eds.). (2006). Theoretical frameworks in qualitative research. Thousand Oaks, CA: Sage","year":2008,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":139,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Task (project management); Qualitative research; Epistemology; Sociology; Process (computing); Guideline; Engineering ethics; Computer science; Management science; Data science; Engineering; Social science; Philosophy; Political science; Systems engineering; Law","score_opus":0.48917081457279643,"score_gpt":0.7036625099608368,"score_spread":0.21449169538804036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121899445","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.076942444,0.8781567,0.0014596147,0.010154634,0.00084167684,0.0019565597,0.00012506766,0.000036972262,0.030326325],"genre_scores_gemma":[0.2777932,0.6989488,0.00046680408,0.0144277215,0.00021599908,0.0002207215,0.000021391485,0.000052135445,0.007853219],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98159456,0.0072711613,0.0027846028,0.000978129,0.0064751203,0.00089643133],"domain_scores_gemma":[0.9870134,0.008189272,0.0011448971,0.0012634421,0.0018794837,0.000509496],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.045562625,0.00040758486,0.0014579847,0.001885266,0.00067904306,0.0012658411,0.005061719,0.000322991,0.18822537],"category_scores_gemma":[0.009803932,0.00029520396,0.00031485516,0.004338606,0.0013298804,0.003910657,0.0013306452,0.0023085687,0.00058052404],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020376961,0.00034821295,0.02545398,0.00006886714,0.000058235284,0.00008972354,0.00277355,0.000099350116,0.00042634588,0.0010703491,0.9511336,0.018274026],"study_design_scores_gemma":[0.0011649678,0.00006772091,0.13313942,0.0033414,0.000047329555,0.000049693288,0.0015215375,0.0007845294,0.0014414949,0.06719663,0.7904986,0.0007466822],"about_ca_topic_score_codex":0.00035830663,"about_ca_topic_score_gemma":0.00008589508,"teacher_disagreement_score":0.20085075,"about_ca_system_score_codex":0.00020020524,"about_ca_system_score_gemma":0.00094933907,"threshold_uncertainty_score":0.99999315},"labels":[],"label_agreement":null},{"id":"W2122097906","doi":"10.1093/ije/dys069","title":"Commentary: Reporting and assessing evidence for interaction: why, when and how?","year":2012,"lang":"en","type":"letter","venue":"International Journal of Epidemiology","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Juvenile Diabetes Research Foundation","funders":"Wellcome Trust","keywords":"MEDLINE; Medicine; Psychology; Political science; Law","score_opus":0.7144297374333387,"score_gpt":0.633221009065258,"score_spread":0.08120872836808068,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122097906","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0055197948,0.0022969423,0.029956618,0.9561275,0.0058012027,0.0001366107,0.00001259161,0.0000049041146,0.00014380424],"genre_scores_gemma":[0.030201832,0.00075379567,0.024709182,0.9323137,0.011394666,0.000013318419,0.00004017353,0.00001861186,0.0005547438],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9941478,0.0013252001,0.0028678225,0.00035786265,0.0010185213,0.00028283297],"domain_scores_gemma":[0.9551336,0.03154667,0.011092711,0.00022681437,0.0018926614,0.00010752061],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.033207882,0.00020685488,0.00086264085,0.0005290252,0.00011100008,0.00033629048,0.0006537306,0.00030773034,0.00038137933],"category_scores_gemma":[0.065925166,0.00014472158,0.00022327082,0.000056088043,0.00017868222,0.0018794042,0.00021316974,0.0010863966,0.000003767952],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004320835,0.000008338137,0.07122048,0.000013331498,0.00014243048,0.000028276829,0.00014902116,0.000010525349,0.000018734112,0.000089806505,0.8811671,0.047108736],"study_design_scores_gemma":[0.00032724714,0.00012408604,0.009572568,0.0003915366,0.00007141916,0.0014408979,0.0002330066,0.0012605314,0.000008852755,0.016747838,0.9696855,0.00013654426],"about_ca_topic_score_codex":0.000028295188,"about_ca_topic_score_gemma":0.000012174178,"teacher_disagreement_score":0.08851836,"about_ca_system_score_codex":0.00017800598,"about_ca_system_score_gemma":0.00015412625,"threshold_uncertainty_score":0.99551594},"labels":[],"label_agreement":null},{"id":"W2122162752","doi":"10.7202/1032814ar","title":"Outils et méthodes d’évaluation continue de la formation","year":2015,"lang":"fr","type":"article","venue":"Documentation et bibliothèques","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Political science; Humanities; Philosophy","score_opus":0.2603960221367995,"score_gpt":0.5495678041799853,"score_spread":0.2891717820431858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122162752","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2035242,0.008785142,0.5055601,0.046876296,0.0030682385,0.001262154,0.000097932985,0.0002558907,0.23057005],"genre_scores_gemma":[0.8813248,0.011601366,0.042530723,0.007961668,0.00031719697,0.00016541361,0.0002690931,0.000043002787,0.055786718],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9884232,0.0070185065,0.0011492283,0.00044493747,0.0025382666,0.0004258375],"domain_scores_gemma":[0.99477935,0.0025578502,0.0006833495,0.0004005412,0.0012678319,0.00031108622],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["scholarly_communication","insufficient_payload"],"category_scores_codex":[0.036306363,0.00029287572,0.00033189447,0.002509453,0.0001921714,0.010212092,0.0004029542,0.0002460125,0.010509178],"category_scores_gemma":[0.0031162133,0.000275574,0.00013536659,0.0034234133,0.00022425887,0.031618003,0.000102603764,0.00032407598,0.0013202508],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020910185,0.0005142922,0.027870094,0.00009574969,0.00008339342,0.000010413223,0.06959564,0.010960674,0.0017363686,0.35672185,0.31594896,0.21625344],"study_design_scores_gemma":[0.003397033,0.00043322757,0.031199852,0.00023885937,0.00010992601,0.00006977904,0.015754307,0.08111743,0.006324475,0.26811376,0.59268355,0.0005577691],"about_ca_topic_score_codex":0.00055270275,"about_ca_topic_score_gemma":0.00031217726,"teacher_disagreement_score":0.6778006,"about_ca_system_score_codex":0.0005827278,"about_ca_system_score_gemma":0.0022183398,"threshold_uncertainty_score":0.99996966},"labels":[],"label_agreement":null},{"id":"W2123038534","doi":"10.1111/j.1440-1800.2011.00550.x","title":"Back‐ and fore‐grounding ontology: exploring the linkages between critical realism, pragmatism, and methodologies in health &amp; rehabilitation sciences","year":2011,"lang":"en","type":"article","venue":"Nursing Inquiry","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Pragmatism; Critical realism (philosophy of perception); Ontology; Realism; Rehabilitation; Epistemology; Sociology; Engineering ethics; Philosophy; Medicine; Engineering; Physical therapy","score_opus":0.7947285193433391,"score_gpt":0.6089759851920545,"score_spread":0.18575253415128457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123038534","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9456837,0.0005293761,0.023783222,0.02715038,0.0008786001,0.000272911,0.0000020195164,0.000028349858,0.0016714173],"genre_scores_gemma":[0.87502456,0.000110839974,0.12442764,0.00027967023,0.00008531424,0.000026750316,0.0000014490272,0.0000055451715,0.000038247585],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99626726,0.0016839583,0.00066896953,0.00043959767,0.0006203192,0.00031987234],"domain_scores_gemma":[0.9888616,0.010500458,0.00018485534,0.00026901916,0.00010338413,0.0000806652],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02004429,0.00011911444,0.00029459223,0.0003323615,0.00053829607,0.00021673643,0.00027613124,0.00006569206,0.00006947624],"category_scores_gemma":[0.0066068848,0.0000696251,0.000027103077,0.0005097632,0.0018690141,0.0010032865,0.00006981777,0.00020462583,0.00001317223],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001262752,0.000036302754,0.41372976,0.000043789987,0.0000053058766,3.9523258e-7,0.17628317,0.000020825632,0.000024561326,0.03956599,0.0008552312,0.36942208],"study_design_scores_gemma":[0.00014753957,0.0002620619,0.79143393,0.00023077869,0.0000057291077,0.0000076153597,0.04009124,0.00034954734,0.00002128677,0.16659588,0.0007657319,0.000088663444],"about_ca_topic_score_codex":0.00027670278,"about_ca_topic_score_gemma":0.00015553828,"teacher_disagreement_score":0.3777042,"about_ca_system_score_codex":0.00008462715,"about_ca_system_score_gemma":0.0001256138,"threshold_uncertainty_score":0.7909536},"labels":[],"label_agreement":null},{"id":"W2123413191","doi":"10.1177/1049732310379119","title":"Commentary 3: The Disciplinary Divide","year":2010,"lang":"en","type":"letter","venue":"Qualitative Health Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Discipline; Sociology; Psychology; Engineering ethics; Social science; Engineering","score_opus":0.8917660211022507,"score_gpt":0.7720822596696154,"score_spread":0.11968376143263526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123413191","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00077618076,0.0005137473,0.00036154545,0.9887032,0.0011691094,0.0015369953,0.00028487126,0.000029460321,0.0066248886],"genre_scores_gemma":[0.0017374562,0.00019273364,0.00049318484,0.9657681,0.0041554365,0.00047347604,0.00040685927,0.000044143824,0.026728632],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.93840516,0.04187696,0.0018811041,0.0011323468,0.015095835,0.0016085891],"domain_scores_gemma":[0.935848,0.05885768,0.0006804175,0.0021112936,0.0022278796,0.00027471472],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.16610472,0.00032337406,0.0006817551,0.0009066217,0.0028484003,0.000695239,0.003184648,0.0007388032,0.005187098],"category_scores_gemma":[0.006195349,0.0001709245,0.0002213129,0.0018724367,0.0015817985,0.00035729495,0.0010617044,0.018159628,0.004206143],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001990601,0.00003917366,0.00009512322,0.00006693139,0.00002024613,0.00001156798,0.046760485,0.0000010552021,0.0000012714298,0.00064167177,0.93411535,0.018227246],"study_design_scores_gemma":[0.00020151559,0.00037513694,0.0009483998,0.000071804374,0.0000026201649,0.000003043553,0.024631968,0.000133324,0.0000025557933,0.0866922,0.8867714,0.00016603335],"about_ca_topic_score_codex":0.00090321066,"about_ca_topic_score_gemma":0.0009255878,"teacher_disagreement_score":0.15990937,"about_ca_system_score_codex":0.00048469618,"about_ca_system_score_gemma":0.002507133,"threshold_uncertainty_score":0.99844974},"labels":[],"label_agreement":null},{"id":"W2123532490","doi":"10.4000/osp.4354","title":"Les pratiques des conseillers d’orientation du Québec en matière d’évaluation psychométrique dans les écoles secondaires : dimensions évaluées, tests utilisés et exercice des activités réservées par le projet de loi 21","year":2014,"lang":"fr","type":"article","venue":"L’Orientation scolaire et professionnelle","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.09937420421634718,"score_gpt":0.43792133402569705,"score_spread":0.33854712980934987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123532490","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8813038,0.0007682258,0.07566995,0.030957222,0.0017380752,0.002502045,0.00007346412,0.00027189765,0.006715323],"genre_scores_gemma":[0.96195304,0.0010465254,0.02510679,0.0012112675,0.00029712796,0.0010556452,0.0002610604,0.000109363966,0.0089591555],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9819794,0.011344323,0.0020892764,0.0014429871,0.0022249161,0.00091909565],"domain_scores_gemma":[0.9887531,0.0062179565,0.0015098695,0.00093672384,0.0021333566,0.00044901864],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.015005582,0.0008332216,0.00083663187,0.0006649451,0.0032921298,0.00079858047,0.00077744795,0.000709297,0.002256212],"category_scores_gemma":[0.005835458,0.0007389261,0.0003109526,0.001625182,0.0012204513,0.004729262,0.00030748954,0.0009841787,0.00020712157],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038708607,0.0012608734,0.42203742,0.00051952974,0.00010828568,0.000005785676,0.38323265,0.006104898,0.0062277135,0.0125108315,0.0075050425,0.16009988],"study_design_scores_gemma":[0.0025928568,0.00063638436,0.6785531,0.0020773867,0.00016384687,0.000039009403,0.23240626,0.044373963,0.012420711,0.013404515,0.012462585,0.00086937833],"about_ca_topic_score_codex":0.042049248,"about_ca_topic_score_gemma":0.2594341,"teacher_disagreement_score":0.25651568,"about_ca_system_score_codex":0.0011877923,"about_ca_system_score_gemma":0.009566799,"threshold_uncertainty_score":0.9995062},"labels":[],"label_agreement":null},{"id":"W2123646142","doi":"10.1016/s0840-4704(10)60508-x","title":"Le programme de Formation en recherche pour cadres qui exercent dans la santé (FORCES): Perceptions de la première cohorte de boursiers","year":2007,"lang":"fr","type":"article","venue":"Healthcare Management Forum","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University; McGill University","funders":"","keywords":"Humanities; Political science; Art","score_opus":0.13642173417529824,"score_gpt":0.5006085389510527,"score_spread":0.3641868047757545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123646142","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23196138,0.0018132697,0.44021353,0.107003234,0.0008016887,0.0030179175,0.00006204537,0.0002726178,0.21485431],"genre_scores_gemma":[0.9211528,0.0053143464,0.04465886,0.0028060838,0.0002266583,0.0002656828,0.00007174052,0.00005304513,0.025450813],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.98926806,0.004521238,0.0012225863,0.00065535755,0.001594799,0.0027379715],"domain_scores_gemma":[0.9961324,0.0016363601,0.00042341577,0.0006757597,0.00029332924,0.00083875546],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.046666726,0.00036868322,0.00035990754,0.000513674,0.0010080402,0.00056282885,0.0007967804,0.0006177133,0.0005423985],"category_scores_gemma":[0.0006579777,0.0003732337,0.00024269303,0.000978304,0.0002976216,0.0008721026,0.0002823898,0.0009163733,0.00019378078],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013447601,0.00045046862,0.082503036,0.0006784365,0.000090421,0.00006603019,0.039553214,0.0014319515,0.00008546826,0.16493869,0.030040877,0.68002695],"study_design_scores_gemma":[0.001212249,0.00027312947,0.22145474,0.0005851116,0.00012332905,0.00014819151,0.44548059,0.03266926,0.00016270202,0.03362028,0.2637963,0.00047411793],"about_ca_topic_score_codex":0.001717541,"about_ca_topic_score_gemma":0.007828533,"teacher_disagreement_score":0.6891914,"about_ca_system_score_codex":0.0047666905,"about_ca_system_score_gemma":0.0024574553,"threshold_uncertainty_score":0.99987197},"labels":[],"label_agreement":null},{"id":"W2123913288","doi":"10.1016/j.jneb.2008.03.116","title":"Peer education, Exercising, and Eating Right (PEER): Training of Peers in an Undergraduate Faculty Teaching Partnership","year":2009,"lang":"en","type":"article","venue":"Journal of Nutrition Education and Behavior","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"U.S. Department of Agriculture; U.S. Department of Education","keywords":"Social cognitive theory; Scopus; Medical education; Psychology; Outreach; General partnership; Formative assessment; Health promotion; Social learning theory; Pedagogy; Medicine; Social psychology; Nursing; MEDLINE; Public health; Political science","score_opus":0.1919986632698613,"score_gpt":0.5169824116687163,"score_spread":0.32498374839885497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123913288","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9853232,0.00017984527,0.00011531377,0.012873832,0.0003655687,0.00018490144,0.0000032383214,0.0000050742665,0.0009490355],"genre_scores_gemma":[0.9901271,0.00004187531,0.007899234,0.00032844915,0.00020035729,0.000014873292,0.000024196715,0.000004991591,0.0013589376],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9971977,0.00024734804,0.0009551461,0.00018736324,0.0012825249,0.00012991187],"domain_scores_gemma":[0.9971134,0.00013918309,0.0007552902,0.00013334892,0.0016863364,0.00017245908],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042538634,0.0001134147,0.00026296088,0.00063572556,0.00016231716,0.0002503409,0.00016006647,0.0000679164,0.000094110546],"category_scores_gemma":[0.00074426085,0.00009072522,0.000057472655,0.00030329134,0.000049702936,0.0012440401,0.00000858392,0.00026446488,0.0000014071076],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003597079,0.0063428343,0.18317308,0.000023000488,0.0000044503113,0.0000013657166,0.020785702,0.000021565553,0.0022235238,0.0021769986,0.008487281,0.7767242],"study_design_scores_gemma":[0.0010047292,0.00045115626,0.88816047,0.00035987602,0.00006051818,0.000121758,0.08789022,0.00023720729,0.00033538992,0.009666031,0.011549518,0.0001631366],"about_ca_topic_score_codex":0.000014093665,"about_ca_topic_score_gemma":0.00002904172,"teacher_disagreement_score":0.7765611,"about_ca_system_score_codex":0.00007766547,"about_ca_system_score_gemma":0.0006149792,"threshold_uncertainty_score":0.36996672},"labels":[],"label_agreement":null},{"id":"W2124445109","doi":"10.26522/brocked.v12i2.38","title":"The Use of Think-aloud Methods in Qualitative Research An Introduction to Think-aloud Methods","year":2003,"lang":"en","type":"article","venue":"Brock Education Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":755,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Think aloud protocol; Qualitative research; Interpretation (philosophy); Reciprocity (cultural anthropology); Task (project management); Psychology; Reading aloud; Participant observation; Qualitative property; Triangulation; Process (computing); Computer science; Social psychology; Human–computer interaction; Linguistics; Sociology; Reading (process); Mathematics; Engineering; Social science","score_opus":0.6737008481614124,"score_gpt":0.7246427914241172,"score_spread":0.05094194326270485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2124445109","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6080451,0.0006264746,0.3324538,0.048157535,0.008068267,0.001009897,0.000004380924,0.000023127292,0.0016114244],"genre_scores_gemma":[0.04158712,0.00016573217,0.9433522,0.0008075286,0.0012809801,0.000017568622,0.0000045555726,0.000023429398,0.012760853],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9591155,0.03538527,0.0017662224,0.000520398,0.0027431364,0.00046947182],"domain_scores_gemma":[0.9836898,0.009815085,0.0006854397,0.0009203319,0.0044868365,0.00040255085],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0843245,0.0001555936,0.00030053803,0.0010459402,0.00090428744,0.0008765942,0.000781614,0.00009896222,0.0012114765],"category_scores_gemma":[0.06162749,0.00009916981,0.000103497274,0.0028076752,0.00013512078,0.0014533658,0.00006932524,0.00088208856,0.00008394738],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013395245,0.00039671364,0.00063876604,0.0000058460537,0.00002894188,2.587471e-7,0.28603205,0.0032860858,0.005484136,0.031238284,0.15039809,0.52235687],"study_design_scores_gemma":[0.00030072493,0.00032974457,0.0096808355,0.000027085234,0.000010293194,0.000057361827,0.5165219,0.0012150855,0.0039873254,0.14676446,0.3209326,0.00017263216],"about_ca_topic_score_codex":0.000051977357,"about_ca_topic_score_gemma":0.00012405346,"teacher_disagreement_score":0.61089844,"about_ca_system_score_codex":0.0003257608,"about_ca_system_score_gemma":0.003042244,"threshold_uncertainty_score":0.99970156},"labels":[],"label_agreement":null},{"id":"W2125410695","doi":"10.1002/ev.221","title":"The partnership of <i>new directions for evaluation</i> and the American evaluation association","year":2007,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Association (psychology); General partnership; Political science; Computer science; Sociology; Psychology; Law","score_opus":0.21838504639813228,"score_gpt":0.5369309968417352,"score_spread":0.3185459504436029,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125410695","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5878284,0.009630384,0.20287034,0.08705153,0.011363352,0.044238314,0.00014805535,0.00037526834,0.05649438],"genre_scores_gemma":[0.98035777,0.0004153797,0.0025899415,0.00049642933,0.0011904417,0.002527056,0.00014581822,0.000038955397,0.012238192],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98942703,0.0018327346,0.0015968974,0.0006445365,0.006022083,0.00047668867],"domain_scores_gemma":[0.9735965,0.015857397,0.0020884972,0.0007377647,0.0075501776,0.000169655],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.121397234,0.00024084326,0.0004173595,0.00041389957,0.0018357547,0.00042475754,0.00040066402,0.000116550465,0.00028313257],"category_scores_gemma":[0.042096213,0.00015333366,0.00033392344,0.001967295,0.00023943264,0.00059771095,0.000043523178,0.00017574777,0.000026560183],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00062348205,0.000063570405,0.0040616393,0.0000042613074,0.00013628756,5.4737774e-9,0.0016692926,0.0026879767,0.00014231981,0.004862284,0.050348476,0.9354004],"study_design_scores_gemma":[0.012209879,0.00033359247,0.10805281,0.000024069535,0.0015555527,0.0000030442486,0.003718077,0.45060465,0.0014719767,0.137317,0.2844199,0.0002894347],"about_ca_topic_score_codex":0.0004474797,"about_ca_topic_score_gemma":0.0069186585,"teacher_disagreement_score":0.935111,"about_ca_system_score_codex":0.00096684886,"about_ca_system_score_gemma":0.002148149,"threshold_uncertainty_score":0.99946374},"labels":[],"label_agreement":null},{"id":"W2126111248","doi":"10.1111/capa.12059","title":"La fonction d'évaluation dans l'administration publique québécoise : analyse de la cohérence du système d'actions","year":2014,"lang":"fr","type":"article","venue":"Canadian Public Administration","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université Laval; Université de Montréal","funders":"","keywords":"Humanities; Political science; Valuation (finance); Transparency (behavior); Philosophy; Business; Accounting; Law","score_opus":0.0828089893422985,"score_gpt":0.39713476135761455,"score_spread":0.3143257720153161,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126111248","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34129962,0.00021097901,0.26231217,0.22065933,0.0033732688,0.0011905152,0.00025806268,0.00020496105,0.17049107],"genre_scores_gemma":[0.98946595,0.00014415948,0.0014904388,0.0013133468,0.0008200011,0.00021242576,0.00063236145,0.000040459072,0.005880853],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99063796,0.0045881323,0.0013937356,0.000909607,0.0016207411,0.00084985024],"domain_scores_gemma":[0.99349093,0.0018602262,0.00078823266,0.00087186514,0.0014265059,0.001562233],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.015414211,0.00044911058,0.00041532583,0.001322395,0.0012387506,0.0033152658,0.00067058584,0.0008405582,0.0029562048],"category_scores_gemma":[0.006581694,0.00049529306,0.00022855567,0.0022364731,0.00058444333,0.0036211505,0.000034032193,0.0006485113,0.00035863018],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005555108,0.0003754743,0.04781983,0.00006566325,0.00009358546,0.000037708473,0.0018229426,0.000547732,0.00047213072,0.7681744,0.015090074,0.16544491],"study_design_scores_gemma":[0.0006668712,0.0005462139,0.088763915,0.000074277596,0.00015601983,0.00044321333,0.0027164775,0.18290748,0.00025924382,0.01139224,0.7115341,0.00053993665],"about_ca_topic_score_codex":0.026258789,"about_ca_topic_score_gemma":0.82105803,"teacher_disagreement_score":0.79479927,"about_ca_system_score_codex":0.0034241513,"about_ca_system_score_gemma":0.05407734,"threshold_uncertainty_score":0.9997499},"labels":[],"label_agreement":null},{"id":"W2127799896","doi":"10.7179//psri_2014.24.06","title":"Intersecciones entre evaluación participativa y pedagogía social","year":2014,"lang":"es","type":"article","venue":"Pedagogia Social Revista Interuniversitaria","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Sociology","score_opus":0.14922127261642823,"score_gpt":0.4838247521468176,"score_spread":0.3346034795303894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127799896","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80942506,0.00029428385,0.0074242787,0.028127743,0.0029107756,0.0010386881,0.00020380788,0.0002406088,0.15033475],"genre_scores_gemma":[0.98728955,0.00007237481,0.00017828411,0.00076579064,0.0016162097,0.000015331749,0.00006956812,0.000053967906,0.009938909],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9913594,0.0021306141,0.0014582811,0.001221648,0.0028123413,0.0010176952],"domain_scores_gemma":[0.99552196,0.00096033013,0.0011681017,0.000649043,0.0013555207,0.0003450576],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0046427925,0.0007114639,0.0011826287,0.00057190657,0.0020260413,0.0015889849,0.0018071879,0.0004720696,0.033578224],"category_scores_gemma":[0.0014401143,0.00067797606,0.0008780896,0.0010713825,0.0006410755,0.0012509469,0.0008900128,0.0007939034,0.0050386945],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008844392,0.00066132226,0.031660106,0.00028083072,0.00062132685,0.00002849111,0.09677782,0.00004561764,0.0006938991,0.61351734,0.09912221,0.15570661],"study_design_scores_gemma":[0.0024388982,0.00058601587,0.05449827,0.00023481542,0.00062735827,0.0000054565758,0.07085839,0.008916095,0.00007600638,0.0022534549,0.8583268,0.0011784412],"about_ca_topic_score_codex":0.00016457328,"about_ca_topic_score_gemma":0.00010643697,"teacher_disagreement_score":0.75920457,"about_ca_system_score_codex":0.0007923243,"about_ca_system_score_gemma":0.0009525673,"threshold_uncertainty_score":0.99956715},"labels":[],"label_agreement":null},{"id":"W2128827052","doi":"10.1177/1356389009105884","title":"Critical Connections between Participatory Evaluation, Organizational Learning and Intentional Change in Pluralistic Organizations","year":2009,"lang":"en","type":"article","venue":"Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":84,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Praxis; Citizen journalism; Sociology; Resistance (ecology); Process (computing); Organizational learning; Participatory action research; Organization development; Epistemology; Psychology; Knowledge management; Political science; Computer science","score_opus":0.34842097867393707,"score_gpt":0.5590078097974384,"score_spread":0.2105868311235013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128827052","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9656277,0.00032888804,0.008712304,0.01967823,0.0005410725,0.0012393533,0.000019854593,0.00008691916,0.0037656908],"genre_scores_gemma":[0.99817777,0.000014788179,0.00042147023,0.00051410834,0.0003066624,0.00013198525,0.00029346632,0.000011254289,0.00012852467],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9938929,0.0013719725,0.0008459202,0.00042300383,0.0032189058,0.00024727744],"domain_scores_gemma":[0.99278617,0.0013774202,0.00020330882,0.00020592935,0.005293069,0.00013409088],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01267365,0.00015303114,0.00022024271,0.0005594899,0.0004610747,0.00027558868,0.00016487714,0.00010366692,0.011743152],"category_scores_gemma":[0.034166325,0.00014300161,0.000032200063,0.00208726,0.00009882198,0.0009961962,0.000043768592,0.0002207755,0.00029297],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012361186,0.00016695779,0.8767616,0.000004692659,0.000015407191,5.0444913e-7,0.0047862697,0.0034267898,0.00033790158,0.052694105,0.00042273954,0.06137066],"study_design_scores_gemma":[0.00062780915,0.0000793889,0.6779665,0.00001935413,0.000072163966,0.0000030833667,0.0007567983,0.25420234,0.000039562117,0.06569722,0.00040540364,0.00013037668],"about_ca_topic_score_codex":0.000018889175,"about_ca_topic_score_gemma":0.00011294318,"teacher_disagreement_score":0.25077555,"about_ca_system_score_codex":0.0003001598,"about_ca_system_score_gemma":0.00060758844,"threshold_uncertainty_score":0.98916024},"labels":[],"label_agreement":null},{"id":"W2129456902","doi":"10.1136/ip.8.1.1","title":"Evaluation and other issues","year":2002,"lang":"en","type":"editorial","venue":"Injury Prevention","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Children's Hospital; McGill University","funders":"","keywords":"Consolation; Skepticism; Psychological intervention; Intervention (counseling); Psychology; Public relations; sort; Nudge theory; Internet privacy; Computer security; Computer science; Engineering ethics; Social psychology; Political science; Engineering; Epistemology; Psychiatry","score_opus":0.19922930105865655,"score_gpt":0.5631343257050921,"score_spread":0.3639050246464356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129456902","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002242176,0.0020470708,0.00041542458,0.0004818547,0.9681629,0.0009251456,0.00011986605,0.0000633852,0.02554217],"genre_scores_gemma":[0.006364313,0.0008107171,0.00070040434,0.00012895413,0.87604654,0.00023706029,0.00019672514,0.000053111373,0.115462154],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9899523,0.0011352018,0.000803906,0.0006145745,0.00731499,0.0001790254],"domain_scores_gemma":[0.99661654,0.0006016442,0.0006098905,0.00057953695,0.0015254477,0.0000669156],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.018183518,0.00021446032,0.00032137948,0.00035406815,0.00014665359,0.00044646292,0.00036326173,0.00048036824,0.013777263],"category_scores_gemma":[0.004757662,0.00017122152,0.00011817079,0.00030968548,0.00005391153,0.00048324314,0.00009425629,0.0003314586,0.0013763895],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009953099,0.000031880747,0.000070195645,0.0000056858385,0.00001823024,9.522902e-8,0.00011961275,0.00000580848,0.000010501207,0.00004820223,0.74668545,0.2529944],"study_design_scores_gemma":[0.0003603951,0.00018164392,0.00023560849,0.00007593158,0.0001187498,3.6507714e-7,0.00006179504,0.0044911294,0.00003227543,0.0255957,0.9686562,0.00019024161],"about_ca_topic_score_codex":0.000028379887,"about_ca_topic_score_gemma":0.00007303249,"teacher_disagreement_score":0.25280413,"about_ca_system_score_codex":0.00013758577,"about_ca_system_score_gemma":0.00031669356,"threshold_uncertainty_score":0.99940115},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W2130276747","doi":"10.1177/1356389015593357","title":"Towards a comprehensive framework for the evaluation of small and medium enterprise policy","year":2015,"lang":"en","type":"article","venue":"Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Additionality; Relevance (law); Public policy; Policy analysis; Process management; Business; Management science; Knowledge management; Computer science; Political science; Economics; Public economics; Public administration; Economic growth","score_opus":0.4988657924257035,"score_gpt":0.574468999590146,"score_spread":0.07560320716444247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130276747","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.724194,0.0022599397,0.23669784,0.026420504,0.0017335059,0.004328517,0.0000337664,0.000029612189,0.004302332],"genre_scores_gemma":[0.99111056,0.000037485523,0.0075392663,0.0005634573,0.00031489236,0.00032858108,0.000019026409,0.000008251424,0.00007846703],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9932095,0.00096221705,0.0006148007,0.00029674167,0.0047601885,0.00015654344],"domain_scores_gemma":[0.9899485,0.0020753134,0.00045589934,0.00049777917,0.0069250916,0.00009742288],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.030734038,0.00011669674,0.00020239675,0.00024030142,0.00013270754,0.00012152822,0.0003244335,0.00008305423,0.00036750198],"category_scores_gemma":[0.020636955,0.00007208049,0.00007153903,0.00055184006,0.000103980725,0.00024812034,0.00008198497,0.00009073166,0.000036001995],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018457943,0.00007992711,0.005062198,0.000011574569,0.000060676106,4.188981e-8,0.011760584,0.019257698,0.00019132164,0.010928967,0.003929641,0.9485328],"study_design_scores_gemma":[0.0015211235,0.00016395721,0.114888825,0.000021411874,0.00016129362,0.0000015527995,0.0034680725,0.58593744,0.000351086,0.28925675,0.004149003,0.00007950145],"about_ca_topic_score_codex":0.00007209998,"about_ca_topic_score_gemma":0.000075696335,"teacher_disagreement_score":0.9484533,"about_ca_system_score_codex":0.00018982218,"about_ca_system_score_gemma":0.0021575463,"threshold_uncertainty_score":0.99806327},"labels":[],"label_agreement":null},{"id":"W2130917968","doi":"10.14574/ojrnhc.v11i2.13","title":"The Challenge of Evaluation in Rural Preceptorship","year":2011,"lang":"en","type":"article","venue":"Online Journal of Rural Nursing and Health Care","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Saskatchewan; University of Alberta","funders":"","keywords":"Preceptor; Scope (computer science); Nursing; Medical education; Grounded theory; Medicine; Psychology; Sociology; Qualitative research; Computer science","score_opus":0.28202339227649476,"score_gpt":0.5395176729376205,"score_spread":0.2574942806611258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130917968","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9542129,0.017971162,0.00003475677,0.025112553,0.0009769363,0.00019203192,0.000005044841,0.0000025188394,0.0014921065],"genre_scores_gemma":[0.9968824,0.002312684,0.00054572267,0.00008985493,0.0001313173,0.0000010196802,0.0000029508417,0.0000034921175,0.00003056659],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9972434,0.00041055298,0.000931259,0.000060086975,0.0011981371,0.0001565677],"domain_scores_gemma":[0.9977919,0.00018574383,0.0008127843,0.00013712788,0.0009772456,0.00009523843],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0073309545,0.0000691452,0.00023105921,0.00018452526,0.00014475084,0.00002855529,0.00017550522,0.000038378894,0.000110329565],"category_scores_gemma":[0.0002751706,0.0000383526,0.000058528654,0.00021681904,0.00007714166,0.00022480861,0.000011226579,0.00020543391,0.0000015231047],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000118878976,0.00008399588,0.020329831,0.000012641459,0.000004204259,1.6284524e-7,0.025457406,0.00003240107,0.000006348258,0.00041260823,0.00082117313,0.95272034],"study_design_scores_gemma":[0.0016833205,0.0018876272,0.7887391,0.0015288579,0.00002245288,0.00002968455,0.18421231,0.003124107,0.00005107259,0.017160622,0.0014560785,0.000104776766],"about_ca_topic_score_codex":0.00004715699,"about_ca_topic_score_gemma":0.00049932004,"teacher_disagreement_score":0.95261556,"about_ca_system_score_codex":0.00016545034,"about_ca_system_score_gemma":0.0005610166,"threshold_uncertainty_score":0.25407773},"labels":[],"label_agreement":null},{"id":"W2131259125","doi":"10.1177/104973230001000308","title":"Evaluating Interpretive Inquiry: Reviewing the Validity Debate and Opening the Dialogue","year":2000,"lang":"en","type":"review","venue":"Qualitative Health Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":951,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Foundationalism; Epistemology; Lifeworld; Field (mathematics); External validity; Trustworthiness; Qualitative research; Ontology; Psychology; Sociology; Engineering ethics; Social psychology; Social science; Philosophy","score_opus":0.975849557890781,"score_gpt":0.8206803585145628,"score_spread":0.1551691993762182,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131259125","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011059151,0.9834147,0.00030422804,0.008291163,0.000393175,0.0044529364,0.000071335315,0.000018572997,0.0029432937],"genre_scores_gemma":[0.00036054346,0.99514246,0.0004701236,0.0009978937,0.00037334408,0.0012022452,0.000037019294,0.000040686486,0.001375688],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.81208396,0.17283314,0.0037080764,0.0015280431,0.008469529,0.0013772268],"domain_scores_gemma":[0.8344231,0.15944597,0.0017436853,0.001894422,0.0020997378,0.00039303672],"candidate_categories":["metaresearch","sts","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.37619522,0.00044936757,0.002025991,0.0005715187,0.003394076,0.0011718795,0.0023726958,0.0001817146,0.0013303488],"category_scores_gemma":[0.053242784,0.0001914916,0.00036380856,0.0031869134,0.0013555791,0.00045191197,0.0009575284,0.0029487342,0.0010872498],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011706365,0.000013725235,0.000002776512,0.001473656,0.00003348584,0.000001157283,0.12821622,0.0000028605275,2.1231203e-8,0.0013348999,0.004806342,0.86410314],"study_design_scores_gemma":[0.00010891572,0.00042988113,0.000019250261,0.011831273,0.000040963063,0.000016686503,0.044787697,0.00070960034,8.927292e-8,0.0055138916,0.93633556,0.00020617859],"about_ca_topic_score_codex":0.00027059298,"about_ca_topic_score_gemma":0.00007957742,"teacher_disagreement_score":0.9315292,"about_ca_system_score_codex":0.0006707384,"about_ca_system_score_gemma":0.0051043024,"threshold_uncertainty_score":0.999865},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"not_applicable","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W2131390173","doi":"10.3138/cjpe.29.2.142","title":"Cousins, J. B., &amp; Chouinard, J. A. (Eds.). (2012). <i>Participatory evaluation up close: An integration of research-based knowledge.</i>","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Citizen journalism; Participatory action research; Sociology; Psychology; Computer science; Anthropology; World Wide Web","score_opus":0.6397693202422317,"score_gpt":0.6152156273843152,"score_spread":0.02455369285791642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131390173","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97429883,0.002531088,0.009240357,0.0024466454,0.0030140784,0.003047635,0.000019687364,0.000029149143,0.005372525],"genre_scores_gemma":[0.9956681,0.000020120915,0.0031364667,0.00013255818,0.0004426826,0.00020207124,0.00010335596,0.00002487559,0.0002697322],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98329985,0.0070517953,0.0019123338,0.00039121677,0.00678217,0.0005626066],"domain_scores_gemma":[0.97374004,0.00080995704,0.0013132354,0.00087699085,0.022405144,0.000854659],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12187791,0.00021963265,0.00045249006,0.0020740745,0.00048989704,0.00045140172,0.0008336053,0.00020222264,0.0034348727],"category_scores_gemma":[0.015206418,0.00017862966,0.00018638776,0.0019310263,0.00054518,0.0015328806,0.000020413727,0.0005231085,0.00024274565],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007584391,0.00020909775,0.0030613132,0.000015866717,0.000021600525,4.3677656e-7,0.0029694207,0.0051443544,0.0008792125,0.0009452294,0.012389973,0.9742876],"study_design_scores_gemma":[0.003614059,0.0025831645,0.048135635,0.00030337542,0.0002968731,0.000016417747,0.0021241393,0.63264036,0.001974932,0.028588396,0.27935314,0.0003694677],"about_ca_topic_score_codex":0.0005668274,"about_ca_topic_score_gemma":0.06763281,"teacher_disagreement_score":0.9739182,"about_ca_system_score_codex":0.00086062733,"about_ca_system_score_gemma":0.014532616,"threshold_uncertainty_score":0.9974761},"labels":[],"label_agreement":null},{"id":"W2131675472","doi":"10.1111/j.1754-7121.2011.00179.x","title":"Evidence and equity: Struggles over federal employment equity policy in Canada, 1984-95","year":2011,"lang":"en","type":"article","venue":"Canadian Public Administration","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"York University","funders":"","keywords":"Equity (law); Politics; Commission; Political science; Deliberation; Humanities; Public administration; Sociology; Welfare economics; Economics; Philosophy; Law","score_opus":0.433190882402293,"score_gpt":0.48346880686515864,"score_spread":0.050277924462865664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131675472","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9465724,0.00021321265,0.00011995985,0.0310691,0.00032838018,0.00038034734,0.00008103444,0.000014311297,0.021221226],"genre_scores_gemma":[0.99669504,0.00004565437,0.00013948836,0.0023677612,0.0000866349,0.000030203164,0.000020557982,0.0000074229565,0.00060725916],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99698114,0.00017413884,0.0006211713,0.00042327202,0.0012652755,0.0005349879],"domain_scores_gemma":[0.9981266,0.00019155105,0.00019040627,0.00040034365,0.0002614076,0.0008296576],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0023698604,0.00015513667,0.00019141832,0.00039803493,0.00026142297,0.00060806016,0.0004919554,0.000073677234,0.0028467248],"category_scores_gemma":[0.0017009586,0.00014156128,0.000025462023,0.0008179637,0.000075110846,0.0012712858,0.00013547725,0.00014526887,0.000031276995],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021801563,0.000034376153,0.72643024,0.000009043531,0.00001033839,0.00003511192,0.0005821167,0.0000020253958,0.000025311401,0.09658531,0.015737763,0.16052657],"study_design_scores_gemma":[0.00027155344,0.00013894029,0.9546341,0.0000294826,0.0000037333298,0.000014854102,0.0011787448,0.0018131507,0.00009062517,0.008597348,0.03298632,0.00024117141],"about_ca_topic_score_codex":0.961832,"about_ca_topic_score_gemma":0.99992394,"teacher_disagreement_score":0.22820386,"about_ca_system_score_codex":0.0021954842,"about_ca_system_score_gemma":0.047249254,"threshold_uncertainty_score":0.9980648},"labels":[],"label_agreement":null},{"id":"W2131951821","doi":"10.55016/ojs/ajer.v53i2.55264","title":"Action Research: A Spiral Inquiry for Valid and Useful Knowledge","year":2007,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Psychology; Educational research; Action research; Action (physics); Research methodology; Spiral (railway); Mathematics education; Sociology; Mathematics; Physics","score_opus":0.8756614244315128,"score_gpt":0.7273174432813411,"score_spread":0.14834398115017178,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131951821","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95076233,0.0005499939,0.00022968072,0.017397063,0.0009958697,0.0003000259,0.0000015673686,4.1564078e-7,0.029763049],"genre_scores_gemma":[0.95232284,0.000118292424,0.0007005375,0.0000921531,0.0017434033,0.000017985616,0.0000033266704,0.000010706598,0.04499073],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9943332,0.00077110884,0.0008790298,0.00027220135,0.0032409912,0.00050347944],"domain_scores_gemma":[0.9015002,0.090835705,0.00023412255,0.00026572667,0.0068323156,0.0003318772],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05656623,0.000086528176,0.00019113485,0.0017519789,0.0005977439,0.00032839252,0.0006299827,0.00008568636,0.0059595746],"category_scores_gemma":[0.060503855,0.000062808205,0.00009709145,0.0014136209,0.0003796905,0.0007952649,0.00012139919,0.0006046351,0.0004742888],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014659129,0.001350102,0.29983038,0.00007573864,0.00010971957,0.0000011426134,0.01757367,0.00005523071,0.0034619009,0.0848135,0.4964928,0.0947699],"study_design_scores_gemma":[0.0010226376,0.0009771084,0.35759884,0.00007784775,0.000010571414,0.00008922157,0.010779272,0.00040621593,0.001327092,0.04040901,0.58717334,0.00012885852],"about_ca_topic_score_codex":0.00007997705,"about_ca_topic_score_gemma":0.0014444432,"teacher_disagreement_score":0.094641045,"about_ca_system_score_codex":0.0002679869,"about_ca_system_score_gemma":0.0025906987,"threshold_uncertainty_score":0.9949491},"labels":[],"label_agreement":null},{"id":"W2132391446","doi":"10.1037/0021-9010.93.3.711","title":"Using frame-of-reference training to understand the implications of rater idiosyncrasy for rating accuracy.","year":2008,"lang":"en","type":"article","venue":"Journal of Applied Psychology","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University; University of Manitoba","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Idiosyncrasy; Normative; Psychology; Frame of reference; Frame (networking); Relational frame theory; Applied psychology; Cognitive psychology; Computer science; Epistemology","score_opus":0.7397751505922106,"score_gpt":0.6055301082324799,"score_spread":0.13424504235973067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132391446","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76886046,0.000030598345,0.22235599,0.002398283,0.00020178611,0.00022512149,0.0000062585427,0.0000019278878,0.005919595],"genre_scores_gemma":[0.9718624,0.000018708155,0.02700809,0.0009986575,0.00008187234,0.0000050560448,4.2613095e-7,0.0000057526127,0.000019036319],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99802977,0.00007959108,0.0010910305,0.00014754514,0.00050161994,0.00015043208],"domain_scores_gemma":[0.996293,0.0015442485,0.0011953968,0.00031115228,0.0005956167,0.0000605957],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032670593,0.000080563004,0.00031412134,0.00022239321,0.00017462508,0.00002109937,0.0005378918,0.00006396533,0.00022136676],"category_scores_gemma":[0.00042488312,0.00004804912,0.00009015504,0.00042314376,0.00012412229,0.00011714123,0.000027001952,0.00016594901,0.0000057333837],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020079142,0.00041917196,0.015558804,0.000026403337,0.0003039408,0.0000028609174,0.07400417,0.034827184,0.58129954,0.09328,0.021136755,0.17713325],"study_design_scores_gemma":[0.010049698,0.0029202322,0.4217845,0.00019650451,0.00027151144,0.0010089743,0.08529468,0.008042775,0.03504163,0.36804685,0.066439524,0.00090312964],"about_ca_topic_score_codex":0.0000010479512,"about_ca_topic_score_gemma":0.0000038938515,"teacher_disagreement_score":0.5462579,"about_ca_system_score_codex":0.000023256904,"about_ca_system_score_gemma":0.00026671978,"threshold_uncertainty_score":0.24238108},"labels":[],"label_agreement":null},{"id":"W2132793090","doi":"10.7202/013475ar","title":"Le débat américain sur la certification des enseignants et le piège d’une politique éducative « evidence-based »","year":2006,"lang":"fr","type":"article","venue":"Revue des sciences de l éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Political science; Humanities; Philosophy","score_opus":0.7318172828517989,"score_gpt":0.5303427419023886,"score_spread":0.2014745409494103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132793090","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7593719,0.005669685,0.05405135,0.10709413,0.0014522341,0.0007576219,0.000034671757,0.000093829134,0.07147457],"genre_scores_gemma":[0.97233164,0.0013128084,0.013665472,0.00079970935,0.00027577346,0.00014068643,0.00003622715,0.000023100663,0.011414584],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99296343,0.0028962211,0.001076328,0.0009949114,0.0012896134,0.00077950914],"domain_scores_gemma":[0.9930088,0.003941468,0.0007987561,0.00065870804,0.0013531595,0.00023911637],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":["sts"],"category_scores_codex":[0.014502084,0.00033101055,0.0003662574,0.0006018107,0.0018535829,0.0012660115,0.0010241632,0.00022123122,0.0004089016],"category_scores_gemma":[0.003981518,0.0003212954,0.00018494659,0.0034928578,0.003240983,0.0044505284,0.000074407275,0.00028125718,0.00042505254],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006424671,0.0024220888,0.031515237,0.0004323205,0.000023138387,0.000008468732,0.073936455,0.04473357,0.009858692,0.7028136,0.012597035,0.12159514],"study_design_scores_gemma":[0.00080745574,0.0005480173,0.38136277,0.0024955205,0.00007270064,0.00014191675,0.03811921,0.18233031,0.013106212,0.35222584,0.027824372,0.0009656634],"about_ca_topic_score_codex":0.027625201,"about_ca_topic_score_gemma":0.011489953,"teacher_disagreement_score":0.35058776,"about_ca_system_score_codex":0.00128882,"about_ca_system_score_gemma":0.015405983,"threshold_uncertainty_score":0.9999239},"labels":[],"label_agreement":null},{"id":"W2133213181","doi":"10.3138/jvme.31.1.61","title":"Ensuring that the competent are truly competent: an overview of common methods and procedures used to set standards on high-stakes examinations","year":2004,"lang":"en","type":"review","venue":"Journal of Veterinary Medical Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Certification; Licensure; Set (abstract data type); Computer science; Test (biology); Selection (genetic algorithm); Factoring; Norm (philosophy); Task (project management); Medical education; Medicine; Accounting; Political science; Artificial intelligence; Engineering; Business; Law","score_opus":0.710843790843106,"score_gpt":0.6648786064823116,"score_spread":0.04596518436079444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133213181","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039819,0.95236254,0.0006831541,0.0036829954,0.0022482267,0.00095685135,0.00010745625,0.00001144016,0.00012834909],"genre_scores_gemma":[0.056275822,0.93915296,0.0035299885,0.00052670966,0.0003463189,0.000056408506,0.000033987337,0.000028964598,0.000048872014],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9905888,0.0025586933,0.0019368202,0.00033226243,0.0043881685,0.00019529875],"domain_scores_gemma":[0.99311537,0.0023214489,0.002574753,0.0005512926,0.001011771,0.00042535426],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015358073,0.0003086618,0.0014770573,0.0006583631,0.00021499884,0.00019196558,0.001020977,0.00018196936,0.00054708007],"category_scores_gemma":[0.004549564,0.00016758197,0.000284359,0.00063218706,0.00016039264,0.00036517347,0.00012708521,0.00061584596,0.0000053564354],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039816885,0.00047178566,0.00006991167,0.0025794455,0.00006709231,0.0000071851127,0.0017062625,0.00004246333,0.0000024156307,0.0006833876,0.000632472,0.99369776],"study_design_scores_gemma":[0.00058172183,0.0028948302,0.016972091,0.039264925,0.00035336264,0.0008346696,0.0035558606,0.000079867794,0.000009607257,0.0012968797,0.9338579,0.0002982552],"about_ca_topic_score_codex":0.000020314419,"about_ca_topic_score_gemma":0.000051572802,"teacher_disagreement_score":0.9933995,"about_ca_system_score_codex":0.00040425573,"about_ca_system_score_gemma":0.0063654273,"threshold_uncertainty_score":0.9992676},"labels":[],"label_agreement":null},{"id":"W2133487638","doi":"10.1177/1356389012452052","title":"Applications of contribution analysis to outcome planning and impact evaluation","year":2012,"lang":"en","type":"article","venue":"Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Accountability; General partnership; Participatory evaluation; Context (archaeology); Participatory planning; Citizen journalism; Theory of change; Process management; Process (computing); Value (mathematics); Management science; Appeal; Conceptual framework; Knowledge management; Public relations; Sociology; Computer science; Political science; Business; Public administration; Environmental planning; Engineering","score_opus":0.3089908516284891,"score_gpt":0.6239675731195479,"score_spread":0.31497672149105876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133487638","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8170985,0.00045789767,0.17897859,0.0003859971,0.00012398083,0.0012746659,0.000020354686,0.0000145714575,0.0016454589],"genre_scores_gemma":[0.99837637,0.000002308337,0.0009015559,0.00010003592,0.000099110715,0.00031838156,0.00013409088,0.0000047654157,0.00006336592],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.994406,0.0006871073,0.0008399382,0.00027206357,0.0035808806,0.00021403242],"domain_scores_gemma":[0.9959242,0.00056153705,0.00046913346,0.00043904711,0.0024425576,0.00016352547],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.034517214,0.000113389215,0.00028397792,0.0009128731,0.00015045394,0.00008520959,0.00016359605,0.00006327224,0.003159418],"category_scores_gemma":[0.0033353234,0.000086491134,0.0001213477,0.002497255,0.000027858054,0.00068384095,0.00004763156,0.000064810854,0.00015929806],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019178764,0.000050127663,0.82389617,0.0000014911046,0.00010025096,6.4614176e-9,0.00092222355,0.036873713,0.00055159716,0.00065994373,0.00017906491,0.1367462],"study_design_scores_gemma":[0.00037762488,0.000044588593,0.753021,0.0000028525865,0.0006131851,5.1769604e-7,0.0003534239,0.24259792,0.00029459273,0.0018472763,0.0007664554,0.000080584825],"about_ca_topic_score_codex":0.00002591621,"about_ca_topic_score_gemma":0.00001997886,"teacher_disagreement_score":0.20572421,"about_ca_system_score_codex":0.0002516858,"about_ca_system_score_gemma":0.00017361452,"threshold_uncertainty_score":0.99775183},"labels":[],"label_agreement":null},{"id":"W2133584145","doi":"","title":"Improving the Utility of Large-Scale Assessments in Canada","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Education / Revue canadienne de l éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Strengths and weaknesses; Scale (ratio); Schedule; Mathematics education; Reliability (semiconductor); Psychology; Computer science; Social psychology","score_opus":0.11606232739226982,"score_gpt":0.40760642900818467,"score_spread":0.2915441016159148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133584145","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98691106,0.00008783513,0.0012501364,0.004887987,0.0035998276,0.00014540166,0.000016366424,8.4977785e-7,0.0031005088],"genre_scores_gemma":[0.9978553,0.0000041780677,0.0004907617,0.00091153855,0.00020050089,0.000009931269,0.000008875982,0.0000076056463,0.00051129924],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9975908,0.00045736507,0.0010084803,0.00018418914,0.00034354615,0.00041561728],"domain_scores_gemma":[0.9960342,0.00047889195,0.00097296806,0.00049251306,0.0013816563,0.00063973665],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008568233,0.00010319335,0.00023800631,0.0005151918,0.00015892848,0.00008449422,0.00069015444,0.000048030957,0.0010280868],"category_scores_gemma":[0.0036526797,0.000082950464,0.00006183882,0.0008174643,0.00004410539,0.00035292562,0.000010262238,0.00024535277,0.0000052187356],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012387196,0.000077651006,0.81374437,0.00004388819,0.000016244318,0.0000020828036,0.02421531,0.0008800939,0.00014365846,0.0026835406,0.030410128,0.12777065],"study_design_scores_gemma":[0.00023033314,0.000048994436,0.8650723,0.00007219709,0.000018399951,0.000044534536,0.055855636,0.022267941,0.00011933637,0.0031605898,0.052993026,0.000116726646],"about_ca_topic_score_codex":0.9283084,"about_ca_topic_score_gemma":0.9997468,"teacher_disagreement_score":0.12765391,"about_ca_system_score_codex":0.0036363837,"about_ca_system_score_gemma":0.06808227,"threshold_uncertainty_score":0.9998851},"labels":[],"label_agreement":null},{"id":"W2133886430","doi":"10.1002/wcc.73","title":"Participatory methods of integrated assessment—a review","year":2010,"lang":"en","type":"article","venue":"Wiley Interdisciplinary Reviews Climate Change","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":162,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Citizen journalism; Political science; Field (mathematics); Process (computing); Management science; Public relations; Sociology; Engineering ethics; Computer science; Engineering; Law","score_opus":0.5007791023596583,"score_gpt":0.6263696570533983,"score_spread":0.12559055469374003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133886430","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1926612,0.43912852,0.017493792,0.05115327,0.027030228,0.02175086,0.001249047,0.0007262395,0.24880686],"genre_scores_gemma":[0.1964722,0.6643722,0.11628592,0.013064925,0.001437167,0.00588559,0.00052332133,0.00018449816,0.0017741907],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9931013,0.0018531834,0.0027088572,0.0006942975,0.00113319,0.00050916127],"domain_scores_gemma":[0.9951908,0.0007189489,0.0015022013,0.001691998,0.00064924,0.0002468211],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.029176679,0.00037396062,0.0014364753,0.00031701673,0.00022771307,0.00008861165,0.0012567971,0.00013405234,0.019379571],"category_scores_gemma":[0.001277296,0.00023450695,0.00053829263,0.0013386675,0.00023912362,0.0008409367,0.0011491282,0.0006422149,0.0011106041],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023362247,0.00026892268,0.015224872,0.0013592257,0.000025561209,0.000004269289,0.001491436,4.773237e-7,0.004527886,0.0020384837,0.031593654,0.94344187],"study_design_scores_gemma":[0.0005218335,0.0004648865,0.024314739,0.009393409,0.00023807681,0.000039343417,0.0011190615,0.0046726046,0.0006186977,0.004190897,0.9537614,0.00066506775],"about_ca_topic_score_codex":0.000005010729,"about_ca_topic_score_gemma":0.00008612648,"teacher_disagreement_score":0.9427768,"about_ca_system_score_codex":0.000064251384,"about_ca_system_score_gemma":0.0001345316,"threshold_uncertainty_score":0.99966717},"labels":[],"label_agreement":null},{"id":"W2134222447","doi":"10.5267/j.msl.2013.09.021","title":"Evaluating the quality of in-service trainings for employees of Islamic Azad University (Buin-Zahra Branch) using CIPP model","year":2013,"lang":"en","type":"article","venue":"Management Science Letters","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Islam; Quality (philosophy); Service quality; Management; Service (business); Psychology; Computer science; Business; Marketing; Philosophy; Theology; Economics","score_opus":0.40227057348641865,"score_gpt":0.5107818989261874,"score_spread":0.10851132543976877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134222447","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9492131,0.000003139011,0.04179772,0.006684057,0.00010553035,0.00076563784,0.000004662456,0.000009042296,0.0014171398],"genre_scores_gemma":[0.982746,0.0000024209505,0.014840953,0.0022209492,0.000009076456,0.000009686683,7.911425e-7,0.0000045017478,0.0001656385],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960948,0.00020000197,0.00069869513,0.00044538203,0.002243708,0.0003173625],"domain_scores_gemma":[0.9979715,0.0005276423,0.0005718835,0.0005907747,0.00030605658,0.00003215114],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013591493,0.000113997514,0.00023972752,0.0004994858,0.00028356077,0.00011259676,0.0015787631,0.000022008568,0.000105718434],"category_scores_gemma":[0.0002932269,0.000082173654,0.000086302185,0.002134998,0.00044159783,0.0011173057,0.00029353783,0.000075865486,0.000011633624],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007508956,0.00013005263,0.04008018,0.00012911462,0.000033242166,3.1870522e-7,0.010709272,0.68905056,0.20288959,0.020091191,0.00056934805,0.036242053],"study_design_scores_gemma":[0.0006628236,0.00005376925,0.13435388,0.00003877069,0.000018246712,1.3077728e-7,0.0055109127,0.8500603,0.0006417744,0.008508976,0.00003137769,0.00011908949],"about_ca_topic_score_codex":0.00051580154,"about_ca_topic_score_gemma":0.00013910825,"teacher_disagreement_score":0.20224781,"about_ca_system_score_codex":0.000115484,"about_ca_system_score_gemma":0.000078842284,"threshold_uncertainty_score":0.4710567},"labels":[],"label_agreement":null},{"id":"W2134246778","doi":"10.7202/900396ar","title":"L’échantillonnage et le problème de la validité externe de la recherche en éducation","year":2009,"lang":"fr","type":"article","venue":"Revue des sciences de l éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Humanities; Philosophy; Political science","score_opus":0.855464181828813,"score_gpt":0.6475501836071665,"score_spread":0.20791399822164647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134246778","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7370507,0.0028337261,0.11135875,0.050136376,0.0012913938,0.00051860965,0.000008420134,0.000087081906,0.09671491],"genre_scores_gemma":[0.861507,0.0023273113,0.12455151,0.0015168712,0.00034117678,0.000049252023,0.000009477348,0.000013303969,0.009684088],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9857057,0.011479429,0.00064322335,0.00065971067,0.00087790383,0.0006340548],"domain_scores_gemma":[0.9917226,0.006796394,0.0004356877,0.00046805473,0.00033880776,0.00023847059],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07835226,0.00023893721,0.00025167732,0.00039732963,0.0007364245,0.0013444113,0.0009942121,0.00050023134,0.00049324974],"category_scores_gemma":[0.011491931,0.00023035677,0.00013223417,0.0018793626,0.0010681914,0.0018129551,0.000062341074,0.0006337788,0.00030119333],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002412119,0.0013326223,0.010586958,0.00013583274,0.000016963526,0.000008944919,0.24135041,0.011387591,0.018636238,0.40414208,0.007797703,0.30458054],"study_design_scores_gemma":[0.0004417676,0.0004231218,0.12405306,0.0004750266,0.000056689067,0.00046882854,0.02176338,0.17486595,0.0044643614,0.63302654,0.039488398,0.00047287543],"about_ca_topic_score_codex":0.00037837768,"about_ca_topic_score_gemma":0.00017401576,"teacher_disagreement_score":0.30410767,"about_ca_system_score_codex":0.0030157105,"about_ca_system_score_gemma":0.008916396,"threshold_uncertainty_score":0.99969226},"labels":[],"label_agreement":null},{"id":"W2134305609","doi":"10.1177/0894318405283541","title":"Advancing the Art of Theory-Based Practice","year":2006,"lang":"en","type":"article","venue":"Nursing Science Quarterly","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Nursing theory; Psychology; Epistemology; Computer science; Sociology; MEDLINE; Philosophy; Political science","score_opus":0.04069470678947497,"score_gpt":0.470626940589732,"score_spread":0.429932233800257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134305609","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22740471,0.00009628338,0.20967843,0.045012753,0.0021491367,0.0005061473,0.00000463439,0.00007779325,0.5150701],"genre_scores_gemma":[0.99177045,8.936924e-8,0.0064223944,0.00079953327,0.00006919073,0.0000056024855,7.614254e-7,0.0000041753938,0.00092780736],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99540645,0.00034272924,0.00053785846,0.00035144534,0.003033851,0.00032769304],"domain_scores_gemma":[0.9961036,0.0018112316,0.00042494808,0.00068107055,0.0009197032,0.000059442078],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017989822,0.000094128605,0.00013852629,0.00027567573,0.0005336363,0.00037247603,0.0009826482,0.000025492134,0.00028645585],"category_scores_gemma":[0.0013176071,0.000054149714,0.00006351658,0.0018985331,0.0011457071,0.001382093,0.0000022651345,0.000115614166,0.00024633695],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012490901,0.00049560866,0.0030824856,0.000003916345,0.0000035394462,0.0000021059147,0.009804754,0.007999762,0.024899883,0.43266025,0.011890885,0.5090319],"study_design_scores_gemma":[0.00153598,0.0024218226,0.07574715,0.00030017484,0.000082060906,0.000054101263,0.12082874,0.27208433,0.019423664,0.43642718,0.070437245,0.0006575849],"about_ca_topic_score_codex":0.000017833005,"about_ca_topic_score_gemma":0.000018039198,"teacher_disagreement_score":0.76436573,"about_ca_system_score_codex":0.00009825732,"about_ca_system_score_gemma":0.0007381741,"threshold_uncertainty_score":0.62349486},"labels":[],"label_agreement":null},{"id":"W2135447880","doi":"10.26522/tl.v1i2.107","title":"Introduction to Hamilton-Wentworth District School Board Assessment and Evaluation Guildelines","year":2003,"lang":"en","type":"article","venue":"Teaching and Learning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Political science; Subject (documents); School district; Management; Public administration; Medical education; Library science; Sociology; Pedagogy; Medicine; Computer science","score_opus":0.10140683310074997,"score_gpt":0.4726871259997044,"score_spread":0.3712802928989545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135447880","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9645011,0.00016846281,0.02436191,0.0034276282,0.0003854855,0.00024474133,5.6190885e-7,0.00004925331,0.0068608816],"genre_scores_gemma":[0.985185,0.000043140106,0.0111442655,0.00029069142,0.00033024076,0.00002466766,0.000010034098,0.000008761609,0.0029631783],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9955548,0.0020581419,0.00042827506,0.00048931834,0.0012769932,0.00019246951],"domain_scores_gemma":[0.9987191,0.00044652398,0.00017080965,0.0002532234,0.00024301534,0.00016733869],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022274604,0.00013009546,0.00017790259,0.00023595005,0.0009152845,0.00046808287,0.00010308732,0.000043166827,0.0006868904],"category_scores_gemma":[0.006522135,0.00010067653,0.00002975266,0.00026727174,0.000024688585,0.0003889678,0.000041945535,0.00061725633,0.00007120203],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017101785,0.000047586334,0.2817885,0.0000080735235,0.000018045439,5.023732e-7,0.0031183716,0.029131297,0.0005163695,0.002960867,0.010742222,0.67165107],"study_design_scores_gemma":[0.0006359552,0.00021856805,0.35374805,0.000023664705,0.000040324852,0.000011895536,0.005427416,0.15257543,0.000023656268,0.0008419386,0.4862144,0.00023869183],"about_ca_topic_score_codex":0.00004928801,"about_ca_topic_score_gemma":0.000019000965,"teacher_disagreement_score":0.6714124,"about_ca_system_score_codex":0.00009587165,"about_ca_system_score_gemma":0.00011952477,"threshold_uncertainty_score":0.7808076},"labels":[],"label_agreement":null},{"id":"W2135685446","doi":"10.7202/011035ar","title":"L’évaluation dans les universités en Europe : une décennie de changements","year":2005,"lang":"fr","type":"article","venue":"Revue des sciences de l éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Humanities; Political science; Art","score_opus":0.717892791931803,"score_gpt":0.5484953608156194,"score_spread":0.16939743111618355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135685446","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83616716,0.0016032082,0.042686295,0.034010366,0.001588705,0.00035626715,0.0000135594655,0.00004531002,0.083529145],"genre_scores_gemma":[0.89440423,0.002591595,0.042181037,0.0006627654,0.0007991224,0.000020032827,0.000021538735,0.000014756084,0.059304945],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995972,0.0012006763,0.0005228503,0.00056835206,0.0011635117,0.00057260983],"domain_scores_gemma":[0.99802804,0.00047184664,0.0003495231,0.00037087547,0.00057758274,0.00020215203],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.011010193,0.0001979799,0.00018445881,0.00042482183,0.0013352323,0.00046096346,0.0009305124,0.00013355422,0.0024565444],"category_scores_gemma":[0.0010029043,0.0001958324,0.000085878295,0.002866648,0.00085469877,0.0018376571,0.00011763316,0.00018529526,0.0013265068],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012228574,0.00028360912,0.03549574,0.00005863276,0.00001654567,0.0000036919346,0.15471354,0.059336144,0.002173201,0.015674055,0.0042223795,0.72801024],"study_design_scores_gemma":[0.00037313023,0.00028962904,0.19404596,0.00024165113,0.00008811033,0.00008430255,0.026922664,0.5880139,0.00092859956,0.006334356,0.18234664,0.00033106975],"about_ca_topic_score_codex":0.0010791641,"about_ca_topic_score_gemma":0.003588429,"teacher_disagreement_score":0.72767913,"about_ca_system_score_codex":0.0020445578,"about_ca_system_score_gemma":0.0024281414,"threshold_uncertainty_score":0.9999649},"labels":[],"label_agreement":null},{"id":"W2136594003","doi":"10.7202/1024718ar","title":"L’évaluation de la qualité de dispositifs scolaires","year":2014,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Humanities; Amen; Political science; Sociology; Philosophy","score_opus":0.1522770821919167,"score_gpt":0.5214918071004983,"score_spread":0.36921472490858154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136594003","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70060587,0.00063108053,0.2266179,0.044036124,0.0029874695,0.0007047426,0.00001480994,0.00009731641,0.0243047],"genre_scores_gemma":[0.96485364,0.00036972025,0.016963914,0.0023040199,0.0008339032,0.00018912587,0.00020143452,0.000046552228,0.014237669],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.94822204,0.04556527,0.0014210633,0.00081713405,0.0033270086,0.00064751017],"domain_scores_gemma":[0.98754966,0.009525956,0.000737768,0.00083946815,0.0010967779,0.00025036238],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.18881468,0.0003711072,0.00040357147,0.00050404784,0.0005035501,0.0009342338,0.00057867117,0.0004979242,0.0044564228],"category_scores_gemma":[0.016788423,0.0003700311,0.00021011035,0.0010500426,0.00021773626,0.0015436218,0.00007716447,0.0005081717,0.0016199904],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005606399,0.00053942256,0.089963175,0.00008715248,0.000058992187,7.4626587e-7,0.17263068,0.03376997,0.0026965202,0.05487216,0.0154785905,0.6298465],"study_design_scores_gemma":[0.00075785496,0.00013744755,0.63229746,0.00014046613,0.00012276256,0.000020366517,0.0024666227,0.26396334,0.0009178832,0.05473705,0.044119604,0.00031913666],"about_ca_topic_score_codex":0.0005989066,"about_ca_topic_score_gemma":0.0005792976,"teacher_disagreement_score":0.6295274,"about_ca_system_score_codex":0.0013893567,"about_ca_system_score_gemma":0.0064353417,"threshold_uncertainty_score":0.9998752},"labels":[],"label_agreement":null},{"id":"W2137088305","doi":"","title":"The Impact of Centralization on Local School District Governance in Canada.","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Educational Administration and Policy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Corporate governance; Ideology; Politics; Public administration; School district; Political science; Accountability; Economic growth; Sociology; Economics; Pedagogy; Management; Law","score_opus":0.05035330453245811,"score_gpt":0.429718646906069,"score_spread":0.37936534237361086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137088305","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9446851,0.00014673536,0.000034399985,0.0491416,0.00023282156,0.00011931643,0.00004372014,2.6962752e-7,0.0055960533],"genre_scores_gemma":[0.9987722,0.00005348336,0.000016730186,0.000348611,0.00014056975,0.0000033662757,0.0000061375968,0.0000024455176,0.0006564774],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985975,0.00009277583,0.0005922223,0.00007510022,0.0004937455,0.00014864259],"domain_scores_gemma":[0.99792576,0.00056343735,0.0004411738,0.00011314246,0.000517749,0.00043872182],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005206157,0.00006806225,0.00010668776,0.00016368098,0.00011928218,0.00014764398,0.0002099458,0.000022339605,0.0023770265],"category_scores_gemma":[0.0019426112,0.000041892585,0.000040580802,0.00045462756,0.000071779345,0.0002699128,0.0000030510253,0.000100004334,0.000016431202],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031473908,0.00003972392,0.7669624,0.0000029287244,0.000017463773,0.0000012070141,0.00028165823,0.0042239474,0.000011673401,0.10585586,0.08849092,0.034080707],"study_design_scores_gemma":[0.00015385309,0.00010706646,0.9869545,0.000015422442,0.0000013997906,0.000016623188,0.00047258358,0.0010548914,0.000023510083,0.006415419,0.004741713,0.00004299005],"about_ca_topic_score_codex":0.81636167,"about_ca_topic_score_gemma":0.95772225,"teacher_disagreement_score":0.21999209,"about_ca_system_score_codex":0.0011351372,"about_ca_system_score_gemma":0.065206416,"threshold_uncertainty_score":0.9985349},"labels":[],"label_agreement":null},{"id":"W2138575632","doi":"10.5539/ass.v4n2p91","title":"Towards Local Government Strategic Planning in Vietnam: Systemic Governance Interventions for Sustainability","year":2008,"lang":"en","type":"article","venue":"Asian Social Science","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Corporate governance; Argument (complex analysis); Participatory planning; Strategic planning; Government (linguistics); Citizen journalism; Business; Sustainability; Local government; Empirical research; Psychological intervention; Public relations; Process management; Political science; Public administration; Economics; Economic growth; Marketing; Psychology","score_opus":0.1824995608747527,"score_gpt":0.4856528977977967,"score_spread":0.303153336923044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138575632","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6406103,0.00022160746,0.06731289,0.0059841024,0.0009780693,0.0015042706,0.000064626336,0.000058399764,0.28326574],"genre_scores_gemma":[0.9987154,0.000006667151,0.0003242029,0.00010316247,0.0000763999,0.000098223674,0.0000011345833,0.000004688354,0.00067011395],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9953304,0.00013700107,0.0007184203,0.0005377548,0.0028215914,0.0004548402],"domain_scores_gemma":[0.99866295,0.00014570748,0.000326084,0.00027307696,0.00048133085,0.00011087565],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006657173,0.00012320207,0.00026091308,0.000079444995,0.00086069905,0.0001757969,0.00092572754,0.00006029149,0.00014523997],"category_scores_gemma":[0.0010074326,0.00010188365,0.00017454101,0.0015544374,0.00079533487,0.00073249376,0.00014263068,0.0001430118,0.000026630323],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014639346,0.0004912556,0.100724466,0.00016699679,0.0000127800095,0.00003201275,0.021891264,0.0009011452,0.00029085815,0.33923313,0.0016706274,0.5344391],"study_design_scores_gemma":[0.0009406932,0.00022538683,0.85418415,0.00013048596,0.000007250031,0.00002110249,0.076091945,0.008894079,0.00011724481,0.057639558,0.0014373076,0.0003107925],"about_ca_topic_score_codex":0.00004376758,"about_ca_topic_score_gemma":0.0000914928,"teacher_disagreement_score":0.7534597,"about_ca_system_score_codex":0.0017717921,"about_ca_system_score_gemma":0.0015212428,"threshold_uncertainty_score":0.6619888},"labels":[],"label_agreement":null},{"id":"W2139159602","doi":"10.1002/ev.92","title":"PIE à la Mode: Mainstreaming Evaluation and Accountability in Each Program in Every County of a Statewide School Readiness Initiative","year":2003,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Accountability; Mandate; Mainstreaming; Legislature; Program evaluation; Plan (archaeology); Mainstream; Benchmarking; Quality (philosophy); Public administration; Political science; Public relations; Medical education; Psychology; Business; Pedagogy; Special education; Medicine","score_opus":0.2119641125322008,"score_gpt":0.5393907107995318,"score_spread":0.327426598267331,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139159602","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98210937,0.00018831757,0.0027732728,0.00019257599,0.00027478216,0.0034440882,0.000032928037,0.000027695702,0.0109569775],"genre_scores_gemma":[0.99452746,0.000055186498,0.0037799543,0.000038879563,0.000026755646,0.0013294251,0.00007134672,0.000011652381,0.00015934033],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9943261,0.001667312,0.0010709392,0.0005440626,0.002153022,0.00023855153],"domain_scores_gemma":[0.9955288,0.0017365307,0.00041634138,0.0003542086,0.0018787419,0.00008536489],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.027279759,0.00016566992,0.00030932573,0.00076898735,0.00013090347,0.00014455822,0.00013214721,0.00012610806,0.0004491635],"category_scores_gemma":[0.013508805,0.00015063235,0.000061816616,0.0017149854,0.00007781114,0.0012546488,0.000022206565,0.0001723772,0.000006877861],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021016084,0.0005914194,0.2649134,0.000027827922,0.00002262746,1.5727095e-7,0.0031826752,0.024247803,0.00031867274,0.0008954399,0.00047523575,0.7051146],"study_design_scores_gemma":[0.004210941,0.00014913382,0.5022712,0.00007911863,0.00007120272,0.0000026770376,0.0038223832,0.43560478,0.0006198055,0.050855793,0.0021303445,0.00018266654],"about_ca_topic_score_codex":0.00056548486,"about_ca_topic_score_gemma":0.006039717,"teacher_disagreement_score":0.7049319,"about_ca_system_score_codex":0.00076483964,"about_ca_system_score_gemma":0.0021745216,"threshold_uncertainty_score":0.9948008},"labels":[],"label_agreement":null},{"id":"W2139287644","doi":"10.7202/1024721ar","title":"Évaluation des compétences dans un programme de formation en enseignement","year":2014,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Rimouski","funders":"","keywords":"Humanities; Political science; Philosophy; Sociology","score_opus":0.23398995375631845,"score_gpt":0.46215067997860737,"score_spread":0.22816072622228892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139287644","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37516665,0.000571824,0.5771292,0.027212866,0.002543639,0.0013196622,0.000014495352,0.00011145026,0.015930226],"genre_scores_gemma":[0.88039505,0.00056710764,0.10811439,0.00097032683,0.0005785796,0.00039349386,0.0004638867,0.00004158891,0.008475593],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9702334,0.021656802,0.0019607826,0.0008771854,0.004339307,0.0009325597],"domain_scores_gemma":[0.99265945,0.0031928176,0.0010379916,0.00079483003,0.002028607,0.0002863162],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.12616897,0.00047353646,0.00046169633,0.0005634926,0.0010046253,0.0008805508,0.00067704136,0.00038911783,0.0037017886],"category_scores_gemma":[0.008871987,0.00044731473,0.00022293287,0.0013741937,0.0002539468,0.0026749808,0.0001028445,0.00042371047,0.0012508663],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028186194,0.0004242158,0.0066695325,0.000103211576,0.00004239673,3.037086e-7,0.29761484,0.015437146,0.001564766,0.009101046,0.0030790775,0.6659353],"study_design_scores_gemma":[0.0011003072,0.00041781255,0.40643594,0.0002291933,0.00018975596,0.000027516593,0.01573801,0.43107677,0.003326516,0.12623599,0.014785696,0.0004365224],"about_ca_topic_score_codex":0.00030172875,"about_ca_topic_score_gemma":0.001542518,"teacher_disagreement_score":0.66549873,"about_ca_system_score_codex":0.002224599,"about_ca_system_score_gemma":0.003106853,"threshold_uncertainty_score":0.9997979},"labels":[],"label_agreement":null},{"id":"W2139543842","doi":"10.1016/j.evalprogplan.2012.03.016","title":"When does a conceptual framework become a theory? Reflections from an accidental theorist","year":2012,"lang":"en","type":"article","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Credibility; Citizen journalism; General partnership; Epistemology; Logic model; Accidental; Conceptual framework; Sociology; Management science; Point (geometry); Computer science; Work (physics); Engineering ethics; Political science; Engineering; Social science; Philosophy; Mathematics; Law","score_opus":0.28428521749575497,"score_gpt":0.5820025195645955,"score_spread":0.2977173020688405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139543842","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.971715,0.0011102387,0.014996468,0.0009674318,0.0013731214,0.0008058863,0.00002889672,0.00018138408,0.008821626],"genre_scores_gemma":[0.98201966,0.0000105491445,0.015889166,0.00076840917,0.00060193264,0.0001758749,0.00014314165,0.000013474973,0.00037779377],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9957217,0.001303095,0.00051857735,0.00039131154,0.0017425297,0.00032280452],"domain_scores_gemma":[0.99734676,0.0014062541,0.00026664644,0.00040027685,0.00033077045,0.00024927087],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011746623,0.00017222996,0.0002141941,0.00017855626,0.0005791229,0.0006566763,0.00028506,0.00013032446,0.01459442],"category_scores_gemma":[0.0017257942,0.0001124749,0.0000635832,0.0003299379,0.00016291295,0.0014630291,0.000078721765,0.00026569737,0.0002087954],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009461466,0.00019505525,0.23173404,0.0000012110261,0.00004152235,4.6606067e-7,0.04924391,0.00010628053,0.000081390695,0.02102435,0.00047188913,0.6970053],"study_design_scores_gemma":[0.001115302,0.000416467,0.42089155,0.00007742876,0.00014735624,0.000012729786,0.06561858,0.02824932,0.0002062982,0.38771266,0.09508263,0.0004696806],"about_ca_topic_score_codex":0.000039276245,"about_ca_topic_score_gemma":0.00004795199,"teacher_disagreement_score":0.6965356,"about_ca_system_score_codex":0.00006123308,"about_ca_system_score_gemma":0.00010839471,"threshold_uncertainty_score":0.98630637},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W2139909475","doi":"10.12927/hcpol.2008.20266","title":"Health Services Researchers Working within Healthcare Organizations: The Intriguing Sound of Three Hands Clapping","year":2008,"lang":"en","type":"article","venue":"Healthcare policy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Cancer Care Ontario","funders":"","keywords":"Health care; Biostatistics; Peer review; Public relations; Sociology; Health policy; Medical education; Engineering ethics; Political science; Library science; Medicine; Nursing; Public health; Engineering; Law; Computer science","score_opus":0.4308044487543925,"score_gpt":0.5496367521836477,"score_spread":0.11883230342925521,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139909475","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.59896636,0.0041891825,0.0018367183,0.39182517,0.00050309405,0.0012478286,0.000027097376,0.00012826455,0.0012763214],"genre_scores_gemma":[0.9872947,0.0008810341,0.0008148926,0.010125363,0.0005393915,0.000032517615,0.000020466967,0.000029266666,0.00026241192],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99328613,0.0011482869,0.0016110954,0.0005136658,0.002714321,0.00072650943],"domain_scores_gemma":[0.9946275,0.0010698929,0.0010337068,0.0010568253,0.0018098906,0.00040223435],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.008518879,0.00021137776,0.0004971961,0.0007511159,0.0019298039,0.0001765483,0.0010818245,0.0001333023,0.00012220751],"category_scores_gemma":[0.0014082743,0.00014177336,0.00008601743,0.0054146736,0.00027032482,0.00036682718,0.0002480004,0.00057796424,0.00009918153],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008223193,0.00007508812,0.7430663,0.0004606818,0.00003990177,0.0000040689542,0.09538998,0.0015051323,0.000016413915,0.07402718,0.0016215496,0.08371147],"study_design_scores_gemma":[0.0033521478,0.0015943182,0.6638124,0.0023185404,0.000018382307,0.00031909498,0.07094587,0.040605173,0.0002795712,0.1837049,0.0320117,0.0010379188],"about_ca_topic_score_codex":0.022733096,"about_ca_topic_score_gemma":0.03412635,"teacher_disagreement_score":0.3883283,"about_ca_system_score_codex":0.0004980797,"about_ca_system_score_gemma":0.00574694,"threshold_uncertainty_score":0.99988955},"labels":[],"label_agreement":null},{"id":"W2140061750","doi":"10.3138/cjpe.29.3.134","title":"From the Outside, Looking In with a Smile: A Summary and Discussion of CES's Credentialed Evaluator Designation","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Credentialing; Credential; Management; Action (physics); Political science; Context (archaeology); Humanities; Sociology; Public relations; Law; Art; Geography; Economics","score_opus":0.3069585015711737,"score_gpt":0.4904886684929546,"score_spread":0.18353016692178087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140061750","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99144953,0.00095035747,0.0018591677,0.0037201822,0.00036794308,0.001120146,0.000009154853,0.0000036115919,0.00051991775],"genre_scores_gemma":[0.99705064,0.000009075789,0.0026254035,0.00008188971,0.00012422285,0.000039592305,0.000012399609,0.000007507659,0.000049275695],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99515665,0.0010767912,0.0008562973,0.00018214624,0.002554526,0.00017359694],"domain_scores_gemma":[0.9959604,0.0003691143,0.00083307904,0.00022709927,0.002304762,0.00030554715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019321483,0.00010705558,0.00023696144,0.00045075166,0.000100328056,0.00027299792,0.00032943065,0.0000616141,0.00028358307],"category_scores_gemma":[0.002799577,0.000052242896,0.000047127258,0.00072148273,0.000121780315,0.000711816,0.000016895376,0.00016750596,0.0000046752352],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013370415,0.000044525146,0.2553846,0.0000033416168,0.000029763833,0.0000061186524,0.008266307,0.0037640943,0.000109257366,0.000056246667,0.0022023504,0.72999966],"study_design_scores_gemma":[0.006483807,0.0015046025,0.7008967,0.00060247775,0.0003011081,0.000041219395,0.023526419,0.229813,0.00036873936,0.028088788,0.008090224,0.0002829263],"about_ca_topic_score_codex":0.0023860384,"about_ca_topic_score_gemma":0.060597923,"teacher_disagreement_score":0.7297168,"about_ca_system_score_codex":0.00027958886,"about_ca_system_score_gemma":0.0052931546,"threshold_uncertainty_score":0.95654374},"labels":[],"label_agreement":null},{"id":"W2140465263","doi":"10.1002/ev.240","title":"Going through the process: An examination of the operationalization of process use in empirical research on evaluation","year":2007,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":74,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Operationalization; Process (computing); Empirical research; Empirical examination; Process management; Research methodology; Psychology; Management science; Computer science; Sociology; Epistemology; Business; Actuarial science; Engineering","score_opus":0.6748434947289444,"score_gpt":0.6733453144103931,"score_spread":0.001498180318551312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140465263","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9813769,0.000051532646,0.009700155,0.0011799309,0.0004178843,0.0033300424,0.000008975244,0.000014058818,0.0039205323],"genre_scores_gemma":[0.9985067,0.000007810736,0.00039470024,0.000110008106,0.00013540682,0.00037813673,0.000067022425,0.000013013911,0.00038717742],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9887614,0.002412768,0.0012260202,0.00047911072,0.0068864324,0.00023426254],"domain_scores_gemma":[0.98722726,0.0033135866,0.00056874315,0.0006070317,0.0082423845,0.00004099082],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04806614,0.00012549986,0.00018253624,0.00061130815,0.000539225,0.00014168727,0.00046469906,0.00012063411,0.00032320528],"category_scores_gemma":[0.017565576,0.000076621276,0.00008133943,0.003995198,0.00013870366,0.0015985633,0.000028361046,0.00020772747,0.0000091055845],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003842263,0.0009781404,0.085231856,0.000043762768,0.00002950153,4.0312486e-8,0.030426534,0.55634403,0.0014380395,0.01084527,0.0014849453,0.31279367],"study_design_scores_gemma":[0.0012861461,0.00026660494,0.50764436,0.00007751615,0.000046251967,9.898677e-7,0.007140429,0.441682,0.00993726,0.030862842,0.0009655764,0.00009003848],"about_ca_topic_score_codex":0.00009816256,"about_ca_topic_score_gemma":0.003767385,"teacher_disagreement_score":0.42241248,"about_ca_system_score_codex":0.0004021439,"about_ca_system_score_gemma":0.0016397331,"threshold_uncertainty_score":0.9907099},"labels":[],"label_agreement":null},{"id":"W2140628270","doi":"10.1177/1098214014532166","title":"How Analogue Research Can Advance Descriptive Evaluation Theory","year":2014,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Interpersonal communication; Frame (networking); Computer science; Management science; Accountability; Evaluation methods; Epistemology; Psychology; Social psychology; Political science","score_opus":0.3507628690464508,"score_gpt":0.5660418537784816,"score_spread":0.21527898473203078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140628270","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9120359,0.00032604244,0.067234166,0.011547325,0.0009122904,0.00064081606,0.0000052131795,0.0000102750755,0.007288008],"genre_scores_gemma":[0.9956565,0.0000432569,0.0031110814,0.00034695634,0.00041944554,0.00003445047,0.000009024697,0.000013549981,0.00036573078],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9736034,0.012856439,0.0010029294,0.00037559037,0.01181072,0.0003508941],"domain_scores_gemma":[0.9778165,0.003449526,0.0017511661,0.00058841193,0.016192803,0.00020159551],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.16305058,0.00015598346,0.00041681246,0.0010700745,0.0003130811,0.00042164233,0.00061805925,0.000044879085,0.0008065109],"category_scores_gemma":[0.034939047,0.0001113944,0.00015164564,0.0021306393,0.000456819,0.0011465694,0.00005744426,0.00044316752,0.000071104885],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014223078,0.000058432386,0.0035215092,0.0000012766269,0.00003330616,6.2869026e-7,0.0026022254,0.0064878063,0.00095811253,0.004125887,0.0015502726,0.98051834],"study_design_scores_gemma":[0.0028320681,0.004219403,0.14805347,0.000113558555,0.00026536357,0.000072556824,0.052338794,0.34884262,0.0018248559,0.41952598,0.021515062,0.0003962717],"about_ca_topic_score_codex":0.000024098523,"about_ca_topic_score_gemma":0.00014303891,"teacher_disagreement_score":0.980122,"about_ca_system_score_codex":0.0006674662,"about_ca_system_score_gemma":0.0016091487,"threshold_uncertainty_score":0.97319007},"labels":[],"label_agreement":null},{"id":"W2140886572","doi":"10.7202/1025773ar","title":"Un canevas d’item pour évaluer la compétence d’investigation scientifique en laboratoire","year":2014,"lang":"fr","type":"article","venue":"McGill Journal of Education / Revue des sciences de l éducation de McGill","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Humanities; Political science; Valuation (finance); Philosophy; Business","score_opus":0.42403237569570407,"score_gpt":0.49230300071791044,"score_spread":0.06827062502220638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140886572","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8368566,0.0016501184,0.013431421,0.0714636,0.01628402,0.0005990986,0.00012159558,0.000052448042,0.05954107],"genre_scores_gemma":[0.8872379,0.00082107465,0.08895787,0.0047434056,0.0009492567,0.000035148423,0.000012856419,0.00003647746,0.017205989],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9895587,0.0048799324,0.0019936562,0.0007687373,0.0020322131,0.000766742],"domain_scores_gemma":[0.98729396,0.0037381297,0.002442646,0.00062869437,0.005089672,0.0008069008],"candidate_categories":["metaresearch","metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.035307348,0.00040565108,0.0005535309,0.0012924394,0.0026759245,0.000770492,0.0018111151,0.00031173736,0.0017182297],"category_scores_gemma":[0.012947612,0.00037641698,0.00026620663,0.0038937149,0.0018845227,0.0029358282,0.00012138025,0.0006546622,0.0003160398],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006158895,0.0015379784,0.026118144,0.00046164272,0.00008983831,0.000010881243,0.021206524,0.029084131,0.006417069,0.36903843,0.03470602,0.5112677],"study_design_scores_gemma":[0.0007681645,0.0005154099,0.057792496,0.0019086774,0.00020906964,0.002424441,0.013634789,0.0812611,0.009320223,0.17997792,0.65140957,0.0007781695],"about_ca_topic_score_codex":0.00029320997,"about_ca_topic_score_gemma":0.0002971479,"teacher_disagreement_score":0.6167035,"about_ca_system_score_codex":0.0029348633,"about_ca_system_score_gemma":0.007911168,"threshold_uncertainty_score":0.99986875},"labels":[],"label_agreement":null},{"id":"W2141845170","doi":"10.7202/014411ar","title":"Évaluation de l’utilisation et de la présentation des résultats d’analyses factorielles et d’analyses en composantes principales en éducation","year":2007,"lang":"fr","type":"article","venue":"Revue des sciences de l éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":65,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Humanities; Philosophy","score_opus":0.7685778086784194,"score_gpt":0.6585129927282665,"score_spread":0.11006481595015294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141845170","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7418279,0.0013449324,0.23984434,0.0036680386,0.0012760132,0.00046307023,0.000017271532,0.000070831935,0.011487581],"genre_scores_gemma":[0.90159166,0.0025765128,0.09302174,0.00048125317,0.0005368034,0.00006040167,0.00015242197,0.000026519041,0.0015527012],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.98712474,0.007894718,0.0014173513,0.00088369555,0.0018196728,0.00085981126],"domain_scores_gemma":[0.9851701,0.011843916,0.0010342852,0.00046462181,0.001171355,0.00031569356],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.055427276,0.0004153179,0.0004209743,0.0010922682,0.0013164848,0.001416291,0.00080504344,0.00036429366,0.0006633304],"category_scores_gemma":[0.013445105,0.0003940617,0.00022934492,0.0027134528,0.0016645085,0.0034052948,0.00009595342,0.00041690614,0.00016662465],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000072317016,0.0007716792,0.16232298,0.0002894547,0.00009929146,0.000004683879,0.49170807,0.14654125,0.06920534,0.037265036,0.0007801978,0.090939686],"study_design_scores_gemma":[0.00040976267,0.0002613976,0.59677356,0.00043441236,0.00026136293,0.00013230671,0.08914411,0.20857757,0.024115942,0.07700399,0.0024348432,0.00045070858],"about_ca_topic_score_codex":0.0023305449,"about_ca_topic_score_gemma":0.0049852887,"teacher_disagreement_score":0.43445063,"about_ca_system_score_codex":0.0044737225,"about_ca_system_score_gemma":0.007293979,"threshold_uncertainty_score":0.99998367},"labels":[],"label_agreement":null},{"id":"W2142219519","doi":"","title":"System-Wide Program Assessment with Performance Indicators: Alberta's Performance Funding Mechanisms.","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Performance measurement; Business; Performance indicator; Process management; Political science; Accounting; Marketing","score_opus":0.14727823206226057,"score_gpt":0.4519045550663222,"score_spread":0.30462632300406167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142219519","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9649002,0.00011576724,0.0008916878,0.00087647216,0.0006103365,0.0025440531,0.0000044402746,0.00004707519,0.030009992],"genre_scores_gemma":[0.98206955,0.00003031482,0.01618524,0.000159444,0.0001795644,0.00042658765,0.000023719538,0.000030972733,0.0008946069],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9924899,0.0005770651,0.0015188581,0.00043900654,0.004249873,0.0007253268],"domain_scores_gemma":[0.9951773,0.0002815121,0.0011584765,0.00056906586,0.0018846106,0.0009289871],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.014610207,0.0003147581,0.00048723977,0.0013165412,0.00070553925,0.00093795906,0.00091078854,0.00014737938,0.005684865],"category_scores_gemma":[0.00035567192,0.00022317725,0.00015133007,0.0020273048,0.00015743419,0.0017825487,0.000015840144,0.00048394522,0.0002700378],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004678719,0.00008465419,0.0908091,0.000032844197,0.000056412508,0.0000074152463,0.0005525503,0.006194991,0.0000045362267,0.0003741831,0.0004817914,0.90135473],"study_design_scores_gemma":[0.003021059,0.0058676153,0.443175,0.00074413774,0.00033743845,0.0003880192,0.0024658793,0.41123438,0.00023361966,0.00036605637,0.13149238,0.0006744256],"about_ca_topic_score_codex":0.00049013254,"about_ca_topic_score_gemma":0.006258432,"teacher_disagreement_score":0.9006803,"about_ca_system_score_codex":0.0013159168,"about_ca_system_score_gemma":0.0074588903,"threshold_uncertainty_score":0.9981679},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"other","about_ca_system":false,"about_ca_topic":true,"confidence":"low"},{"model":"opus","categories":[],"domain":null,"study_design":"design_other","genre":"other","about_ca_system":true,"about_ca_topic":true,"confidence":"low"}],"label_agreement":"split"},{"id":"W2142374214","doi":"10.1177/1075547001022004003","title":"Climbing the Ladder of Research Utilization","year":2001,"lang":"en","type":"article","venue":"Science Communication","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":269,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Climbing; Climb; Transmission (telecommunications); Stage (stratigraphy); Knowledge management; Computer science; Engineering; Biology; Telecommunications; Ecology","score_opus":0.8407600227914698,"score_gpt":0.7017700442979139,"score_spread":0.13898997849355588,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142374214","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8391384,0.00036072978,0.0025549207,0.014403293,0.00017669647,0.00032875192,8.1654986e-7,0.000022938431,0.14301348],"genre_scores_gemma":[0.99774283,0.0004134464,0.00068488985,0.00013871338,0.000013966695,0.000013773783,0.000001810501,0.000002173257,0.0009883663],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99531806,0.0007044934,0.00041671123,0.00019703856,0.0031696951,0.00019401201],"domain_scores_gemma":[0.9943008,0.0014979517,0.00019243793,0.0017551875,0.0022123689,0.000041275915],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.042682488,0.000040966257,0.0000714237,0.0003821314,0.000967512,0.00025779288,0.002718281,0.00002324063,0.0005794945],"category_scores_gemma":[0.004292473,0.000023951648,0.00002558507,0.0050884904,0.0014521907,0.00086602086,0.00042851293,0.00016875357,0.00019135066],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003485223,0.00020449195,0.17222036,0.0000040916952,0.0000045127763,1.9175994e-7,0.01592463,0.0018773387,0.012467764,0.27098694,0.0046282425,0.52164656],"study_design_scores_gemma":[0.0003056232,0.00010413432,0.5898822,0.00005315683,0.0000043934683,0.0000066953085,0.021465784,0.1388094,0.0071089277,0.123942204,0.118191324,0.00012619612],"about_ca_topic_score_codex":0.000049299546,"about_ca_topic_score_gemma":0.00010902861,"teacher_disagreement_score":0.5215204,"about_ca_system_score_codex":0.000059137066,"about_ca_system_score_gemma":0.0003865595,"threshold_uncertainty_score":0.98575985},"labels":[],"label_agreement":null},{"id":"W2143390912","doi":"10.1007/978-1-4020-9747-8_1","title":"Where Theory Meets Practice","year":2009,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Bureaucracy; Authoritarianism; Government (linguistics); Political science; Public relations; Control (management); Empirical evidence; Public administration; Administration (probate law); Management; Democracy; Economics; Law; Politics","score_opus":0.20051355081475875,"score_gpt":0.5012097622933234,"score_spread":0.3006962114785646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143390912","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[9.386313e-7,0.0011864003,0.0009316074,0.012875352,0.00042319804,0.00021123573,0.000005892342,0.000057853595,0.9843075],"genre_scores_gemma":[0.00038533055,0.0010158048,0.0027100923,0.0067673475,0.00023139744,0.0000032397686,0.000007361395,0.000017711844,0.98886174],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99542755,0.00015450218,0.00072010484,0.0005147161,0.0030125245,0.0001705852],"domain_scores_gemma":[0.99513066,0.0024011768,0.00056357123,0.0009135568,0.0008773057,0.000113711765],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.007956801,0.0002447856,0.00033783383,0.00024514025,0.00012448753,0.00031782844,0.000681858,0.0002583595,0.119522445],"category_scores_gemma":[0.0011111312,0.00015738765,0.00017314921,0.000063515356,0.000061396764,0.0006017276,0.00008989784,0.00033766488,0.019704357],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018137926,0.000008773871,0.0000015139785,0.0000012061028,0.000014554063,0.0000051222237,0.00006100465,0.000008272775,9.701556e-7,0.5939565,0.10136729,0.3045567],"study_design_scores_gemma":[0.000101258986,0.000062166495,0.000026683694,0.000027135937,0.00002693498,0.000010850964,0.00012509678,0.000074441436,0.0000035697142,0.30894813,0.69044,0.00015372202],"about_ca_topic_score_codex":0.0000025443007,"about_ca_topic_score_gemma":0.000055425717,"teacher_disagreement_score":0.5890727,"about_ca_system_score_codex":0.00006286144,"about_ca_system_score_gemma":0.00035252544,"threshold_uncertainty_score":0.9810589},"labels":[],"label_agreement":null},{"id":"W2143645386","doi":"","title":"How to Change 5000 Schools: A Practical and Positive Approach for Leading Change at Every Level","year":2008,"lang":"en","type":"book","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":191,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Embodied cognition; Public administration; Political science; Economic growth; Public education; Public relations; Economics","score_opus":0.7024683524713844,"score_gpt":0.5225452151253678,"score_spread":0.17992313734601662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143645386","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004211693,0.0013550404,0.10815155,0.083415285,0.0010986713,0.0105160745,0.0011425387,0.0001525788,0.79374707],"genre_scores_gemma":[0.0009883288,0.00031629854,0.049273655,0.009161486,0.0012421613,0.001016544,0.00022037393,0.000044711138,0.93773645],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956311,0.00013225643,0.0005226922,0.0010550235,0.0022007115,0.00045822348],"domain_scores_gemma":[0.9965678,0.0012057938,0.00037566328,0.0005391589,0.0009515804,0.00036000597],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0026988585,0.0003979882,0.0006796927,0.0005848215,0.00041277142,0.00057983544,0.00038436137,0.00038151987,0.0003288017],"category_scores_gemma":[0.0014550939,0.00028992374,0.00018204517,0.00026035582,0.00008286752,0.0014097879,0.00038247948,0.00036747844,0.0004577431],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018078278,0.000075428834,0.00026893138,0.000045600733,0.00007359911,0.000009396464,0.0028232052,0.0000013856302,0.0000132303385,0.007745384,0.9180648,0.070698306],"study_design_scores_gemma":[0.0008033417,0.0005657942,0.0032062395,0.00012445358,0.00007305833,0.00013637505,0.0011756636,0.0051481957,0.00005905103,0.0016874446,0.9862731,0.00074729807],"about_ca_topic_score_codex":0.000012565881,"about_ca_topic_score_gemma":0.000102887214,"teacher_disagreement_score":0.14398935,"about_ca_system_score_codex":0.00051093707,"about_ca_system_score_gemma":0.00069513003,"threshold_uncertainty_score":0.9999553},"labels":[],"label_agreement":null},{"id":"W2144145370","doi":"10.3917/risa.812.0431","title":"Les compétences en technologies de l’information dans les programmes universitaires de premier cycle en administration publique en Afrique du Sud","year":2015,"lang":"fr","type":"article","venue":"Revue Internationale des Sciences Administratives","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École Nationale d'Administration Publique","funders":"","keywords":"Political science; Humanities; Philosophy","score_opus":0.1254808675585312,"score_gpt":0.4214636834185518,"score_spread":0.2959828158600206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144145370","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80704117,0.0012060651,0.047967132,0.08011221,0.000654989,0.0007494032,0.00016426934,0.0002384262,0.06186634],"genre_scores_gemma":[0.9559166,0.0009457209,0.038866296,0.00009009004,0.00021238854,0.00009875139,0.000050205388,0.000010846316,0.0038091147],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9949919,0.0011507848,0.0009723545,0.00059605093,0.0016759512,0.0006129847],"domain_scores_gemma":[0.99474496,0.0022636803,0.0007298095,0.00031311568,0.0016793816,0.00026903723],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00784172,0.00037671314,0.00035079167,0.0006244551,0.00091482745,0.0014690046,0.0019457571,0.0003836272,0.00034747785],"category_scores_gemma":[0.007148374,0.00033660146,0.0001590184,0.0012121475,0.0031218808,0.0058308993,0.0002847406,0.00041562854,0.00007830637],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017184258,0.00046258225,0.23471984,0.00013380745,0.00009324876,0.00003808384,0.081943646,0.006443592,0.0001805729,0.39954185,0.0013018799,0.27496907],"study_design_scores_gemma":[0.0008795783,0.0039618206,0.06715182,0.00076813507,0.00007439417,0.0007317578,0.41965723,0.19382413,0.006355153,0.11961017,0.18610123,0.00088458514],"about_ca_topic_score_codex":0.0015840014,"about_ca_topic_score_gemma":0.008285885,"teacher_disagreement_score":0.3377136,"about_ca_system_score_codex":0.0021922735,"about_ca_system_score_gemma":0.007121059,"threshold_uncertainty_score":0.9999086},"labels":[],"label_agreement":null},{"id":"W2144226050","doi":"10.26522/brocked.v16i2.30","title":"A Systematic Process for Educational Policy Development: Based on a Systems Approach to Training and Project Management","year":2007,"lang":"en","type":"article","venue":"Brock Education Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Brock University","funders":"","keywords":"Process (computing); Equity (law); Training (meteorology); Educational management; Policy development; Process management; Mathematics education; Pedagogy; Psychology; Public relations; Sociology; Political science; Engineering ethics; Computer science; Business; Public administration; Engineering; Law","score_opus":0.2297078464147301,"score_gpt":0.5134758963839476,"score_spread":0.28376804996921756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144226050","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12896702,0.0007818878,0.71770525,0.009936291,0.0048350007,0.0140196625,0.000014518915,0.00008923,0.12365115],"genre_scores_gemma":[0.9611953,0.0000026560938,0.025821012,0.0014008147,0.00090415863,0.0009454558,0.000012658299,0.000017096309,0.009700854],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9967543,0.00013220779,0.0010296613,0.00032124075,0.001468609,0.00029401702],"domain_scores_gemma":[0.9975719,0.00054790784,0.0004963136,0.00020814723,0.00086889963,0.000306851],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0048837205,0.00015473134,0.00024948292,0.001501479,0.00053019787,0.0006075672,0.00034857637,0.000042216092,0.000021805898],"category_scores_gemma":[0.0015882878,0.00011304603,0.000051502328,0.0009504458,0.000013629442,0.00026377168,0.000017093946,0.000106829146,0.000032187254],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010927853,0.006959925,0.012741556,0.034390163,0.0007580231,0.0000022617912,0.1874122,0.07302254,0.00014424813,0.110185586,0.1654418,0.4078489],"study_design_scores_gemma":[0.006438185,0.0012116112,0.109455,0.01753258,0.0003146919,0.0012995536,0.54093736,0.10664822,0.00018942151,0.0144596035,0.19912902,0.0023847779],"about_ca_topic_score_codex":0.0000021962408,"about_ca_topic_score_gemma":0.000002550706,"teacher_disagreement_score":0.83222824,"about_ca_system_score_codex":0.00031029986,"about_ca_system_score_gemma":0.0052271257,"threshold_uncertainty_score":0.9272697},"labels":[],"label_agreement":null},{"id":"W2144447286","doi":"10.1023/b:wate.0000026606.43479.f2","title":"Editorial: Research: Why is it done?","year":2004,"lang":"en","type":"editorial","venue":"Water Air & Soil Pollution","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Engineering ethics; Computer science; Data science; Engineering","score_opus":0.21859546936829852,"score_gpt":0.5056596509227164,"score_spread":0.2870641815544178,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144447286","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020020003,0.00008261857,0.00024826435,0.02679012,0.96215457,0.000455459,0.00025033555,0.00008131602,0.009737116],"genre_scores_gemma":[0.007973438,0.00021848707,0.000058538724,0.0012113256,0.9574062,0.00010578533,0.0004064063,0.00005848912,0.032561302],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9778163,0.0011299874,0.001472681,0.001361307,0.017096836,0.0011229257],"domain_scores_gemma":[0.99263006,0.00092724385,0.0003590379,0.0016259353,0.0041491613,0.00030855706],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.02183906,0.0004926184,0.0006778694,0.0011472718,0.0008629501,0.00089384156,0.0017652995,0.0016401142,0.0039319918],"category_scores_gemma":[0.0030709794,0.00031617947,0.00036564167,0.00097229524,0.00034651734,0.0010315989,0.0005324197,0.0021028526,0.020762002],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000095863645,0.00007855853,0.0000064124347,0.00002045344,0.000029661594,0.000002651514,0.0021821868,0.00040104034,0.00013564335,0.000047490248,0.99532104,0.0016789903],"study_design_scores_gemma":[0.0010298413,0.00023999678,0.000024212042,0.00013575204,0.00002993895,8.869632e-7,0.00037135975,0.00010676234,0.0016228377,0.016846882,0.97916764,0.00042389098],"about_ca_topic_score_codex":0.0015991187,"about_ca_topic_score_gemma":0.0011629356,"teacher_disagreement_score":0.025578795,"about_ca_system_score_codex":0.0012240544,"about_ca_system_score_gemma":0.0024259894,"threshold_uncertainty_score":0.999929},"labels":[],"label_agreement":null},{"id":"W2147225835","doi":"10.33524/cjar.v14i2.81","title":"SEEING THE CHILDREN FOR THE TREES","year":2015,"lang":"en","type":"article","venue":"The Canadian Journal of Action Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Nipissing University","funders":"","keywords":"Action (physics); Scope (computer science); Action research; Epistemology; Sociology; Psychology; Pedagogy; Computer science; Philosophy","score_opus":0.8403200451844858,"score_gpt":0.6565792953300275,"score_spread":0.18374074985445832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147225835","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5716509,0.0013720157,0.0020936003,0.41155517,0.0019545231,0.0009442433,0.000014921606,0.000004498551,0.010410121],"genre_scores_gemma":[0.9950259,0.000027843162,0.000040693736,0.00045718896,0.00057901675,0.00000896166,3.707323e-7,0.0000045096626,0.0038555209],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965343,0.0007370904,0.00031681912,0.00007550373,0.002077245,0.0002590463],"domain_scores_gemma":[0.9941158,0.002900999,0.00017456156,0.00035548376,0.0021775742,0.00027552724],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.040917505,0.00004652282,0.000080462756,0.00027595513,0.0016223106,0.00074136676,0.0012749389,0.000029165541,0.00046833043],"category_scores_gemma":[0.004320481,0.000016433192,0.00008071207,0.0006606516,0.0002707045,0.00026864628,0.000024423041,0.00049759826,0.00009968717],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012264223,0.0000123283835,0.028963871,9.797271e-7,0.00009212394,0.0000024944513,0.0070625893,0.009891034,0.000052938634,0.0048129973,0.7133921,0.23559393],"study_design_scores_gemma":[0.00052628084,0.00025715164,0.18639398,0.000011381782,0.000016871683,0.000121792786,0.018402042,0.008366083,0.00023190826,0.019639285,0.7659757,0.000057494777],"about_ca_topic_score_codex":0.007004474,"about_ca_topic_score_gemma":0.20143734,"teacher_disagreement_score":0.42337498,"about_ca_system_score_codex":0.00023187108,"about_ca_system_score_gemma":0.0041163974,"threshold_uncertainty_score":0.9996774},"labels":[],"label_agreement":null},{"id":"W2147443902","doi":"10.7202/900586ar","title":"Apprendre à penser pour mieux résoudre les conflits interpersonnels en classe maternelle","year":2009,"lang":"fr","type":"article","venue":"Revue des sciences de l éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Rimouski","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.6060791804386243,"score_gpt":0.5450952203679784,"score_spread":0.06098396007064588,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147443902","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9097985,0.0035439103,0.012099325,0.030315187,0.0026995486,0.0003674154,0.000016416156,0.000056277586,0.041103445],"genre_scores_gemma":[0.92259574,0.00078755553,0.01130536,0.0010693386,0.00055265374,0.000019526933,0.000012600998,0.000011372654,0.06364587],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99581546,0.00087196165,0.00078138855,0.0008207003,0.0010620942,0.0006484247],"domain_scores_gemma":[0.9976103,0.000665916,0.00041696048,0.0005013275,0.0005406543,0.00026488397],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.005430919,0.00029333364,0.00033469978,0.00041148966,0.0009771164,0.0009987868,0.0012093112,0.00023053761,0.005644829],"category_scores_gemma":[0.0010969406,0.00026277846,0.00017082987,0.0013203836,0.0009129143,0.001610314,0.00008932707,0.00027728177,0.0024304495],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054417098,0.0008187287,0.025642091,0.00023486046,0.000034748755,0.000018672965,0.26403764,0.009200943,0.005645884,0.07997672,0.03107238,0.5832629],"study_design_scores_gemma":[0.000889125,0.0011480693,0.1429488,0.0013800598,0.00011641472,0.00055371976,0.17144889,0.47794223,0.0042727594,0.11459734,0.08361084,0.0010917478],"about_ca_topic_score_codex":0.00021076282,"about_ca_topic_score_gemma":0.00043326998,"teacher_disagreement_score":0.58217114,"about_ca_system_score_codex":0.00077641744,"about_ca_system_score_gemma":0.0011999591,"threshold_uncertainty_score":0.9999824},"labels":[],"label_agreement":null},{"id":"W2147588626","doi":"10.1177/1049732308316206","title":"In Search of Respect for Qualitative Research","year":2008,"lang":"en","type":"letter","venue":"Qualitative Health Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Qualitative research; Psychology; Sociology; Social science","score_opus":0.9616366199794026,"score_gpt":0.8329368087756758,"score_spread":0.12869981120372687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147588626","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004867874,0.0014988306,0.00084955344,0.97638845,0.00041876556,0.0056484076,0.00090312556,0.000020066867,0.009404939],"genre_scores_gemma":[0.04375245,0.0072097373,0.028784502,0.57307976,0.009055182,0.0099596195,0.0016745053,0.0006228517,0.3258614],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.6889884,0.24778832,0.007411365,0.0036443425,0.04651922,0.0056483718],"domain_scores_gemma":[0.7768478,0.2009005,0.0008095276,0.001826229,0.019240195,0.00037576328],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","sts","insufficient_payload"],"category_scores_codex":[0.46920064,0.0004610424,0.0019791124,0.00991927,0.0013080272,0.00024976,0.0030292273,0.0009469093,0.0017050463],"category_scores_gemma":[0.06431436,0.00037062235,0.00038342882,0.009917449,0.0032232313,0.0006422748,0.00061358797,0.01051621,0.0012582153],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032356885,0.00012396406,0.0000189989,0.000540275,0.000025862075,0.000024127374,0.3247902,0.000009245321,0.000009412839,0.005935013,0.6661219,0.0020774156],"study_design_scores_gemma":[0.001066769,0.0024144438,0.00014913947,0.00034514093,0.0000011824586,0.000003131031,0.22962162,0.00034573907,0.00009697401,0.10328008,0.6624194,0.0002564094],"about_ca_topic_score_codex":0.0041593546,"about_ca_topic_score_gemma":0.0009310814,"teacher_disagreement_score":0.40488628,"about_ca_system_score_codex":0.0023666313,"about_ca_system_score_gemma":0.0166153,"threshold_uncertainty_score":0.99999213},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"evaluation","study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"evaluation","study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W2148675934","doi":"10.7202/900522ar","title":"Le processus de sélection dans les écoles secondaires polyvalentes","year":2009,"lang":"fr","type":"article","venue":"Revue des sciences de l éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université Laval","funders":"","keywords":"Humanities; Philosophy","score_opus":0.5186314078293547,"score_gpt":0.5330731581324368,"score_spread":0.014441750303082146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148675934","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8189278,0.005822557,0.03466115,0.03575826,0.0016949958,0.00036877347,0.00001187904,0.00008362031,0.10267095],"genre_scores_gemma":[0.9704697,0.0008692627,0.0085744895,0.000648976,0.00043063753,0.000028237195,0.0000072026605,0.000008506059,0.018962966],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967918,0.0005495613,0.0006108845,0.0006079803,0.0008291178,0.00061066874],"domain_scores_gemma":[0.9982603,0.00035191086,0.00039883563,0.0003134869,0.00047196043,0.00020346089],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0055010994,0.00021053893,0.00022280775,0.00040269876,0.0020520147,0.0008753577,0.00077848573,0.00015735955,0.0007444616],"category_scores_gemma":[0.0011531616,0.00020402049,0.00012079389,0.0019271454,0.0011757954,0.0018923809,0.00003792538,0.00020448942,0.00021209271],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027902772,0.0006918504,0.047468774,0.00018809404,0.00001532431,0.0000037142906,0.094451874,0.018162075,0.0096462285,0.13470851,0.004378146,0.6902575],"study_design_scores_gemma":[0.0005686194,0.0014045804,0.2833565,0.0007949159,0.00009031457,0.00049724936,0.08742042,0.2882021,0.017432032,0.28342798,0.036050674,0.0007546092],"about_ca_topic_score_codex":0.00094540603,"about_ca_topic_score_gemma":0.0036229135,"teacher_disagreement_score":0.6895029,"about_ca_system_score_codex":0.0010096501,"about_ca_system_score_gemma":0.0053071254,"threshold_uncertainty_score":0.9992472},"labels":[],"label_agreement":null},{"id":"W2148790212","doi":"10.1177/1757975909339769","title":"Le transfert de connaissances et les règles de fonctionnement du système universitaire: besoin de changements <sup>i</sup>","year":2009,"lang":"fr","type":"article","venue":"Global Health Promotion","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Humanities; Political science; Art","score_opus":0.12049999922768247,"score_gpt":0.45504875793489147,"score_spread":0.334548758707209,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148790212","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48847124,0.0038330539,0.16828224,0.32950467,0.00080178544,0.0013566432,0.00016758464,0.00013350308,0.007449271],"genre_scores_gemma":[0.9882163,0.003071805,0.003182488,0.004039477,0.00029925967,0.000033419277,0.0000511696,0.000009672068,0.0010964205],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9946421,0.0018670124,0.00077906786,0.00054946716,0.0011923774,0.0009699903],"domain_scores_gemma":[0.998459,0.00010146407,0.00031485845,0.00029458775,0.00034947734,0.00048063794],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.007588848,0.00028157784,0.00037313567,0.00015020631,0.0011007368,0.00021075748,0.0004240463,0.00023970682,0.0007144234],"category_scores_gemma":[0.00014657613,0.00029286693,0.00014328305,0.0007491791,0.00014747023,0.0009360008,0.00004357784,0.0002456542,0.00014563497],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014959305,0.0018780561,0.024643645,0.00030311223,0.00005666369,0.00001740737,0.008904188,0.008983377,0.000024169502,0.1562231,0.020461405,0.7783553],"study_design_scores_gemma":[0.0067689545,0.008716067,0.48383853,0.0020127539,0.00015465259,0.00021727353,0.036907375,0.20553045,0.00013925512,0.09072734,0.16407904,0.00090832874],"about_ca_topic_score_codex":0.003016373,"about_ca_topic_score_gemma":0.0024838417,"teacher_disagreement_score":0.7774469,"about_ca_system_score_codex":0.0034864314,"about_ca_system_score_gemma":0.0048595564,"threshold_uncertainty_score":0.9999524},"labels":[],"label_agreement":null},{"id":"W2149719915","doi":"10.1177/1098214008325023","title":"An Assessment of the Theoretical Underpinnings of Practical Participatory Evaluation","year":2008,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":63,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Context (archaeology); Process (computing); Citizen journalism; Key (lock); Management science; Participatory action research; Knowledge management; Empirical research; Action (physics); Computer science; Epistemology; Psychology; Sociology; Engineering","score_opus":0.36844893795092876,"score_gpt":0.6248471033074683,"score_spread":0.25639816535653953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2149719915","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98149073,0.000031573632,0.013610761,0.0024161558,0.0003237666,0.00032163633,0.0000021530177,0.0000026822338,0.0018005405],"genre_scores_gemma":[0.9947462,0.000019502751,0.004898443,0.00022399008,0.0000836296,0.0000115048415,0.00000169863,0.00000774221,0.0000072674625],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9849417,0.0044905725,0.0016997985,0.0001763577,0.008526938,0.00016458913],"domain_scores_gemma":[0.98865235,0.0014654833,0.0033602405,0.0005662707,0.0058382675,0.000117376825],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03925495,0.00011468368,0.0004232621,0.00025957252,0.00013436508,0.000028677747,0.00041794972,0.00004117019,0.0020681585],"category_scores_gemma":[0.006563201,0.000067684785,0.0001947159,0.000962702,0.0011591988,0.00067592826,0.000042855077,0.00024272942,0.000005732771],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004904929,0.0018145251,0.5240415,0.000012317576,0.00025527197,0.0000031477127,0.013053106,0.08304765,0.01791772,0.05378032,0.0018608829,0.3037231],"study_design_scores_gemma":[0.00083759765,0.0014297705,0.63061154,0.000033861055,0.00023298239,0.00006556228,0.004369862,0.34352988,0.0019356196,0.016793266,0.00007942671,0.00008065625],"about_ca_topic_score_codex":0.000009599368,"about_ca_topic_score_gemma":0.00000506154,"teacher_disagreement_score":0.30364245,"about_ca_system_score_codex":0.00019915319,"about_ca_system_score_gemma":0.003895509,"threshold_uncertainty_score":0.9988441},"labels":[],"label_agreement":null},{"id":"W2150098308","doi":"10.46743/2160-3715/2013.1492","title":"Toddling Towards Childhood: A Bibliometric Analysis of the First QROM Lustrum (2006 - 2010)","year":2015,"lang":"en","type":"article","venue":"The Qualitative Report","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Narrative; Sociology; Diversity (politics); Social science; Sample (material); Qualitative research; Content analysis; Narrative inquiry; Public relations; Political science; Anthropology; Literature","score_opus":0.4888674644030126,"score_gpt":0.5984291104202918,"score_spread":0.10956164601727919,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150098308","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9697867,0.00025321153,0.0026623646,0.008721891,0.0006869478,0.00029114843,0.000041379393,0.00002000532,0.017536338],"genre_scores_gemma":[0.9943582,0.000015632642,0.0003929238,0.00033499242,0.000060449955,0.00001996462,0.000010147515,0.0000073942942,0.0048002987],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99296975,0.0010363285,0.0013562848,0.00036434902,0.00403897,0.00023433096],"domain_scores_gemma":[0.99347556,0.0019937267,0.0014100194,0.0013435119,0.0016700844,0.00010712369],"candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":["metaresearch","bibliometrics"],"category_scores_codex":[0.0358491,0.00014905122,0.00047011767,0.013580297,0.00025220984,0.00014582604,0.0009583036,0.00005814777,0.00061989116],"category_scores_gemma":[0.012049938,0.00006725577,0.00036142976,0.14391033,0.00025572578,0.00030399818,0.00024345501,0.00018216288,0.00009131226],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013663789,0.00062396005,0.51008326,0.000017230452,0.0030968336,0.000025183797,0.31990278,0.021809889,0.0000699525,0.005191584,0.094136454,0.044906277],"study_design_scores_gemma":[0.0002676793,0.000078427416,0.93979084,0.000012481326,0.00033533145,0.00001736155,0.032355547,0.004037998,0.00020336892,0.009530947,0.013232028,0.00013801231],"about_ca_topic_score_codex":0.0008364651,"about_ca_topic_score_gemma":0.00031447312,"teacher_disagreement_score":0.4297076,"about_ca_system_score_codex":0.00008952747,"about_ca_system_score_gemma":0.0007065768,"threshold_uncertainty_score":0.9975999},"labels":[],"label_agreement":null},{"id":"W2150819211","doi":"10.7202/017421ar","title":"Mesure de résultats des travaux communautaires chez les jeunes contrevenants : l’I.É.R.T.C.","year":2005,"lang":"en","type":"article","venue":"Criminologie","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Openness to experience; Psychology; Participant observation; Work (physics); Social psychology; Applied psychology; Sociology; Social science","score_opus":0.6832887231936352,"score_gpt":0.5491357359473314,"score_spread":0.13415298724630376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150819211","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9836901,0.0011153612,0.0012052016,0.0063856356,0.0001721817,0.00016652133,0.000008861389,0.00014147506,0.007114702],"genre_scores_gemma":[0.9922871,0.0003383301,0.0034549653,0.0008841322,0.00011548181,0.000027449309,0.0000056405206,0.000011631569,0.0028752922],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99724305,0.00045622798,0.0006000258,0.0003554338,0.00083035853,0.00051492854],"domain_scores_gemma":[0.9974456,0.0012408973,0.00019260429,0.0006234215,0.000369179,0.00012830526],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0033555639,0.00019857791,0.0003192449,0.00018318463,0.00046253743,0.00021503081,0.0010119566,0.00015815218,0.0023643496],"category_scores_gemma":[0.0027137145,0.00013443547,0.00011874715,0.00026914402,0.00046931682,0.00045506388,0.00014513444,0.00023756895,0.0010090222],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028079305,0.000098518765,0.13484913,0.0000065742056,0.000016304095,0.00000547006,0.003247645,0.0005138537,0.0012719708,0.00058337534,0.00922727,0.8501518],"study_design_scores_gemma":[0.0008788636,0.00014648863,0.88469857,0.000032845255,0.000035345714,0.000025977512,0.012163175,0.0055983975,0.013299483,0.022453511,0.060381304,0.00028601385],"about_ca_topic_score_codex":0.000111671136,"about_ca_topic_score_gemma":0.0007136635,"teacher_disagreement_score":0.8498658,"about_ca_system_score_codex":0.00011652949,"about_ca_system_score_gemma":0.00029788745,"threshold_uncertainty_score":0.9997688},"labels":[],"label_agreement":null},{"id":"W2150927259","doi":"10.3138/cjpe.27.003","title":"The Art of the Nudge: Five Practices for Developmental Evaluators","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Servant; Psychology; Adaptation (eye); Servant leadership; Energy (signal processing); Pedagogy; Applied psychology; Public relations; Social psychology; Political science; Computer science","score_opus":0.5020626007095538,"score_gpt":0.5787691116820812,"score_spread":0.07670651097252745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150927259","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9608999,0.0018735748,0.0006508701,0.0192021,0.0049543967,0.003883451,0.000018555074,0.00000582638,0.008511353],"genre_scores_gemma":[0.99470854,0.000011069606,0.0036954382,0.00026207822,0.00021421861,0.00012675842,0.0000034962923,0.0000074375766,0.0009709466],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9955459,0.00073329115,0.0008957553,0.00010337824,0.0024201907,0.00030143108],"domain_scores_gemma":[0.9926672,0.0012130376,0.0022974194,0.00023987725,0.0033106382,0.00027182678],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.036570325,0.00009411802,0.0001539886,0.00017599436,0.0005625016,0.00025182776,0.0006672526,0.000054056363,0.0005739893],"category_scores_gemma":[0.017172627,0.000047000995,0.00016052752,0.0005574756,0.00015483206,0.000815033,0.000018982513,0.0001526935,0.000044043634],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036845264,0.00005077911,0.0847872,0.0000044167255,0.000065259694,1.10843146e-7,0.0031514221,0.00029070047,0.000060770682,0.0011040999,0.052906036,0.85754234],"study_design_scores_gemma":[0.00086578936,0.00026820062,0.18730994,0.00002742228,0.00016959535,0.00003942937,0.007618861,0.011328597,0.0006366092,0.004598858,0.7870238,0.00011294409],"about_ca_topic_score_codex":0.00012267273,"about_ca_topic_score_gemma":0.008814751,"teacher_disagreement_score":0.85742944,"about_ca_system_score_codex":0.0003638521,"about_ca_system_score_gemma":0.0072142,"threshold_uncertainty_score":0.998414},"labels":[],"label_agreement":null},{"id":"W2152495376","doi":"10.21432/t22p41","title":"An Extended Systematic Review of Canadian Policy Documents on e-Learning: What We’re Doing and Not Doing","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Learning and Technology","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Concordia University","funders":"","keywords":"Popularity; Consistency (knowledge bases); Public policy; Government (linguistics); Public relations; Policy learning; Political science; Knowledge management; Computer science; Artificial intelligence","score_opus":0.08455851744487888,"score_gpt":0.40414647402412585,"score_spread":0.319587956579247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2152495376","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8549493,0.080173135,0.00025859926,0.038828865,0.0008134716,0.0010238673,0.0000075984494,0.00006059026,0.023884574],"genre_scores_gemma":[0.98596394,0.012654706,0.00063584716,0.00036252313,0.000026126903,0.0000035409337,7.586561e-7,0.000010657223,0.00034191745],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9978109,0.00038186926,0.0008381023,0.00020795506,0.00043428992,0.00032688453],"domain_scores_gemma":[0.9976265,0.00018753861,0.00083315634,0.0002391033,0.00049676263,0.00061693107],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038041617,0.00013887543,0.000562515,0.004121547,0.00033387318,0.00017528729,0.00039826805,0.000136756,0.00038624855],"category_scores_gemma":[0.002192539,0.0001052806,0.000051022962,0.0012166215,0.00016399498,0.00052377384,0.00001936507,0.0005837622,0.000015518855],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000078826204,0.00008050091,0.23692644,0.031036118,0.00048163065,0.00074467645,0.02508919,0.00031557246,0.0006232752,0.05305687,0.001161455,0.65040547],"study_design_scores_gemma":[0.0041635674,0.010704589,0.016592199,0.41680196,0.00085828424,0.004338301,0.2498318,0.0031343368,0.0020843253,0.012494687,0.2769509,0.0020450517],"about_ca_topic_score_codex":0.011874664,"about_ca_topic_score_gemma":0.07356549,"teacher_disagreement_score":0.6483604,"about_ca_system_score_codex":0.0001221692,"about_ca_system_score_gemma":0.0015428597,"threshold_uncertainty_score":0.9947053},"labels":[],"label_agreement":null},{"id":"W2152855101","doi":"10.71781/5337","title":"Cahier des charges fonctionnel pour la conception et l’évaluation des plans d’intervention","year":2011,"lang":"fr","type":"dissertation","venue":"Open MIND","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Valuation (finance); Psychology; Political science; Economics; Accounting","score_opus":0.3298641184757035,"score_gpt":0.5163201472642462,"score_spread":0.18645602878854273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2152855101","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84279054,0.00030509382,0.016235495,0.00027049732,0.0017820505,0.0011290257,0.00015316419,0.0000064655683,0.13732766],"genre_scores_gemma":[0.73181397,0.00076530804,0.024979692,0.00008336717,0.0002487728,0.00025005077,0.0021411106,0.00005031183,0.23966742],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99344397,0.0021574553,0.0014305345,0.0009945399,0.0015436588,0.00042983735],"domain_scores_gemma":[0.9958273,0.00071045535,0.0011799682,0.00054765935,0.001544364,0.00019026041],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.012454278,0.00048230696,0.0005516627,0.00044723868,0.0008920459,0.0015594313,0.0010375923,0.00056408445,0.102171734],"category_scores_gemma":[0.001042786,0.00043623638,0.00032095268,0.0006005303,0.00037686265,0.0029633748,0.00014553772,0.0004759986,0.011093239],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025360344,0.00048509397,0.01623974,0.000055611326,0.000096244934,0.0000035997964,0.052409206,0.0003857042,0.0018742345,0.0010592765,0.00046945256,0.9266682],"study_design_scores_gemma":[0.0051171677,0.00095242815,0.70633185,0.002943722,0.00070345006,0.000062597785,0.101264596,0.028300658,0.018704096,0.03251576,0.10159061,0.0015130434],"about_ca_topic_score_codex":0.001460638,"about_ca_topic_score_gemma":0.0239779,"teacher_disagreement_score":0.92515516,"about_ca_system_score_codex":0.00029355253,"about_ca_system_score_gemma":0.0011848399,"threshold_uncertainty_score":0.99980897},"labels":[],"label_agreement":null},{"id":"W2153554254","doi":"","title":"Program Evaluation and Impact Assessment in International Non-Governmental Organizations (INGOs): Exploring Roles, Benefits, and Challenges","year":2013,"lang":"en","type":"article","venue":"Canadian journal of nonprofit and social economy research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Humanities; Management; Public relations; Sociology; Philosophy; Economics","score_opus":0.43010747490797296,"score_gpt":0.5173102999246516,"score_spread":0.08720282501667864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153554254","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9824025,0.0010046661,0.0000054747566,0.010481481,0.00009471528,0.0005288841,0.0000052606256,0.0000015116736,0.005475475],"genre_scores_gemma":[0.9984623,0.00095980597,0.00020909256,0.000045258454,0.00017535107,0.00009101884,0.0000042452484,0.000007215578,0.000045713507],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9981188,0.00020829424,0.0004339175,0.00019100647,0.00078997563,0.00025797205],"domain_scores_gemma":[0.9979689,0.00020696559,0.00015105926,0.00007326678,0.0012865737,0.00031321158],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0063813347,0.0000853941,0.00018162522,0.00060886994,0.00034357863,0.0007621203,0.00019909153,0.000060006758,0.00090272335],"category_scores_gemma":[0.00027083268,0.00007099964,0.000026110765,0.0002665713,0.00013783594,0.0012763959,0.00005686318,0.00029995333,0.000008720469],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000058676055,0.000022816475,0.4094661,0.0000065572567,0.000029345176,0.0000020254788,0.0052028513,0.000030017945,0.000013274598,0.0022718108,0.00034438062,0.582605],"study_design_scores_gemma":[0.0007666771,0.00019627684,0.9503119,0.00002952865,0.0000058514433,0.000013830076,0.030646995,0.009751958,0.0000095099995,0.0031676206,0.0050065704,0.000093289585],"about_ca_topic_score_codex":0.0019513636,"about_ca_topic_score_gemma":0.016874528,"teacher_disagreement_score":0.58251166,"about_ca_system_score_codex":0.00070813263,"about_ca_system_score_gemma":0.0018043064,"threshold_uncertainty_score":0.98841876},"labels":[],"label_agreement":null},{"id":"W2153662413","doi":"10.1111/j.1937-8327.1997.tb00057.x","title":"Research Design Decisions: An Integrated Quantitative and Qualitative Model for Decision-Making Researchers (You Too Can Be Lord of the Rings)","year":2008,"lang":"en","type":"article","venue":"Performance Improvement Quarterly","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Experiential learning; Point (geometry); Process (computing); Computer science; Management science; Research design; Data science; Qualitative property; Knowledge management; Psychology; Sociology; Mathematics education; Engineering","score_opus":0.6268712313570375,"score_gpt":0.5887370006997235,"score_spread":0.03813423065731403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153662413","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8068454,0.000067299654,0.19018759,0.00092163496,0.00015270649,0.0015543494,0.0000722262,0.000019467705,0.00017927338],"genre_scores_gemma":[0.9397849,0.00011770069,0.058271486,0.0002831002,0.000027106118,0.0003666311,0.0000067568844,0.00002610134,0.0011162324],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9918451,0.0011203616,0.0014005404,0.0008188231,0.004088416,0.0007268153],"domain_scores_gemma":[0.98431325,0.0104745375,0.0005124765,0.0010638223,0.0034225495,0.00021338127],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.025827315,0.00028637925,0.00045919738,0.00093024946,0.0013974194,0.00025856504,0.0013810755,0.00012368878,0.00007897451],"category_scores_gemma":[0.0056044003,0.0001772006,0.00013161483,0.002051117,0.0008635662,0.0014748367,0.00016227191,0.00051905337,0.000013947267],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021618663,0.00040223164,0.0023620373,0.00003829106,0.00007645168,0.0000013524589,0.24155344,0.015879646,0.0039766706,0.004666919,0.003997215,0.72488385],"study_design_scores_gemma":[0.00103803,0.005260849,0.004926372,0.00020310399,0.000012164048,0.000003407173,0.09023291,0.8768555,0.0012156036,0.019546049,0.0004507598,0.00025524368],"about_ca_topic_score_codex":0.00009855332,"about_ca_topic_score_gemma":0.00033823692,"teacher_disagreement_score":0.86097586,"about_ca_system_score_codex":0.00024826245,"about_ca_system_score_gemma":0.0013036502,"threshold_uncertainty_score":0.9999026},"labels":[],"label_agreement":null},{"id":"W2153743208","doi":"10.12927/hcpap..17126","title":"Evidence-Based Practice in Steeltown: A Good Start on Needed Cultural Change","year":2003,"lang":"en","type":"letter","venue":"A Nudge Too Far? A Nudge at All? On Paying People to Be Healthy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Canadian Foundation for Healthcare Improvement","funders":"","keywords":"Public relations; Tacit knowledge; Negotiation; Marshalling; Politics; Sociology; Health care; Health policy; Political science; Knowledge management; Social science; Law; Computer science","score_opus":0.47879301597489593,"score_gpt":0.506701940986113,"score_spread":0.027908925011217056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153743208","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04407211,0.00064158224,0.000054807242,0.94393027,0.0023807643,0.0038332622,0.0001830808,0.0001914992,0.004712637],"genre_scores_gemma":[0.0020553153,0.0008053744,0.0010716675,0.9862815,0.00041219685,0.0019796705,0.00034996303,0.00016307631,0.006881214],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98067284,0.004147288,0.0028776105,0.0027909428,0.007270399,0.0022409016],"domain_scores_gemma":[0.98045444,0.012955647,0.001890216,0.0026252696,0.0012905551,0.0007838847],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","insufficient_payload"],"category_scores_codex":[0.01176703,0.0013639047,0.0019177848,0.0018305563,0.0007595593,0.0009960845,0.0019787955,0.0012566897,0.0030928107],"category_scores_gemma":[0.009269979,0.0010588171,0.0005625518,0.0035097345,0.00008961564,0.0018494059,0.00033280044,0.0034752947,0.0061761746],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014069186,0.00039960383,0.00068423914,0.00009268201,0.000047400095,0.00019682993,0.008487909,0.00010824322,0.000018151095,0.00010501933,0.9795783,0.008874663],"study_design_scores_gemma":[0.0024124077,0.0033960573,0.002018216,0.000027139538,0.0000763638,0.00004078539,0.0026399826,0.0013296775,0.000039292303,0.000047016576,0.9867476,0.0012254575],"about_ca_topic_score_codex":0.0025841696,"about_ca_topic_score_gemma":0.0040361555,"teacher_disagreement_score":0.042351265,"about_ca_system_score_codex":0.003186299,"about_ca_system_score_gemma":0.002187235,"threshold_uncertainty_score":0.9999112},"labels":[],"label_agreement":null},{"id":"W2153744473","doi":"10.26686/pq.v11i3.4546","title":"The policy worker and the professor: understanding how New Zealand policy workers utilise academic research","year":2015,"lang":"en","type":"article","venue":"Policy Quarterly","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Prime minister; Government (linguistics); Political science; Public administration; Work (physics); Research policy; Public policy; Management; Sociology; Public relations; Politics; Law; Engineering; Economics","score_opus":0.5736288714791905,"score_gpt":0.5826868139904564,"score_spread":0.009057942511265904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153744473","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09657591,0.0006615369,0.00043224337,0.87465465,0.00034046633,0.0010258494,0.000010219766,0.0000656179,0.026233515],"genre_scores_gemma":[0.92022425,0.00020877535,0.000044106433,0.0017599098,0.0024471118,0.00006201881,0.0000018524267,0.000024121699,0.07522784],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99228907,0.0021436552,0.0006615046,0.0005087348,0.003327968,0.0010690624],"domain_scores_gemma":[0.99274814,0.0047213663,0.00032669684,0.0010855538,0.0004431403,0.00067508616],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.020687738,0.00025287346,0.00033295446,0.0010221443,0.001276259,0.0017433158,0.0014575451,0.00018983362,0.00003202847],"category_scores_gemma":[0.0060001872,0.00012216388,0.00011240955,0.0036644286,0.0012208293,0.0007233811,0.00019131023,0.0010074966,0.00029448554],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00055965426,0.000017936964,0.011222462,0.0000030759948,0.000043482887,0.0000012932376,0.057373617,0.000015555539,0.000009578151,0.42399383,0.35343516,0.15332438],"study_design_scores_gemma":[0.0033710096,0.00023526259,0.009632504,0.00004028973,0.000010553024,0.000016467813,0.07498059,0.0019409801,0.000005678884,0.7269392,0.1826398,0.00018767502],"about_ca_topic_score_codex":0.0048238044,"about_ca_topic_score_gemma":0.0012541305,"teacher_disagreement_score":0.8728947,"about_ca_system_score_codex":0.00066421437,"about_ca_system_score_gemma":0.005062879,"threshold_uncertainty_score":0.99929297},"labels":[],"label_agreement":null},{"id":"W2155294372","doi":"10.1111/j.1541-1338.2012.00581.x","title":"Cognizance and Consultation of Randomized Controlled Trials among Ministerial Policy Analysts","year":2012,"lang":"en","type":"article","venue":"Review of Policy Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Centre Hospitalier Universitaire de Québec; Université Laval","keywords":"Randomized controlled trial; Political science; Randomized experiment; Psychology; Public relations; Public administration; Medicine","score_opus":0.5457738126704711,"score_gpt":0.6909429540534592,"score_spread":0.1451691413829881,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155294372","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55052483,0.27542937,0.0006241383,0.059028335,0.0005947074,0.021895537,0.00023251209,0.000029687077,0.091640845],"genre_scores_gemma":[0.92329746,0.074306495,0.00022573667,0.00051319384,0.00061880745,0.0002445401,0.000009624996,0.0000069216344,0.00077719433],"study_design_codex":"design_other","study_design_gemma":"randomized_trial","domain_scores_codex":[0.97608614,0.01609042,0.0038314853,0.00023425362,0.0033723565,0.00038535614],"domain_scores_gemma":[0.91393113,0.07532498,0.003975582,0.0009183613,0.005342146,0.000507806],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.21290809,0.0001316927,0.0041512386,0.0011980119,0.000091456146,0.00007091768,0.0003549347,0.00006646563,0.00080095755],"category_scores_gemma":[0.41816708,0.00007171602,0.000564989,0.0021929755,0.0007612447,0.0003327183,0.00011787364,0.00013002622,0.00004053896],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.14380291,0.0012091857,0.024008784,0.014255072,0.002641987,0.0000017017005,0.011124124,0.000014721282,0.009731785,0.18706977,0.06249972,0.54364026],"study_design_scores_gemma":[0.86272216,0.0006828799,0.028797027,0.015720056,0.001447775,0.0000148390845,0.002234227,0.004172922,0.006558343,0.019514665,0.057362176,0.0007729241],"about_ca_topic_score_codex":0.00034494724,"about_ca_topic_score_gemma":0.000011689343,"teacher_disagreement_score":0.7189193,"about_ca_system_score_codex":0.00004772966,"about_ca_system_score_gemma":0.0010818709,"threshold_uncertainty_score":0.87699234},"labels":[],"label_agreement":null},{"id":"W2155342581","doi":"","title":"Ontario's Private Schools: Who Chooses Them and Why?","year":2007,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Business","score_opus":0.23264561839315193,"score_gpt":0.4672837176304044,"score_spread":0.23463809923725246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155342581","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7664153,0.000025093255,0.008843511,0.0015115017,0.00015328574,0.000107982596,5.539715e-7,0.00002542765,0.22291733],"genre_scores_gemma":[0.9475028,0.00001611373,0.0035318919,0.0027538615,0.000054588123,0.0000029913176,9.510407e-7,0.000003999166,0.04613284],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9980074,0.000041250823,0.00039844617,0.00026731435,0.0010817435,0.00020380324],"domain_scores_gemma":[0.99893427,0.00033701916,0.00009639145,0.0003302165,0.00017046268,0.00013165628],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0047050845,0.0000912159,0.0001409391,0.00011031406,0.00014046219,0.00030359856,0.00027228682,0.000043893848,0.016028585],"category_scores_gemma":[0.00024011235,0.000055989647,0.000035487417,0.0002785019,0.00003771505,0.00053675333,0.000091815076,0.00013242329,0.0010410597],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024235726,0.000026701846,0.8201251,0.0000010465744,0.000011029324,0.0000021437436,0.0007350823,0.000006795753,0.00011530696,0.017682804,0.016062368,0.14520739],"study_design_scores_gemma":[0.00026761723,0.000036485526,0.59160906,0.0000061965425,0.0000037856378,0.0000053252033,0.00060658494,0.00027480043,0.00078591733,0.01392856,0.39238685,0.000088795015],"about_ca_topic_score_codex":0.0010799838,"about_ca_topic_score_gemma":0.02370234,"teacher_disagreement_score":0.37632447,"about_ca_system_score_codex":0.00005825633,"about_ca_system_score_gemma":0.00012219048,"threshold_uncertainty_score":0.9997367},"labels":[],"label_agreement":null},{"id":"W2155432674","doi":"10.1016/j.evalprogplan.2013.12.001","title":"Government and voluntary sector differences in organizational capacity to do and use evaluation","year":2013,"lang":"en","type":"article","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":60,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Government (linguistics); Turnover; Business; Work (physics); Organizational effectiveness; Public relations; Capacity building; Public sector; Psychology; Knowledge management; Political science; Management; Engineering; Economics; Computer science","score_opus":0.26169651629310603,"score_gpt":0.47235094517419796,"score_spread":0.21065442888109193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155432674","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9960236,0.00024442349,0.00032086147,0.0011095181,0.00012776027,0.0016406066,0.0000122492975,0.000019776233,0.0005011993],"genre_scores_gemma":[0.9953582,0.000019474463,0.0037315993,0.00040015974,0.00004510651,0.00032123696,0.000022807768,0.000006641792,0.000094747615],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9957517,0.00050288683,0.00044776863,0.00044272927,0.0026775282,0.00017740887],"domain_scores_gemma":[0.9983582,0.00057409157,0.00014840873,0.00015479658,0.0006120219,0.00015247361],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0062627913,0.00014166924,0.00018316507,0.0001732062,0.00018726577,0.0008855403,0.00009331982,0.00006432436,0.001895826],"category_scores_gemma":[0.001964564,0.00010994887,0.000012632625,0.00046088346,0.00005765787,0.00087727583,0.00008263477,0.000106860156,0.00003162247],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010892903,0.00003269978,0.7862641,0.0000040202567,0.000006409363,1.2255771e-7,0.0032671997,0.00020091524,0.00011293134,0.00016324435,0.00034123223,0.20959619],"study_design_scores_gemma":[0.0005395694,0.00011861185,0.7527942,0.00003670548,0.000015368847,0.0000032614944,0.0013271803,0.24129008,0.00001752594,0.003231833,0.00051249,0.0001131667],"about_ca_topic_score_codex":0.00011362147,"about_ca_topic_score_gemma":0.00013714665,"teacher_disagreement_score":0.24108917,"about_ca_system_score_codex":0.00010452016,"about_ca_system_score_gemma":0.00009511807,"threshold_uncertainty_score":0.9990166},"labels":[],"label_agreement":null},{"id":"W2155601053","doi":"10.1177/1356389004046292","title":"What Counts is not Falling... but Landing","year":2004,"lang":"en","type":"article","venue":"Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Douglas Mental Health University Institute; Douglas College","funders":"Canadian Institutes of Health Research; U.S. Public Health Service","keywords":"Strengths and weaknesses; Process management; Falling (accident); Process (computing); Management science; Computer science; Operations research; Political science; Business; Psychology; Engineering; Medicine; Environmental health","score_opus":0.36712162891403827,"score_gpt":0.545401205321608,"score_spread":0.1782795764075697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155601053","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92755425,0.00027927163,0.006742318,0.009161123,0.003438715,0.00042069584,0.0000063643515,0.00004777552,0.052349467],"genre_scores_gemma":[0.99431556,0.000074281306,0.000447267,0.0014050642,0.00013809718,0.000013810451,0.000011164338,0.0000042245697,0.0035905119],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970722,0.000080479724,0.00026106922,0.00018754521,0.0023031516,0.00009552032],"domain_scores_gemma":[0.99907464,0.000108738735,0.00011256081,0.00022441888,0.00044530744,0.000034349123],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.005076817,0.00005653532,0.000077223165,0.00010844682,0.00010164884,0.00031791552,0.00015293533,0.000038686205,0.009722084],"category_scores_gemma":[0.00042916366,0.000043299173,0.000036302517,0.00023856878,0.000015740961,0.00072246196,0.000018467708,0.000054187076,0.00785042],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040870516,0.000106230436,0.0068528005,0.0000071623153,0.000029563618,0.0000014235293,0.0075694574,0.015738226,0.0033912587,0.007198231,0.029173158,0.92989165],"study_design_scores_gemma":[0.004603031,0.00023121231,0.11026843,0.00018699931,0.000106086874,0.000011026098,0.0066615185,0.3872756,0.020782955,0.23567007,0.23353624,0.0006668172],"about_ca_topic_score_codex":0.000007615105,"about_ca_topic_score_gemma":0.000015394933,"teacher_disagreement_score":0.9292248,"about_ca_system_score_codex":0.00012192347,"about_ca_system_score_gemma":0.00023405065,"threshold_uncertainty_score":0.99292207},"labels":[],"label_agreement":null},{"id":"W2155670182","doi":"10.3917/rfap.119.0515","title":"Trente ans d'évaluation de programme au Canada : l'institutionnalisation interne en quête de qualité","year":2006,"lang":"fr","type":"article","venue":"Revue française d administration publique","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université Laval","funders":"","keywords":"Institutionalisation; Normative; Valuation (finance); Political science; Public administration; Principal (computer security); Administration (probate law); Welfare economics; Business; Accounting; Economics; Computer science; Law","score_opus":0.06900062897304839,"score_gpt":0.38487479123826146,"score_spread":0.3158741622652131,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155670182","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75475925,0.0007683581,0.1023545,0.11975861,0.0033025802,0.0011891786,0.00025303566,0.00011936149,0.017495135],"genre_scores_gemma":[0.97507364,0.00010133184,0.003707059,0.0010642563,0.0019556116,0.00024099203,0.0008550728,0.0000305683,0.016971458],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9930101,0.0018428579,0.0018161224,0.0007455724,0.0016719898,0.00091335626],"domain_scores_gemma":[0.99634784,0.0007591611,0.0008451542,0.00062356796,0.0009814937,0.00044277],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00959245,0.00041408767,0.0004339617,0.00035878323,0.0004904522,0.0008202699,0.0005985145,0.00041285384,0.0020644544],"category_scores_gemma":[0.0021569033,0.0004387748,0.00021872272,0.0011526602,0.00021542412,0.0018336277,0.00005326801,0.00048335563,0.0001107253],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022948865,0.001082036,0.2940274,0.00038430566,0.00009088114,0.000081286256,0.009281363,0.017855233,0.00078791595,0.4932605,0.022726845,0.16019277],"study_design_scores_gemma":[0.0010950769,0.000316924,0.18809779,0.0003020847,0.00009879729,0.00017211006,0.0013909048,0.07980801,0.0017679518,0.004490562,0.7219171,0.0005426816],"about_ca_topic_score_codex":0.69711053,"about_ca_topic_score_gemma":0.970133,"teacher_disagreement_score":0.69919026,"about_ca_system_score_codex":0.0030614524,"about_ca_system_score_gemma":0.07903438,"threshold_uncertainty_score":0.9998064},"labels":[],"label_agreement":null},{"id":"W2155811669","doi":"10.1136/eb-2014-101738","title":"The science and art of theoretical location","year":2014,"lang":"en","type":"editorial","venue":"Evidence-Based Nursing","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Convention; Conversation; Epistemology; Sociology; Context (archaeology); Qualitative research; Order (exchange); Engineering ethics; Social science; Philosophy; Engineering; Communication; History","score_opus":0.10591439462372099,"score_gpt":0.48343356328561055,"score_spread":0.37751916866188956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155811669","genre_codex":"editorial","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010487159,0.0019107282,0.020168362,0.015996298,0.95426404,0.00054021773,0.000007736805,0.000034006323,0.0060299058],"genre_scores_gemma":[0.7069517,0.00037325473,0.0009645208,0.0002360458,0.29050732,0.00003717049,0.000011270052,0.000026900476,0.0008918577],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9887359,0.0007369854,0.0008531188,0.0006307781,0.0087142,0.0003290305],"domain_scores_gemma":[0.96963733,0.023473015,0.0007013358,0.0009911426,0.0050574527,0.00013973498],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.043320246,0.00019021191,0.0003316207,0.00036583198,0.0007488621,0.00083397207,0.0013147292,0.00021209854,0.00015275287],"category_scores_gemma":[0.07834287,0.000110753936,0.000065572865,0.0014039873,0.004844635,0.00061579404,0.000068167516,0.00041804355,0.00011255155],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006436418,0.000019339719,0.0000543437,0.000019788898,0.0000023230268,1.162424e-7,0.00015686709,0.00018559083,0.00008183064,0.011071777,0.86813927,0.12020439],"study_design_scores_gemma":[0.00051066134,0.0006117949,0.0012319534,0.005710614,0.000088005,0.0000014522465,0.00050950237,0.08906246,0.0019206956,0.047430344,0.8525055,0.00041699444],"about_ca_topic_score_codex":0.0000042512297,"about_ca_topic_score_gemma":0.000005025455,"teacher_disagreement_score":0.70590293,"about_ca_system_score_codex":0.00029131066,"about_ca_system_score_gemma":0.0047694263,"threshold_uncertainty_score":0.9978636},"labels":[],"label_agreement":null},{"id":"W2155913158","doi":"10.1177/160940690300200302","title":"Toward Holism: The Significance of Methodological Pluralism","year":2003,"lang":"en","type":"article","venue":"International Journal of Qualitative Methods","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":94,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Holism; Perspective (graphical); Pluralism (philosophy); Management science; Epistemology; Engineering ethics; Qualitative research; Data science; Computer science; Psychology; Sociology; Social science; Artificial intelligence; Engineering","score_opus":0.9447556766072378,"score_gpt":0.7672779849004199,"score_spread":0.17747769170681793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155913158","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05798972,0.00036302145,0.9187823,0.0122205755,0.0022858495,0.00012272563,0.0000123627315,0.0000037222328,0.008219706],"genre_scores_gemma":[0.52571034,0.000045720983,0.47280908,0.00079358293,0.00011609009,0.0000051426523,4.5519926e-7,0.000004337323,0.0005152432],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96681,0.02788702,0.0018387898,0.00019540194,0.0031193406,0.0001494427],"domain_scores_gemma":[0.9626271,0.030958511,0.0019598969,0.00022695053,0.0041494137,0.00007813091],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11560115,0.00011930074,0.00043332967,0.00029706003,0.00005733011,0.000100888996,0.0013239926,0.000055025488,0.0017863397],"category_scores_gemma":[0.04979748,0.00005956689,0.000315673,0.00045236532,0.00033678242,0.00038876277,0.00005999896,0.0003112795,0.000019380592],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003903323,0.00022751448,0.0013855664,0.0000058038795,0.00050252234,0.000018342964,0.12031373,0.0019248826,0.018174483,0.64803183,0.0053938683,0.2036311],"study_design_scores_gemma":[0.0009927534,0.00034188924,0.007531769,0.000034681292,0.000037706093,0.00011251302,0.068000235,0.0004906148,0.042084802,0.76318103,0.1170265,0.00016550472],"about_ca_topic_score_codex":0.000009522831,"about_ca_topic_score_gemma":0.0000013877753,"teacher_disagreement_score":0.46772063,"about_ca_system_score_codex":0.00007084049,"about_ca_system_score_gemma":0.00031091736,"threshold_uncertainty_score":0.99912614},"labels":[],"label_agreement":null},{"id":"W2156126520","doi":"10.24908/eoe-ese-rse.v2i0.1735","title":"Devolution and Control in Alberta","year":2008,"lang":"en","type":"article","venue":"Encounters in Theory and History of Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Devolution (biology); Restructuring; Control (management); Process (computing); Public administration; Plan (archaeology); Political science; Key (lock); Business; Economics; Finance; Management; Sociology; Computer science; Geography","score_opus":0.05230797602771933,"score_gpt":0.39037484364191655,"score_spread":0.33806686761419724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156126520","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97752947,0.0017162325,0.00043700897,0.0002653647,0.0007359662,0.00010008285,5.5494405e-7,0.0000017982958,0.019213552],"genre_scores_gemma":[0.99426264,0.00012012048,0.000070970724,0.00034626012,0.000017930963,0.000012621192,0.0000012200522,0.0000018452909,0.005166404],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990608,0.00024887366,0.00027862433,0.00014305112,0.0002086804,0.00005994033],"domain_scores_gemma":[0.9990737,0.00062005746,0.000111505295,0.00011130669,0.000058868292,0.000024593064],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025943487,0.00004726338,0.0001083151,0.0002929691,0.00003085747,0.000004549612,0.000072167684,0.000031632764,0.00025879286],"category_scores_gemma":[0.00046268513,0.00004149229,0.000012091105,0.00010232733,0.00018603903,0.00027463835,0.000007832759,0.000056010635,0.000006999663],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004942796,0.00041701572,0.7474981,0.000026140333,0.0000067655365,8.480241e-7,0.09321,0.00012290993,0.0011595963,0.09573695,0.011821799,0.049505625],"study_design_scores_gemma":[0.0011490493,0.0001145355,0.84071517,0.00007061474,0.0000068715185,0.000016715607,0.008150587,0.0023190496,0.00002848033,0.071411684,0.075861454,0.00015576686],"about_ca_topic_score_codex":0.00031665975,"about_ca_topic_score_gemma":0.00090133504,"teacher_disagreement_score":0.09321712,"about_ca_system_score_codex":0.0002248848,"about_ca_system_score_gemma":0.00042655462,"threshold_uncertainty_score":0.28336003},"labels":[],"label_agreement":null},{"id":"W2156151290","doi":"10.1093/scipol/scu022","title":"Sustainable Development, Evaluation and Policy-Making: Theory, Practise and Quality Assurance edited by Anneke von Raggamby and Frieder Rubik","year":2014,"lang":"en","type":"article","venue":"Science and Public Policy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"GDG Environnement","funders":"","keywords":"German; Sustainable development; Sustainability; Quality (philosophy); Modernization theory; Sociology; Political science; Epistemology; Law; Philosophy; Ecology; Linguistics","score_opus":0.11885368812914267,"score_gpt":0.4976547236581108,"score_spread":0.37880103552896816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156151290","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9438381,0.0005020424,0.0015879677,0.027017847,0.0001325897,0.00052104925,0.000011966726,0.000039452985,0.026348943],"genre_scores_gemma":[0.9939509,0.00015545446,0.00051087915,0.0029442173,0.0001975398,0.00004068054,0.0000062132094,0.000007906707,0.0021861915],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9945602,0.000745723,0.00057155464,0.0008182529,0.0025926826,0.0007116302],"domain_scores_gemma":[0.9956816,0.0012851832,0.0004333031,0.00044531818,0.0016990927,0.00045552602],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03543052,0.00021246707,0.0002809524,0.001008711,0.0014848071,0.0022824565,0.0004036737,0.00009516472,0.00008522112],"category_scores_gemma":[0.032071263,0.00016005982,0.000016323092,0.002425704,0.0011753605,0.0035724745,0.0003787589,0.00015322349,0.000010257877],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047585367,0.00007901714,0.064353995,0.000048037797,0.000015164057,3.6641865e-7,0.0066698915,0.0000051719026,0.0014989461,0.29978764,0.0070398413,0.6204543],"study_design_scores_gemma":[0.0012634093,0.00013041835,0.5014686,0.000025029496,0.000012184163,0.000023351871,0.006378313,0.008287271,0.0003280348,0.07364906,0.4080124,0.00042190903],"about_ca_topic_score_codex":0.0006013841,"about_ca_topic_score_gemma":0.00017045121,"teacher_disagreement_score":0.6200324,"about_ca_system_score_codex":0.00017249418,"about_ca_system_score_gemma":0.0035987727,"threshold_uncertainty_score":0.9998151},"labels":[],"label_agreement":null},{"id":"W2156859842","doi":"10.1177/1098214014535658","title":"The Ethical Tipping Points of Evaluators in Conflict Zones","year":2014,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"International Development Research Centre","funders":"","keywords":"Affect (linguistics); Section (typography); Ethical issues; Face (sociological concept); Psychology; Engineering ethics; Conflict of interest; Sociology; Social psychology; Public relations; Political science; Law; Social science; Computer science","score_opus":0.17093914735823218,"score_gpt":0.5305063413621447,"score_spread":0.3595671940039125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156859842","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9824148,0.00011507779,0.005631241,0.00953013,0.00043741133,0.0001641932,5.41453e-7,0.0000024067506,0.0017042385],"genre_scores_gemma":[0.997949,0.00006562105,0.0012230847,0.0006066838,0.000109936365,0.000004964359,5.781604e-7,0.0000054510124,0.00003465832],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99025714,0.003298657,0.0015510487,0.00015422425,0.0045698606,0.00016905447],"domain_scores_gemma":[0.98979723,0.004575419,0.002650918,0.00032687577,0.002571414,0.00007811784],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.066231444,0.00009237957,0.00035338348,0.00035607076,0.00010738301,0.000081087404,0.0004307726,0.000048909333,0.0003315472],"category_scores_gemma":[0.02091448,0.00005319772,0.00012258843,0.000918387,0.0003102502,0.00024442092,0.00003661621,0.00037275304,0.00003740172],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016457368,0.00005105074,0.04854803,0.0000020903417,0.000027967986,3.9387817e-7,0.0022453647,0.0075888275,0.0006303901,0.0030107512,0.00093381363,0.9367967],"study_design_scores_gemma":[0.001973331,0.0016602199,0.62253845,0.0001215376,0.00007932783,0.00003361523,0.007795542,0.31858924,0.0006269467,0.034579743,0.01182913,0.00017288617],"about_ca_topic_score_codex":0.000023085135,"about_ca_topic_score_gemma":0.00006439133,"teacher_disagreement_score":0.9366239,"about_ca_system_score_codex":0.00009960783,"about_ca_system_score_gemma":0.0005958839,"threshold_uncertainty_score":0.98733276},"labels":[],"label_agreement":null},{"id":"W2157111091","doi":"10.1177/1356389010380001","title":"To Be or Not to Be a Profession: Pros, Cons and Challenges for Evaluation","year":2010,"lang":"en","type":"article","venue":"Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"École Nationale d'Administration Publique; Université Laval","funders":"","keywords":"Professionalization; Institutionalisation; Certification; Charter; Political science; Public relations; Accreditation; Valuation (finance); Quality (philosophy); Sociology; Engineering ethics; Public administration; Law; Accounting; Business; Engineering","score_opus":0.6053607172548194,"score_gpt":0.6135973810690398,"score_spread":0.00823666381422039,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157111091","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79473704,0.000077760444,0.0013335758,0.19377165,0.0015355375,0.006384036,0.000033159653,0.000042387277,0.002084868],"genre_scores_gemma":[0.9816914,0.000031661108,0.00793967,0.005393663,0.00030901915,0.0026318098,0.00004603757,0.000017702278,0.0019390256],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99355215,0.00054636714,0.0006621632,0.00069810695,0.004267258,0.00027397982],"domain_scores_gemma":[0.99454087,0.0011910578,0.00024414496,0.00062086707,0.0031648166,0.00023823256],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.032717694,0.00017851626,0.00024907006,0.00036657625,0.0003688266,0.0002379841,0.0003112247,0.00013259394,0.0035911864],"category_scores_gemma":[0.014972149,0.00012306368,0.000051224604,0.00051089254,0.00004082708,0.0005212143,0.00010860922,0.00014390281,0.00019810378],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005851957,0.00012769984,0.0006174099,0.000027536666,0.000017848599,1.7389266e-7,0.016419306,0.00047202804,0.011196504,0.0037353323,0.021085361,0.9457156],"study_design_scores_gemma":[0.005952696,0.0017382143,0.18162662,0.000082208506,0.00022010591,0.00001019036,0.013685881,0.3799471,0.008680734,0.012741659,0.3946256,0.00068901037],"about_ca_topic_score_codex":0.0000064786745,"about_ca_topic_score_gemma":0.0016139788,"teacher_disagreement_score":0.9450266,"about_ca_system_score_codex":0.00009894803,"about_ca_system_score_gemma":0.0010592877,"threshold_uncertainty_score":0.99731964},"labels":[],"label_agreement":null},{"id":"W2160783283","doi":"10.7202/1000033ar","title":"La composante organisationnelle des cycles d’apprentissage au primaire : une définition opérationnelle","year":2010,"lang":"fr","type":"article","venue":"McGill Journal of Education / Revue des sciences de l éducation de McGill","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.44025641671962035,"score_gpt":0.5051631700720816,"score_spread":0.06490675335246121,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160783283","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91300136,0.0005590744,0.007939446,0.013168112,0.010979246,0.0003876718,0.00009162955,0.00003682194,0.053836655],"genre_scores_gemma":[0.9317564,0.00083510875,0.06002306,0.0007296475,0.00087594957,0.000030112105,0.00002407299,0.000035550238,0.0056900936],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9936281,0.001558103,0.0019830535,0.0006135908,0.0014904254,0.0007267243],"domain_scores_gemma":[0.9918558,0.0016920412,0.00220325,0.00055185106,0.003071313,0.00062573864],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01401305,0.00039778053,0.0004990765,0.0010639705,0.0043842685,0.00065270887,0.0013927077,0.0003505662,0.0044052955],"category_scores_gemma":[0.0042789686,0.00038013258,0.0003014215,0.0028505607,0.0026390776,0.0035969128,0.000117705735,0.00085248466,0.00028565133],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015212852,0.005206724,0.042932753,0.0006412768,0.00015787245,0.000022785536,0.076757,0.015560492,0.03411147,0.22997263,0.016992237,0.57749265],"study_design_scores_gemma":[0.0014932088,0.001068924,0.14464706,0.0015939067,0.0003781549,0.006582893,0.118441515,0.021545194,0.013679352,0.33944228,0.3499347,0.0011928155],"about_ca_topic_score_codex":0.0004463813,"about_ca_topic_score_gemma":0.0025972736,"teacher_disagreement_score":0.57629985,"about_ca_system_score_codex":0.002326996,"about_ca_system_score_gemma":0.006486107,"threshold_uncertainty_score":0.99986506},"labels":[],"label_agreement":null},{"id":"W2161793276","doi":"10.1177/1558689813486190","title":"Unexpected but Most Welcome","year":2013,"lang":"en","type":"article","venue":"Journal of Mixed Methods Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Ministère de l’Emploi et de la Solidarité Sociale (Québec)","funders":"","keywords":"Stakeholder; Participatory evaluation; Measure (data warehouse); Citizen journalism; Computer science; Nothing; Process (computing); Multimethodology; Management science; Process management; Data science; Sociology; Public relations; Political science; Business; Engineering; Social science; Data mining; World Wide Web; Epistemology","score_opus":0.6298937978534725,"score_gpt":0.7019491751601077,"score_spread":0.07205537730663514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161793276","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8402962,0.000700548,0.11410846,0.015138201,0.0021540956,0.00044102053,0.0000029119656,0.000012600163,0.02714593],"genre_scores_gemma":[0.5158321,0.00021795135,0.4617166,0.00024948866,0.00080615754,0.000025741665,8.716128e-7,0.000022304208,0.021128792],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9848286,0.0074263862,0.0013438329,0.0002310602,0.0057139327,0.00045622446],"domain_scores_gemma":[0.9811134,0.0095649455,0.0005166724,0.00057175575,0.007845482,0.00038774326],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.080926925,0.00010809578,0.00040521834,0.0014005504,0.0002639675,0.0005474431,0.0013533384,0.00009984719,0.013693645],"category_scores_gemma":[0.02303025,0.000065035616,0.00016404522,0.0024490464,0.00017594974,0.00085881114,0.00023427213,0.0009859635,0.001355206],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059051683,0.00012844961,0.004578287,0.0000053501535,0.000042282267,0.000012487565,0.00046035994,0.00010688142,0.105052136,0.00087887916,0.11959955,0.7690763],"study_design_scores_gemma":[0.0022803892,0.0014426893,0.30615792,0.000085717125,0.000018990602,0.00022287152,0.015698964,0.015437648,0.086093016,0.14423199,0.42797917,0.00035065232],"about_ca_topic_score_codex":0.00007241668,"about_ca_topic_score_gemma":0.000010936937,"teacher_disagreement_score":0.76872563,"about_ca_system_score_codex":0.00014673175,"about_ca_system_score_gemma":0.0008134454,"threshold_uncertainty_score":0.9994224},"labels":[],"label_agreement":null},{"id":"W2162732236","doi":"","title":"DeMars, C. (2010). Item Response Theory.Oxford: Oxford University Press.","year":2012,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Item response theory; Psychology; Media studies; Political science; Sociology; Psychometrics; Clinical psychology","score_opus":0.17473999545789362,"score_gpt":0.41546517673204064,"score_spread":0.24072518127414702,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162732236","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6152927,0.00013701436,0.022773238,0.0022914717,0.001114065,0.0003236743,0.00001961021,0.00012395252,0.35792425],"genre_scores_gemma":[0.77604496,0.000069065274,0.0014873421,0.0005617324,0.00007675082,0.0000019898773,0.000003589577,0.000006713454,0.22174785],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9966173,0.0011178243,0.0003428773,0.00026648337,0.0012744594,0.0003810096],"domain_scores_gemma":[0.99558413,0.0031070232,0.00015860597,0.00065294316,0.00025297704,0.0002443171],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.014345465,0.00012852783,0.00017671104,0.00020361652,0.0002477855,0.000111021036,0.0006438539,0.000086258406,0.011674404],"category_scores_gemma":[0.001607925,0.000088982604,0.00009862003,0.00044469495,0.0000817206,0.0012616629,0.00020871508,0.00012898471,0.00047035658],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027275935,0.00034060545,0.2984854,0.0000065683157,0.000060915103,0.0000060472858,0.0025165826,0.00022605961,0.00027188135,0.34729618,0.250762,0.09730018],"study_design_scores_gemma":[0.00033894464,0.00005042749,0.18147169,0.0000028516542,0.000010391251,0.0000039126094,0.0018727316,0.001528423,0.00033181798,0.0013235313,0.812943,0.00012228651],"about_ca_topic_score_codex":0.000012232513,"about_ca_topic_score_gemma":0.000012449003,"teacher_disagreement_score":0.562181,"about_ca_system_score_codex":0.00008254993,"about_ca_system_score_gemma":0.00016251265,"threshold_uncertainty_score":0.9892291},"labels":[],"label_agreement":null},{"id":"W2162944595","doi":"10.1186/s13012-015-0326-x","title":"Education and training for implementation science: our interest in manuscripts describing education and training materials","year":2015,"lang":"en","type":"article","venue":"Implementation Science","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":58,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; St. Michael's Hospital","funders":"National Institute for Health and Care Research","keywords":"Training (meteorology); Curriculum; Work (physics); Health informatics; Medical education; Medicine; Health services research; Health administration; Engineering ethics; Public health; Pedagogy; Sociology; Engineering; Nursing","score_opus":0.7886044086246378,"score_gpt":0.6504294089889567,"score_spread":0.13817499963568103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162944595","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99230105,0.000044266173,0.0021616344,0.0023611046,0.0016409033,0.0009659148,0.000020791034,0.000019721267,0.00048464414],"genre_scores_gemma":[0.9872471,0.000009581216,0.011519272,0.00070903543,0.000129093,0.00025779364,0.000033270917,0.000008945176,0.00008592835],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99624765,0.00013721388,0.00096571114,0.0007727053,0.001387788,0.00048890745],"domain_scores_gemma":[0.9977085,0.00014870396,0.0004735527,0.00026017395,0.0011103655,0.00029868426],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.018462226,0.00016429037,0.00021343805,0.0013978153,0.00062439975,0.0017510644,0.00048232524,0.000030793744,0.000101121754],"category_scores_gemma":[0.0013156441,0.0001483922,0.000018857121,0.0017690866,0.00029479957,0.004594625,0.00014855686,0.00006662963,0.000009307029],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020272191,0.000040688672,0.020986674,0.000008135177,0.0000017666807,1.08050095e-7,0.03973136,0.000008813246,0.05130983,0.010283372,0.00066079706,0.8769482],"study_design_scores_gemma":[0.0017273496,0.0002360137,0.24123359,0.00005592099,0.000013505018,0.00002978651,0.70890254,0.0012140922,0.023950841,0.02012368,0.0022155787,0.00029709286],"about_ca_topic_score_codex":0.00027110166,"about_ca_topic_score_gemma":0.00093221647,"teacher_disagreement_score":0.8766511,"about_ca_system_score_codex":0.0004009347,"about_ca_system_score_gemma":0.0060350094,"threshold_uncertainty_score":0.9995999},"labels":[],"label_agreement":null},{"id":"W2163053247","doi":"10.1097/01.aids.0000343760.70078.89","title":"Evaluation design for large-scale HIV prevention programmes: the case of Avahan, the India AIDS initiative","year":2008,"lang":"en","type":"review","venue":"AIDS","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":126,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Centre hospitalier universitaire de Québec","funders":"","keywords":"Monitoring and evaluation; Program evaluation; Government (linguistics); Scale (ratio); Bespoke; Medicine; Environmental health; Business; Economic growth; Political science; Geography; Public administration; Economics","score_opus":0.4563612954648097,"score_gpt":0.5529884177901366,"score_spread":0.09662712232532694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163053247","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007935634,0.91472095,0.07380412,0.00013774533,0.0005971811,0.009006983,0.0001789033,0.000023867273,0.0014508866],"genre_scores_gemma":[0.0016927943,0.9862549,0.0057289554,0.00014618061,0.0002607279,0.0043416377,0.00023249497,0.000037184018,0.0013051762],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99074054,0.0047195056,0.0015149474,0.0005107265,0.0021996095,0.00031469777],"domain_scores_gemma":[0.9902488,0.0053886506,0.0015905505,0.0009761104,0.0017373551,0.000058512273],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.032004274,0.00031839777,0.0009006106,0.00030114737,0.0005730175,0.00017148974,0.00090470305,0.00022260977,0.00060768833],"category_scores_gemma":[0.0032124342,0.00014371637,0.0006963463,0.0014382118,0.00015588115,0.00036204926,0.00012084708,0.0003027705,0.00014709587],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000075732178,0.00009899541,0.000018824623,0.00017695282,0.00012209281,0.0000022748304,0.0018949069,0.000038782942,3.8320216e-8,0.000548913,0.0079910075,0.9890996],"study_design_scores_gemma":[0.00066949637,0.00076809083,0.000027497523,0.00087009935,0.0012995868,0.00018666519,0.0036348263,0.007812673,0.0000066871353,0.00736526,0.9771262,0.00023292536],"about_ca_topic_score_codex":0.000005247908,"about_ca_topic_score_gemma":0.000036409587,"teacher_disagreement_score":0.9888667,"about_ca_system_score_codex":0.0001501094,"about_ca_system_score_gemma":0.0021757383,"threshold_uncertainty_score":0.9967553},"labels":[],"label_agreement":null},{"id":"W2163301915","doi":"10.1017/s0008423907070904","title":"Institutionnaliser l'évaluation des politiques publiques. Étude comparée des dispositifs en Belgique, en France, en Suisse et aux Pays-Bas","year":2007,"lang":"fr","type":"article","venue":"Canadian Journal of Political Science","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Political science; Humanities; Valuation (finance); Art; Business","score_opus":0.11762441690014966,"score_gpt":0.474901470727904,"score_spread":0.3572770538277543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163301915","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87886804,0.0027554557,0.035611913,0.060980145,0.0020931608,0.00030991607,0.00008586186,0.000018379995,0.019277133],"genre_scores_gemma":[0.9826039,0.00021235057,0.008344693,0.005349794,0.0007802509,0.0000043240784,0.0000052944188,0.000016481203,0.002682919],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9911267,0.0013469595,0.0017039912,0.0005187765,0.002944405,0.0023591456],"domain_scores_gemma":[0.98610824,0.002149836,0.00043676732,0.00043616022,0.0055888733,0.005280105],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.039994206,0.00034847917,0.0005246197,0.0016014895,0.0012631477,0.0014841936,0.0018444486,0.00027100157,0.0024228182],"category_scores_gemma":[0.016854528,0.00028938678,0.00023797023,0.0024436514,0.0060928124,0.005268404,0.0001043987,0.00086890435,0.00016390829],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000015559543,0.00007584831,0.11034526,0.000024893716,0.0000148757645,0.00010102091,0.005573021,0.00029532105,0.0001800708,0.86084,0.0008028496,0.021731282],"study_design_scores_gemma":[0.00042484485,0.00034703067,0.85756207,0.00043546766,0.000048201447,0.00039258754,0.0027864948,0.001982828,0.0013957734,0.099825814,0.034469713,0.00032918435],"about_ca_topic_score_codex":0.09726661,"about_ca_topic_score_gemma":0.24859522,"teacher_disagreement_score":0.76101416,"about_ca_system_score_codex":0.0042220424,"about_ca_system_score_gemma":0.036050145,"threshold_uncertainty_score":0.99995583},"labels":[],"label_agreement":null},{"id":"W2163998785","doi":"10.3138/cjpe.0023.002","title":"Organizational Capacity To Do and Use Evaluation: Results of a Pan-Canadian Survey of Evaluators","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"National Research Council Canada; Atlantic Canada Opportunities Agency; University of Ottawa","funders":"","keywords":"Respondent; Psychology; Stakeholder; Knowledge management; Organizational learning; Context (archaeology); Descriptive statistics; Exploratory research; Social psychology; Applied psychology; Public relations; Sociology; Political science; Computer science; Social science; Geography","score_opus":0.44394440400345575,"score_gpt":0.5021568546325215,"score_spread":0.058212450629065715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163998785","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99422735,0.00026081371,0.0002009356,0.0019620545,0.0004326339,0.0016345764,0.00022293083,0.0000035435696,0.0010551838],"genre_scores_gemma":[0.9956908,0.000009099865,0.0038756004,0.00022913197,0.00006957332,0.000015649593,0.00006818087,0.000009861198,0.000032094275],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99121886,0.0018470892,0.0019122459,0.00033029428,0.0043599303,0.000331548],"domain_scores_gemma":[0.97623914,0.0006689486,0.0015821394,0.00044647063,0.020055244,0.0010080272],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04944271,0.00017886134,0.00043879458,0.0017237766,0.000191066,0.00030952296,0.00047850894,0.00013393667,0.0011856246],"category_scores_gemma":[0.043004718,0.00015280329,0.00008777263,0.00252158,0.00013753299,0.0007612117,0.000012404374,0.00018023246,0.000019497973],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013065216,0.00009618478,0.35095757,0.0000063049483,0.0000622109,0.0000019552324,0.0039940155,0.0054195817,0.00018056046,0.0009057941,0.0039238227,0.63432133],"study_design_scores_gemma":[0.0015145114,0.00093271345,0.96733075,0.000071717564,0.00011326695,0.00001919332,0.00033704267,0.020850612,0.00019237297,0.006691575,0.0017896463,0.00015660589],"about_ca_topic_score_codex":0.05135973,"about_ca_topic_score_gemma":0.57705003,"teacher_disagreement_score":0.63416475,"about_ca_system_score_codex":0.0006370758,"about_ca_system_score_gemma":0.01531216,"threshold_uncertainty_score":0.9997274},"labels":[],"label_agreement":null},{"id":"W2165257846","doi":"10.56645/jmde.v11i25.433","title":"The \"Usability\" of Evaluation Reports: A Precursor to Evaluation Use in Government Organizations","year":2015,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"École Nationale d'Administration Publique","funders":"Social Sciences and Humanities Research Council; Social Sciences and Humanities Research Council of Canada; Australian Government","keywords":"Summative assessment; Formative assessment; Government (linguistics); Public relations; Usability; Business; Treasury; Data collection; Thematic analysis; Program evaluation; Qualitative research; Psychology; Political science; Public administration; Computer science; Sociology","score_opus":0.29165285448490014,"score_gpt":0.5123901997387377,"score_spread":0.22073734525383754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165257846","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9889758,0.00031322363,0.0028550143,0.0024235507,0.0015328017,0.0025047513,0.000008020618,0.0000059140903,0.0013808775],"genre_scores_gemma":[0.99617356,0.000023389275,0.0033185775,0.000035630506,0.00012457809,0.00013769077,0.000014060414,0.000015643322,0.0001568416],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9743057,0.004122294,0.0036810185,0.0004513661,0.017171705,0.00026789747],"domain_scores_gemma":[0.9732037,0.0018211743,0.0038407054,0.00090200687,0.02000094,0.00023142587],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14191337,0.0001956673,0.00040056926,0.00043618502,0.00020908004,0.00019815937,0.0004622726,0.00010299572,0.0006723349],"category_scores_gemma":[0.095248975,0.00012772724,0.00013359773,0.0023116567,0.00008715726,0.0017213187,0.00018571029,0.00022591953,0.000040522074],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00082402903,0.0009453921,0.3233956,0.000008523831,0.000070342525,0.0000040442646,0.020664144,0.48450318,0.0018663296,0.000240195,0.0037779915,0.16370022],"study_design_scores_gemma":[0.001995044,0.0006626174,0.53359896,0.00008255702,0.00021970835,0.000039104292,0.008102494,0.43444344,0.0010282716,0.019201647,0.00048413035,0.00014204699],"about_ca_topic_score_codex":0.000033172382,"about_ca_topic_score_gemma":0.0008898177,"teacher_disagreement_score":0.21020333,"about_ca_system_score_codex":0.0020740733,"about_ca_system_score_gemma":0.0039006397,"threshold_uncertainty_score":0.9123721},"labels":[],"label_agreement":null},{"id":"W2165295550","doi":"10.1093/reseval/rvs041","title":"Accountability, performance assessment, and evaluation: Policy pressures and responses from research councils","year":2013,"lang":"en","type":"article","venue":"Research Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Accountability; Public administration; Political science; Library science; Higher education; Sociology; Management; Law; Computer science; Economics","score_opus":0.8015169397706693,"score_gpt":0.7149106275809038,"score_spread":0.08660631218976544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165295550","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9679695,0.0012661503,0.00006588069,0.009967044,0.00015083457,0.0036379402,0.000032060936,0.000031982672,0.016878622],"genre_scores_gemma":[0.99455184,0.0009756837,0.0008102734,0.00013911384,0.00042805518,0.0015580436,0.000049224636,0.0000209204,0.0014668312],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9490788,0.016416078,0.0011344568,0.0014208776,0.03094723,0.0010025306],"domain_scores_gemma":[0.95960355,0.013683899,0.00023301927,0.0014374848,0.024642669,0.00039938954],"candidate_categories":["metaresearch","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.2249294,0.00023261645,0.0003545237,0.0016384261,0.0015535095,0.0025078154,0.000801266,0.00020152939,0.011011381],"category_scores_gemma":[0.024933863,0.00017834459,0.0000466495,0.0025046438,0.0009609738,0.0030534654,0.0005682752,0.00089540443,0.0008199532],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016649226,0.00016313628,0.23861459,0.000032512344,0.000047311085,4.0750496e-7,0.0037833303,0.00040381908,0.0036101511,0.0011998188,0.01997693,0.7320015],"study_design_scores_gemma":[0.000879486,0.00023779755,0.6272569,0.000039654115,0.000016453374,0.0000024408757,0.0023579474,0.30806273,0.00020924892,0.0535362,0.007266427,0.00013476491],"about_ca_topic_score_codex":0.0026609222,"about_ca_topic_score_gemma":0.0005345074,"teacher_disagreement_score":0.7318667,"about_ca_system_score_codex":0.0012366205,"about_ca_system_score_gemma":0.0064249216,"threshold_uncertainty_score":0.99995804},"labels":[],"label_agreement":null},{"id":"W2165907622","doi":"10.1177/0193945910373600","title":"A Questionnaire for Assessing Community Health Nurses’ Learning Needs","year":2010,"lang":"en","type":"article","venue":"Western Journal of Nursing Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Dalhousie University; McMaster University","funders":"","keywords":"Needs assessment; Psychology; Medical education; Exploratory factor analysis; Reliability (semiconductor); Confirmatory factor analysis; Nursing; Medicine; Psychometrics; Computer science; Clinical psychology","score_opus":0.5126712989687248,"score_gpt":0.6732361794085924,"score_spread":0.1605648804398676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165907622","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9699642,0.00015133596,0.011459245,0.014330014,0.0018709389,0.00022380572,0.0000011879717,0.00001980818,0.001979447],"genre_scores_gemma":[0.9950044,0.000014329219,0.0031716828,0.00012627777,0.00046799408,0.0000045717975,0.0000016158264,0.000016393504,0.001192737],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9922614,0.0029254805,0.0010055158,0.0001405889,0.0031850669,0.0004819356],"domain_scores_gemma":[0.9919415,0.0031514124,0.0007039845,0.00042356367,0.0034589518,0.00032059866],"candidate_categories":["metaresearch","sts","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.057965536,0.00010811849,0.000336692,0.0012491619,0.0016524993,0.0011398765,0.0009793217,0.00008982716,0.00008576145],"category_scores_gemma":[0.007133867,0.00008063323,0.00013728178,0.0010363713,0.00032338686,0.0010779226,0.000052863164,0.003021512,0.00003251782],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011399833,0.00040152008,0.16891755,0.000018711089,0.0000119109245,0.0000022652546,0.0177892,0.00038585177,0.0020588366,0.000637807,0.005773831,0.8038885],"study_design_scores_gemma":[0.0033228253,0.004164651,0.74821985,0.0036916232,0.00002633161,0.0007706807,0.1063089,0.016529107,0.0006400331,0.06571957,0.05020256,0.00040389865],"about_ca_topic_score_codex":0.000037059235,"about_ca_topic_score_gemma":0.00011304145,"teacher_disagreement_score":0.8034846,"about_ca_system_score_codex":0.00028786305,"about_ca_system_score_gemma":0.0015613904,"threshold_uncertainty_score":0.99989706},"labels":[],"label_agreement":null},{"id":"W2167466379","doi":"","title":"Recognizing a Centre of Excellence in Ontario's Colleges","year":2012,"lang":"en","type":"article","venue":"The College Quarterly","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Excellence; Higher education; Pedagogy; Political science; Psychology; Sociology; Mathematics education; Law","score_opus":0.15603741447870642,"score_gpt":0.4027176693878569,"score_spread":0.2466802549091505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167466379","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97204685,0.00012497556,0.000065761786,0.002279378,0.00055285904,0.00032083815,0.00001145179,0.000009922848,0.024587972],"genre_scores_gemma":[0.98686427,0.0000040399254,0.00034579294,0.0001476257,0.000047641715,0.000015316069,0.0000010879521,0.000005330934,0.012568897],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9974937,0.00035404108,0.00064416864,0.00018096565,0.0010167431,0.00031040446],"domain_scores_gemma":[0.9980669,0.0009426587,0.00024546648,0.00047971634,0.00018731889,0.00007796212],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004999766,0.00010916885,0.00024010653,0.00018052045,0.000116117175,0.000038702983,0.0005415807,0.000047251426,0.0035559414],"category_scores_gemma":[0.00013712501,0.00006607002,0.00007281903,0.0007216567,0.000074493815,0.0004556983,0.000030275143,0.0001630642,0.0003523332],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023103695,0.0005374171,0.77643234,0.000013292065,0.000030923664,0.000005116112,0.13072824,0.00008356205,0.001055738,0.015223528,0.022486305,0.053172506],"study_design_scores_gemma":[0.0020521844,0.000570278,0.7639435,0.00013062377,0.000030045923,0.000018989525,0.11092116,0.0032003468,0.0010207883,0.014699502,0.10299281,0.00041980794],"about_ca_topic_score_codex":0.003491648,"about_ca_topic_score_gemma":0.09471546,"teacher_disagreement_score":0.09122381,"about_ca_system_score_codex":0.000111667665,"about_ca_system_score_gemma":0.00029085862,"threshold_uncertainty_score":0.9973549},"labels":[],"label_agreement":null},{"id":"W2167854448","doi":"10.1177/1524839902238290","title":"Ethical Review of Health Promotion Program Evaluation Proposals","year":2003,"lang":"en","type":"article","venue":"Health Promotion Practice","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Institute of Gender and Health","funders":"","keywords":"Accountability; Promotion (chess); Health promotion; Public relations; Engineering ethics; Ethical code; Political science; Public health; Medicine; Medical education; Nursing; Engineering; Law","score_opus":0.58707870000933,"score_gpt":0.6782369886060745,"score_spread":0.09115828859674446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167854448","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003187236,0.020189533,0.03149414,0.8807127,0.0020159937,0.027936932,0.000019065603,0.00029186258,0.034152523],"genre_scores_gemma":[0.6992308,0.05694079,0.15710875,0.07714629,0.00035058707,0.006420281,0.00040333022,0.000117828895,0.0022813315],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9568526,0.02920206,0.004150838,0.00096600055,0.00814972,0.00067875965],"domain_scores_gemma":[0.9889956,0.0011958701,0.0039110314,0.0008604714,0.0047488655,0.00028813945],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.17498149,0.00021776532,0.0006800465,0.00027932812,0.00047451095,0.000121420475,0.0003139437,0.0001936725,0.003813558],"category_scores_gemma":[0.050288524,0.00016810598,0.00012608212,0.0018365616,0.0000929307,0.0013816459,0.00004169108,0.0007826635,0.00046812266],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000206114,0.0027990153,0.00046336575,0.0031691422,0.00001894552,5.185213e-7,0.0007864239,0.000029737663,0.000011846852,0.016902538,0.018552337,0.9572455],"study_design_scores_gemma":[0.0019884116,0.009645979,0.003890307,0.007001538,0.00009753308,0.0001900722,0.0014894886,0.010044541,0.0002293071,0.015681788,0.9492955,0.00044548587],"about_ca_topic_score_codex":0.000039554096,"about_ca_topic_score_gemma":0.000024358633,"teacher_disagreement_score":0.95680004,"about_ca_system_score_codex":0.0005093936,"about_ca_system_score_gemma":0.00720507,"threshold_uncertainty_score":0.99842316},"labels":[],"label_agreement":null},{"id":"W2168593338","doi":"10.1111/j.1754-7121.2006.tb01978.x","title":"Advising for impact: lessons from the Rae review on the use of special‐purpose advisory commissions","year":2006,"lang":"en","type":"article","venue":"Canadian Public Administration","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Council of Ontario Universities","funders":"","keywords":"Stakeholder; Commission; Political science; Politics; Public administration; Advisory committee; Stakeholder engagement; Public relations; Business; Law","score_opus":0.4270938017657796,"score_gpt":0.4868065596985704,"score_spread":0.059712757932790794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168593338","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.060661606,0.001117037,0.0033894556,0.91671085,0.0007917352,0.0025651627,0.0018137923,0.000025769525,0.012924612],"genre_scores_gemma":[0.9910966,0.00011104089,0.00023378151,0.005915578,0.0005200045,0.00006402515,0.0002974625,0.000009834603,0.0017516309],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977598,0.00033230215,0.0006479413,0.00024582754,0.00076372665,0.00025039702],"domain_scores_gemma":[0.99512047,0.0029884768,0.00038564572,0.0007544647,0.00053019944,0.00022074633],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0025260388,0.00013177864,0.00020101636,0.00012707706,0.0006266671,0.00049374107,0.0005494396,0.00006477341,0.0033516148],"category_scores_gemma":[0.003758082,0.00006786268,0.00016139074,0.0005809103,0.000110552435,0.00047083912,0.000017055067,0.0001379795,0.000060442646],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012177329,0.00003868746,0.002186838,0.0000063803413,0.00001115716,6.9452915e-7,0.00006703239,0.000024160527,0.000020860418,0.100620225,0.8123934,0.08461837],"study_design_scores_gemma":[0.00013537247,0.00008310314,0.029840885,0.00011764966,0.00001899372,0.0000016154271,0.00020405151,0.001515803,0.00004115425,0.004444876,0.9635066,0.00008991463],"about_ca_topic_score_codex":0.0031594974,"about_ca_topic_score_gemma":0.30551496,"teacher_disagreement_score":0.93043506,"about_ca_system_score_codex":0.00016813402,"about_ca_system_score_gemma":0.0036396235,"threshold_uncertainty_score":0.9975594},"labels":[],"label_agreement":null},{"id":"W2169129678","doi":"10.5539/jsd.v6n4p70","title":"Participation of Minorities in Cost-share Programs-The Experience of a Small Underserved Landowners’ Group in Alabama","year":2013,"lang":"en","type":"article","venue":"Journal of Sustainable Development","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"U.S. Department of Agriculture","keywords":"General partnership; Agency (philosophy); Business; Compromise; Transparency (behavior); Public relations; Resource (disambiguation); Political science; Sociology; Finance","score_opus":0.16988317732084895,"score_gpt":0.40183069628156254,"score_spread":0.23194751896071358,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169129678","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9978861,0.00009160879,0.00029637245,0.0007580508,0.00006697019,0.0005731889,2.9857037e-7,0.0000016976489,0.00032568054],"genre_scores_gemma":[0.99675137,0.000021471655,0.0022378785,0.000061859915,0.00001023985,0.00012817996,0.0000017164479,0.0000036859583,0.0007835974],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9969024,0.00019531835,0.0014562041,0.0001171165,0.0010617288,0.0002672453],"domain_scores_gemma":[0.99735504,0.0002835268,0.0008180015,0.00015700415,0.0013252931,0.00006110283],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038806351,0.00009362325,0.00029480233,0.00045044694,0.000050001523,0.0000889025,0.00041541108,0.000043570617,0.00035273805],"category_scores_gemma":[0.00065739924,0.000056440276,0.000052860083,0.00084771734,0.00007500445,0.0006232545,0.00008163842,0.00012960669,0.000005288085],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000108932516,0.0004004347,0.881761,0.00008975814,0.000019424755,0.000023665641,0.070509,0.0011550088,0.00025750682,0.0008253248,0.00027709565,0.044572853],"study_design_scores_gemma":[0.0009415596,0.0001340457,0.76296467,0.0001125961,0.000003155545,0.000002930907,0.2306436,0.00085082726,0.001243622,0.0011458654,0.0018853698,0.00007178236],"about_ca_topic_score_codex":0.00024391759,"about_ca_topic_score_gemma":0.0005719997,"teacher_disagreement_score":0.1601346,"about_ca_system_score_codex":0.00024026853,"about_ca_system_score_gemma":0.00063487416,"threshold_uncertainty_score":0.3862234},"labels":[],"label_agreement":null},{"id":"W2170382471","doi":"10.26522/tl.v1i2.106","title":"Implementation of Assessment and Evaluation Practices in Haltom Catholic District School Board","year":2003,"lang":"en","type":"article","venue":"Teaching and Learning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Variety (cybernetics); Curriculum; School district; Mathematics education; School teachers; Sociology; Medical education; Pedagogy; Political science; Psychology; Computer science; Medicine","score_opus":0.19753452439139219,"score_gpt":0.56798575565802,"score_spread":0.3704512312666278,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170382471","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9915871,0.00019751569,0.0009924235,0.00036396235,0.00005303897,0.00018160164,5.392062e-7,0.00000974587,0.006614081],"genre_scores_gemma":[0.9964197,0.000054923286,0.0032933047,0.00004718023,0.00001284343,0.000017038386,0.000004922572,0.0000041384255,0.00014591202],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9952997,0.002929783,0.0004452654,0.00025361998,0.00094777625,0.0001238733],"domain_scores_gemma":[0.9981071,0.0009953355,0.00060781965,0.0001235995,0.00011197788,0.000054173368],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02696011,0.000076721975,0.00014637479,0.00023036824,0.0002881112,0.00017979977,0.00006702668,0.000030319301,0.00037307426],"category_scores_gemma":[0.0043721106,0.00006182369,0.000017292765,0.00019498996,0.000023447632,0.00054318516,0.00002662021,0.00046970567,0.0000053761114],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031800678,0.00001738097,0.7630112,0.000006106892,0.0000036164768,2.091646e-7,0.004242839,0.0008844256,0.00031404686,0.00083555,0.000023035564,0.23065843],"study_design_scores_gemma":[0.0006831843,0.000098923556,0.9404545,0.000017939077,0.000018869287,0.000003596711,0.024634385,0.027963903,0.0000456895,0.0005098454,0.005493279,0.00007589363],"about_ca_topic_score_codex":0.0007867241,"about_ca_topic_score_gemma":0.00024910684,"teacher_disagreement_score":0.23058254,"about_ca_system_score_codex":0.00006960463,"about_ca_system_score_gemma":0.00022796672,"threshold_uncertainty_score":0.934389},"labels":[],"label_agreement":null},{"id":"W2170746357","doi":"","title":"Rol de la evidencia científica en las decisiones políticas relacionadas con los sistemas de salud","year":2013,"lang":"es","type":"article","venue":"Redalyc (Universidad Autónoma del Estado de México)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Political science; Context (archaeology); Welfare economics; Economics; Geography","score_opus":0.04202000195730238,"score_gpt":0.36374814356197066,"score_spread":0.3217281416046683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170746357","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9419613,0.0011346681,0.016427044,0.0092571415,0.000578341,0.0010930499,0.000071535556,0.00021670104,0.029260209],"genre_scores_gemma":[0.9750486,0.0008440869,0.011266419,0.0012976669,0.00029504573,0.00005287475,0.00002287648,0.000085205254,0.011087231],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98970777,0.0029136797,0.0013647632,0.0013631583,0.0031015612,0.0015490663],"domain_scores_gemma":[0.98847944,0.006699204,0.00090794906,0.0016519693,0.0010585249,0.001202925],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.007883372,0.0007558913,0.0009673733,0.0014888163,0.0011579405,0.0017323947,0.0021772697,0.0009630243,0.008526995],"category_scores_gemma":[0.0031488903,0.00072642876,0.00061863917,0.0022881415,0.0006668237,0.0023675212,0.0006680164,0.0010226096,0.003905996],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009272705,0.0022140264,0.38363856,0.0005416872,0.00085880497,0.0019639765,0.020214329,0.008947504,0.03263451,0.2418385,0.089372456,0.21684837],"study_design_scores_gemma":[0.0028251386,0.0006017676,0.6469316,0.00089546444,0.0004566777,0.0007307506,0.017766794,0.21287291,0.001247485,0.015518671,0.09878218,0.0013705632],"about_ca_topic_score_codex":0.0006527142,"about_ca_topic_score_gemma":0.00015303557,"teacher_disagreement_score":0.26329303,"about_ca_system_score_codex":0.002229216,"about_ca_system_score_gemma":0.0043065543,"threshold_uncertainty_score":0.9995187},"labels":[],"label_agreement":null},{"id":"W2171350126","doi":"10.7202/706789ar","title":"L’utilisation de l’évaluation dans le développement des interventions sociales","year":2005,"lang":"fr","type":"article","venue":"Service social","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université Laval; Centre Jeunesse de Quebec","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.4821012836422089,"score_gpt":0.5273699641336717,"score_spread":0.045268680491462765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171350126","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6645818,0.000964281,0.043394636,0.27196223,0.0012469401,0.0004363074,0.000053152075,0.00007253547,0.017288113],"genre_scores_gemma":[0.968048,0.00027765328,0.013711995,0.0037034212,0.0018717407,0.000074378004,0.0000990637,0.00002602483,0.01218773],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9955399,0.0011957968,0.0009343552,0.00039213753,0.0014276595,0.00051015173],"domain_scores_gemma":[0.9979899,0.0002449224,0.00042192984,0.00022317076,0.0009924402,0.0001276339],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0070214826,0.00021907302,0.00026001837,0.00018360789,0.0018480448,0.00039646443,0.00048789472,0.00024247772,0.0060714693],"category_scores_gemma":[0.00027698075,0.00023920482,0.00033234918,0.001062911,0.0003397728,0.0012283949,0.00013920465,0.00023590644,0.001757778],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032045187,0.00068454456,0.012914679,0.00019004199,0.000092852984,8.1471075e-7,0.1331188,0.0023682052,0.0010393084,0.045308586,0.006572523,0.79767764],"study_design_scores_gemma":[0.002147329,0.00013280715,0.56290036,0.00026982455,0.00025808933,0.0000067587453,0.0872538,0.07829082,0.001391268,0.2016354,0.06513357,0.0005799204],"about_ca_topic_score_codex":0.0016935488,"about_ca_topic_score_gemma":0.031889107,"teacher_disagreement_score":0.7970977,"about_ca_system_score_codex":0.001494448,"about_ca_system_score_gemma":0.0026791159,"threshold_uncertainty_score":0.9994514},"labels":[],"label_agreement":null},{"id":"W2171507080","doi":"10.1177/1356389011430371","title":"Evaluation models and evaluation use","year":2012,"lang":"en","type":"article","venue":"Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Université de Montréal","funders":"Canadian Institutes of Health Research; U.S. Public Health Service","keywords":"Context (archaeology); Management science; Psychological intervention; Process (computing); Perspective (graphical); Field (mathematics); Evaluation methods; Impact evaluation; Systematic review; Affect (linguistics); Program evaluation; Computer science; Knowledge management; Process management; Psychology; Political science; Engineering; Artificial intelligence; Medicine; MEDLINE","score_opus":0.6626932025379391,"score_gpt":0.5990196685991209,"score_spread":0.06367353393881814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171507080","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9668698,0.0015645671,0.0068127415,0.0008694028,0.0014973313,0.0022817894,0.000008145826,0.00005124658,0.020044986],"genre_scores_gemma":[0.9968998,0.000045826982,0.0014463653,0.00027284288,0.00042087593,0.00048293208,0.000109272034,0.000017682662,0.00030444245],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97816,0.0040842025,0.0009581088,0.0005798193,0.015796611,0.0004212246],"domain_scores_gemma":[0.9907592,0.0012668835,0.00049075537,0.0007430733,0.006521757,0.0002183534],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12947914,0.0002182865,0.00024430937,0.00047638564,0.0003357339,0.0005037873,0.0002409877,0.00013676015,0.0077032982],"category_scores_gemma":[0.012562397,0.00017696261,0.000079074096,0.00078560994,0.00006728505,0.0062922225,0.00008957772,0.00014819198,0.0006465879],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002554527,0.0001227148,0.016240744,0.0000028776585,0.000031931464,3.5881353e-8,0.0036830197,0.047439437,0.00043990175,0.004128042,0.004689848,0.9231959],"study_design_scores_gemma":[0.0011752428,0.000037207457,0.16239081,0.000010815628,0.00033469076,0.0000036638567,0.00065824087,0.77540463,0.000173651,0.057667717,0.0019632413,0.00018010789],"about_ca_topic_score_codex":0.000022014376,"about_ca_topic_score_gemma":0.00008454061,"teacher_disagreement_score":0.9230158,"about_ca_system_score_codex":0.0005734608,"about_ca_system_score_gemma":0.0008599508,"threshold_uncertainty_score":0.9957552},"labels":[],"label_agreement":null},{"id":"W2172099595","doi":"10.17169/fqs-7.2.122","title":"Editorial: Responsibility, Solidarity, and Ethics in Cogenerative Dialogue as Research Methods","year":2008,"lang":"en","type":"editorial","venue":"Forum: Qualitative Social Research (Freie Universität Berlin)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Solidarity; Psychology; Engineering ethics; Research ethics; Sociology; Political science; Engineering; Law","score_opus":0.6717801759627409,"score_gpt":0.7270169718183215,"score_spread":0.05523679585558061,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2172099595","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004486441,0.0008312224,0.0013357782,0.018542377,0.939202,0.0031859286,0.0015943989,0.000093913535,0.030727915],"genre_scores_gemma":[0.0065299305,0.0032808415,0.0035021915,0.00017235203,0.9504456,0.00018735544,0.0008442908,0.00015139447,0.034886047],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.7768294,0.1736774,0.0028564886,0.0038683244,0.039364457,0.0034039365],"domain_scores_gemma":[0.61363804,0.34426966,0.0010598543,0.0017972457,0.03819434,0.0010408477],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","research_integrity"],"consensus_categories":["metaresearch","sts","research_integrity"],"category_scores_codex":[0.29346776,0.00077626435,0.001879114,0.005024595,0.0058210255,0.0012306761,0.0033806795,0.004465372,0.00063567306],"category_scores_gemma":[0.3165152,0.00073236204,0.00045899834,0.007206913,0.007270454,0.0026672466,0.0037981758,0.018540055,0.000685295],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012328728,0.00020127054,0.00002121359,0.000045134064,0.00010810408,0.00004503016,0.22807679,0.000007922374,0.00006766654,0.028804488,0.73904324,0.0023462716],"study_design_scores_gemma":[0.001486403,0.0008852231,0.00003092193,0.000090014495,0.000016379581,7.4486485e-7,0.200242,0.00012769604,0.000050536455,0.18506151,0.6115516,0.00045700214],"about_ca_topic_score_codex":0.0061099427,"about_ca_topic_score_gemma":0.015023625,"teacher_disagreement_score":0.17059226,"about_ca_system_score_codex":0.0036412838,"about_ca_system_score_gemma":0.026357321,"threshold_uncertainty_score":0.99980617},"labels":[],"label_agreement":null},{"id":"W2175989841","doi":"10.4102/aej.v3i1.145","title":"Use of evidence in policy making in South Africa: An exploratory study of attitudes of senior government officials","year":2015,"lang":"en","type":"article","venue":"African Evaluation Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Evidence-based policy; Presidency; Government (linguistics); Political science; Public policy; Politics; Context (archaeology); Public administration; Public relations; Medicine; Geography","score_opus":0.7719629586370481,"score_gpt":0.5688494283805711,"score_spread":0.20311353025647705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2175989841","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99851495,0.00010417434,0.0003431935,0.00020384643,0.000121730394,0.0004907176,0.0000079133915,0.0000026258715,0.00021083094],"genre_scores_gemma":[0.9990598,0.000009598797,0.0007911572,0.000021956324,0.000067601744,0.000019290204,3.9231327e-7,0.000007501957,0.000022732462],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9876138,0.00288549,0.0020330383,0.0002588784,0.0070127575,0.00019605807],"domain_scores_gemma":[0.9947947,0.0008328197,0.0019130313,0.00043785488,0.0019022264,0.0001193395],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.033912484,0.00012627384,0.0004714988,0.00084344175,0.000040022358,0.00007401465,0.00047662752,0.000043952936,0.00020460623],"category_scores_gemma":[0.011356196,0.000090240064,0.000060915998,0.0017856834,0.00008016733,0.001427778,0.00010150994,0.00016911015,0.000005238645],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028453677,0.0010433982,0.6727449,0.0000068563095,0.000020860827,0.0000020413386,0.20652895,0.09683301,0.0010995903,0.00008718243,0.00005602455,0.021292621],"study_design_scores_gemma":[0.0018626428,0.001466657,0.7219332,0.00022481008,0.00004044844,0.0000030641813,0.24367328,0.029361954,0.0003748878,0.0008693312,0.000055151104,0.00013459913],"about_ca_topic_score_codex":0.00006123302,"about_ca_topic_score_gemma":0.0010600754,"teacher_disagreement_score":0.06747106,"about_ca_system_score_codex":0.00050237705,"about_ca_system_score_gemma":0.0019229755,"threshold_uncertainty_score":0.99697155},"labels":[],"label_agreement":null},{"id":"W217609455","doi":"10.46743/2160-3715/2011.1075","title":"Mixed Methods Design: A Beginner's Guide","year":2014,"lang":"en","type":"article","venue":"The Qualitative Report","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Morse code; Multimethodology; Qualitative research; Computer science; Research design; Management science; Sociology; Data science; Mathematics education; Psychology; Engineering; Social science","score_opus":0.6913829235059147,"score_gpt":0.7088385477922557,"score_spread":0.017455624286341065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W217609455","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011355861,0.00004352988,0.9020228,0.009038453,0.0005913092,0.00024626285,0.0000012932695,0.000044236356,0.0766563],"genre_scores_gemma":[0.4964971,0.00000823855,0.44534612,0.0019088619,0.00022968571,0.00012057213,0.0000063829834,0.000020118165,0.055862915],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.984079,0.012049745,0.0012507143,0.00043374943,0.0019375785,0.00024918775],"domain_scores_gemma":[0.9800563,0.016855277,0.0008259705,0.0012220148,0.0009398488,0.00010061747],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14272918,0.00014390302,0.0003163845,0.0001245626,0.0002869605,0.00015614986,0.0006234078,0.00004688834,0.0010139924],"category_scores_gemma":[0.024826763,0.00007362148,0.00013212602,0.00064216065,0.00021947263,0.00024572606,0.0001078616,0.00014497686,0.000701943],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010273282,0.0001130543,0.0005010198,0.00000752734,0.00014747451,0.000024939956,0.09844204,0.0021262981,0.0030187701,0.16617674,0.20415202,0.5251874],"study_design_scores_gemma":[0.00026787253,0.00020384962,0.0041281567,0.000010255462,0.000025732683,0.00009429344,0.03314054,0.017927835,0.0032742182,0.33793792,0.6027753,0.00021404627],"about_ca_topic_score_codex":0.000045694156,"about_ca_topic_score_gemma":0.000013551048,"teacher_disagreement_score":0.52497333,"about_ca_system_score_codex":0.000050842245,"about_ca_system_score_gemma":0.00025713025,"threshold_uncertainty_score":0.9998992},"labels":[],"label_agreement":null},{"id":"W2177445649","doi":"10.3138/cjpe.0028.009","title":"The Emerging Field of Evaluation and the Growth of the Evaluation Profession: The Russian Experience","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Institutionalisation; Field (mathematics); Political science; Capacity development; Private sector; Evaluation methods; Foundation (evidence); Engineering ethics; Environmental resource management; Engineering; Economics; Law","score_opus":0.20594391447379515,"score_gpt":0.5328023639531525,"score_spread":0.3268584494793574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2177445649","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9142254,0.0018031457,0.00089890277,0.072722115,0.0021428338,0.0043048915,0.0000021695707,0.0000040427485,0.0038965112],"genre_scores_gemma":[0.9990184,0.000036042333,0.00016380897,0.00030149898,0.00015990163,0.00025120974,0.0000016480955,0.000006692171,0.000060823208],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9879033,0.0051233335,0.0013222524,0.0001939201,0.005219756,0.0002374621],"domain_scores_gemma":[0.99087065,0.0022160204,0.0019306778,0.0006513149,0.0042066197,0.00012470338],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08238429,0.00013145445,0.00023639112,0.00017949282,0.001052972,0.0002658433,0.00091824005,0.000074649295,0.00045930088],"category_scores_gemma":[0.018550863,0.000049844497,0.00016319756,0.00092761306,0.0005963411,0.00042746533,0.000049602913,0.00029211852,0.0000030272906],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007038811,0.000019295943,0.018175252,0.000007105399,0.0000342258,6.380719e-8,0.011377116,0.001097351,0.000052712392,0.014570975,0.0008896599,0.95370585],"study_design_scores_gemma":[0.0027623142,0.00036947036,0.23607671,0.0001854899,0.00040825497,0.000022696595,0.012890796,0.65077627,0.0011200982,0.0883175,0.0069366177,0.0001338166],"about_ca_topic_score_codex":0.0004379454,"about_ca_topic_score_gemma":0.008022066,"teacher_disagreement_score":0.95357203,"about_ca_system_score_codex":0.0001560525,"about_ca_system_score_gemma":0.003187804,"threshold_uncertainty_score":0.9897163},"labels":[],"label_agreement":null},{"id":"W2178177024","doi":"10.1080/09650792.2015.1042984","title":"Conceptualizing indicator domains for evaluating action research","year":2015,"lang":"en","type":"article","venue":"Educational Action Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Roads University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Conversation; Action research; Action (physics); Presentation (obstetrics); Process (computing); Psychology; Computer science; Management science; Process management; Pedagogy; Medicine","score_opus":0.9591009759835989,"score_gpt":0.7949866063831985,"score_spread":0.16411436960040038,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2178177024","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9332626,0.00021694053,0.0031719063,0.04012678,0.002726434,0.0016987163,0.00002586102,0.000047976602,0.01872281],"genre_scores_gemma":[0.9691539,0.000025468353,0.0038434803,0.00019402985,0.0017932979,0.0010538957,0.00008353599,0.0000210831,0.023831356],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98518634,0.0030241185,0.0007257847,0.0007192452,0.00966358,0.0006809044],"domain_scores_gemma":[0.9778267,0.011421808,0.00022548281,0.0006055123,0.009465622,0.00045488938],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.0821102,0.00012482493,0.00018872351,0.0015371213,0.0015499919,0.000708626,0.00077434996,0.00013739143,0.004860784],"category_scores_gemma":[0.029562484,0.00010472607,0.00008858455,0.0024472005,0.00039231335,0.0010563709,0.00016868339,0.000779537,0.0036175135],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005456505,0.0007416461,0.02512315,0.000037105987,0.00005199232,4.4535184e-7,0.010939174,0.0013769442,0.0073392577,0.07289687,0.7412574,0.13969035],"study_design_scores_gemma":[0.0015472074,0.000780965,0.051502105,0.000035521916,0.000007462978,0.0000113760825,0.085156955,0.020478511,0.0033515482,0.24212736,0.5947429,0.00025807664],"about_ca_topic_score_codex":0.0001156302,"about_ca_topic_score_gemma":0.00011488082,"teacher_disagreement_score":0.16923049,"about_ca_system_score_codex":0.0012418677,"about_ca_system_score_gemma":0.00665896,"threshold_uncertainty_score":0.99974984},"labels":[],"label_agreement":null},{"id":"W2179175560","doi":"10.3138/cjpe.0026.004","title":"L’évaluation des interventions complexes : quelle peut être la contribution des approches configurationnelles?","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"École Nationale d'Administration Publique","funders":"","keywords":"Operationalization; Epistemology; Psychological intervention; Sociology; Valuation (finance); Psychology; Philosophy; Economics","score_opus":0.42523218998141776,"score_gpt":0.5299160107559208,"score_spread":0.104683820774503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2179175560","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9313954,0.0038863423,0.0551345,0.0009117895,0.00086044194,0.0014915382,0.000021274338,0.000026865027,0.0062718177],"genre_scores_gemma":[0.990214,0.000036119436,0.00892231,0.000054715423,0.00028604385,0.00012015191,0.000083231265,0.00001277482,0.00027067837],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9945048,0.0016911448,0.0013180802,0.00018912589,0.0018595874,0.00043727382],"domain_scores_gemma":[0.99129564,0.0005842677,0.000957866,0.0002519337,0.006321395,0.00058888673],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.026494825,0.00017454717,0.0002953831,0.0007617609,0.0008064476,0.0006400399,0.00036746653,0.00012314787,0.0033961497],"category_scores_gemma":[0.007715263,0.0001420783,0.00028804032,0.0008602303,0.0004335187,0.0018963172,0.000015647889,0.00022683936,0.0001450946],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026700438,0.00021125608,0.108408295,0.000028439867,0.00007427628,0.0000013953077,0.0069645336,0.0023602068,0.00036805385,0.006931157,0.0020676383,0.87255806],"study_design_scores_gemma":[0.002437833,0.0007255099,0.7935768,0.00040633173,0.00044719715,0.00021735535,0.010407368,0.051549643,0.001188708,0.09989465,0.03874882,0.00039981984],"about_ca_topic_score_codex":0.0004021985,"about_ca_topic_score_gemma":0.013302973,"teacher_disagreement_score":0.8721582,"about_ca_system_score_codex":0.000575293,"about_ca_system_score_gemma":0.0024933387,"threshold_uncertainty_score":0.9975149},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W2179332549","doi":"10.3109/0142159x.2015.1060307","title":"Connecting medical education to patient outcomes: The promise of contribution analysis","year":2015,"lang":"en","type":"article","venue":"Medical Teacher","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Psychological intervention; Causal analysis; Medical education; Work (physics); Psychology; Medicine; Management science; Risk analysis (engineering); Nursing; Engineering","score_opus":0.17160787154719045,"score_gpt":0.5260174192779721,"score_spread":0.3544095477307816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2179332549","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9368613,0.000053127176,0.008743133,0.04898423,0.00046134306,0.00027068338,0.000001256638,0.000017082424,0.0046078595],"genre_scores_gemma":[0.9963146,0.0000017998865,0.00012909023,0.0027893668,0.00007544184,0.000042330594,0.000010699681,0.0000034959546,0.0006331626],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99264437,0.000616867,0.0007590755,0.00023063495,0.0055911476,0.00015790253],"domain_scores_gemma":[0.99754035,0.00048100128,0.0002389765,0.00041976527,0.0007730505,0.00054683635],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.014841132,0.00008380123,0.00029241169,0.00018559727,0.0000770978,0.00004553156,0.00052674906,0.000107308435,0.016398104],"category_scores_gemma":[0.067354135,0.000040981467,0.00012415188,0.0011642426,0.000062139836,0.00009688916,0.000121930585,0.00020650896,0.00023353734],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035235047,0.00050203584,0.5543677,0.000001712806,0.00014583758,0.0000012464684,0.0068845195,0.00018470974,0.0000026910354,0.0016058208,0.023374416,0.41289407],"study_design_scores_gemma":[0.0025625592,0.00054186856,0.24021564,0.00009282515,0.00039158098,0.00001170438,0.023681385,0.35076413,0.00014857187,0.006290895,0.37489173,0.0004071083],"about_ca_topic_score_codex":0.00014053792,"about_ca_topic_score_gemma":0.0003421081,"teacher_disagreement_score":0.41248697,"about_ca_system_score_codex":0.00008805057,"about_ca_system_score_gemma":0.0012480618,"threshold_uncertainty_score":0.98450106},"labels":[],"label_agreement":null},{"id":"W2180823206","doi":"10.1177/2158244015604193","title":"The Mobilization of Scientific Evidence by Public Policy Analysts","year":2015,"lang":"en","type":"article","venue":"SAGE Open","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Canadian Institutes of Health Research","keywords":"Mobilization; Mediation; Public policy; Field (mathematics); Path analysis (statistics); Government (linguistics); Policy analysis; Political science; Public economics; Test (biology); Positive economics; Psychology; Econometrics; Economics; Public administration; Computer science","score_opus":0.5517309626375979,"score_gpt":0.584428211461108,"score_spread":0.032697248823510106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2180823206","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8319848,0.0029640973,0.008260618,0.046829406,0.0015093167,0.0019434,0.00003740659,0.00003606845,0.106434874],"genre_scores_gemma":[0.97655344,0.000045761204,0.00014721081,0.00017307594,0.000026320638,0.000021791113,0.000006496963,0.0000031060006,0.023022806],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.996955,0.00038262884,0.0004456075,0.00025681645,0.0018058317,0.00015412149],"domain_scores_gemma":[0.99735624,0.0005401706,0.0002838069,0.0007678797,0.0009345441,0.00011734967],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.017607965,0.000057287794,0.00011926579,0.00016587152,0.0003312651,0.0021675932,0.0019083369,0.000023743885,0.00045252306],"category_scores_gemma":[0.0069603566,0.000031577878,0.00003346959,0.0022318615,0.00018442859,0.0016180745,0.0004149674,0.00004454521,0.00031994568],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060166403,0.0000897705,0.10943526,0.0000041192366,0.000022338309,4.4113315e-7,0.002244226,0.00035069673,0.0032486268,0.012249534,0.31002846,0.56226635],"study_design_scores_gemma":[0.0009755593,0.00028737946,0.032358147,0.000081771344,0.00001769883,0.0000026263508,0.005935486,0.03384332,0.00534925,0.04692272,0.8739522,0.0002738577],"about_ca_topic_score_codex":0.0001883786,"about_ca_topic_score_gemma":0.00060370954,"teacher_disagreement_score":0.5639237,"about_ca_system_score_codex":0.00006698335,"about_ca_system_score_gemma":0.0013289235,"threshold_uncertainty_score":0.9988682},"labels":[],"label_agreement":null},{"id":"W2181536920","doi":"10.66752/1077-5315.4453","title":"Factors Affecting Program Evaluation Behaviours of Natural Resource Extension Practitioners--Motivation and Capacity Building","year":2006,"lang":"en","type":"article","venue":"Journal of Extension","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Natural resource; Extension (predicate logic); Resource (disambiguation); Psychology; Program evaluation; Capacity building; Applied psychology; Knowledge management; Environmental resource management; Marketing; Business; Social psychology; Computer science; Political science; Economics; Economic growth","score_opus":0.2568006224286208,"score_gpt":0.47590331813216324,"score_spread":0.21910269570354246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2181536920","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99726814,0.00022459359,0.0009451278,0.00040312193,0.0005051147,0.00043146717,0.0000016309648,0.000013760227,0.00020703196],"genre_scores_gemma":[0.9944613,0.000009818933,0.005284263,0.000035702433,0.00015574583,0.0000021659123,0.0000092273785,0.00000940427,0.00003239516],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99508125,0.00055914867,0.001122248,0.0002559458,0.0028168352,0.00016457889],"domain_scores_gemma":[0.9935719,0.0011250027,0.002166967,0.00023017188,0.0028340616,0.00007192344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010029309,0.00014864808,0.00033880715,0.0005437707,0.00023293812,0.00013932267,0.0001479284,0.0000921239,0.0000601094],"category_scores_gemma":[0.0045031146,0.000097642136,0.0001404453,0.00055088935,0.00007991116,0.0012032926,0.00004804914,0.0003119049,0.0000011271184],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031043362,0.00077920133,0.25363907,0.000027170261,0.000038918173,0.000006611395,0.0018028202,0.0129014375,0.43965945,0.00050986075,0.0037008177,0.2866242],"study_design_scores_gemma":[0.0007519968,0.00040485352,0.95912313,0.00017151727,0.000084942374,0.00006745804,0.0016600832,0.01954249,0.015570263,0.0020496235,0.00045601476,0.000117594864],"about_ca_topic_score_codex":0.000046244473,"about_ca_topic_score_gemma":0.000019870959,"teacher_disagreement_score":0.7054841,"about_ca_system_score_codex":0.00012877576,"about_ca_system_score_gemma":0.00011699988,"threshold_uncertainty_score":0.5390974},"labels":[],"label_agreement":null},{"id":"W2182857497","doi":"10.3138/cjpe.29.3.154","title":"A Point of No Return Finally Reached: The Journey Ahead","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Point (geometry); Mathematics; Economics; Econometrics; History; Geometry","score_opus":0.5769749004666175,"score_gpt":0.5455323490261877,"score_spread":0.031442551440429733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2182857497","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93933815,0.0015094898,0.0013887278,0.02266029,0.0027846538,0.0017873495,0.000012779575,0.000011192433,0.030507347],"genre_scores_gemma":[0.99543166,0.000009792527,0.0033675926,0.0003260754,0.0002915363,0.000023950277,0.000005098549,0.000008458412,0.000535809],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9941154,0.0009528297,0.0012291349,0.0001489448,0.003302815,0.00025087103],"domain_scores_gemma":[0.98849094,0.00028388415,0.0012585428,0.00041358493,0.00895736,0.000595687],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.039952103,0.00011312529,0.00026032559,0.0004698727,0.00014210962,0.00029842142,0.0007345899,0.00007586592,0.0014183185],"category_scores_gemma":[0.010862658,0.00006629348,0.0001597994,0.00076247193,0.00014695598,0.00059144205,0.000017121252,0.00029511235,0.00013062023],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000099723,0.00008989103,0.026711786,0.000006842538,0.000067968256,0.000011588533,0.007821334,0.0028033603,0.00010088372,0.0010878514,0.08723984,0.87395895],"study_design_scores_gemma":[0.0047634756,0.0045646653,0.16348813,0.00028258518,0.0003889684,0.0004888606,0.0147936875,0.19366665,0.00042496674,0.07994007,0.53673476,0.00046318167],"about_ca_topic_score_codex":0.00061778206,"about_ca_topic_score_gemma":0.012360817,"teacher_disagreement_score":0.87349576,"about_ca_system_score_codex":0.00037292606,"about_ca_system_score_gemma":0.010889496,"threshold_uncertainty_score":0.9994945},"labels":[],"label_agreement":null},{"id":"W2183451661","doi":"10.3138/cjpe.0021.007","title":"The Role of Culture and the Future of the Evaluation Function: Considerations and Key Questions","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Treasury Board of Canada Secretariat","funders":"","keywords":"Function (biology); Extension (predicate logic); Key (lock); Work (physics); Political science; Public relations; Administration (probate law); Sociology; Public administration; Computer science; Engineering; Law","score_opus":0.13572695358587547,"score_gpt":0.46709632153462205,"score_spread":0.3313693679487466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2183451661","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8872782,0.054375917,0.0014178305,0.037510473,0.0032988272,0.005543644,0.000026160264,0.000009427067,0.010539499],"genre_scores_gemma":[0.9989298,0.00011652523,0.0005060536,0.00013635059,0.00020096118,0.00003169051,0.000002244204,0.000003762897,0.00007258417],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99598765,0.0010189929,0.0008549409,0.00011502732,0.0018835099,0.00013989197],"domain_scores_gemma":[0.99310654,0.00081871863,0.00093845266,0.00028475354,0.0047146343,0.00013688048],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.031008836,0.00008600448,0.00016008918,0.00015852082,0.00079051754,0.00023405955,0.00021163434,0.00007236754,0.00021878417],"category_scores_gemma":[0.0035298911,0.00003789291,0.00008904807,0.000518556,0.00053590507,0.0003046755,0.000016077776,0.00021079644,0.0000013367854],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057011148,0.000019050767,0.018867414,0.0000030219462,0.00005398057,1.449551e-7,0.004799527,0.0008115549,0.0001003969,0.06725311,0.001352075,0.9066827],"study_design_scores_gemma":[0.002437026,0.00036925395,0.48464984,0.000067154375,0.0005460708,0.0000971729,0.023640975,0.045013998,0.00026008,0.32621896,0.11658648,0.00011300825],"about_ca_topic_score_codex":0.00020347278,"about_ca_topic_score_gemma":0.039375164,"teacher_disagreement_score":0.9065697,"about_ca_system_score_codex":0.00009249206,"about_ca_system_score_gemma":0.0024104102,"threshold_uncertainty_score":0.9977803},"labels":[],"label_agreement":null},{"id":"W2183771102","doi":"","title":"Q-Squared in Impact Assessment: A Review*","year":2013,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trent University","funders":"","keywords":"Counterfactual thinking; Unobservable; Causal inference; Econometrics; Narrative; Inference; Computer science; Psychology; Mathematics; Artificial intelligence; Social psychology; Linguistics","score_opus":0.2419102388224151,"score_gpt":0.6140354382439517,"score_spread":0.37212519942153655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2183771102","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39080554,0.0010344998,0.0026530086,0.019582711,0.0002717853,0.0013053623,0.0000026783555,0.000058202888,0.5842862],"genre_scores_gemma":[0.9874206,0.00046037143,0.0016714096,0.0038725594,0.000021632666,0.000095433636,0.0000045053757,0.000004315404,0.0064491727],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99739116,0.00021974868,0.0006382037,0.00024554913,0.0013030474,0.00020227506],"domain_scores_gemma":[0.9986212,0.0003677721,0.00012841467,0.0004787562,0.0003082124,0.00009563366],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.004078082,0.00009414039,0.00023334274,0.0002064424,0.00003950417,0.00019059172,0.00038722248,0.000030054982,0.12623952],"category_scores_gemma":[0.00052679627,0.00005227428,0.00009489709,0.0008980598,0.000019304292,0.0008108162,0.000055230696,0.00010710555,0.0068196724],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002694143,0.000118655524,0.40250036,0.000022025824,0.000008162792,0.0000015350248,0.00018102532,0.00015010634,0.000222946,0.0023293924,0.36742225,0.22704084],"study_design_scores_gemma":[0.00034880277,0.00007125897,0.9446481,0.000095105504,0.0000025829763,0.000002502279,0.00025576807,0.025447736,0.000018007902,0.00900487,0.019985119,0.00012013023],"about_ca_topic_score_codex":0.00026647002,"about_ca_topic_score_gemma":0.00010834035,"teacher_disagreement_score":0.5966151,"about_ca_system_score_codex":0.000087842425,"about_ca_system_score_gemma":0.00022985479,"threshold_uncertainty_score":0.99395365},"labels":[],"label_agreement":null},{"id":"W2183871221","doi":"10.22329/csw.v13i2.5868","title":"Mirror Method as an Approach for Critical Evaluation in Social Work","year":2019,"lang":"en","type":"article","venue":"Critical Social Work","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Oppression; Dialogical self; Ideology; Process (computing); Work (physics); Sociology; Critical thinking; Epistemology; Management science; Engineering ethics; Psychology; Computer science; Social psychology; Pedagogy; Political science; Engineering","score_opus":0.3772284306187488,"score_gpt":0.6092019457085979,"score_spread":0.2319735150898491,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2183871221","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5147499,0.0001903975,0.2509959,0.10238387,0.0042118183,0.004559313,0.00005996261,0.0002147974,0.12263406],"genre_scores_gemma":[0.93795544,3.67728e-7,0.058814313,0.0014245523,0.0005340044,0.00032814208,0.000037315433,0.000022692342,0.00088320125],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99362713,0.0015522151,0.0007976532,0.00074682134,0.0026626673,0.0006134961],"domain_scores_gemma":[0.9940427,0.0043869633,0.000076918695,0.0002816089,0.0010243012,0.00018751093],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0144839175,0.00020162418,0.00048033588,0.00017708536,0.000895686,0.0004409069,0.00053026766,0.0003386595,0.007168247],"category_scores_gemma":[0.00946176,0.00017695443,0.00023106491,0.0020268706,0.00023975191,0.0005676403,0.00008583674,0.00035533085,0.00085427216],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006706108,0.0009958388,0.019787543,0.000048417565,0.000020355024,0.0000018758168,0.005872534,0.000075077405,0.000084061816,0.77246785,0.0056520486,0.19432378],"study_design_scores_gemma":[0.0025844283,0.0003192929,0.2068058,0.000035258214,0.00012318065,0.0000021844373,0.0089086285,0.042948153,0.00006187773,0.7134398,0.024027135,0.0007442386],"about_ca_topic_score_codex":0.000008424716,"about_ca_topic_score_gemma":0.000006876869,"teacher_disagreement_score":0.42320552,"about_ca_system_score_codex":0.0001755148,"about_ca_system_score_gemma":0.0003485842,"threshold_uncertainty_score":0.9999237},"labels":[],"label_agreement":null},{"id":"W2184422954","doi":"10.3138/cjpe.30.2.159","title":"Meeting at the Crossroads: Interactivity, Technology, and Evaluation Utilization","year":2015,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Interactivity; Business; Computer science; Knowledge management; Multimedia","score_opus":0.5349738231760608,"score_gpt":0.5834254372741116,"score_spread":0.048451614098050766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2184422954","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90829206,0.00023029128,0.0020039568,0.010921385,0.00026417067,0.00026465912,8.8150455e-7,0.000037490314,0.07798513],"genre_scores_gemma":[0.9945814,0.000010505765,0.00030135486,0.0003351935,0.000028252822,0.0000270469,0.0000036189836,0.0000032585815,0.0047093625],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976351,0.00025259634,0.00028946638,0.00023504766,0.0014815436,0.000106236665],"domain_scores_gemma":[0.9981855,0.00042155114,0.00016052074,0.0003273649,0.0008587314,0.00004631436],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011876229,0.00006635275,0.00008498029,0.00021484322,0.00024091855,0.0002542354,0.00021469421,0.00004916628,0.0011824904],"category_scores_gemma":[0.0036355937,0.000035001143,0.000017597993,0.000763553,0.00012548477,0.0004835107,0.0002635595,0.00007190846,0.00035724125],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003185765,0.00005323091,0.22343288,0.0000013781142,0.000010761742,2.5737947e-7,0.001965505,0.0017424492,0.00071359944,0.007247988,0.025978385,0.7388217],"study_design_scores_gemma":[0.0011220449,0.00012769227,0.058430005,0.000016803167,0.00002702329,0.00002422664,0.013216477,0.6902125,0.007914164,0.07739838,0.15132627,0.00018439784],"about_ca_topic_score_codex":0.000019610885,"about_ca_topic_score_gemma":0.0005252021,"teacher_disagreement_score":0.7386373,"about_ca_system_score_codex":0.00010125334,"about_ca_system_score_gemma":0.00014303403,"threshold_uncertainty_score":0.9997306},"labels":[],"label_agreement":null},{"id":"W2184816201","doi":"","title":"Workshop on Evaluating Impact and Identifying Measures of Success: When are Outreach Initiatives Successful?","year":2008,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Outreach; Public relations; Program evaluation; Engineering management; Political science; Business; Medical education; Engineering; Public administration; Medicine","score_opus":0.5492619356512645,"score_gpt":0.5548249631168325,"score_spread":0.005563027465568027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2184816201","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96877915,0.00035058163,0.0018130313,0.0005560385,0.00012745117,0.0002085625,0.000008215265,0.000030914885,0.028126046],"genre_scores_gemma":[0.9974069,0.00019583288,0.0011543173,0.00021027379,0.00005414996,0.000013765995,0.0000035375301,0.000010083333,0.0009511455],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9952901,0.00047751857,0.00079414767,0.0004280845,0.0027719096,0.0002382677],"domain_scores_gemma":[0.99606097,0.0019956916,0.00057573174,0.000436774,0.0008094271,0.000121384895],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005033348,0.00018651936,0.00039636093,0.00042675025,0.00031780615,0.00020036622,0.0004217506,0.00006947586,0.0021786524],"category_scores_gemma":[0.0031998698,0.000116342286,0.000117623655,0.0005320522,0.00016348115,0.0012089448,0.00011404872,0.00016526478,0.000073357696],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000072523246,0.000081083046,0.9473861,0.0000087871595,0.00003914753,0.000003116066,0.005245672,0.0009639625,0.00034917955,0.0002772936,0.0010820656,0.044491086],"study_design_scores_gemma":[0.0007532891,0.0001778796,0.97319907,0.00012202648,0.000017070375,0.000009604993,0.010035149,0.010308847,0.0016465246,0.003399331,0.00013693229,0.0001942637],"about_ca_topic_score_codex":0.00008527152,"about_ca_topic_score_gemma":0.00020281764,"teacher_disagreement_score":0.044296823,"about_ca_system_score_codex":0.000050887214,"about_ca_system_score_gemma":0.00020430006,"threshold_uncertainty_score":0.9987335},"labels":[],"label_agreement":null},{"id":"W2185313922","doi":"10.3138/cjpe.29.3.1","title":"Building the Foundation for the CES Professional Designation Program","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Foundation (evidence); Psychology; Archaeology; History","score_opus":0.6387757866045108,"score_gpt":0.6092163742699974,"score_spread":0.029559412334513424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2185313922","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50269675,0.003844945,0.29660168,0.13939947,0.020927109,0.03235478,0.000022802507,0.000104282466,0.004048173],"genre_scores_gemma":[0.9787304,0.00000451997,0.019257376,0.00029623637,0.0005823387,0.0008605972,0.000017488954,0.000010275376,0.00024078053],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99535763,0.0007087234,0.00081089826,0.00016530373,0.0026996417,0.00025782196],"domain_scores_gemma":[0.99091554,0.0011476709,0.00089800684,0.00026488389,0.0064885328,0.00028537473],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03797134,0.00011096298,0.00014341279,0.0003097591,0.0007091533,0.00090976054,0.000702409,0.00006644703,0.00028777734],"category_scores_gemma":[0.007833311,0.00005383614,0.00012482317,0.0007547781,0.00013807394,0.0008442778,0.000013908367,0.00019393474,0.000024328863],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028116678,0.000034956396,0.0023018185,0.000001942969,0.000023371895,2.6394918e-7,0.0011261838,0.0057526636,0.000016785149,0.0027652772,0.009516237,0.97843236],"study_design_scores_gemma":[0.0011926627,0.0007770341,0.02715463,0.000038262526,0.00014226013,0.000024926112,0.0037868782,0.42831945,0.00010594409,0.05911112,0.4792265,0.00012034813],"about_ca_topic_score_codex":0.0001508719,"about_ca_topic_score_gemma":0.005389328,"teacher_disagreement_score":0.978312,"about_ca_system_score_codex":0.00042423984,"about_ca_system_score_gemma":0.007701662,"threshold_uncertainty_score":0.99792373},"labels":[],"label_agreement":null},{"id":"W2185731738","doi":"10.3138/cjpe.19.001","title":"The Role of the Evaluator in a Political World","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Politics; Power (physics); Simplicity; Argument (complex analysis); Elite; Ambiguity; Servant; Sociology; Independence (probability theory); Fundamentalism; Environmental ethics; Law; Political science; Political economy; Epistemology; Philosophy","score_opus":0.22938257899034617,"score_gpt":0.5204448598505118,"score_spread":0.2910622808601656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2185731738","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96268165,0.0012328262,0.00007808899,0.021587493,0.0010176109,0.0013863068,0.000004697785,0.0000032814817,0.012008054],"genre_scores_gemma":[0.9991939,0.000002950341,0.00039119725,0.00018071769,0.00009499727,0.000036285157,5.7847336e-7,0.000004892448,0.00009449571],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99540824,0.0006664001,0.00095686,0.000112963084,0.0025415523,0.00031400664],"domain_scores_gemma":[0.9966816,0.00036500185,0.0005285559,0.00033604458,0.0018122591,0.00027658942],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018371304,0.00007869399,0.00015623578,0.00040477485,0.00021611982,0.0002021653,0.0007169961,0.000040932864,0.0004017472],"category_scores_gemma":[0.004548977,0.000039879993,0.00013567084,0.0012574816,0.00020382133,0.0002547996,0.000017038954,0.00023759346,0.000027364584],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022951117,0.00006305381,0.11483586,0.0000017491217,0.000018536803,0.0000015069131,0.0011808595,0.0054785525,0.00007306213,0.084596515,0.00040132875,0.793326],"study_design_scores_gemma":[0.0016475286,0.00026484963,0.448495,0.00010678878,0.00006424385,0.00003033235,0.0041524554,0.021979114,0.00094538793,0.44784227,0.07435546,0.00011657752],"about_ca_topic_score_codex":0.0011857838,"about_ca_topic_score_gemma":0.15661411,"teacher_disagreement_score":0.79320943,"about_ca_system_score_codex":0.00066271605,"about_ca_system_score_gemma":0.009871162,"threshold_uncertainty_score":0.99574196},"labels":[],"label_agreement":null},{"id":"W2186584638","doi":"","title":"A research-into-practice series produced by a partnership between the Literacy and Numeracy Secretariat and the Ontario Association of Deans of Education","year":2009,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Numeracy; General partnership; Literacy; Mathematics education; Political science; Sociology; Pedagogy; Psychology","score_opus":0.13080630623477021,"score_gpt":0.5206135019411552,"score_spread":0.389807195706385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2186584638","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8610836,0.0002360729,0.00008118135,0.124694,0.000052585336,0.00047510065,0.0000021196647,0.0000052618784,0.013370042],"genre_scores_gemma":[0.98645544,0.00008168338,0.000717248,0.0005144144,0.00005050303,0.000016190992,0.000005870011,0.0000023805565,0.0121562565],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99637634,0.0011434784,0.00054678816,0.00022570444,0.0015680923,0.00013960936],"domain_scores_gemma":[0.99210316,0.005690738,0.0004897272,0.00037224527,0.0012983846,0.00004571863],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020667268,0.000076593875,0.00019997593,0.00009900499,0.0002773982,0.00029721245,0.00025633015,0.00004744355,0.00016890893],"category_scores_gemma":[0.005485075,0.000036776477,0.000033567896,0.0005124351,0.00015833885,0.001249796,0.000051966992,0.00022253186,0.0000063530115],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007652609,0.00027512832,0.59041333,0.000022175856,0.000114937844,1.0133643e-7,0.16052838,0.000012691576,0.00080470066,0.0850687,0.019747343,0.14224721],"study_design_scores_gemma":[0.0014137016,0.00045143816,0.68197334,0.000043129985,0.00010754443,0.0000032906023,0.018960616,0.0006538561,0.0037903357,0.15536052,0.13709517,0.00014704232],"about_ca_topic_score_codex":0.0048413733,"about_ca_topic_score_gemma":0.0030299006,"teacher_disagreement_score":0.14210019,"about_ca_system_score_codex":0.00009457304,"about_ca_system_score_gemma":0.00054756756,"threshold_uncertainty_score":0.7318741},"labels":[],"label_agreement":null},{"id":"W2188387579","doi":"10.3138/cjpe.019.002","title":"Reporting on Outcomes: Setting Performance Expectations and Telling Performance Stories","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Government of Canada","funders":"","keywords":"Outcome (game theory); Chart; Public relations; Actuarial science; Business; Psychology; Political science; Economics; Microeconomics; Statistics","score_opus":0.4090562215533984,"score_gpt":0.5347074822731473,"score_spread":0.12565126071974897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2188387579","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9946532,0.00020183981,0.0005174054,0.0016683356,0.0006848122,0.0005423995,0.0000016648283,0.0000137693105,0.0017165403],"genre_scores_gemma":[0.991978,0.000016008666,0.0075618383,0.00015350117,0.00014390783,0.000043588545,0.000005142505,0.0000113683745,0.00008667346],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9953899,0.00015964889,0.0019269014,0.00023779419,0.0019787769,0.00030697644],"domain_scores_gemma":[0.99464965,0.00025197462,0.0024813951,0.00025791704,0.0020090959,0.00034994798],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014154803,0.00015267487,0.00028690894,0.0006951425,0.00065470283,0.00045525967,0.0002574006,0.000066306144,0.0001733925],"category_scores_gemma":[0.006707187,0.00011536335,0.00008894204,0.0006148996,0.000096602984,0.001083278,0.000010932609,0.00028389398,0.000039063198],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010768681,0.000026098262,0.2800477,0.000009756869,0.000019910842,0.000004961333,0.006424821,0.03151759,0.000019854457,0.00022050705,0.00006768226,0.6816303],"study_design_scores_gemma":[0.0018400806,0.0014915611,0.8909363,0.00036846226,0.00010267994,0.00017955535,0.016012026,0.08072186,0.000848031,0.0027070027,0.004422542,0.0003698901],"about_ca_topic_score_codex":0.000120906894,"about_ca_topic_score_gemma":0.0019793878,"teacher_disagreement_score":0.68126047,"about_ca_system_score_codex":0.0004796234,"about_ca_system_score_gemma":0.0034215883,"threshold_uncertainty_score":0.80296135},"labels":[],"label_agreement":null},{"id":"W2188606052","doi":"10.3138/cjpe.0028.011","title":"A Good Start, but We Can Do Better","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Globe; Engineering ethics; Computer science; Psychology; Engineering management; Process management; Knowledge management; Risk analysis (engineering); Business; Management science; Engineering","score_opus":0.31888172658606007,"score_gpt":0.4975859348037114,"score_spread":0.17870420821765132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2188606052","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9479666,0.0005312665,0.0030803462,0.030605787,0.0020304853,0.001178524,0.000017307702,0.000017194432,0.014572536],"genre_scores_gemma":[0.99455214,0.000007869703,0.0037510942,0.00081776746,0.00042164823,0.000037069956,0.0000072286816,0.000010594516,0.00039460813],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9952235,0.00075889775,0.000900536,0.00020900683,0.0025813282,0.00032671215],"domain_scores_gemma":[0.9955965,0.00025574482,0.0006609061,0.00036248058,0.0024827947,0.00064157514],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017098479,0.00012731942,0.00024090717,0.00067505403,0.00021942254,0.0006355171,0.0005163736,0.00007876074,0.0043619196],"category_scores_gemma":[0.0022444546,0.000095100244,0.00013555007,0.00057221047,0.00008211859,0.00047535173,0.00001149639,0.00023020482,0.00018901097],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000062151785,0.00002006219,0.025739275,0.0000024339247,0.00001774335,0.0000026536513,0.0009756158,0.0006209504,0.000034546676,0.0006280677,0.0073298425,0.9646226],"study_design_scores_gemma":[0.0017565512,0.0011049367,0.100794025,0.000084684485,0.00012821492,0.000071851806,0.0018872323,0.061667014,0.00019794454,0.048575453,0.7834445,0.00028757766],"about_ca_topic_score_codex":0.00039684647,"about_ca_topic_score_gemma":0.022685625,"teacher_disagreement_score":0.964335,"about_ca_system_score_codex":0.00032611476,"about_ca_system_score_gemma":0.0037751277,"threshold_uncertainty_score":0.99654824},"labels":[],"label_agreement":null},{"id":"W2188824898","doi":"10.3138/cjpe.0020.004","title":"Two Decades of the <i>Canadian Journal of Program Evaluation</i> : A Content Analysis","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Milestone; Editorial board; Content analysis; Library science; Descriptive statistics; History; Sociology; Social science; Computer science; Statistics; Mathematics","score_opus":0.43548977213527457,"score_gpt":0.5284019432527968,"score_spread":0.0929121711175222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2188824898","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9833433,0.002284182,0.00078764604,0.0041623907,0.0015726063,0.0032868916,0.000032534736,0.0000062833356,0.0045241443],"genre_scores_gemma":[0.99448824,0.00000600943,0.004802921,0.00014196393,0.00029379004,0.000092975235,0.0000157676,0.000013261327,0.0001450668],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9889911,0.0017216859,0.0027613952,0.00024531013,0.0058067595,0.00047374723],"domain_scores_gemma":[0.9775122,0.0003230216,0.003657634,0.0005491957,0.017214991,0.0007429751],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.037571117,0.00021776067,0.0006174396,0.0024439644,0.00052181684,0.0007768497,0.0012290018,0.00013624405,0.0022142287],"category_scores_gemma":[0.0045722057,0.0001412889,0.0007702761,0.0040913513,0.0004011367,0.00077413674,0.000016711221,0.00041999528,0.000013717866],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002185915,0.00012306335,0.4070786,0.000005793582,0.0003584933,0.000005141841,0.0009214479,0.04127736,0.000075475575,0.00078582985,0.0028393173,0.5465076],"study_design_scores_gemma":[0.003081575,0.00089194503,0.8315656,0.00013437448,0.003235838,0.00010919985,0.002096076,0.1065454,0.00059734297,0.013604321,0.037865132,0.00027316902],"about_ca_topic_score_codex":0.030768434,"about_ca_topic_score_gemma":0.8137094,"teacher_disagreement_score":0.782941,"about_ca_system_score_codex":0.0011109059,"about_ca_system_score_gemma":0.028828973,"threshold_uncertainty_score":0.9986979},"labels":[],"label_agreement":null},{"id":"W2189153528","doi":"","title":"Framework Analysis: A Qualitative Methodology for Applied Policy Research","year":2009,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":854,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"MacEwan University","funders":"","keywords":"Qualitative research; Management science; Computer science; Political science; Sociology; Economics; Social science","score_opus":0.6192653351074647,"score_gpt":0.7019230970789018,"score_spread":0.08265776197143704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2189153528","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032346066,0.00060887524,0.92598665,0.03501193,0.000104316525,0.00033246417,0.0000040032255,0.000018675324,0.0055870344],"genre_scores_gemma":[0.9705904,0.00046581024,0.024216069,0.0009791125,0.00084217684,0.000030340363,0.0000038843127,0.000007981389,0.0028642325],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9913538,0.0028161115,0.00081997865,0.0004146873,0.0021631634,0.0024322567],"domain_scores_gemma":[0.99006814,0.007769687,0.00036741773,0.00043689125,0.0012117899,0.00014605315],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12636437,0.00013594101,0.00044740856,0.002029389,0.00062595075,0.0002576015,0.0009085363,0.00014299442,0.00025635018],"category_scores_gemma":[0.009798103,0.00009551478,0.00031197525,0.0045887283,0.000100068006,0.00022246,0.000037348003,0.0021918034,0.00013087117],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016006782,0.000035159435,0.00008069808,4.3483453e-7,0.0002478764,1.7057941e-7,0.006065797,0.00035584517,0.00013998372,0.8545552,0.00034187298,0.1380169],"study_design_scores_gemma":[0.00040494528,0.00065903453,0.0011068317,0.0000028532597,0.00006782715,0.000012102035,0.047980834,0.0008079889,0.00007229988,0.94356096,0.005218952,0.00010536591],"about_ca_topic_score_codex":0.000026153253,"about_ca_topic_score_gemma":0.00037933735,"teacher_disagreement_score":0.93824434,"about_ca_system_score_codex":0.00091169396,"about_ca_system_score_gemma":0.00619019,"threshold_uncertainty_score":0.99944377},"labels":[],"label_agreement":null},{"id":"W2189472627","doi":"10.1080/07011784.2015.1088403","title":"Towards sustainable water governance: Examining water governance issues in Québec through the lens of multi-loop social learning","year":2015,"lang":"en","type":"article","venue":"Canadian Water Resources Journal / Revue canadienne des ressources hydriques","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université du Québec à Montréal; McGill University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Corporate governance; Watershed; Watershed management; Business; Credibility; Knowledge management; Social learning; Public relations; Environmental resource management; Process management; Political science; Computer science; Economics","score_opus":0.1313460584901011,"score_gpt":0.35574152826528205,"score_spread":0.22439546977518096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2189472627","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9783839,0.002138667,0.00003597746,0.01397931,0.00028854838,0.00031376173,0.000021320275,0.000026803295,0.0048117265],"genre_scores_gemma":[0.97367567,0.0004250494,0.00015568902,0.00057454436,0.0005305869,0.000031721884,0.000014987703,0.00006518819,0.024526551],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.993129,0.0011963142,0.0015568266,0.00066042185,0.0011392358,0.0023182018],"domain_scores_gemma":[0.99655765,0.0001777148,0.00051250047,0.00057697674,0.0014163703,0.0007588115],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.008324246,0.00048040942,0.00083169487,0.00042961905,0.001552971,0.0009626989,0.0018643894,0.00024490742,0.0008783275],"category_scores_gemma":[0.0012075191,0.00024811795,0.00022800667,0.00050319295,0.00074303796,0.0016042812,0.00027199215,0.0010710065,0.00009038597],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008581702,0.00003062543,0.016903074,0.00005625503,0.00006857919,0.00039706114,0.9619595,0.012007398,0.000721006,0.00005242041,0.00036124396,0.0073570423],"study_design_scores_gemma":[0.0008468144,0.0002659884,0.0066263215,0.0001535567,0.000029658688,0.0001922456,0.0426922,0.0017928104,0.0062449016,0.0015779822,0.9391165,0.00046104784],"about_ca_topic_score_codex":0.72171074,"about_ca_topic_score_gemma":0.90672565,"teacher_disagreement_score":0.9387552,"about_ca_system_score_codex":0.0025220658,"about_ca_system_score_gemma":0.00018300998,"threshold_uncertainty_score":0.9999971},"labels":[],"label_agreement":null},{"id":"W2189561476","doi":"","title":"Capacity, Collaboration and Culture The Future of the Policy Research Function in the Government of Canada","year":2009,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Function (biology); Public policy; Political science; Business; Public administration; Public relations; Economic growth; Economics","score_opus":0.139385849954244,"score_gpt":0.4718037360870511,"score_spread":0.3324178861328071,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2189561476","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77372974,0.00010058987,0.000026118623,0.18794604,0.0001406182,0.00035235428,0.000010930716,0.0000010726466,0.037692547],"genre_scores_gemma":[0.99624527,0.00004178284,0.000020502921,0.0016566487,0.00008608089,0.000004421161,2.9090504e-7,7.1539796e-7,0.0019443039],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99559593,0.0005158297,0.00024602184,0.000093055016,0.003458586,0.00009059394],"domain_scores_gemma":[0.9989097,0.00027446233,0.00010884151,0.0003121126,0.00038009256,0.000014769308],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005447966,0.000040303014,0.00006555983,0.000030063928,0.00018806798,0.00005755677,0.00035008852,0.000028152264,0.00009212685],"category_scores_gemma":[0.00037220825,0.000013368145,0.0000146128,0.0013708577,0.00006655869,0.00010820418,0.000033081487,0.0001337082,4.6359315e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000120036246,0.00013729018,0.06387094,0.000009486447,0.000011135397,2.1473696e-7,0.031708695,0.0011690735,0.0042255605,0.34920126,0.46485966,0.08468663],"study_design_scores_gemma":[0.00020398201,0.000115448136,0.83084625,0.000007252594,0.0000027706647,9.913475e-7,0.061647486,0.0012905773,0.0012298276,0.021391893,0.08323263,0.00003090993],"about_ca_topic_score_codex":0.013468784,"about_ca_topic_score_gemma":0.5347251,"teacher_disagreement_score":0.7669753,"about_ca_system_score_codex":0.00010852561,"about_ca_system_score_gemma":0.0006976393,"threshold_uncertainty_score":0.9931006},"labels":[],"label_agreement":null},{"id":"W2194127335","doi":"","title":"The Changing Landscape of Development Evaluation Training","year":2014,"lang":"en","type":"preprint","venue":"RePEc: Research Papers in Economics","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mandate; Context (archaeology); General partnership; Excellence; Curriculum; Political science; Knowledge management; Public relations; Psychology; Computer science; Pedagogy; Geography","score_opus":0.28790780597046456,"score_gpt":0.5023847172227492,"score_spread":0.21447691125228469,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2194127335","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8512759,0.00016606714,0.000084776,0.00084169087,0.00085505814,0.00093097566,0.000005947667,0.000012716203,0.14582685],"genre_scores_gemma":[0.9960836,0.00087103184,0.00077702047,0.000045264893,0.00015331795,0.0002951299,0.000026137917,0.000017333394,0.0017311372],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99376255,0.0011588883,0.0013925458,0.00067495636,0.0024101567,0.00060092536],"domain_scores_gemma":[0.99402094,0.0034458514,0.0005745772,0.001060667,0.00080225646,0.000095727795],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07297662,0.00017615472,0.00041284037,0.0009195896,0.0004061676,0.00033015505,0.0012625023,0.00019155547,0.00044070827],"category_scores_gemma":[0.004277184,0.00012436863,0.000115592884,0.0003381934,0.00016982472,0.00010385508,0.0009305976,0.0007505058,0.000036652975],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002300622,0.00001844396,0.0042520384,0.00001404085,0.000024687624,2.5652844e-7,0.0048830626,0.041141137,0.000010299705,0.0002706527,0.000056432167,0.94930595],"study_design_scores_gemma":[0.00072445744,0.00006137083,0.035182964,0.00021474352,0.0000085126885,0.0000020232183,0.01762359,0.84005815,0.00024563892,0.009172475,0.09640053,0.00030553187],"about_ca_topic_score_codex":0.0000044826693,"about_ca_topic_score_gemma":0.00027695685,"teacher_disagreement_score":0.9490004,"about_ca_system_score_codex":0.00046490287,"about_ca_system_score_gemma":0.0031361764,"threshold_uncertainty_score":0.95456564},"labels":[],"label_agreement":null},{"id":"W219521914","doi":"10.3138/cjpe.0025.010","title":"Successful or Not: It Depends on Your Frame of Reference","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Frame (networking); Point (geometry); Frame of reference; Key (lock); Psychology; Knowledge management; Computer science; Engineering ethics; Process management; Business; Computer security; Engineering","score_opus":0.7666920347927102,"score_gpt":0.5786637113913813,"score_spread":0.1880283234013289,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W219521914","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9679827,0.00009061893,0.0008627351,0.0016229618,0.0009826178,0.00081152655,0.000024933517,0.000008749527,0.02761316],"genre_scores_gemma":[0.9956588,0.000012741411,0.0034369228,0.0003923115,0.00008771529,0.000026746397,0.00000629791,0.000008763146,0.0003697098],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9951945,0.0005398358,0.0011570122,0.00020437618,0.0026431046,0.00026117213],"domain_scores_gemma":[0.994279,0.00028373284,0.0011088871,0.0003825401,0.0034934275,0.00045240266],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.014023587,0.00012926906,0.00028439736,0.00080235116,0.00012877819,0.00015059164,0.0007222843,0.00011187669,0.016205456],"category_scores_gemma":[0.0040231114,0.00008592452,0.000109742316,0.00075584586,0.0001001028,0.0005957747,0.00001304332,0.00026783854,0.00014763878],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022570105,0.00009965375,0.034038868,0.0000063628313,0.000032932043,0.000012480396,0.0029505377,0.00023257268,0.00005063462,0.0010970366,0.0025026218,0.9587506],"study_design_scores_gemma":[0.0034431275,0.0072886893,0.83037895,0.00036566614,0.00029549457,0.00013141305,0.008917135,0.02886638,0.005588109,0.016929744,0.09721553,0.00057976006],"about_ca_topic_score_codex":0.0012902553,"about_ca_topic_score_gemma":0.032950368,"teacher_disagreement_score":0.95817083,"about_ca_system_score_codex":0.00020890833,"about_ca_system_score_gemma":0.005270085,"threshold_uncertainty_score":0.9846958},"labels":[],"label_agreement":null},{"id":"W2197614560","doi":"10.55016/ojs/ajer.v61i1.56031","title":"(Non)Construction of the Teacher: An Inquiry into Ontario’s Equity and Inclusive Education Strategy","year":2015,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Equity (law); Context (archaeology); Educational equity; Public policy; Teacher education; Pedagogy; Education policy; Political science; Policy analysis; Student achievement; Public relations; Psychology; Sociology; Mathematics education; Academic achievement; Public administration; Higher education","score_opus":0.48076056025723346,"score_gpt":0.6267502700201021,"score_spread":0.14598970976286862,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2197614560","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9418136,0.00013510423,0.000009162126,0.014880417,0.0008768942,0.00014586633,3.6630772e-7,1.6733536e-7,0.042138457],"genre_scores_gemma":[0.9866466,0.000018305373,0.00055790745,0.00011182734,0.00043782438,0.000007767167,0.0000029756625,0.000004569436,0.012212254],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99546933,0.00062034494,0.00071632717,0.00017954824,0.0028533228,0.00016111274],"domain_scores_gemma":[0.9910566,0.0034934317,0.00051440834,0.00035155148,0.0043081758,0.00027581464],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009644485,0.00007907611,0.00016680226,0.00040966936,0.00026318547,0.00019348026,0.00082105736,0.00006468375,0.0044186725],"category_scores_gemma":[0.010798242,0.000048945465,0.000055842374,0.00064205035,0.0004150022,0.0010791663,0.00037208668,0.00044271728,0.00005020675],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016473967,0.00058871805,0.83082694,0.000011307164,0.00003439062,5.8952068e-8,0.04183049,0.00029950848,0.00045797555,0.029291946,0.025962215,0.070531726],"study_design_scores_gemma":[0.00044526014,0.00050556706,0.7319708,0.00005709795,0.000016705051,0.00008714187,0.043134883,0.00031426697,0.00032697737,0.20944434,0.013606907,0.0000900727],"about_ca_topic_score_codex":0.015582953,"about_ca_topic_score_gemma":0.062377587,"teacher_disagreement_score":0.1801524,"about_ca_system_score_codex":0.0005749295,"about_ca_system_score_gemma":0.02303486,"threshold_uncertainty_score":0.9975342},"labels":[],"label_agreement":null},{"id":"W2198693010","doi":"10.55016/ojs/ajer.v48i4.54941","title":"Editorial: Not Without Value","year":2002,"lang":"en","type":"editorial","venue":"Alberta Journal of Educational Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Value (mathematics); Psychology; Statistics; Mathematics education; Mathematics","score_opus":0.3026845883468232,"score_gpt":0.5954863190797588,"score_spread":0.2928017307329356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2198693010","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005329118,0.00036903552,0.0000035401204,0.015277616,0.9103622,0.00020478963,0.000026194697,5.8937e-7,0.07322316],"genre_scores_gemma":[0.0011006278,0.00056920655,0.00016151686,0.000066257984,0.755756,0.000020267444,0.000034370263,0.000032944256,0.24225877],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9702569,0.0018086222,0.002202083,0.00056930626,0.02454158,0.0006214852],"domain_scores_gemma":[0.7885992,0.19170119,0.0014447677,0.0008301741,0.01694439,0.00048031379],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.026917873,0.00030209604,0.00076137943,0.0018462008,0.00046872598,0.0009870658,0.0031950392,0.0007470322,0.080710165],"category_scores_gemma":[0.32044533,0.00021479915,0.00039030408,0.0014005688,0.00030723398,0.00091250055,0.00025383665,0.003468427,0.008178232],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001303403,0.00025395094,0.00087611243,0.000015192262,0.00007697777,3.1096383e-7,0.00038269238,0.00006909587,0.00001612706,0.001302639,0.9961756,0.00070095144],"study_design_scores_gemma":[0.00058244437,0.00034991658,0.0003407453,0.0001530452,0.000036654004,0.000009542477,0.00016405278,0.00013700992,0.00001687042,0.0037678154,0.9942338,0.00020809144],"about_ca_topic_score_codex":0.00049482746,"about_ca_topic_score_gemma":0.0004352543,"teacher_disagreement_score":0.29352745,"about_ca_system_score_codex":0.0007056112,"about_ca_system_score_gemma":0.014047676,"threshold_uncertainty_score":0.9988306},"labels":[],"label_agreement":null},{"id":"W2201453635","doi":"10.7870/cjcmh-2007-0015","title":"Relever Le Défi Des Plans De Services Individualisés (PSI) Au Québec: Leçons Tirées De L'Expérience Des équipes D'Intervention Jeunesse (éIJ)","year":2007,"lang":"fr","type":"article","venue":"Canadian Journal of Community Mental Health","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Humanities; Context (archaeology); Political science; Sociology; Psychology; Art; Geography","score_opus":0.14776646087159037,"score_gpt":0.4619890766792137,"score_spread":0.31422261580762334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2201453635","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9739646,0.0069729364,0.0016856584,0.014501503,0.0010441559,0.00021690101,0.00021335397,0.000010031465,0.0013908927],"genre_scores_gemma":[0.99304444,0.000652921,0.0020552196,0.0029328514,0.00017099341,0.0000029303264,0.000029295945,0.000022326474,0.0010889965],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9931518,0.002967989,0.0015654955,0.00014982448,0.0009296327,0.0012352754],"domain_scores_gemma":[0.994691,0.00091859786,0.0010777512,0.00045243994,0.00057730515,0.0022828784],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.024517318,0.00027632437,0.00048309038,0.0007214315,0.0044308775,0.0003791638,0.001575719,0.00016776942,0.0007817086],"category_scores_gemma":[0.00037054459,0.00026909524,0.0002378641,0.0007524782,0.00092480704,0.0017533016,0.00010153458,0.0012176891,0.000048996877],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000081746985,0.00033984362,0.47492403,0.00027172788,0.000060597366,0.00003583317,0.37703067,0.00026621312,0.00003723911,0.00087653194,0.001582771,0.14449282],"study_design_scores_gemma":[0.0010821295,0.0011036566,0.6940027,0.0019074539,0.000032592594,0.0008873326,0.23545112,0.00040654544,0.00045846333,0.004910254,0.05950162,0.0002561434],"about_ca_topic_score_codex":0.89573854,"about_ca_topic_score_gemma":0.9957895,"teacher_disagreement_score":0.21907867,"about_ca_system_score_codex":0.0060693105,"about_ca_system_score_gemma":0.027406376,"threshold_uncertainty_score":0.9999761},"labels":[],"label_agreement":null},{"id":"W2201941744","doi":"10.7202/1034033ar","title":"L’évaluation des stages par les acteurs de la formation pratique : modalités, supervision, évaluation et guide de stage","year":2015,"lang":"fr","type":"article","venue":"Revue des sciences de l éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Humanities; Political science; Sociology; Philosophy","score_opus":0.7273270400982633,"score_gpt":0.5808805270924902,"score_spread":0.14644651300577316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2201941744","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7523048,0.0016491566,0.2221706,0.008736794,0.0007582822,0.00059338124,0.00003114112,0.00007370875,0.013682159],"genre_scores_gemma":[0.84600055,0.0032710177,0.13966832,0.0007524953,0.00029454753,0.0001571413,0.00010541944,0.000028585604,0.009721936],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98656815,0.008240642,0.001353395,0.000735865,0.002264292,0.0008376706],"domain_scores_gemma":[0.9940037,0.002035588,0.00079561013,0.0005948206,0.0021090957,0.00046117473],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07690177,0.00036440938,0.0003545003,0.00064814696,0.0015748963,0.0018949467,0.0009150258,0.0003855191,0.0008203092],"category_scores_gemma":[0.013830043,0.00034558895,0.00014523118,0.0020221465,0.0017946581,0.0064649456,0.00012773622,0.00039036863,0.00021330989],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00004300831,0.00039631285,0.098042615,0.0002828085,0.00002079929,0.0000037848392,0.24842821,0.25567013,0.0043231803,0.023180991,0.0065919207,0.36301625],"study_design_scores_gemma":[0.0006076969,0.0005002621,0.12485832,0.00044880953,0.00007895868,0.00013824897,0.043986607,0.678447,0.0035116815,0.121256,0.025731899,0.0004344861],"about_ca_topic_score_codex":0.002606282,"about_ca_topic_score_gemma":0.0028865635,"teacher_disagreement_score":0.4227769,"about_ca_system_score_codex":0.004230525,"about_ca_system_score_gemma":0.01190291,"threshold_uncertainty_score":0.9998996},"labels":[],"label_agreement":null},{"id":"W2206814819","doi":"10.32597/dissertations/437/","title":"A Study of Perceptions Held Toward Teacher Evaluation Policies and Practices by Teachers and Their Supervisors in Adventist Schools in Canada","year":2002,"lang":"en","type":"dissertation","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Psychology; Perception; School teachers; Mathematics education; Population; Class (philosophy); Medical education; Pedagogy; Medicine; Sociology; Computer science; Demography","score_opus":0.20740828274514214,"score_gpt":0.49567658533018116,"score_spread":0.288268302585039,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2206814819","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99217516,0.0007113039,0.0000018042376,0.00069687056,0.00012304902,0.0010710459,0.000019806204,0.0000052836485,0.005195656],"genre_scores_gemma":[0.9947442,0.00036960375,0.000029273744,0.000057820806,0.0000143086245,0.00015590378,0.00010100672,0.0000121915455,0.0045156833],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9957106,0.0008284523,0.0010146857,0.00051460887,0.0017303237,0.00020130511],"domain_scores_gemma":[0.9981642,0.00041801113,0.0007133988,0.00030115177,0.00032235953,0.000080916005],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00424326,0.00024048265,0.00046366648,0.0005945528,0.00008388362,0.00017748005,0.0002674159,0.00012358963,0.002294133],"category_scores_gemma":[0.0013927665,0.00017737599,0.000030144049,0.0006468133,0.00002479942,0.0006220161,0.00003925513,0.0004091026,0.0000055590317],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002703466,0.00034602286,0.8633387,0.000019986837,0.000026301017,6.455095e-7,0.08526316,0.00011945412,0.000121345765,0.0000056190656,0.0036885669,0.04704318],"study_design_scores_gemma":[0.00059103686,0.000083053346,0.50942916,0.00003667725,0.000019982455,8.148619e-7,0.48547697,0.003972885,0.000012054347,0.00006143118,0.00019886791,0.00011706816],"about_ca_topic_score_codex":0.81523854,"about_ca_topic_score_gemma":0.9941278,"teacher_disagreement_score":0.4002138,"about_ca_system_score_codex":0.00037577626,"about_ca_system_score_gemma":0.0011557313,"threshold_uncertainty_score":0.9986179},"labels":[],"label_agreement":null},{"id":"W2211337001","doi":"10.1007/s11077-015-9234-9","title":"Policy logics, framing strategies, and policy change: lessons from universal pre-k policy debates in California and Florida","year":2015,"lang":"en","type":"article","venue":"Policy Sciences","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Framing (construction); Legitimacy; Public policy; Politics; State (computer science); Policy analysis; Sociology; Economics; Investment (military); Public administration; Political science; Political economy; Public economics; Economic growth; Law","score_opus":0.36555727174856634,"score_gpt":0.5274881700309149,"score_spread":0.16193089828234852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2211337001","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8841435,0.00061096053,0.00026871377,0.1021707,0.00018271597,0.0003393658,0.00018613148,0.000060876093,0.012037065],"genre_scores_gemma":[0.9937041,0.0005208381,0.00083818915,0.0027161455,0.0017717107,0.00002094871,0.000009556079,0.000011221258,0.00040730296],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9958364,0.00035815954,0.0006070569,0.0008065681,0.0016115487,0.00078028155],"domain_scores_gemma":[0.9977599,0.0007498877,0.00029249815,0.0004070624,0.00023237568,0.0005583232],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00360316,0.0002990885,0.00041008543,0.0025356228,0.00048175865,0.0014394214,0.0009327597,0.00014895806,0.00005286914],"category_scores_gemma":[0.0041338517,0.00022217189,0.000046827496,0.0045629246,0.0011550892,0.0024108163,0.0004906079,0.00023053765,0.00007202702],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007670782,0.00011286141,0.29399744,0.000017695827,0.000023732726,0.000012367746,0.03908986,0.0016862046,0.0003195614,0.52172524,0.0010878928,0.14185047],"study_design_scores_gemma":[0.0012919669,0.00033366733,0.44724718,0.00005994097,0.000010591461,0.000021184762,0.027802795,0.028479911,0.00015453082,0.47685722,0.01718802,0.00055301643],"about_ca_topic_score_codex":0.15948191,"about_ca_topic_score_gemma":0.0148176355,"teacher_disagreement_score":0.15324973,"about_ca_system_score_codex":0.00032896968,"about_ca_system_score_gemma":0.0067861676,"threshold_uncertainty_score":0.9995972},"labels":[],"label_agreement":null},{"id":"W2212108873","doi":"10.55016/ojs/ajer.v52i2.55134","title":"A Special Education Program Evaluation for Accountability Purposes: An In-Depth Case Study","year":2006,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Accountability; Psychology; Mathematics education; Program evaluation; Pedagogy; Special education; Educational research; Evaluation methods; Sociology; Political science; Public administration; Engineering","score_opus":0.49678721393923575,"score_gpt":0.6637065650467828,"score_spread":0.16691935110754708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2212108873","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9667214,0.00007343895,0.0000070295214,0.0034860559,0.0011946844,0.0041366783,0.0000025267345,6.2909317e-7,0.024377566],"genre_scores_gemma":[0.9892446,0.0000037712025,0.00094264094,0.00004440747,0.0048554894,0.0013195901,0.0000235827,0.000010860664,0.0035550862],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9922389,0.0015634181,0.0014014146,0.00039156995,0.0040795,0.00032522995],"domain_scores_gemma":[0.9744626,0.015933562,0.00049211615,0.0004571916,0.008490528,0.00016397942],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.02967458,0.0001229528,0.00024719586,0.0011593113,0.00033305606,0.0005382537,0.00064302044,0.0000659939,0.010248481],"category_scores_gemma":[0.019271322,0.000094396004,0.0001042761,0.0014585864,0.00010975513,0.0015376894,0.00004695005,0.00033442382,0.0001034433],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028216452,0.013741665,0.69690764,0.0000110845285,0.00001948852,0.0000017753817,0.0048953467,0.0006805415,0.000036209105,0.003031055,0.02772431,0.25266874],"study_design_scores_gemma":[0.002456519,0.0026457424,0.8023999,0.000039460803,0.000052925614,0.00052819186,0.0673359,0.005936096,0.000030116269,0.036285155,0.08206193,0.00022809005],"about_ca_topic_score_codex":0.004284506,"about_ca_topic_score_gemma":0.117595375,"teacher_disagreement_score":0.25244063,"about_ca_system_score_codex":0.0007107545,"about_ca_system_score_gemma":0.0104088755,"threshold_uncertainty_score":0.9991542},"labels":[],"label_agreement":null},{"id":"W2212762088","doi":"10.1186/s13643-015-0163-7","title":"All in the Family: systematic reviews, rapid reviews, scoping reviews, realist reviews, and more","year":2015,"lang":"en","type":"editorial","venue":"Systematic Reviews","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":303,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"","keywords":"Medicine; Systematic review; MEDLINE; Engineering ethics","score_opus":0.5113523182310088,"score_gpt":0.5556523779986046,"score_spread":0.04430005976759577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2212762088","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000010900591,0.7436713,0.00027560315,0.0007508305,0.15230195,0.099761784,0.00005890639,0.000046493922,0.0031320667],"genre_scores_gemma":[0.0000023886935,0.8733447,0.0014701115,0.0036282649,0.079453744,0.03706316,0.00041871393,0.00012973222,0.004489147],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.8271449,0.111520074,0.043581266,0.0039007897,0.0119743105,0.001878621],"domain_scores_gemma":[0.9264865,0.020725856,0.03624544,0.013466978,0.0021572984,0.00091796153],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow"],"category_scores_codex":[0.43983933,0.0028273042,0.028321017,0.001079043,0.00053132325,0.0021509086,0.0067367787,0.0012560991,0.00043785866],"category_scores_gemma":[0.26769328,0.0012841655,0.0027535097,0.0037045386,0.00033387222,0.0013313404,0.00070704694,0.0024386256,0.012367594],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037099253,0.000041649757,0.000004420238,0.45515758,0.000029944675,0.000006238925,0.0013457619,3.3594807e-7,8.271194e-7,0.00005325998,0.5407882,0.0025680605],"study_design_scores_gemma":[0.0003621221,0.00008031388,0.000002769934,0.44371673,0.00083778065,0.000034276392,0.0004266732,0.00007718839,6.695248e-8,0.00017224632,0.55355227,0.0007375491],"about_ca_topic_score_codex":0.00015354974,"about_ca_topic_score_gemma":0.0004097344,"teacher_disagreement_score":0.17214604,"about_ca_system_score_codex":0.00093892287,"about_ca_system_score_gemma":0.0011231423,"threshold_uncertainty_score":0.9998628},"labels":[],"label_agreement":null},{"id":"W2213186415","doi":"","title":"Using Action Research and Provincial Test Results to Improve Student Learning, 6(20)","year":2002,"lang":"en","type":"article","venue":"IEJLL: International Electronic Journal for Leadership in Learning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Test (biology); Mathematics education; Action research; Action (physics); Psychology; Work (physics); Pedagogy; Medical education; Engineering; Medicine","score_opus":0.648830462067373,"score_gpt":0.5803999903671401,"score_spread":0.06843047170023298,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2213186415","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9545874,0.00044503427,0.0074283583,0.02902896,0.0018674957,0.0009886051,0.000011602066,0.00005377085,0.005588744],"genre_scores_gemma":[0.969075,0.00011756914,0.00038213623,0.00017021755,0.00071833807,0.000034627938,0.000005071208,0.00002502097,0.029471984],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9941644,0.0005701707,0.00095559005,0.000566029,0.0027422153,0.0010016044],"domain_scores_gemma":[0.9955686,0.0024090447,0.0004456119,0.00015333423,0.0012448211,0.00017863509],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.017957142,0.00018027781,0.00023568505,0.0012387875,0.0007656096,0.0008866138,0.0006648276,0.00011656034,0.00036015135],"category_scores_gemma":[0.011664542,0.0001584192,0.00009274712,0.000713196,0.00008467939,0.00083012175,0.000114859475,0.0024530587,0.00011022969],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002538161,0.0013374279,0.2961148,0.000060151993,0.00026696973,0.00004373999,0.035644606,0.27020782,0.036441926,0.011135447,0.006060556,0.34014836],"study_design_scores_gemma":[0.006912177,0.0069557023,0.01777416,0.0003361553,0.000026857866,0.00038121178,0.060543053,0.59568614,0.0014415813,0.011267793,0.29792497,0.0007501813],"about_ca_topic_score_codex":0.000030289666,"about_ca_topic_score_gemma":0.00047809296,"teacher_disagreement_score":0.33939818,"about_ca_system_score_codex":0.0014309315,"about_ca_system_score_gemma":0.0003913269,"threshold_uncertainty_score":0.9998483},"labels":[],"label_agreement":null},{"id":"W2213900741","doi":"","title":"Community Outreach: Bringing Parliament to Life","year":2015,"lang":"en","type":"article","venue":"Canadian parliamentary review","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Outreach; Parliament; Legislature; Queen (butterfly); Government (linguistics); Public administration; Political science; Public relations; Politics; Law","score_opus":0.4812346742979844,"score_gpt":0.4936847717709378,"score_spread":0.012450097472953392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2213900741","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29254374,0.11287384,0.0010164309,0.3324025,0.0044662813,0.006098846,0.0003656886,0.00024116733,0.24999152],"genre_scores_gemma":[0.74596775,0.0030452642,0.0013539508,0.24511224,0.0002115811,0.00018936678,0.00009311574,0.00003285077,0.0039938786],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99602103,0.00086348265,0.0008722396,0.00034454354,0.0013904384,0.00050825917],"domain_scores_gemma":[0.9952055,0.00018767113,0.00017660593,0.0012090387,0.00036131206,0.0028598255],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.009556695,0.00021666897,0.00049881294,0.00032285374,0.00031253515,0.000218967,0.0010892731,0.000040015944,0.0050504287],"category_scores_gemma":[0.0016814475,0.00017701021,0.00012397068,0.0009324833,0.00004341762,0.00036602086,0.00014184734,0.00029868443,0.006548959],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037119112,0.000027726473,0.018199159,0.00005629358,0.000019441819,0.0000069248167,0.0007282966,0.000081433995,0.000001748007,0.00010877109,0.84064114,0.14012536],"study_design_scores_gemma":[0.00024145553,0.00009959103,0.0076831263,0.00062837097,0.000031539996,0.000008055175,0.0027802559,0.0001887893,0.0000066405455,0.0003671288,0.98772573,0.00023928717],"about_ca_topic_score_codex":0.13346104,"about_ca_topic_score_gemma":0.37962076,"teacher_disagreement_score":0.453424,"about_ca_system_score_codex":0.0008552437,"about_ca_system_score_gemma":0.002027829,"threshold_uncertainty_score":0.9958591},"labels":[],"label_agreement":null},{"id":"W2219533472","doi":"10.1007/978-94-010-0309-4_42","title":"Evaluating Educational Programs and Projects in Canada","year":2003,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Ministry of Natural Resources and Wildlife","funders":"","keywords":"Accountability; Political science; Quality (philosophy); Public administration; Business; Public relations","score_opus":0.4341678597181165,"score_gpt":0.5194907161613748,"score_spread":0.08532285644325827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2219533472","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00540415,0.00021863526,0.00001554596,0.0030970336,0.00041599685,0.00063066196,0.0000035089581,0.0000052964233,0.99020916],"genre_scores_gemma":[0.041161243,0.00004162772,0.002316579,0.0014508844,0.000072093375,0.000057393692,0.000029662266,0.000015747604,0.9548548],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99635583,0.000063226405,0.0006466721,0.00045203834,0.0023109245,0.00017129771],"domain_scores_gemma":[0.99853015,0.00045898053,0.00026308186,0.00029377005,0.00036740996,0.000086612985],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002674531,0.00017302237,0.00025068104,0.0002062164,0.00006849234,0.00013720758,0.00020951768,0.000076684366,0.009523689],"category_scores_gemma":[0.00032782913,0.00012615969,0.000029574017,0.00009821213,0.000034857752,0.00013195918,0.000049676044,0.00019908183,0.00009078988],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012056384,0.000028890183,0.043953456,0.000019285915,0.00002015155,0.0000038469793,0.00032760145,0.00009340549,0.0000020238758,0.16692184,0.030545887,0.75807154],"study_design_scores_gemma":[0.0009939845,0.00027733194,0.022279153,0.0002855832,0.000030648804,0.000040003197,0.0012383168,0.019640299,0.000006478941,0.22845055,0.72579736,0.00096029544],"about_ca_topic_score_codex":0.14816922,"about_ca_topic_score_gemma":0.9474893,"teacher_disagreement_score":0.7993201,"about_ca_system_score_codex":0.0004554349,"about_ca_system_score_gemma":0.009406585,"threshold_uncertainty_score":0.99620914},"labels":[],"label_agreement":null},{"id":"W2222471891","doi":"10.71781/5463","title":"Évaluation du programme de D.E.S.S. en administration scolaire par l'Université de Montréal en partenariat avec la Commission scolaire de Montréal","year":2008,"lang":"fr","type":"dissertation","venue":"Open MIND","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Art","score_opus":0.09655947475745129,"score_gpt":0.3818462884502619,"score_spread":0.2852868136928106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2222471891","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9558587,0.0006987153,0.0017353593,0.007871981,0.00051024667,0.0024415406,0.00006747693,0.00001603682,0.030799927],"genre_scores_gemma":[0.9262079,0.0014808627,0.027047401,0.000119948985,0.00030129845,0.00023975613,0.0011400996,0.000059884645,0.04340286],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99126124,0.0031192324,0.0013291204,0.001070112,0.0022327143,0.0009875565],"domain_scores_gemma":[0.9955205,0.0012204223,0.0010977116,0.00072637876,0.00070509006,0.0007299304],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.010863966,0.00064603117,0.00074227474,0.00035838774,0.002274036,0.0010887522,0.001496529,0.0010523332,0.005182796],"category_scores_gemma":[0.0013627437,0.00062051794,0.00030699847,0.0007402599,0.00015975862,0.0014254979,0.00033616647,0.0007229577,0.0009771901],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018133622,0.0009892251,0.062218994,0.000060479615,0.00015248104,0.00039706944,0.18234015,0.0078390585,0.0020276068,0.00026758792,0.00638595,0.735508],"study_design_scores_gemma":[0.0034439417,0.0010380247,0.44300818,0.00071753043,0.00042097864,0.0005620992,0.036399603,0.26478824,0.00617704,0.000429552,0.24203515,0.0009796623],"about_ca_topic_score_codex":0.0050355447,"about_ca_topic_score_gemma":0.068601765,"teacher_disagreement_score":0.73452836,"about_ca_system_score_codex":0.0027724705,"about_ca_system_score_gemma":0.010171987,"threshold_uncertainty_score":0.9999482},"labels":[],"label_agreement":null},{"id":"W2225238741","doi":"10.1016/j.evalprogplan.2015.12.009","title":"Using RUFDATA to guide a logic model for a quality assurance process in an undergraduate university program","year":2016,"lang":"en","type":"article","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Humber Polytechnic; University of Guelph-Humber","funders":"University of Guelph","keywords":"Logic model; Quality assurance; Process (computing); Engineering management; Engineering; Computer science; Engineering ethics; Medical education; Process management; Political science; Medicine; Operations management; Public administration; Programming language","score_opus":0.6424714629299201,"score_gpt":0.6461729343400731,"score_spread":0.003701471410152979,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2225238741","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7562194,0.000041555344,0.23730692,0.0027881816,0.000077023025,0.0027400693,0.000034399447,0.00010179806,0.000690655],"genre_scores_gemma":[0.9036437,0.000005338311,0.095596,0.00020816653,0.000027093509,0.00016043513,0.00002817227,0.000008297944,0.00032279085],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99672896,0.0005193507,0.0005492353,0.00060780754,0.0012873844,0.00030728176],"domain_scores_gemma":[0.9977599,0.0004889175,0.0002642426,0.00034041874,0.0009845528,0.00016201183],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01156704,0.00014908065,0.00023350414,0.00028714412,0.00024026891,0.00024770212,0.0003403508,0.00007383084,0.000042552554],"category_scores_gemma":[0.0017798282,0.00010434244,0.00004126956,0.0006807561,0.000053254047,0.0010425601,0.000060420425,0.000068041125,0.000009328571],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002336993,0.00020804728,0.081873074,0.000021120402,0.000008912376,8.7415503e-7,0.002223816,0.0617785,0.00030931164,0.0012260106,0.0002615771,0.85185504],"study_design_scores_gemma":[0.0014358443,0.0002831522,0.039397188,0.00011087025,0.000017330296,0.0000014740267,0.0012754404,0.93891776,0.000027560347,0.015225595,0.0031084672,0.00019931512],"about_ca_topic_score_codex":0.00001732268,"about_ca_topic_score_gemma":0.00031286455,"teacher_disagreement_score":0.8771393,"about_ca_system_score_codex":0.00015439179,"about_ca_system_score_gemma":0.0005749469,"threshold_uncertainty_score":0.42549613},"labels":[],"label_agreement":null},{"id":"W2225785994","doi":"10.9707/1944-5660.1263","title":"A Foundation's Theory of Philanthropy: What It Is, What It Provides, How to Do It","year":2015,"lang":"en","type":"article","venue":"The Foundation Review","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Foundation (evidence); Engineering ethics; Epistemology; Knowledge management; Sociology; Political science; Management science; Public relations; Computer science; Engineering; Law","score_opus":0.3473055639022479,"score_gpt":0.5099689853978989,"score_spread":0.162663421495651,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2225785994","genre_codex":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014711414,0.037007608,0.015273285,0.9310138,0.0022538227,0.0031238599,0.0000069559915,0.00004730093,0.0098022055],"genre_scores_gemma":[0.17913672,0.50649565,0.0028185172,0.27010348,0.00079668005,0.0007540261,0.0002115579,0.00007593729,0.039607424],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9944021,0.0011611624,0.0010623244,0.00048008925,0.0026458306,0.00024851254],"domain_scores_gemma":[0.9948465,0.0010269091,0.00085251086,0.0013278682,0.0017660764,0.00018010387],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.019959118,0.00022810794,0.0005235313,0.00017479865,0.00025085246,0.002249213,0.0010922891,0.000055797802,0.0146615],"category_scores_gemma":[0.0034921875,0.00013273788,0.00016749093,0.0012546632,0.00018823365,0.0048599676,0.00019896466,0.00014543485,0.00686423],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003438437,0.000053225776,0.000085708205,0.0001660193,0.000029689603,3.2981623e-7,0.003262209,0.000031348085,0.000015566386,0.0065973788,0.30177003,0.6879541],"study_design_scores_gemma":[0.00028911175,0.00012734064,0.00014537544,0.0024675382,0.0000712056,0.0000067050887,0.010266775,0.00036766098,0.00006341245,0.016946219,0.96906996,0.0001787225],"about_ca_topic_score_codex":0.000009060642,"about_ca_topic_score_gemma":0.00006770807,"teacher_disagreement_score":0.6877754,"about_ca_system_score_codex":0.00013735877,"about_ca_system_score_gemma":0.0007000951,"threshold_uncertainty_score":0.99878657},"labels":[],"label_agreement":null},{"id":"W2227730406","doi":"10.3109/0142159x.2015.1087484","title":"The role of theory-based outcome frameworks in program evaluation: Considering the case of contribution analysis","year":2015,"lang":"en","type":"article","venue":"Medical Teacher","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Outcome (game theory); Psychology; Computer science; Mathematics; Mathematical economics","score_opus":0.21472014778124793,"score_gpt":0.5443165349106759,"score_spread":0.32959638712942796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2227730406","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9810455,0.00059692096,0.008455996,0.006043799,0.0001484184,0.0007205802,0.0000019545723,0.000013405665,0.002973414],"genre_scores_gemma":[0.99941957,0.000002225662,0.00019506196,0.00014792419,0.000030881336,0.00011930273,0.0000038264648,0.0000026965517,0.000078502715],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9942154,0.0019720944,0.0008759736,0.00016455774,0.0026205352,0.00015142972],"domain_scores_gemma":[0.99594045,0.0023253118,0.00033251208,0.00049159914,0.00080672157,0.00010340995],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05663068,0.000073872194,0.00026197283,0.00013007989,0.000083368766,0.000049963877,0.00037475178,0.00015524897,0.002846848],"category_scores_gemma":[0.02804315,0.000032855307,0.00012543412,0.0011770795,0.00034088988,0.00006826364,0.00005549887,0.00039999737,0.000013049299],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006305644,0.00017337414,0.47339034,0.0000012679969,0.00008272549,0.0000073981214,0.0011666226,0.0027917973,0.0000016824686,0.0091551095,0.000116845855,0.5130498],"study_design_scores_gemma":[0.0007568841,0.00007460446,0.0162846,0.000010316398,0.00013337912,0.000005159745,0.005560672,0.9377054,0.000042158677,0.034809116,0.004568653,0.000049049326],"about_ca_topic_score_codex":0.00007535066,"about_ca_topic_score_gemma":0.0008775194,"teacher_disagreement_score":0.93491364,"about_ca_system_score_codex":0.000059935555,"about_ca_system_score_gemma":0.0004919486,"threshold_uncertainty_score":0.9980647},"labels":[],"label_agreement":null},{"id":"W2228177330","doi":"10.3138/cjpe.026.003","title":"Addressing the Challenges Encountered During a Developmental Evaluation: Implications for Evaluation Practice","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Perspective (graphical); Evaluation methods; Program evaluation; Psychology; Government (linguistics); Engineering ethics; Knowledge management; Process management; Medical education; Management science; Political science; Computer science; Business; Medicine; Engineering; Public administration","score_opus":0.8348360624185777,"score_gpt":0.6002670065070299,"score_spread":0.23456905591154775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2228177330","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8328425,0.015467816,0.005574405,0.046295,0.004659841,0.023487747,0.000066616216,0.000063225256,0.07154284],"genre_scores_gemma":[0.98532134,0.00005337842,0.012378754,0.0002323169,0.0003143947,0.0016196299,0.000023535958,0.000018755507,0.000037895737],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99243385,0.0017875788,0.0013927822,0.00037010774,0.0036244453,0.00039125432],"domain_scores_gemma":[0.98062533,0.00083184626,0.0015864918,0.00045611136,0.016162869,0.00033735702],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.061053388,0.00019341332,0.0002478096,0.0006278952,0.0010461098,0.00050167553,0.0007829093,0.000110286455,0.0021435986],"category_scores_gemma":[0.017702868,0.00013675487,0.00017337895,0.0007156166,0.00013359869,0.0018067055,0.000024101611,0.0002284314,0.00004619433],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007216813,0.00008925286,0.002636459,0.000008188193,0.00009501636,6.3052306e-7,0.011882577,0.0006519701,0.00008240125,0.0012469675,0.0010259817,0.9822084],"study_design_scores_gemma":[0.0069380994,0.00085799024,0.7095754,0.00023140627,0.0016113883,0.000524817,0.047645543,0.11636415,0.00054125645,0.07073297,0.04440452,0.0005724671],"about_ca_topic_score_codex":0.0001932257,"about_ca_topic_score_gemma":0.011398829,"teacher_disagreement_score":0.9816359,"about_ca_system_score_codex":0.0015351374,"about_ca_system_score_gemma":0.013701034,"threshold_uncertainty_score":0.99876857},"labels":[],"label_agreement":null},{"id":"W2228904298","doi":"10.1155/2015/364608","title":"From Strategy to Implementation… Continuity and Change","year":2015,"lang":"en","type":"article","venue":"Canadian Respiratory Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Thoracic Society","funders":"","keywords":"Medicine; Process management; Operations management","score_opus":0.4679356813516402,"score_gpt":0.5229931326209236,"score_spread":0.05505745126928341,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2228904298","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99168026,0.0002935104,0.00016035723,0.0033834241,0.0005534752,0.00017467361,0.00007836793,0.00000562486,0.003670278],"genre_scores_gemma":[0.98947674,0.0000033379945,0.00017895414,0.009207562,0.0009111429,0.000010416124,0.0000025731101,0.000005839256,0.00020345507],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99808556,0.00021765847,0.00040523882,0.00019149807,0.00084484206,0.0002552312],"domain_scores_gemma":[0.9972182,0.0000781029,0.00013607315,0.00019329695,0.0005628604,0.00181147],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003663896,0.000084777144,0.00013497371,0.00039039875,0.00020826292,0.0006264704,0.0002805437,0.000040666826,0.0031223882],"category_scores_gemma":[0.00030426896,0.00006798158,0.000027103453,0.00028293676,0.000028478453,0.0005368072,0.000026983127,0.00014402496,0.00038503468],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013229964,0.0000039673455,0.22405465,3.8772208e-7,0.000012417698,0.000043764365,0.0057843756,0.000028363902,0.00007727724,0.0005931469,0.10762793,0.6617605],"study_design_scores_gemma":[0.00056049315,0.00018030449,0.35401163,0.000004684466,0.000004795645,0.000011852118,0.008515116,0.000058332535,0.000047498157,0.0048973635,0.6316033,0.000104597304],"about_ca_topic_score_codex":0.020430436,"about_ca_topic_score_gemma":0.43112153,"teacher_disagreement_score":0.6616559,"about_ca_system_score_codex":0.00024947696,"about_ca_system_score_gemma":0.0020550755,"threshold_uncertainty_score":0.9977889},"labels":[],"label_agreement":null},{"id":"W2229760209","doi":"10.71781/23611","title":"Intervention policière en milieu scolaire : expérience et point de vue des acteurs","year":2010,"lang":"fr","type":"dissertation","venue":"Open MIND","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Texas Education Agency; U.S. Department of Justice; U.S. Department of Health and Human Services","keywords":"Humanities; Political science; Art","score_opus":0.10725059996615875,"score_gpt":0.5057080775685415,"score_spread":0.39845747760238276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2229760209","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.941026,0.00022776904,0.00072651607,0.0015531945,0.0018541674,0.0010613115,0.00008905194,0.0000036598285,0.053458367],"genre_scores_gemma":[0.91273695,0.00024564145,0.018475447,0.00030236586,0.00016850654,0.00016162789,0.0005932628,0.000037517202,0.06727865],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9948427,0.0010017894,0.0012473457,0.00093008054,0.0014150323,0.0005630659],"domain_scores_gemma":[0.9966518,0.0006530887,0.00086861633,0.00078232225,0.0007172372,0.00032691954],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.009000893,0.00043861978,0.0005363065,0.00036571082,0.00059170637,0.0019725587,0.0024963235,0.00056685455,0.06063386],"category_scores_gemma":[0.0016210503,0.00039101677,0.00029135516,0.0007364613,0.00023854623,0.002584421,0.0004015333,0.0009257208,0.004589004],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015331653,0.00030236185,0.0067770043,0.00004235255,0.000029791672,0.000010366373,0.19370104,0.00020098967,0.0047605727,0.000282936,0.00040923746,0.79333],"study_design_scores_gemma":[0.0024641776,0.0012299865,0.31196266,0.003242353,0.00023940296,0.00011742485,0.46066138,0.014561319,0.050323427,0.010866325,0.1428188,0.0015127425],"about_ca_topic_score_codex":0.004610525,"about_ca_topic_score_gemma":0.12066085,"teacher_disagreement_score":0.7918173,"about_ca_system_score_codex":0.00028617872,"about_ca_system_score_gemma":0.001922148,"threshold_uncertainty_score":0.99985415},"labels":[],"label_agreement":null},{"id":"W2229768344","doi":"10.4225/03/58b3a1921c185","title":"Professionalisation of evaluation in Australia","year":2017,"lang":"en","type":"article","venue":"Figshare","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Sociology; Epistemology; Sociological theory; Social science; Symbolic interactionism; Social theory","score_opus":0.7519328361059234,"score_gpt":0.6403048776816878,"score_spread":0.11162795842423567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2229768344","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9302397,0.000036792142,0.0000050641256,0.001749088,0.00048764306,0.0010441737,0.019616917,0.000013733256,0.046806887],"genre_scores_gemma":[0.99412113,2.1658366e-7,0.00007503734,0.000029813127,0.000035097382,0.00009456853,0.0039979485,0.0000020080452,0.0016441825],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9978261,0.00013431716,0.00033460424,0.00014909236,0.0014803602,0.00007550522],"domain_scores_gemma":[0.9982391,0.00018788,0.00043634686,0.00049404876,0.0006182769,0.00002432414],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0021653716,0.00004520882,0.00009242756,0.00011137165,0.000101638914,0.000101687256,0.00035552186,0.000044789114,0.48348147],"category_scores_gemma":[0.011288088,0.000033280987,0.000030764597,0.000104274775,0.0000071512222,0.0005927569,0.0000725463,0.00005789915,0.0023392574],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004067081,0.00015171601,0.15145199,0.00005821257,0.000008341669,0.0000023779946,0.0027418225,0.0024854494,0.00054545334,0.00063878973,0.7069424,0.13493277],"study_design_scores_gemma":[0.00033875462,0.0000147643395,0.96162575,0.00029997856,0.0000015595604,3.0916476e-7,0.00015227927,0.022469727,0.00076663756,0.0047512786,0.009530651,0.000048281618],"about_ca_topic_score_codex":0.000015442007,"about_ca_topic_score_gemma":0.00016125798,"teacher_disagreement_score":0.8101738,"about_ca_system_score_codex":0.000035094054,"about_ca_system_score_gemma":0.00018770318,"threshold_uncertainty_score":0.9984375},"labels":[],"label_agreement":null},{"id":"W2239915461","doi":"10.1007/978-1-4614-0745-4_7","title":"The Evolution of Police Training: The Investigative Skill Education Program","year":2011,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Police Service","funders":"","keywords":"Training (meteorology); Professional development; Public relations; Political science; Medical education; Psychology; Pedagogy; Medicine","score_opus":0.3356975880300975,"score_gpt":0.4820442465974863,"score_spread":0.14634665856738877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2239915461","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00048282777,0.00023751841,0.00015521719,0.0024199036,0.00059104164,0.0010873653,0.000006394415,0.000029316156,0.9949904],"genre_scores_gemma":[0.14014803,0.000093655304,0.0006463373,0.00041549778,0.00020996243,0.00015877117,0.000009137868,0.000015102053,0.8583035],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99716735,0.00013087076,0.0007468129,0.00028809614,0.0015097511,0.00015714465],"domain_scores_gemma":[0.99631643,0.00085104146,0.0008712146,0.0007741054,0.0011126618,0.000074529424],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0035905046,0.00018235183,0.00021717182,0.0001554012,0.0003191275,0.00012694321,0.0008899677,0.00014140637,0.0018035693],"category_scores_gemma":[0.00039969306,0.000077604454,0.00014934682,0.00015739695,0.00074421504,0.000185587,0.00008742554,0.0002535053,0.0004013851],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000047411945,0.000018586934,0.000047507194,0.0000016217851,0.000017980128,8.949272e-9,0.0067731333,0.0000020788623,0.0000024748308,0.6733938,0.0108078495,0.30893022],"study_design_scores_gemma":[0.000053934677,0.000114003575,0.0023761857,0.000033129887,0.000023904811,0.0000015875929,0.007904945,0.00019106927,0.000023404225,0.47693807,0.51224303,0.0000967316],"about_ca_topic_score_codex":0.0003887457,"about_ca_topic_score_gemma":0.0014153292,"teacher_disagreement_score":0.5014352,"about_ca_system_score_codex":0.00012999233,"about_ca_system_score_gemma":0.0025286651,"threshold_uncertainty_score":0.9991089},"labels":[],"label_agreement":null},{"id":"W2242765967","doi":"","title":"Action Research Helps Citizens Prepare Madison County, Florida Vision 2020","year":2011,"lang":"en","type":"article","venue":"Journal of rural and community development","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Participatory action research; Action research; Citizen journalism; Action plan; Government (linguistics); Action (physics); Participatory evaluation; Public administration; Data collection; Sociology; Political science; Public relations; Management; Social science; Pedagogy; Law","score_opus":0.4601214414688607,"score_gpt":0.5236570968421267,"score_spread":0.063535655373266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2242765967","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9924245,0.00015482186,0.00023354057,0.0007814936,0.0004303265,0.00010087964,0.0000018468506,0.0000069552607,0.0058656274],"genre_scores_gemma":[0.99661034,0.00043902703,0.0016474437,0.000115256495,0.00007207915,0.0000038585467,0.0000032240737,0.0000048980637,0.0011038568],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99549043,0.0013765682,0.00079256773,0.000076773,0.0020554075,0.00020825984],"domain_scores_gemma":[0.9971424,0.000602727,0.0003703554,0.00028902886,0.0014232778,0.00017223321],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01638665,0.000105577936,0.00022901197,0.00028632255,0.0010682555,0.00019823469,0.0006132496,0.00006126865,0.0010168317],"category_scores_gemma":[0.00043412863,0.00006860823,0.000055987417,0.00043721427,0.00009557032,0.00063342287,0.00030546112,0.0007939427,0.00006514042],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00069195055,0.0004845466,0.05606143,0.000036159756,0.000080050886,0.000012249623,0.062928215,0.00002004198,0.0010199574,0.00024965854,0.041097574,0.8373182],"study_design_scores_gemma":[0.00078347715,0.000908008,0.8214588,0.00020526243,0.00001078796,0.00015468165,0.096928604,0.00023065957,0.0027461625,0.009770172,0.06661882,0.00018454588],"about_ca_topic_score_codex":0.000071941664,"about_ca_topic_score_gemma":0.00034942612,"teacher_disagreement_score":0.8371336,"about_ca_system_score_codex":0.000157978,"about_ca_system_score_gemma":0.00039922824,"threshold_uncertainty_score":0.99989635},"labels":[],"label_agreement":null},{"id":"W2244140197","doi":"","title":"Building coalitions, collaborating, and managing conflict in the policy arena.","year":2000,"lang":"en","type":"article","venue":"Canadian home economics journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Public relations; Political science; Public administration; Business; Economic growth; Management science; Sociology; Economics","score_opus":0.09602982302959324,"score_gpt":0.415674185292248,"score_spread":0.31964436226265475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2244140197","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9425009,0.00026374764,0.000032932698,0.032262765,0.0001580916,0.00010075806,0.000030749117,0.0000028469224,0.02464721],"genre_scores_gemma":[0.9922781,0.0009811734,0.000418748,0.005196152,0.00036479457,0.000005277757,0.0000021557537,0.0000063976554,0.00074718357],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987055,0.00016635613,0.0004930752,0.00016366196,0.00018286724,0.0002885133],"domain_scores_gemma":[0.9990387,0.0002391976,0.0001355614,0.00020160025,0.00008353068,0.0003014326],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0039537363,0.0000852931,0.00014458408,0.00067668624,0.00047413836,0.0012605306,0.00041830417,0.00003837508,0.0023268417],"category_scores_gemma":[0.00016414632,0.0000652166,0.000031939086,0.00044791447,0.000060210732,0.0004615179,0.000010461698,0.00022343642,0.000093694034],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021962453,0.00001792906,0.13825504,0.0000047487874,0.00003640957,0.000066611196,0.009726758,0.021213872,0.000008364216,0.16717394,0.035148762,0.62832564],"study_design_scores_gemma":[0.0005354435,0.0000320379,0.10456092,0.000017573879,0.0000042570823,0.00029414878,0.00359441,0.0136044435,0.0000025729807,0.05195072,0.8252422,0.00016124749],"about_ca_topic_score_codex":0.0057561905,"about_ca_topic_score_gemma":0.11013968,"teacher_disagreement_score":0.7900935,"about_ca_system_score_codex":0.0003721319,"about_ca_system_score_gemma":0.0016137433,"threshold_uncertainty_score":0.99977624},"labels":[],"label_agreement":null},{"id":"W2246384248","doi":"","title":"The Next Generation of Basic Education Accountability in Alberta, Canada: A Policy Dialogue, 5(19)","year":2001,"lang":"en","type":"article","venue":"IEJLL: International Electronic Journal for Leadership in Learning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Accountability; Government (linguistics); Public relations; Public administration; Political science; Statutory law; Extant taxon; Action (physics); Process (computing); Law; Computer science","score_opus":0.3604317537126912,"score_gpt":0.469113102309753,"score_spread":0.1086813485970618,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2246384248","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9252432,0.00063821784,0.0017401227,0.06669378,0.0021851077,0.0003789867,0.0000020387286,0.00000544738,0.0031130859],"genre_scores_gemma":[0.99249125,0.00030924514,0.00004053527,0.0007705158,0.00066190254,0.000046685487,0.000018182798,0.000010412906,0.0056512672],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99648094,0.000452211,0.0009890317,0.00025351177,0.0012882077,0.0005361039],"domain_scores_gemma":[0.99636525,0.0021792802,0.00056661805,0.00017093316,0.0006475634,0.00007036786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007925907,0.00012694363,0.00018562617,0.00049279036,0.00027483475,0.0002565144,0.00067321706,0.000064925654,0.00020505262],"category_scores_gemma":[0.008257232,0.00009506229,0.0000954718,0.0007082119,0.000056449888,0.0006926862,0.000026160977,0.00075129454,0.00000803657],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007812885,0.00034722357,0.5072291,0.000018374234,0.00009096753,0.0000021720377,0.006649821,0.11018071,0.0012327598,0.11023255,0.00482343,0.25841162],"study_design_scores_gemma":[0.0032292942,0.00047937362,0.16171668,0.00017932738,0.00002072302,0.0002337852,0.046834692,0.21728681,0.00045334065,0.067459665,0.50156087,0.0005454245],"about_ca_topic_score_codex":0.16217567,"about_ca_topic_score_gemma":0.89380395,"teacher_disagreement_score":0.7316283,"about_ca_system_score_codex":0.0025984866,"about_ca_system_score_gemma":0.010578076,"threshold_uncertainty_score":0.995031},"labels":[],"label_agreement":null},{"id":"W2253092986","doi":"10.1177/1098214015615230","title":"Introducing Evidence-Based Principles to Guide Collaborative Approaches to Evaluation","year":2015,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":92,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Carleton University; Queen's University","funders":"","keywords":"Variety (cybernetics); Set (abstract data type); Context (archaeology); Computer science; Management science; Knowledge management; Psychology; Data science; Engineering; Artificial intelligence","score_opus":0.7348226152021603,"score_gpt":0.5424577550404095,"score_spread":0.1923648601617508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2253092986","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8650076,0.0003391762,0.0882647,0.040641308,0.0009562429,0.0015117911,0.000004499857,0.000013522587,0.0032611636],"genre_scores_gemma":[0.9325728,0.0000070909223,0.065023445,0.001676617,0.000465706,0.000093213544,0.0000046557716,0.0000130273775,0.00014345403],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98455256,0.0032861084,0.0016761733,0.0004574558,0.009769458,0.0002582335],"domain_scores_gemma":[0.9818253,0.0014139055,0.0017572227,0.00060114166,0.013891285,0.0005111447],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09005673,0.00018905998,0.00047942105,0.0010615874,0.00013032948,0.0003426085,0.00057880464,0.000034292363,0.000530261],"category_scores_gemma":[0.055608306,0.00013941419,0.00010441913,0.0035294641,0.000089748515,0.0012254459,0.00007743132,0.0001580605,0.00029790687],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027098923,0.000050352206,0.005213894,0.00000105605,0.000020652811,5.1653024e-7,0.0047440515,0.5909342,0.0003893224,0.00013705666,0.0059569688,0.3922809],"study_design_scores_gemma":[0.0023764346,0.0063497913,0.066634975,0.0003442035,0.0003282595,0.000022335802,0.03759166,0.84164125,0.0040908605,0.0033573965,0.036771405,0.00049144577],"about_ca_topic_score_codex":0.00003400631,"about_ca_topic_score_gemma":0.00008961079,"teacher_disagreement_score":0.39178947,"about_ca_system_score_codex":0.0013159086,"about_ca_system_score_gemma":0.0073426478,"threshold_uncertainty_score":0.9982848},"labels":[],"label_agreement":null},{"id":"W2253987632","doi":"","title":"Integrating developmental evaluation within organizational culture","year":2011,"lang":"en","type":"article","venue":"Global Learn","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Organizational culture; Psychology; Knowledge management; Computer science; Public relations; Political science","score_opus":0.21097601412019795,"score_gpt":0.4513598460243382,"score_spread":0.24038383190414025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2253987632","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35113853,0.000050235296,0.005802108,0.00026015926,0.00069593656,0.0002669344,0.000012119422,0.00006344284,0.6417105],"genre_scores_gemma":[0.97080487,0.0000017816112,0.024917644,0.00050087646,0.000060509665,0.0000097507145,0.00003442613,0.00000416877,0.0036659609],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99694186,0.00020771007,0.0004344981,0.0002801116,0.0019966436,0.00013916068],"domain_scores_gemma":[0.9985584,0.000035796715,0.00018649251,0.0001511897,0.0009948214,0.00007330912],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0032950693,0.000101885555,0.00010561043,0.000049492035,0.00019882766,0.00012776759,0.00033125118,0.000062589024,0.017547306],"category_scores_gemma":[0.0019370527,0.000070070724,0.00003441517,0.0008282233,0.00004018656,0.00038825363,0.00007564833,0.00009902673,0.0032863168],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004824918,0.00013800983,0.6997493,0.0000028368158,0.000039079165,0.000002644324,0.01503764,0.00044669094,0.0003979071,0.08796156,0.02238911,0.173787],"study_design_scores_gemma":[0.0016155776,0.00023921508,0.68363667,0.000043042095,0.000051615632,0.00008098831,0.037191924,0.056016065,0.0018125064,0.16829553,0.050381027,0.00063583755],"about_ca_topic_score_codex":0.00003518486,"about_ca_topic_score_gemma":0.00017038424,"teacher_disagreement_score":0.6380446,"about_ca_system_score_codex":0.0002677004,"about_ca_system_score_gemma":0.00069613336,"threshold_uncertainty_score":0.99748975},"labels":[],"label_agreement":null},{"id":"W2256589417","doi":"","title":"Moving Beyond Evaluation to Transit Project Prioritization: Lessons from the Toronto Context","year":2016,"lang":"en","type":"article","venue":"Transportation Research Board 95th Annual Meeting","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Prioritization; Transit (satellite); Computer science; Transport engineering; Environmental planning; Engineering; Environmental science; Geography; Process management; Public transport","score_opus":0.25631364537945883,"score_gpt":0.5330162396636754,"score_spread":0.27670259428421656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2256589417","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91776097,0.000479822,0.021328313,0.04757582,0.000540455,0.0029459537,0.00064015563,0.00010835011,0.008620182],"genre_scores_gemma":[0.9957802,0.00008756565,0.0013790387,0.00078883325,0.00034209446,0.00035921074,0.000064437496,0.000024676783,0.0011739172],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98893744,0.001705661,0.0010596402,0.000806932,0.00682524,0.0006651092],"domain_scores_gemma":[0.9903141,0.004259494,0.00021865878,0.00065863796,0.0043194275,0.0002296525],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.021171834,0.00020655562,0.00028188204,0.000213526,0.00093713676,0.0003761402,0.00086196,0.00010999364,0.0027834044],"category_scores_gemma":[0.0034753515,0.000117535215,0.00012340478,0.0011228056,0.00014797664,0.0018636988,0.000028396815,0.00022912154,0.00033997896],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037982134,0.000092069495,0.0378991,0.000011036974,0.000051604526,0.0000043603254,0.053576812,0.00093407225,0.0063046957,0.0070500653,0.020887723,0.87280864],"study_design_scores_gemma":[0.002969663,0.00045817712,0.74963355,0.0004326922,0.000070784095,4.917292e-7,0.11802752,0.0057178363,0.0025985339,0.008059663,0.11147697,0.0005540887],"about_ca_topic_score_codex":0.0077057043,"about_ca_topic_score_gemma":0.0859826,"teacher_disagreement_score":0.87225455,"about_ca_system_score_codex":0.0003453987,"about_ca_system_score_gemma":0.000994353,"threshold_uncertainty_score":0.9989021},"labels":[],"label_agreement":null},{"id":"W2258168508","doi":"","title":"Updated New Brunswick Visit Program","year":2019,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"History; Computer science","score_opus":0.13879351472631576,"score_gpt":0.4965934052942549,"score_spread":0.35779989056793915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2258168508","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5841471,0.000017494463,0.0011526037,0.004480576,0.000489211,0.00047333166,3.4213795e-7,0.00014993951,0.40908942],"genre_scores_gemma":[0.7081847,0.0000035008748,0.0053495057,0.0015058308,0.000059063696,0.0000024646072,0.0000075521034,0.0000048338215,0.28488255],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99784976,0.000056638775,0.00035033,0.0002782766,0.0012902103,0.00017476655],"domain_scores_gemma":[0.9989726,0.00011497221,0.00009122551,0.000494634,0.00020169756,0.000124849],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0014356732,0.00007732165,0.0001338825,0.000115200266,0.000043623975,0.00028048907,0.00041669217,0.000042094594,0.102544606],"category_scores_gemma":[0.00008748718,0.00004769233,0.000057742054,0.000608949,0.000013130495,0.00040780488,0.00006618709,0.00007184416,0.04633967],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017575017,0.0000793746,0.20114729,0.0000011006574,0.00000954733,5.302417e-7,0.00018764765,0.00023559699,0.00016050851,0.020170212,0.2124043,0.5655863],"study_design_scores_gemma":[0.00047090615,0.0001567985,0.14581393,0.0000025381516,0.0000026395262,0.0000016852217,0.0002453216,0.021126663,0.0003305714,0.0032332994,0.8285124,0.00010331567],"about_ca_topic_score_codex":0.00017260875,"about_ca_topic_score_gemma":0.00031395393,"teacher_disagreement_score":0.61610806,"about_ca_system_score_codex":0.000019283492,"about_ca_system_score_gemma":0.0006521398,"threshold_uncertainty_score":0.95440286},"labels":[],"label_agreement":null},{"id":"W2258454397","doi":"10.3917/rfap.155.0723","title":"Les enjeux liés aux activités d’audit, de conseil et d’évaluation dans les administrations publiques : une perspective canadienne","year":2015,"lang":"fr","type":"article","venue":"Revue française d administration publique","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université Laval; École Nationale d'Administration Publique; Université du Québec à Montréal","funders":"","keywords":"Political science; Humanities; Valuation (finance); Philosophy; Business","score_opus":0.24748292347591686,"score_gpt":0.4821835730986958,"score_spread":0.23470064962277895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2258454397","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1832103,0.0015643528,0.023851233,0.7212427,0.0018694407,0.0012573209,0.00054854783,0.00022444376,0.066231646],"genre_scores_gemma":[0.9679234,0.00042554704,0.0049507404,0.0018207289,0.0008606037,0.0004071857,0.0005225116,0.00007847289,0.023010798],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99080545,0.0030421116,0.0019221038,0.001385911,0.0017336024,0.0011108181],"domain_scores_gemma":[0.98700356,0.0016705812,0.0012353972,0.0011928304,0.0073870006,0.0015106444],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011265369,0.0007531305,0.0008047738,0.00082409807,0.0010389255,0.0020633298,0.0010258795,0.00087037066,0.0033002284],"category_scores_gemma":[0.013280628,0.0007954256,0.0003811467,0.0023508733,0.0007750053,0.0042255027,0.00013531458,0.0011900438,0.0002647291],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020195542,0.0010600411,0.008720111,0.000097072596,0.00014485867,0.00008551855,0.052124772,0.0019467532,0.0005308165,0.88326955,0.026251238,0.025567295],"study_design_scores_gemma":[0.0016391069,0.001719388,0.035715956,0.0003043278,0.00020291607,0.00048470008,0.04979601,0.022966556,0.0015868722,0.02639068,0.8581964,0.0009971043],"about_ca_topic_score_codex":0.34375975,"about_ca_topic_score_gemma":0.69054043,"teacher_disagreement_score":0.8568789,"about_ca_system_score_codex":0.0022531876,"about_ca_system_score_gemma":0.38911182,"threshold_uncertainty_score":0.9994497},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"empirical","about_ca_system":true,"about_ca_topic":true,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":true,"confidence":"high"}],"label_agreement":"split"},{"id":"W2262371495","doi":"10.1162/posc_e_00219","title":"Science, Policy, Values: Exploring the Nexus","year":2016,"lang":"en","type":"article","venue":"Perspectives on Science","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Science policy; Nexus (standard); Value (mathematics); Warrant; Philosophy of science; Political science; Sociology; Public relations; Positive economics; Epistemology; Public administration; Economics; Computer science","score_opus":0.33250062661536767,"score_gpt":0.5334377671102818,"score_spread":0.20093714049491412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2262371495","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7432494,0.000043370044,0.0024322446,0.024408007,0.0010313626,0.00025109507,0.000004593108,0.000071385446,0.2285085],"genre_scores_gemma":[0.9941561,0.00005941599,0.00030892625,0.0006384307,0.00028788898,0.000033928583,2.3616463e-8,0.0000061003147,0.0045091403],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9911166,0.00013217615,0.00038266563,0.0010866531,0.006615369,0.0006665588],"domain_scores_gemma":[0.9952609,0.0013413837,0.00018978203,0.0014376213,0.0015057559,0.0002645853],"candidate_categories":["metaresearch","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["sts"],"category_scores_codex":[0.01808768,0.00015901882,0.00016027596,0.0018891438,0.0021497929,0.0010591376,0.003752683,0.000016385267,0.00055063877],"category_scores_gemma":[0.014023791,0.00006510089,0.00008252662,0.010602166,0.0063251094,0.0035724207,0.00043316907,0.00012634764,0.0018068976],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025254,0.000094718904,0.0025887312,4.5740455e-7,0.0000031956945,0.0000011141169,0.02731061,0.00020837461,0.023983324,0.8035061,0.0005070382,0.14177111],"study_design_scores_gemma":[0.0011339945,0.00093372015,0.5191145,0.000093095274,0.000009409,0.000028122704,0.20411092,0.0068153227,0.02944329,0.2014731,0.036085136,0.0007593704],"about_ca_topic_score_codex":0.000027286109,"about_ca_topic_score_gemma":0.00000735051,"teacher_disagreement_score":0.60203296,"about_ca_system_score_codex":0.0006968308,"about_ca_system_score_gemma":0.0032389865,"threshold_uncertainty_score":0.9999779},"labels":[],"label_agreement":null},{"id":"W2266705734","doi":"10.7202/1034147ar","title":"Soutenir la formation aux pratiques avancées à la maîtrise en travail social","year":2015,"lang":"fr","type":"article","venue":"Canadian social work review","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.21582499731187924,"score_gpt":0.47784118650656443,"score_spread":0.26201618919468517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2266705734","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034700178,0.32982442,0.0005433986,0.31076434,0.0026473345,0.0020837076,0.00029288122,0.00009630161,0.3502776],"genre_scores_gemma":[0.3328163,0.24635094,0.003268016,0.060367547,0.008591352,0.0007570302,0.00057143334,0.00021675999,0.3470606],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99322695,0.0033149393,0.0010981206,0.00038332117,0.0013422306,0.0006344138],"domain_scores_gemma":[0.9970115,0.00054598594,0.00049256097,0.00026363027,0.0008866603,0.00079966465],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.010622758,0.0003209078,0.00071821554,0.0002140037,0.00089083106,0.0005899056,0.0006318037,0.00046628248,0.0054747635],"category_scores_gemma":[0.0015260545,0.00030179825,0.00032020215,0.0018412983,0.00034435713,0.0010913996,0.000054180793,0.00042743306,0.004414505],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037368704,0.000015938298,0.00024091035,0.00021746459,0.00001653313,0.00001016438,0.010094396,8.4304656e-7,2.4557693e-7,0.011392382,0.51332295,0.46468446],"study_design_scores_gemma":[0.0003492481,0.000035450586,0.0020965876,0.0010928467,0.00013200399,0.000012833261,0.0044182176,0.0000733346,0.0000013734331,0.0026902223,0.9887553,0.0003425689],"about_ca_topic_score_codex":0.0022816183,"about_ca_topic_score_gemma":0.0648068,"teacher_disagreement_score":0.4754324,"about_ca_system_score_codex":0.0011416369,"about_ca_system_score_gemma":0.009466879,"threshold_uncertainty_score":0.99994344},"labels":[],"label_agreement":null},{"id":"W2266958001","doi":"10.1007/978-94-6209-932-6_3","title":"The Impact of Differentiation on Teacher Education in Ontario","year":2014,"lang":"en","type":"book-chapter","venue":"SensePublishers eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Brock University; Nipissing University","funders":"","keywords":"Compliance (psychology); Political science; Law; Public administration; Public relations; Psychology; Social psychology","score_opus":0.10069064732531055,"score_gpt":0.4116415471043287,"score_spread":0.31095089977901813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2266958001","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054814972,0.00001737003,0.000033422646,0.00017109865,0.0008106549,0.00039718513,0.0000032437636,0.000012738341,0.9437393],"genre_scores_gemma":[0.331141,0.0000017880393,0.000014670127,0.00008037466,0.00008667155,0.0000081267335,0.000026750138,0.000018010516,0.6686226],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965887,0.00016982367,0.0009405193,0.00042067922,0.0016684539,0.00021183459],"domain_scores_gemma":[0.99690086,0.0006206049,0.00089551636,0.000940082,0.0005568744,0.00008605258],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0030662457,0.00027852325,0.00038992884,0.000549816,0.00012229687,0.0005374443,0.0005447208,0.00027104185,0.0026543043],"category_scores_gemma":[0.0003414296,0.00015891038,0.0003188655,0.00004063508,0.00011691876,0.00015328907,0.000060806124,0.0006275906,0.00014969002],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019273066,0.00009187272,0.015873378,0.000006236118,0.00009414082,6.533217e-7,0.0022346901,0.00031564763,0.000041845364,0.098368324,0.16667283,0.71610767],"study_design_scores_gemma":[0.0008900705,0.00052933244,0.24001403,0.00021778508,0.000043481614,0.0000035889036,0.0003226308,0.0014586378,0.000036358335,0.18118149,0.57474756,0.0005550053],"about_ca_topic_score_codex":0.007247208,"about_ca_topic_score_gemma":0.10106042,"teacher_disagreement_score":0.7155526,"about_ca_system_score_codex":0.0007691663,"about_ca_system_score_gemma":0.003133096,"threshold_uncertainty_score":0.9993636},"labels":[],"label_agreement":null},{"id":"W2268549018","doi":"10.33524/cjar.v16i3.224","title":"WHO CARES? YOU’D BE SURPRISED","year":2015,"lang":"en","type":"article","venue":"The Canadian Journal of Action Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Nipissing University","funders":"","keywords":"Grassroots; CONTEST; Public relations; Action (physics); Relevance (law); Action research; Government (linguistics); Appeal; Sociology; Scale (ratio); Political science; Scope (computer science); Action plan; Thriving; Pedagogy; Social science; Management; Law; Economics; Politics","score_opus":0.8735741171870525,"score_gpt":0.6619608736010777,"score_spread":0.21161324358597478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2268549018","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8504438,0.00029784054,0.00019514977,0.083266504,0.0021560614,0.00031190502,0.000008707571,0.0000045537518,0.0633155],"genre_scores_gemma":[0.985991,0.000017542214,0.000040647865,0.00041645102,0.00033691153,0.000002867748,6.43544e-7,0.000005573415,0.013188356],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9939678,0.0012589504,0.00045597003,0.00010776582,0.0038846782,0.00032485285],"domain_scores_gemma":[0.9927153,0.0006883086,0.00020595794,0.00038482278,0.0051054335,0.00090020185],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.037100617,0.000058318295,0.0001404664,0.00087362167,0.0005997675,0.0006887162,0.0009242884,0.000055134817,0.0021493165],"category_scores_gemma":[0.005197751,0.000032991626,0.00006987338,0.0011419483,0.00023430798,0.0004923222,0.000027393871,0.0006594112,0.00031802384],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011906944,0.000013805498,0.018253103,0.0000022406011,0.000025677651,0.000043391316,0.008131551,0.0015088259,0.00010279723,0.0026291106,0.93720955,0.03196089],"study_design_scores_gemma":[0.000592402,0.00031538872,0.016888643,0.000017812263,0.0000056727804,0.00009398493,0.02257818,0.0018174092,0.00068379595,0.010045142,0.9468851,0.00007643372],"about_ca_topic_score_codex":0.009131265,"about_ca_topic_score_gemma":0.19638553,"teacher_disagreement_score":0.18725426,"about_ca_system_score_codex":0.0005770941,"about_ca_system_score_gemma":0.010769034,"threshold_uncertainty_score":0.99876285},"labels":[],"label_agreement":null},{"id":"W2268779592","doi":"10.1080/02697459.2015.1081335","title":"Plan Evaluation: Challenges and Directions for Future Research","year":2015,"lang":"en","type":"article","venue":"Planning Practice and Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":58,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Plan (archaeology); Outcome (game theory); Management science; Government (linguistics); Subject (documents); Process management; Evaluation methods; Site plan; Political science; Business; Computer science; Engineering; Regional planning; Urban planning; Economics; Geography; Civil engineering","score_opus":0.9129376068496025,"score_gpt":0.7272479990415307,"score_spread":0.18568960780807175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2268779592","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19600104,0.14485897,0.00020318366,0.30920193,0.0015585389,0.002761372,0.000023276869,0.00007554112,0.34531614],"genre_scores_gemma":[0.96822625,0.016902508,0.0043963687,0.00030060275,0.0021715858,0.0006475855,0.000024153096,0.000025011926,0.0073059523],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9911502,0.0027376937,0.00028613757,0.0004936651,0.004928389,0.0004039305],"domain_scores_gemma":[0.97909933,0.014689594,0.000081646525,0.0003426061,0.0055083185,0.00027847255],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.111848734,0.000082952865,0.00014713932,0.0006608701,0.0009781412,0.000598134,0.0002578762,0.00010911769,0.00007710873],"category_scores_gemma":[0.030327419,0.000058435857,0.00001875618,0.0006586705,0.00020426355,0.001000921,0.00018925023,0.0006268428,0.000086800086],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00068585546,0.00017198025,0.003780992,0.000041972235,0.000053357944,0.000009449456,0.05326748,0.00008028763,0.00005007229,0.014779012,0.09932175,0.8277578],"study_design_scores_gemma":[0.0006390392,0.00042252927,0.010906534,0.0000277414,0.000010794264,0.000038504106,0.1411338,0.007024959,0.000022115804,0.014947224,0.82475084,0.0000759176],"about_ca_topic_score_codex":0.000036586454,"about_ca_topic_score_gemma":0.000053279735,"teacher_disagreement_score":0.8276819,"about_ca_system_score_codex":0.00006736223,"about_ca_system_score_gemma":0.0006817961,"threshold_uncertainty_score":0.97784054},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W2269475990","doi":"10.7870/cjcmh-2010-0003","title":"Préciser l'intervention d'une équipe de première ligne en santé mentale: un exercice plus difficile qu'il n'y paraît","year":2010,"lang":"fr","type":"article","venue":"Canadian Journal of Community Mental Health","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Hôpital Louis-H Lafontaine; Université du Québec à Rimouski","funders":"","keywords":"Humanities; Mental health; Psychology; Medicine; Psychotherapist; Art","score_opus":0.0698584862667704,"score_gpt":0.44822717557032793,"score_spread":0.37836868930355755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2269475990","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9476289,0.0046958085,0.00032298197,0.03837871,0.005245243,0.0005800198,0.00036530153,0.000010253696,0.0027727697],"genre_scores_gemma":[0.9919474,0.0011640739,0.001426618,0.0019281049,0.0003854112,0.000008510551,0.000057665846,0.00003247715,0.0030497527],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99133104,0.004255248,0.0019177977,0.00018952525,0.0013316477,0.00097473775],"domain_scores_gemma":[0.9940477,0.00083902373,0.0013582177,0.0007817076,0.00053995114,0.0024333904],"candidate_categories":["metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017138027,0.00034543462,0.00072583405,0.0005955881,0.0020962895,0.00037166846,0.0017595201,0.00026173165,0.008302038],"category_scores_gemma":[0.00048338887,0.00032996153,0.0003506776,0.0007723546,0.00036379922,0.0010221028,0.00013350174,0.002878232,0.00021316904],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031485132,0.001342412,0.022548547,0.00037259972,0.0001743557,0.00006662237,0.11858087,0.00043674043,0.00092557515,0.0019306809,0.08765917,0.7656476],"study_design_scores_gemma":[0.009580138,0.006372794,0.18738139,0.003311825,0.00020783067,0.0032748296,0.22634901,0.009545773,0.0038859271,0.009255939,0.5396144,0.0012201515],"about_ca_topic_score_codex":0.092703424,"about_ca_topic_score_gemma":0.508463,"teacher_disagreement_score":0.7644274,"about_ca_system_score_codex":0.0031348849,"about_ca_system_score_gemma":0.010167712,"threshold_uncertainty_score":0.99991524},"labels":[],"label_agreement":null},{"id":"W2270179582","doi":"10.1007/s11192-015-1828-7","title":"Automated Research Impact Assessment: a new bibliometrics approach","year":2016,"lang":"en","type":"article","venue":"Scientometrics","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":33,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"U.S. Food and Drug Administration; National Institutes of Health; National Institute of Environmental Health Sciences; Réseau Provincial de Recherche en Adaptation-Réadaptation","keywords":"Bibliometrics; Resource (disambiguation); Benchmark (surveying); Computer science; Management science; Data science; Library science; Engineering; Geography","score_opus":0.6967903147110235,"score_gpt":0.6874424372991984,"score_spread":0.009347877411825078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2270179582","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5418639,0.0006420049,0.2162102,0.0050355545,0.0025086624,0.0012672313,0.00009059326,0.0009172055,0.23146464],"genre_scores_gemma":[0.9632463,0.00016126665,0.015639607,0.0001309856,0.00019343436,0.000019914578,0.0000077985615,0.00002208249,0.020578627],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.97665507,0.0008609963,0.0010198152,0.0011070597,0.01915693,0.0012001456],"domain_scores_gemma":[0.9862934,0.006228049,0.00037263863,0.0015860513,0.004489397,0.0010305174],"candidate_categories":["metaresearch","bibliometrics","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","bibliometrics","insufficient_payload"],"category_scores_codex":[0.06576112,0.00023960258,0.00039497874,0.116039366,0.0005627021,0.0020718279,0.0025833403,0.00017146739,0.0044099195],"category_scores_gemma":[0.032625973,0.00012132884,0.00022520231,0.41322955,0.00031930063,0.0018108455,0.00061828695,0.00035501167,0.0033322307],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018263507,0.0003152726,0.23926719,0.000004828919,0.000026282292,0.000003503389,0.00031699587,0.0002884184,0.0011618069,0.0038604664,0.38468292,0.37005407],"study_design_scores_gemma":[0.0018114697,0.00050375226,0.7955891,0.00002105336,0.000009974387,0.000015217668,0.0003743796,0.08485515,0.00031187446,0.008278965,0.10783882,0.00039023362],"about_ca_topic_score_codex":0.000080420345,"about_ca_topic_score_gemma":0.000005186433,"teacher_disagreement_score":0.5563219,"about_ca_system_score_codex":0.00090755435,"about_ca_system_score_gemma":0.0028314725,"threshold_uncertainty_score":0.99896413},"labels":[],"label_agreement":null},{"id":"W2272607809","doi":"","title":"Promouvoir l’évaluation à double aveugle à la Revue canadienne des jeunes chercheurs en éducation: une réponse à Boulanger (2014)","year":2014,"lang":"fr","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Humanities; Political science; Art","score_opus":0.5668473044737703,"score_gpt":0.6315330301729827,"score_spread":0.06468572569921238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2272607809","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9341545,0.016140014,0.0016950584,0.019296037,0.0041532563,0.0011609006,0.00005168576,0.00004257103,0.023305949],"genre_scores_gemma":[0.954321,0.01258259,0.002123366,0.0008045115,0.0009200183,0.00019609566,0.000050379458,0.000083694526,0.02891834],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9899482,0.004185365,0.0021007573,0.000989469,0.001859284,0.00091693166],"domain_scores_gemma":[0.98972476,0.0037003972,0.0018653959,0.0012658611,0.0026794518,0.00076412875],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0379297,0.00055938895,0.001107777,0.0013317837,0.0008160338,0.0036740217,0.0040069176,0.00038150395,0.055490054],"category_scores_gemma":[0.0052261422,0.0005067321,0.0003014854,0.002880618,0.0005785874,0.0059470185,0.0007429414,0.0007727748,0.00057084183],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005175215,0.0010103666,0.43016738,0.00039524754,0.0003049259,0.00002190181,0.029076526,0.005014619,0.014665986,0.002577188,0.24156791,0.27468044],"study_design_scores_gemma":[0.0013169284,0.000055939636,0.6861659,0.00091174565,0.00020094406,0.00007522694,0.0019500945,0.0057923323,0.004283988,0.065324396,0.23324516,0.00067730225],"about_ca_topic_score_codex":0.028429227,"about_ca_topic_score_gemma":0.024439469,"teacher_disagreement_score":0.27400312,"about_ca_system_score_codex":0.0009344959,"about_ca_system_score_gemma":0.0021118459,"threshold_uncertainty_score":0.99973845},"labels":[],"label_agreement":null},{"id":"W2273754433","doi":"","title":"A complementary approach to developing progress markers","year":2011,"lang":"en","type":"article","venue":"CGSPace A Repository of Agricultural Research Outputs (Consultative Group for International Agricultural Research)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Overseas Development Institute; International Development Research Centre","keywords":"Computer science","score_opus":0.3323505730698983,"score_gpt":0.487569284739019,"score_spread":0.1552187116691207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2273754433","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9227858,0.0002260145,0.001409481,0.009895574,0.001079333,0.0051627234,0.0002464057,0.00008986823,0.05910477],"genre_scores_gemma":[0.95136106,0.000030391027,0.030837437,0.000090727815,0.00044169027,0.0011908478,0.00029218267,0.00002387712,0.015731784],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.98553145,0.0016075091,0.001496827,0.0013655483,0.008689398,0.0013092387],"domain_scores_gemma":[0.9694936,0.003883098,0.00051330717,0.00049214764,0.024987644,0.0006301498],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.013596589,0.00042012823,0.0005969935,0.0011463844,0.0014111883,0.000641231,0.00312076,0.00016616606,0.00019000599],"category_scores_gemma":[0.008780059,0.00022934054,0.00035474036,0.0034264897,0.0011342661,0.0014077192,0.0012001797,0.0008665654,0.000211705],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004286018,0.0026208695,0.025316486,0.0002843426,0.0015592416,0.00002732597,0.0607457,0.00015199081,0.09596868,0.27393985,0.5110147,0.024084812],"study_design_scores_gemma":[0.0015916507,0.0014749011,0.85308975,0.00024619812,0.000018914192,0.000047584912,0.08593368,0.00017565362,0.01942776,0.0043218117,0.03310988,0.0005622117],"about_ca_topic_score_codex":0.00050990743,"about_ca_topic_score_gemma":0.00025135404,"teacher_disagreement_score":0.8277733,"about_ca_system_score_codex":0.0010938284,"about_ca_system_score_gemma":0.0003865913,"threshold_uncertainty_score":0.99988884},"labels":[],"label_agreement":null},{"id":"W2273826813","doi":"10.7748/nr2009.04.16.3.70.c6947","title":"Rigour in qualitative research: mechanisms for control","year":2009,"lang":"en","type":"article","venue":"Nurse Researcher","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":149,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University; University of Calgary","funders":"","keywords":"Rigour; Qualitative research; Nursing research; Control (management); Computer science; Management science; Psychology; Engineering ethics; Computational biology; Epistemology; Medicine; Sociology; Nursing; Biology; Artificial intelligence; Engineering; Philosophy; Social science","score_opus":0.7725949983468796,"score_gpt":0.7359392547724206,"score_spread":0.036655743574459,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2273826813","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28477928,0.00051882834,0.15177602,0.27914107,0.00068644364,0.008013288,0.00017287646,0.00013889345,0.2747733],"genre_scores_gemma":[0.98034817,0.000009240783,0.002808023,0.00060073315,0.00007997052,0.00017390412,0.0000051020083,0.000008917328,0.01596596],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99090296,0.0031523395,0.00054539484,0.00047510964,0.004222023,0.00070217886],"domain_scores_gemma":[0.99160594,0.0059388084,0.00007709261,0.0005154974,0.0016669381,0.00019569951],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.06803908,0.00010227219,0.00025026887,0.00084381975,0.00021173232,0.0002546307,0.00073366746,0.0001049549,0.0021051823],"category_scores_gemma":[0.011103868,0.00007252496,0.000091556154,0.0013984602,0.00014210126,0.00039323693,0.000024126948,0.00047426965,0.00090404204],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012982055,0.0007271673,0.0005825724,0.000009915784,0.000023991734,0.000015418596,0.032798156,0.00035482546,0.00539444,0.55371886,0.11020723,0.29486924],"study_design_scores_gemma":[0.002609964,0.0008355054,0.017247966,0.00002586718,0.0000018703427,8.826494e-7,0.030988025,0.024698954,0.00074083306,0.8944019,0.028314833,0.0001333995],"about_ca_topic_score_codex":0.000047788675,"about_ca_topic_score_gemma":0.00016502138,"teacher_disagreement_score":0.69556886,"about_ca_system_score_codex":0.00020170123,"about_ca_system_score_gemma":0.00048259838,"threshold_uncertainty_score":0.9998739},"labels":[],"label_agreement":null},{"id":"W2274124070","doi":"10.3138/cjpe.21.003","title":"Understanding Cultural Competence Through the Evaluation of “Breaking the Silence: A Project to Generate Critical Knowledge About Family Violence within Immigrant Communities”","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Salient; Silence; Cultural competence; Competence (human resources); Immigration; Psychology; Cultural knowledge; Social psychology; Sociology; Pedagogy; Political science","score_opus":0.6873320058970728,"score_gpt":0.5646945822728154,"score_spread":0.12263742362425734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2274124070","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97425044,0.002689261,0.012129166,0.0031728584,0.0013062416,0.002694868,0.000021971904,0.000011423109,0.0037237583],"genre_scores_gemma":[0.99687237,0.000024472045,0.0023620038,0.0002951481,0.00022773759,0.000177462,0.000011371859,0.0000108379,0.000018575989],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.990696,0.0031904764,0.0014655002,0.00021421465,0.004047886,0.00038591516],"domain_scores_gemma":[0.98953354,0.0011267716,0.0008838613,0.00049947505,0.0078116604,0.00014466306],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03511281,0.00019718299,0.00030374635,0.00034975595,0.0010550993,0.00074980396,0.0010913585,0.00007756988,0.00020160618],"category_scores_gemma":[0.0027328883,0.00010554592,0.00015936822,0.0015295506,0.0005716413,0.0008455647,0.00004120522,0.00039503985,0.000017598666],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014345978,0.00029905257,0.015166722,0.000051978397,0.00014045637,0.0000059453905,0.16943906,0.2995904,0.0013239813,0.06541594,0.009112211,0.43931076],"study_design_scores_gemma":[0.0010832933,0.00061197917,0.05080122,0.0007912175,0.0003818456,0.000077305565,0.17691961,0.7140249,0.0002964678,0.052012462,0.0027120225,0.0002876961],"about_ca_topic_score_codex":0.011879437,"about_ca_topic_score_gemma":0.0745038,"teacher_disagreement_score":0.43902308,"about_ca_system_score_codex":0.0009381069,"about_ca_system_score_gemma":0.0067610345,"threshold_uncertainty_score":0.9988697},"labels":[],"label_agreement":null},{"id":"W2275394543","doi":"10.71781/5851","title":"Un cadre d’analyse interactionniste pour éclairer le rapport entre la formation et l’insertion professionnelle des candidats à l’enseignement au Québec","year":2014,"lang":"fr","type":"dissertation","venue":"Open MIND","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Humanities; Political science; Sociology; Philosophy","score_opus":0.12370898528163078,"score_gpt":0.4523156125276991,"score_spread":0.3286066272460683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2275394543","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88193256,0.00012131648,0.006674065,0.0051565683,0.0013401988,0.001444506,0.000045812798,0.000006801658,0.10327817],"genre_scores_gemma":[0.89454985,0.00008269834,0.003655008,0.00027542308,0.00012548578,0.00019943534,0.00189867,0.00003716279,0.09917629],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99344283,0.0016727885,0.0018495786,0.00090341736,0.0016301741,0.00050122954],"domain_scores_gemma":[0.99539816,0.00061313214,0.0018252295,0.0007159135,0.0011538608,0.00029367287],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.006400817,0.0005473469,0.0006849023,0.0004888269,0.0019030824,0.0012508656,0.0010695364,0.00042285735,0.033466708],"category_scores_gemma":[0.000501165,0.0004567681,0.00027766125,0.0006270113,0.00013375982,0.003182769,0.0002609157,0.0005578515,0.004316461],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006544314,0.0009385841,0.021998558,0.00015746517,0.0002491948,0.000018024095,0.12814215,0.0015410045,0.002805209,0.0002801899,0.013482369,0.82973284],"study_design_scores_gemma":[0.0049917977,0.0004972673,0.16390319,0.0023260613,0.00068868056,0.00008973463,0.43890977,0.061845444,0.037397586,0.0012116656,0.28658015,0.0015586388],"about_ca_topic_score_codex":0.045983616,"about_ca_topic_score_gemma":0.43904752,"teacher_disagreement_score":0.8281742,"about_ca_system_score_codex":0.0013323803,"about_ca_system_score_gemma":0.014041862,"threshold_uncertainty_score":0.9997884},"labels":[],"label_agreement":null},{"id":"W2276249050","doi":"","title":"The Policy Agendas Project: Reflections on Theory","year":2013,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Public administration; State (computer science); Regional science; Sociology; Computer science","score_opus":0.4375252673418057,"score_gpt":0.6126762407597731,"score_spread":0.17515097341796743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2276249050","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016534904,0.000010983517,0.0013810169,0.024592409,0.0002977231,0.00034028047,9.878187e-7,0.00004865158,0.95679307],"genre_scores_gemma":[0.75003475,0.000027912662,0.00030913335,0.0042904527,0.00016994726,0.00010237756,6.274393e-7,0.000004246022,0.24506052],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981858,0.00028562706,0.00027156543,0.00017553991,0.0009100506,0.00017138744],"domain_scores_gemma":[0.9977317,0.0013893011,0.00007545028,0.00049921725,0.00026007855,0.00004427445],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003258503,0.00006486475,0.00006235149,0.00018468537,0.0006066298,0.0004802203,0.00039992607,0.000026345375,0.006912483],"category_scores_gemma":[0.0013881737,0.000027467715,0.000053390526,0.00077575597,0.00006885545,0.00024609562,0.00004804313,0.00009348137,0.010816787],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000067495876,0.000024380906,0.00019995766,1.9054708e-7,0.0000055991336,6.724785e-8,0.0006892987,0.00003181359,0.00012761663,0.64424247,0.13732234,0.2173495],"study_design_scores_gemma":[0.00011651851,0.00009944303,0.017887233,0.000001695885,0.0000016408013,0.0000019418383,0.0041521844,0.0013390495,0.00031120388,0.30382302,0.6721975,0.00006856105],"about_ca_topic_score_codex":0.00019149747,"about_ca_topic_score_gemma":0.00019446824,"teacher_disagreement_score":0.7334999,"about_ca_system_score_codex":0.00004336531,"about_ca_system_score_gemma":0.0003080455,"threshold_uncertainty_score":0.9939953},"labels":[],"label_agreement":null},{"id":"W2278381810","doi":"10.1002/ev.20158","title":"Assessing the Practice Impact of Research on Evaluation","year":2015,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Evaluation methods; Program evaluation; Psychology; Applied psychology; Computer science; Political science; Public administration; Reliability engineering; Engineering","score_opus":0.8085447410014557,"score_gpt":0.7537715169629834,"score_spread":0.05477322403847229,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2278381810","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70269233,0.00078611786,0.021272914,0.018694196,0.003574813,0.00707513,0.000020962658,0.00009542397,0.2457881],"genre_scores_gemma":[0.99587554,0.000012628257,0.0016867296,0.00009992368,0.00042095894,0.0003986408,0.000037553007,0.000013541783,0.0014544608],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98442227,0.004374872,0.00078656536,0.00044096666,0.009705986,0.0002693584],"domain_scores_gemma":[0.9732386,0.008652723,0.0005587357,0.0008078654,0.016597202,0.00014491197],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13632615,0.00012462372,0.00018436185,0.00072531746,0.0005902221,0.0005644747,0.00040227128,0.00008864773,0.00096877385],"category_scores_gemma":[0.0782761,0.000075042764,0.00018163363,0.0025628554,0.000097575365,0.0017776948,0.00004383408,0.00024184523,0.0002397557],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020844191,0.00026527254,0.0020550825,0.0000024553053,0.000068227884,5.3648638e-8,0.002552198,0.18361993,0.00024556243,0.0024258113,0.10867351,0.69988346],"study_design_scores_gemma":[0.0028332812,0.0010435717,0.062934116,0.000037927424,0.00020433175,0.0000069576154,0.010940687,0.8076981,0.00063449756,0.07064318,0.042884644,0.00013872793],"about_ca_topic_score_codex":0.00045540484,"about_ca_topic_score_gemma":0.00013619999,"teacher_disagreement_score":0.6997447,"about_ca_system_score_codex":0.0011479032,"about_ca_system_score_gemma":0.005921238,"threshold_uncertainty_score":0.99994445},"labels":[],"label_agreement":null},{"id":"W2278804151","doi":"10.1007/978-1-4615-1563-0_5","title":"Describing and Evaluating Juvenile Offender Programming","year":2001,"lang":"en","type":"book-chapter","venue":"Outreach scholarship","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Management science; Computer science; Juvenile; Economic Justice; Action (physics); Political science; Engineering; Ecology; Law","score_opus":0.5226595569931727,"score_gpt":0.4874891103493299,"score_spread":0.03517044664384278,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2278804151","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016044224,0.0022278472,0.00043281095,0.0009877732,0.00067712134,0.0008939432,0.000020031997,0.00016176594,0.9785545],"genre_scores_gemma":[0.18889533,0.00015734772,0.007933489,0.0008282837,0.0005663159,0.000058383186,0.00008512528,0.00011909985,0.8013566],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99330896,0.00025541734,0.0011920196,0.001102965,0.0036358812,0.00050475483],"domain_scores_gemma":[0.99612886,0.0009526884,0.0007855518,0.00097305013,0.00077544444,0.0003844079],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.013263105,0.00050174666,0.000675371,0.00055914116,0.00051111606,0.001424776,0.0007054116,0.00044592973,0.0061395545],"category_scores_gemma":[0.0026703696,0.00040780884,0.0002305302,0.00018143038,0.00014153545,0.000979374,0.00030030607,0.0011391152,0.0010952281],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022280063,0.000022203696,0.009189517,0.000014367329,0.000045040448,0.000018375791,0.00045322406,0.00001668493,0.0000503922,0.017437395,0.0008834951,0.971847],"study_design_scores_gemma":[0.001464943,0.00041504696,0.005702365,0.00086883735,0.00025896315,0.000182007,0.00056797813,0.0016428597,0.000059003058,0.09749728,0.89003354,0.0013071549],"about_ca_topic_score_codex":0.000010220969,"about_ca_topic_score_gemma":0.000086240805,"teacher_disagreement_score":0.97053987,"about_ca_system_score_codex":0.0001935312,"about_ca_system_score_gemma":0.00048098853,"threshold_uncertainty_score":0.9998374},"labels":[],"label_agreement":null},{"id":"W2279719779","doi":"","title":"Police and Problem Solving: Beyond SARA","year":2010,"lang":"en","type":"article","venue":"Australasian Policing","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"General partnership; Criminology; Work (physics); Sociology; Computer science; Political science; Law; Engineering","score_opus":0.08240081933731644,"score_gpt":0.4410902423234157,"score_spread":0.3586894229860993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2279719779","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8911079,0.0000027873682,0.00008329839,0.0042543546,0.0002528919,0.00014923353,0.0000042682514,0.000042623844,0.10410262],"genre_scores_gemma":[0.9883992,0.0000041334115,0.0037320766,0.00084407895,0.00028270826,0.00000608317,0.0000019548784,0.000011265921,0.006718521],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9980005,0.00005189681,0.00045703392,0.00034075338,0.00078426703,0.00036555604],"domain_scores_gemma":[0.99878097,0.00025343013,0.00016854424,0.00043593693,0.00013869608,0.00022241143],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016506962,0.00014410127,0.000188412,0.00026995485,0.0002496579,0.00037950207,0.00035312763,0.00009711875,0.0012573532],"category_scores_gemma":[0.00012496366,0.00011033997,0.000049190552,0.00043143716,0.00011885097,0.0005431649,0.00009591511,0.00032546144,0.00029538773],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019002367,0.00010365423,0.613122,0.000022296152,0.000036966543,0.000003296891,0.037017897,0.0001262734,0.08499655,0.042584438,0.040365215,0.18160242],"study_design_scores_gemma":[0.0008921122,0.0001527353,0.90990376,0.000030441839,0.000026026943,0.0001340349,0.0048818006,0.0030606035,0.0071306974,0.023578545,0.049720228,0.00048900634],"about_ca_topic_score_codex":0.0024768687,"about_ca_topic_score_gemma":0.0046829134,"teacher_disagreement_score":0.29678178,"about_ca_system_score_codex":0.000017207964,"about_ca_system_score_gemma":0.000118214644,"threshold_uncertainty_score":0.9996556},"labels":[],"label_agreement":null},{"id":"W2280732594","doi":"","title":"Gestion et émasculation des évaluations : le cas du Canada","year":2011,"lang":"fr","type":"article","venue":"Docs.school Publications","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.2524109226161727,"score_gpt":0.4428439298136063,"score_spread":0.1904330071974336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2280732594","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13284831,0.0033364908,0.120624825,0.31656832,0.0050204312,0.0020351296,0.00044177115,0.00031692444,0.4188078],"genre_scores_gemma":[0.9368448,0.00066822034,0.011902693,0.0019364927,0.0003964549,0.00037861703,0.0004011237,0.000034007113,0.047437537],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.994643,0.0010746551,0.0011681785,0.0006810753,0.0019030331,0.0005300662],"domain_scores_gemma":[0.9937908,0.00084976206,0.0005175491,0.001184079,0.0030741487,0.0005836331],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0057854373,0.00029607533,0.00028056774,0.00051181426,0.0013249898,0.0006814849,0.000784511,0.00022962624,0.025561905],"category_scores_gemma":[0.0065424168,0.00029601977,0.00015418773,0.0024035024,0.00027933653,0.0038105454,0.00014259125,0.00048296765,0.0016736685],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014409193,0.0006229713,0.12158385,0.000022994438,0.00010368795,0.0000023957825,0.0061856858,0.00428954,0.00006446592,0.5220945,0.25188658,0.09312894],"study_design_scores_gemma":[0.00039274598,0.000037716207,0.5995156,0.000030443069,0.00006209438,0.000023982393,0.0013098741,0.024866952,0.00006438852,0.021738729,0.35169643,0.0002610608],"about_ca_topic_score_codex":0.52839917,"about_ca_topic_score_gemma":0.8204929,"teacher_disagreement_score":0.80399656,"about_ca_system_score_codex":0.0011135804,"about_ca_system_score_gemma":0.013833521,"threshold_uncertainty_score":0.99997514},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"other","about_ca_system":false,"about_ca_topic":true,"confidence":"low"},{"model":"grok","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":true,"confidence":"low"},{"model":"opus","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":true,"confidence":"low"}],"label_agreement":"split"},{"id":"W2281078387","doi":"","title":"School leadership policy landscape : Toronto, Ontario","year":2013,"lang":"en","type":"book","venue":"Institute of Education, University of London eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Geography; Political science; Educational leadership; Environmental planning; Public administration; Sociology; Pedagogy","score_opus":0.1411057224834323,"score_gpt":0.36781214787994254,"score_spread":0.22670642539651023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2281078387","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009876925,0.0002701479,0.00013953501,0.00075929496,0.0013044601,0.00046836416,0.0000235918,0.000020225576,0.98713744],"genre_scores_gemma":[0.025394045,0.00005328306,0.0009328607,0.00023558688,0.00026575086,0.0000012856098,0.00008330939,0.000012174049,0.9730217],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972054,0.00008112856,0.0006463773,0.00044658332,0.0013967879,0.00022375598],"domain_scores_gemma":[0.99584097,0.00014788614,0.0011013639,0.0009156459,0.0017509974,0.00024314546],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007895128,0.00025886277,0.0005571778,0.0005980877,0.00019064493,0.00006256894,0.0012622837,0.00030400945,0.017013876],"category_scores_gemma":[0.00023236753,0.00026235564,0.00025296962,0.00011105519,0.00041870633,0.0007625832,0.00014001981,0.00027888603,0.00050045433],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009409467,0.00023696145,0.007780682,0.00014696874,0.00018121228,0.0000019011177,0.0102933375,0.000093145456,0.000047177167,0.070826806,0.84335333,0.066944405],"study_design_scores_gemma":[0.00051414757,0.0000955149,0.008296741,0.00022543543,0.000071258844,0.0000036657286,0.0053148875,0.000016163345,0.000026857317,0.0063428143,0.9788337,0.00025882843],"about_ca_topic_score_codex":0.07080481,"about_ca_topic_score_gemma":0.29008213,"teacher_disagreement_score":0.21927734,"about_ca_system_score_codex":0.0013620063,"about_ca_system_score_gemma":0.037971202,"threshold_uncertainty_score":0.9999829},"labels":[],"label_agreement":null},{"id":"W2282835790","doi":"","title":"Essentials of a Qualitative Doctorate (2012) by Immy Holloway & Lorraine Brown","year":2015,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Qualitative research; Psychology; Pedagogy; Sociology; Social science","score_opus":0.6846756803636572,"score_gpt":0.6788583486031226,"score_spread":0.005817331760534672,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2282835790","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8930978,0.0013866952,0.00016113502,0.046360847,0.00077383907,0.00018937331,0.000018673047,3.6967845e-7,0.05801126],"genre_scores_gemma":[0.895968,0.000088591456,0.00048609893,0.000119834505,0.00028778944,0.000009618627,0.000012644965,0.00000849407,0.10301893],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99096906,0.002058304,0.0013467191,0.00021321003,0.0051100664,0.00030263182],"domain_scores_gemma":[0.95450276,0.035251204,0.0008403033,0.00034064864,0.008658919,0.00040613793],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.027608594,0.00010838537,0.0003450034,0.0007178543,0.00012659427,0.00017549528,0.00093621854,0.00006016983,0.03214638],"category_scores_gemma":[0.055429764,0.000073823045,0.0001314893,0.0013539494,0.00031169434,0.0011047618,0.000099085184,0.00034523115,0.0010765761],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029980668,0.000699731,0.011481834,0.000011866279,0.00010675089,4.1592725e-7,0.020286242,0.00018895714,0.005111697,0.019200979,0.94101924,0.0015924762],"study_design_scores_gemma":[0.0040453454,0.0022026983,0.02341122,0.00022141349,0.000057350873,0.00009128907,0.06611781,0.00079206296,0.008376819,0.09838516,0.79583114,0.00046769262],"about_ca_topic_score_codex":0.0003783486,"about_ca_topic_score_gemma":0.00025890832,"teacher_disagreement_score":0.14518811,"about_ca_system_score_codex":0.00015512179,"about_ca_system_score_gemma":0.004627019,"threshold_uncertainty_score":0.9997012},"labels":[],"label_agreement":null},{"id":"W2283637488","doi":"10.3138/cjpe.29.3.vii","title":"Introduction to Professionalization of Evaluation in Canada","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Professionalization; Engineering ethics; Political science; Professional development; Public relations; Professional association; Library science; Sociology; Medical education; Pedagogy; Engineering; Computer science; Law; Medicine","score_opus":0.40279152132935725,"score_gpt":0.5399497411847914,"score_spread":0.1371582198554342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2283637488","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98244333,0.00024736294,0.00090084586,0.010712517,0.0026184733,0.0018652815,0.00000581496,0.000002580712,0.0012037967],"genre_scores_gemma":[0.9974992,0.0000015236837,0.0017957446,0.00015266775,0.00035203545,0.0000856035,0.00002685777,0.0000068569434,0.000079458616],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99239135,0.001092264,0.0013141693,0.00020269754,0.00478763,0.00021190039],"domain_scores_gemma":[0.98840827,0.000119249424,0.00081513554,0.0002637108,0.009879127,0.00051450613],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.030539516,0.00009843724,0.00024443885,0.0010341726,0.000055955697,0.00007493418,0.00027298005,0.00005159315,0.0015290171],"category_scores_gemma":[0.010855281,0.000080692174,0.000042778105,0.0017445898,0.000027090433,0.0006002834,0.000011676994,0.00013685625,0.000022769162],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051807743,0.000044676926,0.11237778,0.000005586194,0.000011913415,0.0000021541368,0.0022995763,0.15689968,0.00006594007,0.00026532696,0.037155244,0.69082034],"study_design_scores_gemma":[0.0031548503,0.000859547,0.5134004,0.00014547577,0.000115153925,0.00004181206,0.011025488,0.34713438,0.00076828926,0.013068842,0.10998768,0.00029809226],"about_ca_topic_score_codex":0.4097814,"about_ca_topic_score_gemma":0.9868402,"teacher_disagreement_score":0.69052225,"about_ca_system_score_codex":0.003521246,"about_ca_system_score_gemma":0.06466466,"threshold_uncertainty_score":0.99938375},"labels":[],"label_agreement":null},{"id":"W2286466655","doi":"10.1177/1744629516633574","title":"Linking user and staff perspectives in the evaluation of innovative transition projects for youth with disabilities","year":2016,"lang":"en","type":"article","venue":"Journal of Intellectual Disabilities","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Workplace Health, Safety and Compensation Commission","funders":"","keywords":"Benchmarking; Formative assessment; Context (archaeology); Psychology; Process (computing); Medical education; Perception; Work (physics); Applied psychology; Quality (philosophy); Process management; Knowledge management; Pedagogy; Engineering; Business; Computer science; Medicine; Marketing","score_opus":0.3436951956240972,"score_gpt":0.4667271129060397,"score_spread":0.12303191728194246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2286466655","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9898535,0.00015150485,0.006843608,0.0017738645,0.000067834626,0.00053765485,0.000033213884,0.0000026709495,0.0007361719],"genre_scores_gemma":[0.9993421,0.00004003139,0.00038091803,0.000034200333,0.000075373064,0.00004215942,0.0000012511589,0.0000061744513,0.000077803685],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99632937,0.0007035728,0.00084164034,0.000179987,0.0018080843,0.00013732412],"domain_scores_gemma":[0.9834011,0.012292852,0.00040503184,0.00018750128,0.0036894665,0.000024048877],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011191835,0.00011920689,0.00028806608,0.0003005503,0.00008042375,0.000090997855,0.00024372299,0.000040963536,0.0003437271],"category_scores_gemma":[0.023431486,0.000048659847,0.00007610956,0.0005600819,0.0006165786,0.0007812497,0.000016629901,0.00011179876,0.0000011519714],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008424067,0.00023074115,0.012674865,0.000029304856,0.000037598995,6.159754e-8,0.9543343,0.00020697503,0.00020460844,0.003787509,0.00022395565,0.027427632],"study_design_scores_gemma":[0.0012556376,0.0018323493,0.0069908793,0.00023750323,0.000034742865,0.000008828954,0.9679837,0.000706758,0.00092215627,0.019837014,0.00010629161,0.00008413612],"about_ca_topic_score_codex":0.000009264168,"about_ca_topic_score_gemma":0.00012310586,"teacher_disagreement_score":0.027343497,"about_ca_system_score_codex":0.000163451,"about_ca_system_score_gemma":0.0004811736,"threshold_uncertainty_score":0.98479456},"labels":[],"label_agreement":null},{"id":"W2286886705","doi":"10.11575/prism/9621","title":"Gap Analysis of Public Mental Health and Addictions Programs (GAP-MAP) Final Report","year":2014,"lang":"en","type":"article","venue":"Open MIND","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mental health; Permission; Addiction; Public health; Public relations; Internet privacy; Psychology; Business; Political science; Law; Psychiatry; Computer science; Medicine; Nursing","score_opus":0.5287257180217191,"score_gpt":0.5597794654386156,"score_spread":0.031053747416896482,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2286886705","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9175939,0.00008312746,0.0035033321,0.012303555,0.00027725263,0.0006979472,0.00005100269,0.0000032125592,0.06548666],"genre_scores_gemma":[0.9833953,0.000012669351,0.009736582,0.00014994905,0.000023345096,0.000021460204,0.0002141825,0.00000317076,0.006443339],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975932,0.00023710036,0.00069529255,0.00034861072,0.0009634051,0.00016239444],"domain_scores_gemma":[0.9984943,0.0001320227,0.0004938702,0.00045808998,0.00023642273,0.00018525038],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0077290507,0.000075035554,0.0003032296,0.00031540424,0.00022295254,0.00045282143,0.00037986474,0.000028237579,0.0078071747],"category_scores_gemma":[0.00035693127,0.00005481363,0.000075653596,0.0011844165,0.00008294759,0.00047101773,0.000168111,0.00006116711,0.00012710904],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008028044,0.00011241729,0.18494819,0.0000011535433,0.000098952434,6.319395e-7,0.0009843832,0.000024882538,0.000011609608,0.000236891,0.0032089313,0.81036395],"study_design_scores_gemma":[0.00051597774,0.00035734064,0.0865526,0.000014503441,0.000085625565,0.000017111885,0.0029173016,0.035457533,0.000035318582,0.00036431098,0.8735608,0.00012161453],"about_ca_topic_score_codex":0.00008886918,"about_ca_topic_score_gemma":0.0012790001,"teacher_disagreement_score":0.87035185,"about_ca_system_score_codex":0.000033087923,"about_ca_system_score_gemma":0.00037472576,"threshold_uncertainty_score":0.9930998},"labels":[],"label_agreement":null},{"id":"W2288957490","doi":"10.20355/c5kg6p","title":"Fairness of Standardized Assessments: Discrepancy between Provincial and Territorial Results","year":2016,"lang":"en","type":"article","venue":"Journal of Contemporary Issues in Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Psychology; Section (typography); Standardized test; Regional science; Political science; Sociology; Mathematics education; Business; Advertising","score_opus":0.1183209692239725,"score_gpt":0.5121441527236013,"score_spread":0.39382318349962875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2288957490","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98222476,0.000634745,0.0016900548,0.00815837,0.0032627508,0.0002502982,0.000058874833,0.000004287105,0.0037158302],"genre_scores_gemma":[0.9959414,0.00010914967,0.0015617809,0.000022753495,0.0014271496,0.000004574767,0.000004698551,0.000005686928,0.0009228237],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.996083,0.00045021184,0.0017359232,0.0001785037,0.0014528132,0.00009954823],"domain_scores_gemma":[0.9962929,0.00079346285,0.0015888576,0.00024254137,0.0009961888,0.00008606995],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00677743,0.00010179969,0.00042690945,0.00042089852,0.000038255876,0.00008496574,0.0003141197,0.000067599096,0.0000627208],"category_scores_gemma":[0.002199217,0.0000578171,0.0000692503,0.00026977845,0.0000837313,0.0016371976,0.00004450885,0.000105300765,0.000003044313],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001278486,0.00029462026,0.6471732,0.000017474671,0.000035493405,0.0000021022754,0.002810349,0.0000012798929,0.0008419693,0.0011104667,0.014178795,0.33225575],"study_design_scores_gemma":[0.00699584,0.0012692345,0.62122744,0.0008147982,0.000029421552,0.000009074044,0.0059405346,0.000022687609,0.003710876,0.045229495,0.31451812,0.00023251149],"about_ca_topic_score_codex":0.000084157495,"about_ca_topic_score_gemma":0.000037395414,"teacher_disagreement_score":0.33202323,"about_ca_system_score_codex":0.000121022436,"about_ca_system_score_gemma":0.0022738439,"threshold_uncertainty_score":0.40337014},"labels":[],"label_agreement":null},{"id":"W2290035607","doi":"10.71781/18602","title":"Évaluation qualitative des déterminants de l'utilisation des connaissances issues de la recherche par les enseignants d'écoles secondaires québécoises en milieu défavorisé","year":2007,"lang":"fr","type":"dissertation","venue":"Open MIND","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Valuation (finance); Humanities; Political science; Sociology; Business; Philosophy; Accounting","score_opus":0.675349864609346,"score_gpt":0.6245563203087864,"score_spread":0.0507935443005596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2290035607","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9595576,0.007559309,0.0026384068,0.0003928286,0.0005591454,0.001458136,0.0001632895,0.000012270789,0.027658993],"genre_scores_gemma":[0.80485016,0.005293879,0.15783973,0.00011558924,0.00030288976,0.00025108512,0.00047426953,0.000071611845,0.03080079],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.97566265,0.017835865,0.0021256583,0.0013656386,0.0020222247,0.0009879842],"domain_scores_gemma":[0.97463197,0.021149293,0.001505465,0.00066109473,0.0016992155,0.0003529672],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.066492945,0.0008081979,0.0010650354,0.0006609719,0.0018494298,0.0018945499,0.0017946624,0.0014781645,0.011882129],"category_scores_gemma":[0.019698767,0.000726743,0.00028344925,0.0010965877,0.0019405371,0.0024158456,0.00018448074,0.0010035144,0.0007394115],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031623885,0.00022678151,0.02999015,0.00011303566,0.000091833994,0.000012583775,0.38993028,0.00033558713,0.0034145883,0.00009668259,0.00033071995,0.5751415],"study_design_scores_gemma":[0.0010662681,0.0004337417,0.28727493,0.0019060635,0.00027493108,0.000028458451,0.5524489,0.0068120426,0.09810519,0.030400546,0.020372497,0.0008764021],"about_ca_topic_score_codex":0.018715851,"about_ca_topic_score_gemma":0.10861282,"teacher_disagreement_score":0.5742651,"about_ca_system_score_codex":0.0012497911,"about_ca_system_score_gemma":0.0058954717,"threshold_uncertainty_score":0.99981815},"labels":[],"label_agreement":null},{"id":"W2290214811","doi":"10.4212/cjhp.v69i1.1531","title":"After the Launch of the CSHP Strategic Plan, What’s Next?","year":2016,"lang":"en","type":"article","venue":"The Canadian Journal of Hospital Pharmacy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Plan (archaeology); Business; Process management; Strategic planning; Business administration; Biology; Marketing","score_opus":0.20477668659383877,"score_gpt":0.42254542689806435,"score_spread":0.21776874030422558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2290214811","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90122116,0.0012939445,0.000011344753,0.09261147,0.0025404338,0.00016567601,0.000015585061,0.0000014720082,0.0021389378],"genre_scores_gemma":[0.9964162,0.00018638805,0.000007869508,0.0018095106,0.00028624988,0.0000038259855,1.17257215e-7,0.00000695951,0.0012828617],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99753284,0.0003198613,0.00060610106,0.000104907995,0.0011850623,0.00025121254],"domain_scores_gemma":[0.9976725,0.0004989669,0.0005477243,0.00044872673,0.0005895273,0.0002425458],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0036732848,0.00011014467,0.00015997575,0.000103955084,0.00030404903,0.0006594338,0.0016747733,0.000022437342,0.0045732944],"category_scores_gemma":[0.0002437841,0.00003360486,0.00018866328,0.00034660325,0.00035812554,0.0014313912,0.00004293029,0.00024646035,0.00013955447],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006029718,0.00020906163,0.28901607,0.000020657279,0.00054945145,0.00016277572,0.026646508,0.0009182218,0.0021031417,0.016199382,0.19502403,0.46854776],"study_design_scores_gemma":[0.0033250188,0.00068705017,0.28976932,0.00038073253,0.00016883746,0.00024068478,0.019249454,0.00063702406,0.0037169782,0.09129698,0.59005153,0.00047639722],"about_ca_topic_score_codex":0.0009572734,"about_ca_topic_score_gemma":0.013352785,"teacher_disagreement_score":0.46807134,"about_ca_system_score_codex":0.00009660829,"about_ca_system_score_gemma":0.0021802604,"threshold_uncertainty_score":0.99633664},"labels":[],"label_agreement":null},{"id":"W2291330032","doi":"10.7202/1034583ar","title":"Approche par compétences et évaluation à large échelle : deux logiques incompatibles ?","year":2016,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Valuation (finance); Humanities; Political science; Philosophy; Business","score_opus":0.21637242338303078,"score_gpt":0.49223903013038867,"score_spread":0.27586660674735786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2291330032","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38536268,0.0018661328,0.40698218,0.17946091,0.0060064127,0.0017994556,0.00013703735,0.00021565698,0.018169526],"genre_scores_gemma":[0.94904464,0.0022390643,0.025735298,0.0022865196,0.00054896,0.00029158616,0.00039493977,0.000051586703,0.019407388],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.97086924,0.020587057,0.0020629095,0.0012707883,0.0044566886,0.000753299],"domain_scores_gemma":[0.98846173,0.006328092,0.0013436121,0.0010509391,0.002588179,0.00022744773],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.109644264,0.0005697638,0.00064712,0.00071359955,0.00059664,0.00060848426,0.0008550701,0.00049645937,0.010654651],"category_scores_gemma":[0.008862278,0.00041485246,0.00025969898,0.0013996804,0.00025730312,0.003269154,0.0001950192,0.00042885242,0.0040142317],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014353918,0.0018217327,0.10073656,0.00016075492,0.00019342428,0.0000018378454,0.2316979,0.003418968,0.007619497,0.05414586,0.09309108,0.50696886],"study_design_scores_gemma":[0.0025672058,0.0004818886,0.6866175,0.00069387845,0.00023909094,0.000015976968,0.008723888,0.052324135,0.006008769,0.113744326,0.12762828,0.00095504633],"about_ca_topic_score_codex":0.00020078834,"about_ca_topic_score_gemma":0.0023458546,"teacher_disagreement_score":0.58588094,"about_ca_system_score_codex":0.0007345225,"about_ca_system_score_gemma":0.0057413685,"threshold_uncertainty_score":0.99989516},"labels":[],"label_agreement":null},{"id":"W2291715699","doi":"","title":"Towards Sustainable Performance Measurement Frameworks for Applied Research in Canadian Community Colleges and Institutes","year":2014,"lang":"en","type":"article","venue":"The College Quarterly","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mandate; Government (linguistics); Political science; Public administration; Higher education; Community college; Public relations; Medical education","score_opus":0.24882532687817682,"score_gpt":0.454869026674778,"score_spread":0.2060436997966012,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2291715699","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92954713,0.00010469939,0.0008533404,0.011917314,0.00021086706,0.0018945297,0.000021081412,0.000019852869,0.05543117],"genre_scores_gemma":[0.99741274,0.000009755628,0.00031811243,0.0007333816,0.00007030984,0.00041247596,0.0000030689332,0.000009754032,0.0010303934],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9958564,0.0010157999,0.00047945554,0.00026510545,0.0016591066,0.0007241057],"domain_scores_gemma":[0.99615294,0.0015842728,0.00008992632,0.0007779694,0.0011741264,0.00022075248],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.049220443,0.00014214715,0.00026169352,0.0005669836,0.0019288579,0.00034316507,0.0009430001,0.00015371913,0.000068305875],"category_scores_gemma":[0.0008383639,0.00009396458,0.000034514396,0.0012296946,0.0002848001,0.00031006854,0.00006472872,0.00081340404,0.00004218925],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004421985,0.00021957814,0.012840105,0.00016918965,0.000036252335,0.0000028627314,0.025857009,0.00074378646,0.00007924035,0.69775283,0.025592329,0.23626463],"study_design_scores_gemma":[0.0027168419,0.002114821,0.14364387,0.00011277893,0.00001556121,0.0000061973037,0.11902615,0.0751036,0.00019101561,0.20770925,0.44890508,0.00045480672],"about_ca_topic_score_codex":0.040102597,"about_ca_topic_score_gemma":0.3772864,"teacher_disagreement_score":0.49004355,"about_ca_system_score_codex":0.00052174955,"about_ca_system_score_gemma":0.0016240395,"threshold_uncertainty_score":0.9993705},"labels":[],"label_agreement":null},{"id":"W2292266222","doi":"10.14288/1.0088989","title":"Considering the social and cultural dimensions of development : an analysis of the use of social impact assessment at the Canadian International Development Agency","year":2009,"lang":"en","type":"article","venue":"cIRcle (University of British Columbia)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Agency (philosophy); Social impact assessment; Political science; Sociology; Psychology; Social science","score_opus":0.124006644640075,"score_gpt":0.37386717036180767,"score_spread":0.24986052572173267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2292266222","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9984295,0.000010275246,0.00005896377,0.00091515185,0.000058614205,0.00015645083,0.00008470639,0.000002639427,0.00028374593],"genre_scores_gemma":[0.998994,0.000009079084,0.0006296267,0.00007280663,0.000006063661,3.711504e-7,0.000017350518,0.0000018476566,0.00026887524],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9981686,0.00018001352,0.00033348604,0.00018090512,0.0010058163,0.00013116491],"domain_scores_gemma":[0.9985316,0.00013854982,0.00043556467,0.00017788116,0.0006561802,0.00006021738],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010912106,0.00004305397,0.0002375664,0.0001038195,0.0010632958,0.000103834296,0.00046575183,0.0000473342,0.00044345765],"category_scores_gemma":[0.0000723976,0.000049794617,0.00014914536,0.00060898956,0.00036339852,0.00029166468,0.00016585414,0.00008104184,7.2534175e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014176051,0.00012574412,0.5822642,0.0000050608105,0.0006111843,0.000002896089,0.029233864,0.0010847648,0.00063963706,0.000036279973,0.0021840534,0.38379812],"study_design_scores_gemma":[0.00022798218,0.000018621071,0.9907258,0.000012253093,0.000095471834,0.0000024071414,0.0058203717,0.0019239269,0.000008517431,0.00005182714,0.0010500632,0.000062722305],"about_ca_topic_score_codex":0.14034376,"about_ca_topic_score_gemma":0.9367984,"teacher_disagreement_score":0.79645467,"about_ca_system_score_codex":0.00028900531,"about_ca_system_score_gemma":0.0010595071,"threshold_uncertainty_score":0.86538076},"labels":[],"label_agreement":null},{"id":"W2292486103","doi":"10.3138/cjpe.024.002","title":"Learning Through Evaluation? Reflections on Two Federal Community-Building Initiatives","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa; Western University","funders":"","keywords":"Stakeholder; Government (linguistics); Corporate governance; Policy learning; Political science; Public relations; Community engagement; Public administration; Stakeholder engagement; Collaborative governance; Action (physics); Business; Computer science","score_opus":0.6156032355612,"score_gpt":0.6355201743114897,"score_spread":0.01991693875028966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2292486103","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88941413,0.00024473816,0.0034088786,0.00643099,0.0011534574,0.0015553606,0.00000409089,0.00003481757,0.09775352],"genre_scores_gemma":[0.9917457,0.000009816325,0.006762714,0.000984135,0.00030049056,0.00005351607,0.000021829144,0.000010875916,0.00011092715],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9901664,0.004688903,0.0010968064,0.0002157717,0.0034744996,0.00035760342],"domain_scores_gemma":[0.9925183,0.0007424623,0.0009813801,0.00035590678,0.0050545586,0.0003473675],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03350315,0.00018207986,0.00029082195,0.0008745705,0.0017668479,0.00086498656,0.00053193525,0.00008512487,0.001848807],"category_scores_gemma":[0.009039882,0.00015104417,0.00017252786,0.0012663756,0.000096395954,0.0016506084,0.000011282849,0.0010039596,0.00008436422],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034480567,0.00014171074,0.005119699,0.0000017072687,0.000040731335,0.0000029090975,0.011347205,0.077498354,0.00018013967,0.004663851,0.0010385702,0.89993066],"study_design_scores_gemma":[0.006374349,0.009852879,0.34873462,0.00034405346,0.00036214557,0.0001537943,0.035991095,0.2041474,0.0006519422,0.3403771,0.052272025,0.00073861604],"about_ca_topic_score_codex":0.00061862636,"about_ca_topic_score_gemma":0.010599865,"teacher_disagreement_score":0.89919204,"about_ca_system_score_codex":0.00092832535,"about_ca_system_score_gemma":0.004767659,"threshold_uncertainty_score":0.9995327},"labels":[],"label_agreement":null},{"id":"W2295689404","doi":"10.6197/heed.2015.0902.04","title":"The Quality Assurance System for Ontario Postsecondary Education: 2010 ~ 2014","year":2015,"lang":"en","type":"article","venue":"Higher Education Evaluation and Development","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Quality assurance; Higher education; Government (linguistics); Corporate governance; Quality (philosophy); Political science; Business; Service (business); Law; Marketing; Finance","score_opus":0.32131186356307917,"score_gpt":0.5235231323211347,"score_spread":0.2022112687580555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2295689404","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6637547,0.0088869585,0.0062028663,0.06051816,0.066667095,0.0077147568,0.000022444816,0.00022404444,0.18600899],"genre_scores_gemma":[0.83075726,0.000017440816,0.010699961,0.0020115168,0.00043822234,0.0019220754,0.0001711936,0.000016473068,0.15396585],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9953152,0.0005276028,0.0010954846,0.00048163874,0.0023574415,0.00022262357],"domain_scores_gemma":[0.9934659,0.0007749199,0.0005759852,0.0005446744,0.00437932,0.00025922235],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017789304,0.00017996259,0.00021037179,0.0001589494,0.0007190415,0.0005635295,0.00035068812,0.000082390434,0.0014922569],"category_scores_gemma":[0.0006485314,0.000121389436,0.000047100835,0.00024952737,0.000062894236,0.0004837127,0.00005066667,0.000109170716,0.00062852725],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008780803,0.00021708672,0.052750725,0.000027003203,0.00003167704,1.9300892e-8,0.0054432345,0.00007643928,0.000018013756,0.023148874,0.5371549,0.3810442],"study_design_scores_gemma":[0.00044551873,0.000020260417,0.410838,0.000015876025,0.000010127277,0.0000023141292,0.0032555517,0.00013744524,0.00005703983,0.0027527206,0.5823408,0.00012434546],"about_ca_topic_score_codex":0.00043429228,"about_ca_topic_score_gemma":0.004439908,"teacher_disagreement_score":0.38091984,"about_ca_system_score_codex":0.0011416187,"about_ca_system_score_gemma":0.028765008,"threshold_uncertainty_score":0.9994205},"labels":[],"label_agreement":null},{"id":"W2297320325","doi":"","title":"How can we synthesise qualitative and quantitative evidence for policy makers and managers?","year":2005,"lang":"en","type":"article","venue":"ePrints Soton (University of Southampton)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Management science; Narrative; Quantitative analysis (chemistry); Qualitative research; Thematic analysis; Computer science; Knowledge management; Data science; Sociology; Social science; Engineering","score_opus":0.34134984535436164,"score_gpt":0.48487900802344763,"score_spread":0.143529162669086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2297320325","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9063357,0.00017798843,0.021897422,0.0697497,0.000048100774,0.0005284093,0.00007015353,0.000022486513,0.0011700594],"genre_scores_gemma":[0.97264457,0.00027455168,0.020324316,0.00013150995,0.000020568234,0.0000017971678,0.0000017086097,0.0000058158007,0.0065951417],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9983279,0.00024120446,0.00018290376,0.00043955073,0.0006135082,0.0001949006],"domain_scores_gemma":[0.996744,0.0022176357,0.00030307783,0.00028434288,0.00030863806,0.00014229995],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023188272,0.00013065971,0.00027680333,0.00037562434,0.00027848437,0.00010725099,0.00031937557,0.00006143825,0.00026471537],"category_scores_gemma":[0.0014399019,0.00012762276,0.00008361554,0.00033486474,0.00047191512,0.0008127645,0.00017509777,0.00008309439,0.00004322291],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009396193,0.00013552276,0.016745575,0.00017247502,0.00022846503,0.0000066935713,0.50613105,0.00018655558,0.0011838346,0.10592186,0.0018947934,0.36645356],"study_design_scores_gemma":[0.0020682926,0.00030736142,0.065464966,0.00026631847,0.00008546353,0.0000053496433,0.8583422,0.013104945,0.00066259294,0.032725673,0.026477499,0.0004893734],"about_ca_topic_score_codex":0.00031750088,"about_ca_topic_score_gemma":0.0008302224,"teacher_disagreement_score":0.36596417,"about_ca_system_score_codex":0.00008266741,"about_ca_system_score_gemma":0.00014921314,"threshold_uncertainty_score":0.5204305},"labels":[],"label_agreement":null},{"id":"W2298222049","doi":"10.3138/cjpe.28.006","title":"Exemple d’application de l’évaluation formative centrée sur l’utilisation des résultats","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Centre Intégré de Santé et de Services Sociaux des Laurentides","funders":"","keywords":"Formative assessment; Valuation (finance); Process (computing); Evaluation methods; Computer science; Process management; Risk analysis (engineering); Business; Psychology; Engineering; Reliability engineering; Pedagogy; Accounting","score_opus":0.29907530459644416,"score_gpt":0.4846502697928911,"score_spread":0.18557496519644695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2298222049","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95948845,0.00023068205,0.03235165,0.0021532073,0.00041738412,0.0022040342,0.0000070798433,0.000020037498,0.0031274597],"genre_scores_gemma":[0.9900087,0.000019649693,0.009064431,0.0002113566,0.00016862988,0.000325958,0.000051597966,0.000013338745,0.00013633227],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99485654,0.00088877266,0.0012490934,0.00022841754,0.002351743,0.00042545705],"domain_scores_gemma":[0.9895742,0.00040352353,0.0011127149,0.00031994804,0.008025879,0.0005637554],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016493807,0.00016260266,0.00024090744,0.0007349076,0.0004162309,0.0006920782,0.00045851257,0.00011523136,0.0034761059],"category_scores_gemma":[0.005024514,0.000132738,0.00013349263,0.001015485,0.00014815888,0.0027009714,0.000012999223,0.00020703717,0.0004056254],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009101356,0.00004682866,0.041722894,0.0000055583632,0.000018735576,4.5749147e-7,0.0072376025,0.0056923586,0.00035902375,0.00035788422,0.0034938036,0.9410558],"study_design_scores_gemma":[0.0009525438,0.00030296494,0.45057508,0.00003484121,0.00006567666,0.00002796874,0.0037754546,0.459669,0.00049966725,0.07080019,0.01313997,0.00015664865],"about_ca_topic_score_codex":0.003416151,"about_ca_topic_score_gemma":0.018093396,"teacher_disagreement_score":0.94089913,"about_ca_system_score_codex":0.00087204564,"about_ca_system_score_gemma":0.005250928,"threshold_uncertainty_score":0.99982387},"labels":[],"label_agreement":null},{"id":"W2298916003","doi":"10.18438/b8bd00","title":"The Changing Nature of Evidence for EBLIP","year":2016,"lang":"en","type":"article","venue":"Evidence Based Library and Information Practice","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Data science","score_opus":0.18814451219803463,"score_gpt":0.47313280800852076,"score_spread":0.2849882958104861,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2298916003","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009592347,0.002808609,0.0961108,0.8857688,0.0008907368,0.0010139564,0.000029625306,0.00007281736,0.003712353],"genre_scores_gemma":[0.9359525,0.005109309,0.00730039,0.04892548,0.00015501265,0.00011043107,0.000004881525,0.000007097864,0.0024349089],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.997658,0.00031809654,0.0006962754,0.00014926403,0.0009988648,0.00017950672],"domain_scores_gemma":[0.95527416,0.043026175,0.00079992146,0.00041309395,0.00041880333,0.000067829365],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.007849951,0.0000930728,0.00011687911,0.00025188006,0.00038417886,0.00055103283,0.0004979376,0.00007929204,0.0003428897],"category_scores_gemma":[0.03970731,0.000039095856,0.000058893675,0.0007282609,0.00010007062,0.22201571,0.00010728341,0.00011825641,0.00006809246],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012002899,0.00001617012,0.0025527321,0.000054510507,0.000013823538,1.9310146e-7,0.00044189117,0.00008367522,0.0002594773,0.4592383,0.013893228,0.5222457],"study_design_scores_gemma":[0.00036301467,0.0001876801,0.0077188443,0.0005063029,0.000015673619,0.000004178772,0.0014304501,0.008192544,0.005942598,0.0024631748,0.9730743,0.00010122669],"about_ca_topic_score_codex":4.4532834e-7,"about_ca_topic_score_gemma":4.899889e-8,"teacher_disagreement_score":0.9591811,"about_ca_system_score_codex":0.000009276787,"about_ca_system_score_gemma":0.00036427254,"threshold_uncertainty_score":0.96838164},"labels":[],"label_agreement":null},{"id":"W2299598717","doi":"10.14288/1.0167083","title":"A theory of program evaluation practices in disability management","year":2014,"lang":"en","type":"article","venue":"cIRcle (University of British Columbia)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Business","score_opus":0.11692346948793358,"score_gpt":0.38914839492370384,"score_spread":0.27222492543577026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2299598717","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9776469,0.000024406125,0.0007089451,0.00017481801,0.00008261575,0.0007847614,0.000009776311,0.000016210395,0.0205516],"genre_scores_gemma":[0.9978075,0.000025794612,0.0017390398,0.0000180389,0.000008309301,0.000005019832,0.0000063440352,0.0000028478005,0.00038709524],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9970999,0.0007676318,0.00028647782,0.0003430823,0.0013769823,0.000125971],"domain_scores_gemma":[0.99800366,0.0004629463,0.00060886337,0.00043290024,0.0004448026,0.000046828696],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011592118,0.000028164804,0.00020496239,0.00006553553,0.00008108076,0.00009105279,0.00045610146,0.000047512156,0.0009863742],"category_scores_gemma":[0.00085447915,0.00007430628,0.000076179895,0.0006063994,0.00027525602,0.0005995333,0.00012598638,0.0000717448,0.000026765585],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015576983,0.00031440656,0.16550648,0.00002649604,0.000009875406,0.0000010651403,0.00021379751,0.00008631017,0.0000079462425,0.000046271143,0.00017373096,0.833598],"study_design_scores_gemma":[0.0009011443,0.00011608966,0.9629053,0.000053471213,0.000031416548,0.0000015815365,0.005538257,0.014064685,5.513153e-7,0.0152186155,0.0010969264,0.00007195554],"about_ca_topic_score_codex":0.00771156,"about_ca_topic_score_gemma":0.1794924,"teacher_disagreement_score":0.8335261,"about_ca_system_score_codex":0.00007592538,"about_ca_system_score_gemma":0.000071063,"threshold_uncertainty_score":0.99992687},"labels":[],"label_agreement":null},{"id":"W2299804191","doi":"10.3390/safety2010008","title":"Conceptual and Methodological Issues in Evaluations of Road Safety Countermeasures","year":2016,"lang":"en","type":"article","venue":"Safety","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Attribution; Conceptualization; Causal chain; Process (computing); Conceptual model; Countermeasure; Logic model; Management science; Risk analysis (engineering); Interpretation (philosophy); Computer science; Process management; Engineering; Psychology; Business; Social psychology; Artificial intelligence","score_opus":0.4366055193485413,"score_gpt":0.5708529922143779,"score_spread":0.1342474728658366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2299804191","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91277474,0.000986591,0.031084508,0.02437044,0.00051393046,0.00061560003,0.0001352239,0.000039441555,0.029479532],"genre_scores_gemma":[0.9955574,0.00043681703,0.0025353148,0.00015720211,0.000036187896,0.000008827109,0.0000021813141,0.0000033176757,0.0012627182],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99636495,0.0012060993,0.0007672042,0.00029217484,0.0012150035,0.00015458239],"domain_scores_gemma":[0.99622905,0.0028862078,0.00019714262,0.0003126653,0.000317312,0.00005763612],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011909673,0.000092140064,0.00030668522,0.0001337976,0.00007425358,0.00002190671,0.00025123777,0.00006968738,0.004834601],"category_scores_gemma":[0.0056249574,0.00004800065,0.000050917508,0.00029112908,0.00037432177,0.0002788465,0.00008337463,0.00006641242,0.000107155145],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004531855,0.000084907166,0.19281486,0.0000034823638,0.000018952378,0.0000015586576,0.002827605,0.00017870041,0.0056572454,0.040748138,0.0018787666,0.7553326],"study_design_scores_gemma":[0.001044846,0.000108645065,0.9448656,0.00003752586,0.0000063892544,0.0000029541125,0.0011376599,0.00065795984,0.00063455297,0.013875157,0.037536882,0.00009183953],"about_ca_topic_score_codex":0.00003332115,"about_ca_topic_score_gemma":0.00018464096,"teacher_disagreement_score":0.75524074,"about_ca_system_score_codex":0.000050453073,"about_ca_system_score_gemma":0.00015245663,"threshold_uncertainty_score":0.9960751},"labels":[],"label_agreement":null},{"id":"W2299937421","doi":"10.3138/cjpe.28.003","title":"Outsource Versus In-House? An Identification of Organizational Conditions Influencing the Choice for Internal or External Evaluators","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Outsourcing; Flemish; Pairwise comparison; Discretion; Identification (biology); Business; Public sector; Locus of control; Marketing; Computer science; Psychology; Social psychology; Political science; Law","score_opus":0.31042600741340926,"score_gpt":0.5320363808943255,"score_spread":0.22161037348091622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2299937421","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99110186,0.000090818256,0.004990685,0.0010127496,0.0009577545,0.0017189381,0.000014949314,0.000009373686,0.0001028624],"genre_scores_gemma":[0.99786884,0.000003384589,0.0014422839,0.00012212583,0.00022705966,0.0002048165,0.000014835935,0.000017514136,0.00009915906],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9955355,0.00056225,0.001542414,0.0002029536,0.0019227989,0.00023409016],"domain_scores_gemma":[0.9910207,0.0009889709,0.001355603,0.00031614874,0.006047868,0.00027073539],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011502423,0.00012085469,0.0002104974,0.0007044006,0.0002451655,0.00047889721,0.00072343554,0.0000732066,0.0027813313],"category_scores_gemma":[0.008697866,0.00007948179,0.00009632278,0.0009214937,0.0001365331,0.0013458112,0.000014010151,0.00017999683,0.000049920014],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023564145,0.00024264364,0.35247943,0.000022350003,0.000114475166,0.0000016508028,0.010540625,0.050902758,0.0033951406,0.002173691,0.002465645,0.57742596],"study_design_scores_gemma":[0.0028554704,0.0008346718,0.7717471,0.000079617836,0.000121827594,0.000022722845,0.0057751536,0.204349,0.00085168966,0.010860137,0.0023425748,0.00016003879],"about_ca_topic_score_codex":0.0011558793,"about_ca_topic_score_gemma":0.022555443,"teacher_disagreement_score":0.5772659,"about_ca_system_score_codex":0.00045124764,"about_ca_system_score_gemma":0.004315408,"threshold_uncertainty_score":0.99965227},"labels":[],"label_agreement":null},{"id":"W2302098269","doi":"10.1177/0193841x16637950","title":"How Do Evaluators Differentiate Successful From Less-Than-Successful Experiences With Collaborative Approaches to Evaluation?","year":2016,"lang":"en","type":"article","venue":"Evaluation Review","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; Queen's University; University of Ottawa","funders":"University of Ottawa","keywords":"Stakeholder; Antecedent (behavioral psychology); Psychology; Control (management); Computer-assisted web interviewing; Applied psychology; Knowledge management; Medical education; Social psychology; Public relations; Computer science; Political science; Business; Marketing; Medicine","score_opus":0.4512052275898277,"score_gpt":0.4632224952179479,"score_spread":0.01201726762812022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2302098269","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89155376,0.035332173,0.012257058,0.044442862,0.001119952,0.008307938,0.00012322952,0.00010871651,0.0067542857],"genre_scores_gemma":[0.9875416,0.0024545793,0.0014131113,0.0011465873,0.0002551433,0.006001501,0.00008972424,0.00004012029,0.0010576345],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.97721094,0.00516171,0.0016038335,0.00178119,0.013663849,0.0005784689],"domain_scores_gemma":[0.9890987,0.0016659063,0.0014054758,0.0018203985,0.005571951,0.0004375296],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.025448257,0.0006103596,0.0010893012,0.00047631975,0.00049192767,0.0012676689,0.0015179805,0.00013760045,0.023181902],"category_scores_gemma":[0.0068408926,0.00031649723,0.00021978641,0.0032830173,0.0002480286,0.002438165,0.00021629638,0.00016821362,0.0011803685],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013037425,0.00020803815,0.037016418,0.00009240625,0.00018196343,0.0000013437661,0.007926441,0.000252876,0.00011702149,0.0010088573,0.010144334,0.9429199],"study_design_scores_gemma":[0.025731193,0.003795957,0.33307865,0.02531322,0.0066817235,0.000032172054,0.23301339,0.07742056,0.0108191,0.06644071,0.2094437,0.0082296245],"about_ca_topic_score_codex":0.000024381407,"about_ca_topic_score_gemma":0.0003772673,"teacher_disagreement_score":0.9346903,"about_ca_system_score_codex":0.0004785463,"about_ca_system_score_gemma":0.0020789178,"threshold_uncertainty_score":0.9999287},"labels":[],"label_agreement":null},{"id":"W2302461675","doi":"","title":"Evidence and Healthy Public Policy: Multiple Sciences, Multiple Frameworks","year":2009,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Public policy; Identification (biology); Political science; Policy studies; Process (computing); Evidence-based policy; Policy analysis; Politics; Policy making; Policy Sciences; Health policy; Science policy; Population; Public administration; Scientific evidence; Public health; Public relations; Public economics; Sociology; Economics; Health care; Epistemology; Law; Medicine; Computer science","score_opus":0.19164723118434948,"score_gpt":0.48363536764059967,"score_spread":0.2919881364562502,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2302461675","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75832087,0.013724873,0.048161794,0.17727384,0.00044353912,0.00035661153,0.0000024648532,0.000064710555,0.0016513123],"genre_scores_gemma":[0.98354495,0.010014927,0.0011121236,0.0042254888,0.0005479947,0.0000042471056,6.6439503e-7,0.0000072715065,0.0005423421],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99391955,0.0004193591,0.0007317401,0.00047755722,0.0021136287,0.0023381708],"domain_scores_gemma":[0.99696344,0.0015162562,0.00042633232,0.00035029082,0.0004322217,0.0003114863],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.02134375,0.00018525678,0.00026880405,0.0006601723,0.0011636477,0.0009280891,0.0009506139,0.0001667268,0.00015071892],"category_scores_gemma":[0.009339102,0.00013117642,0.000100418576,0.001551324,0.00020101485,0.0017206728,0.000076788565,0.002430273,0.00010815544],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006832039,0.000082701285,0.13720708,0.0000013813991,0.000014821542,0.0000011897341,0.00031778993,0.0002783524,0.00014650976,0.14746931,0.0005309094,0.7138817],"study_design_scores_gemma":[0.0013291816,0.0021985346,0.114806026,0.000069105496,0.000010301044,0.00047576998,0.002731463,0.030770335,0.00003763703,0.8334415,0.01377971,0.0003504462],"about_ca_topic_score_codex":0.00009088157,"about_ca_topic_score_gemma":0.0014943382,"teacher_disagreement_score":0.7135312,"about_ca_system_score_codex":0.0007405213,"about_ca_system_score_gemma":0.010106931,"threshold_uncertainty_score":0.99987113},"labels":[],"label_agreement":null},{"id":"W2304313297","doi":"10.5539/jel.v5n2p258","title":"Improving Law Enforcement Cross Cultural Competencies through Continued Education","year":2016,"lang":"en","type":"article","venue":"Journal of Education and Learning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Law enforcement; Enforcement; Interpersonal communication; Multiculturalism; Public relations; Criminal justice ethics; Political science; Cultural diversity; Law; Sociology; Public administration; Criminal justice; Social science","score_opus":0.11409166678806483,"score_gpt":0.49923279841919815,"score_spread":0.38514113163113334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2304313297","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9591861,0.0005152641,0.003372027,0.0024853568,0.0018411772,0.00008206627,4.2505914e-7,0.000007899038,0.032509726],"genre_scores_gemma":[0.981753,0.00008749125,0.0028128962,0.0008013508,0.000330019,0.0000039329084,0.0000011916393,0.0000042804554,0.014205831],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981744,0.00021863384,0.00065354665,0.00012969864,0.0007046937,0.00011902024],"domain_scores_gemma":[0.9969406,0.0004101903,0.000908816,0.00010820145,0.0015458574,0.000086314816],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0026121307,0.00008323457,0.00015937508,0.00010804428,0.00032385936,0.00043076303,0.00017692377,0.000035702917,0.0012034902],"category_scores_gemma":[0.0016400785,0.000044601748,0.000065794105,0.00015148144,0.0000990187,0.0016447192,0.000028569897,0.00016927517,0.000044656343],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053275046,0.00018741644,0.08108536,0.000013080759,0.000022125567,2.5267542e-7,0.012407188,0.00014809318,0.011569836,0.07068834,0.0045740185,0.819251],"study_design_scores_gemma":[0.0007483307,0.00025640384,0.060109917,0.00015675076,0.00001988255,0.00006933318,0.037045974,0.00028407114,0.0012345003,0.0042751157,0.89564466,0.00015503413],"about_ca_topic_score_codex":0.000081685386,"about_ca_topic_score_gemma":0.000014966668,"teacher_disagreement_score":0.89107066,"about_ca_system_score_codex":0.00008604703,"about_ca_system_score_gemma":0.0007539134,"threshold_uncertainty_score":0.99970955},"labels":[],"label_agreement":null},{"id":"W2307309931","doi":"10.14288/1.0099007","title":"Community plan monitoring : a case study","year":2009,"lang":"en","type":"article","venue":"cIRcle (University of British Columbia)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Plan (archaeology); Computer science; Business; Geography","score_opus":0.14190734775545424,"score_gpt":0.363649649647745,"score_spread":0.22174230189229074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2307309931","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9960471,0.00001902385,0.00016708321,0.00011499167,0.00014634365,0.00023195193,0.000021784408,0.000041063275,0.003210683],"genre_scores_gemma":[0.9986807,0.000007987802,0.00024810038,0.000033507615,0.000024409948,2.1337907e-7,0.0000018081915,0.0000029873913,0.0010002526],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99810624,0.0004361533,0.00020830624,0.00022994156,0.0008592383,0.00016013812],"domain_scores_gemma":[0.99860734,0.00020284348,0.0001663963,0.0005444067,0.000365862,0.00011315556],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024942,0.00003357729,0.00022113838,0.00007833943,0.00077371567,0.0002628241,0.0006089933,0.000047330523,0.00030831885],"category_scores_gemma":[0.00013358047,0.00010325985,0.000077838056,0.0005164992,0.00008027829,0.0005450531,0.00012377003,0.00022930896,0.000056274737],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000054531483,0.0004271409,0.25810897,0.0000021491387,0.000010630109,0.0008877706,0.0034098828,0.000027436174,0.000023959703,3.324858e-7,0.0012467313,0.73584956],"study_design_scores_gemma":[0.00075868284,0.00033086562,0.870237,0.000020579748,0.000014985198,0.00037501391,0.12728664,0.00029571608,3.3615478e-7,0.00041550223,0.00017161499,0.00009305252],"about_ca_topic_score_codex":0.14003068,"about_ca_topic_score_gemma":0.37848136,"teacher_disagreement_score":0.73575646,"about_ca_system_score_codex":0.000054698725,"about_ca_system_score_gemma":0.00009087616,"threshold_uncertainty_score":0.86569595},"labels":[],"label_agreement":null},{"id":"W2309457767","doi":"10.3138/cjpe.028.001","title":"Les défis de l’évaluation développementale en recherche : une analyse d’implantation d’un projet «hôpital promoteur de santé»","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Université de Montréal","funders":"","keywords":"Valuation (finance); Context (archaeology); Sociology; Library science; Psychology; Computer science; Business; Geography","score_opus":0.4962628710410104,"score_gpt":0.5603129622147885,"score_spread":0.06405009117377813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2309457767","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9806677,0.00015303359,0.009298029,0.005174303,0.00026093502,0.0018830778,0.000008738362,0.000019372748,0.0025348156],"genre_scores_gemma":[0.9436803,0.00003272679,0.05540807,0.00019416932,0.00022371333,0.00025983882,0.00005569751,0.00001770585,0.00012777565],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99132836,0.0044999425,0.0012160138,0.0002864493,0.0021954896,0.00047375564],"domain_scores_gemma":[0.9944783,0.00074241543,0.0009437529,0.000295631,0.003010384,0.0005295089],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.046370625,0.00019421625,0.00027824653,0.00089523994,0.00033132712,0.0007070454,0.00053672306,0.00022138766,0.004675667],"category_scores_gemma":[0.0069134627,0.00015852405,0.00015609355,0.0014118239,0.00008032482,0.0012196079,0.000017587707,0.00043292588,0.00017047995],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013464266,0.00006641555,0.112634405,0.00000661396,0.000049850532,0.0000048651027,0.010467548,0.0010882404,0.0013675771,0.000053681993,0.0015126717,0.87273467],"study_design_scores_gemma":[0.001118983,0.00052384613,0.8167486,0.000055151544,0.00019077765,0.00015862632,0.0093566375,0.13682427,0.0015009056,0.03136312,0.0019315212,0.00022752782],"about_ca_topic_score_codex":0.006120562,"about_ca_topic_score_gemma":0.019826781,"teacher_disagreement_score":0.87250715,"about_ca_system_score_codex":0.0026280512,"about_ca_system_score_gemma":0.0072604986,"threshold_uncertainty_score":0.9983674},"labels":[],"label_agreement":null},{"id":"W2311665238","doi":"10.56645/jmde.v12i26.437","title":"Book Review: Evaluating Communication for Development: A Framework for Social Change","year":2016,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Social change; Sociology; Political science","score_opus":0.5475983103789693,"score_gpt":0.6087747331216172,"score_spread":0.061176422742647896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2311665238","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06497585,0.12928167,0.64005065,0.15402745,0.0020485595,0.009282116,0.000059833845,0.00004027705,0.00023361969],"genre_scores_gemma":[0.3089563,0.01563419,0.6481081,0.013614448,0.004150811,0.005398609,0.00014085228,0.00012927827,0.0038673973],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99364775,0.00083733245,0.0019318796,0.00027388215,0.0030616473,0.0002474873],"domain_scores_gemma":[0.9868597,0.0043407106,0.0026484374,0.00038544883,0.00567688,0.00008886378],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04425866,0.0001710157,0.0004457327,0.00030151903,0.0006991327,0.00008067839,0.0006788276,0.00011923394,0.0012208633],"category_scores_gemma":[0.011538807,0.000102516904,0.00029846723,0.00033073852,0.000057831996,0.001472148,0.00011044194,0.00012987225,0.00004531691],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040224142,0.00015307481,0.000582914,0.0001234686,0.000055928514,1.257594e-7,0.0054708086,0.00004656855,0.00068622536,0.0007032807,0.07345148,0.9183239],"study_design_scores_gemma":[0.012908835,0.002293864,0.096926615,0.008351177,0.00081964955,0.000031373325,0.0016917037,0.09599756,0.0018413047,0.14750783,0.6307495,0.00088053755],"about_ca_topic_score_codex":2.8455054e-7,"about_ca_topic_score_gemma":0.0000049644486,"teacher_disagreement_score":0.91744334,"about_ca_system_score_codex":0.00038850043,"about_ca_system_score_gemma":0.0008374989,"threshold_uncertainty_score":0.99969214},"labels":[],"label_agreement":null},{"id":"W2312660621","doi":"10.3138/cjpe.0020.008","title":"How Do You Evaluate a Network? A Canadian Child and Youth Health Network Experience","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Calgary; Alberta Health Services","funders":"","keywords":"Key (lock); Child health; Value (mathematics); Program evaluation; Psychology; Knowledge management; Public relations; Business; Computer science; Medicine; Political science; Family medicine; Computer security; Machine learning; Public administration","score_opus":0.2193611529595739,"score_gpt":0.46515968894757764,"score_spread":0.24579853598800375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2312660621","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78329176,0.040886633,0.003608288,0.12778202,0.007434759,0.008144337,0.00013584299,0.00007059203,0.028645772],"genre_scores_gemma":[0.99432105,0.000058674887,0.0027867912,0.0012894424,0.0011751113,0.000060021306,0.000040460334,0.000018541405,0.00024992914],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9941681,0.0009572637,0.0010139862,0.0003999517,0.0025201759,0.0009405349],"domain_scores_gemma":[0.9947832,0.000096882606,0.0010535774,0.00040935457,0.002098518,0.0015584438],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.02030199,0.00023292995,0.00041980846,0.0006574037,0.0010078365,0.0017873374,0.0005189229,0.000115158735,0.00059778907],"category_scores_gemma":[0.0009549903,0.00018879739,0.00012989187,0.0013903403,0.0001695992,0.00089570205,0.000017930348,0.0003362503,0.000018520395],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020679221,0.000025421848,0.09494039,0.0000056155855,0.000032242904,0.000008791056,0.005623577,0.033628788,7.3306467e-7,0.0021754345,0.027977206,0.8355611],"study_design_scores_gemma":[0.0027311877,0.0014070094,0.33627304,0.0004053582,0.00018280352,0.0002992463,0.012601619,0.103174075,0.000004455383,0.024606658,0.5176031,0.0007114657],"about_ca_topic_score_codex":0.07389688,"about_ca_topic_score_gemma":0.8208237,"teacher_disagreement_score":0.83484966,"about_ca_system_score_codex":0.0008943471,"about_ca_system_score_gemma":0.011043857,"threshold_uncertainty_score":0.9992489},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":true,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W2313199284","doi":"10.3138/cjpe.30.2.231","title":"Donaldson, S. L. (Ed.). <i>The future of evaluation in society: A tribute to Michael Scriven.</i>","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Tribute; Theology; Art; Political science; Philosophy; Art history","score_opus":0.25324641466730924,"score_gpt":0.4940376517860622,"score_spread":0.24079123711875294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2313199284","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9095636,0.00687285,0.0021938097,0.072418146,0.0032362514,0.004419117,0.00003355996,0.000009397805,0.001253258],"genre_scores_gemma":[0.99352926,0.00002941749,0.0045761582,0.0010732039,0.00048784254,0.00015271708,0.000020703746,0.000011432044,0.00011924938],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99204725,0.0012419184,0.0013379847,0.00023424772,0.0048185233,0.00032006606],"domain_scores_gemma":[0.98926383,0.00022249717,0.00088278466,0.00037973322,0.008667211,0.00058391906],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.057842333,0.00014446763,0.00031824142,0.00057707087,0.00012435463,0.00022277268,0.0005986534,0.000108059416,0.0005971373],"category_scores_gemma":[0.003229001,0.00009822789,0.00019712924,0.0018057869,0.00009533592,0.00057934877,0.00002349228,0.00027244468,0.000059367834],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050918206,0.000061716055,0.018313395,0.000004330235,0.00002949601,0.0000021487187,0.006794015,0.015635667,0.00006789605,0.00016292075,0.11891209,0.8399654],"study_design_scores_gemma":[0.0049886927,0.001407957,0.10350493,0.00015406388,0.0002538432,0.00006910083,0.018107587,0.20504865,0.00027934735,0.027845385,0.6380162,0.0003241897],"about_ca_topic_score_codex":0.00070413965,"about_ca_topic_score_gemma":0.044976536,"teacher_disagreement_score":0.8396412,"about_ca_system_score_codex":0.0008590298,"about_ca_system_score_gemma":0.012091754,"threshold_uncertainty_score":0.99350876},"labels":[],"label_agreement":null},{"id":"W2313407085","doi":"10.1332/174426412x654031","title":"Use of research-based information by school practitioners and determinants of use: a review of empirical research","year":2012,"lang":"en","type":"review","venue":"Evidence & Policy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":173,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; Université de Montréal; Centre de Liaison Sur l'Intervention et la Prévention Psychosociales","funders":"","keywords":"Empirical research; Research policy; Public relations; Knowledge management; Psychology; Medical education; Political science; Medicine; Computer science; Public administration","score_opus":0.8888262891940105,"score_gpt":0.7463502074399516,"score_spread":0.1424760817540589,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2313407085","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00047423434,0.99608386,0.000030216726,0.0013728997,0.00006131565,0.0016518601,0.00015213365,0.0000066219736,0.00016685003],"genre_scores_gemma":[0.0010790996,0.99748266,0.0005037773,0.00028369416,0.00007111188,0.00014254428,0.00003115755,0.00001295596,0.00039303087],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98466,0.005123359,0.00298491,0.00035783052,0.006384028,0.00048986374],"domain_scores_gemma":[0.976152,0.015198956,0.0022696902,0.001257446,0.004814682,0.00030720132],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.038577177,0.00023384287,0.0015267187,0.002444659,0.00014496282,0.00020799928,0.000904686,0.0002528263,0.0006437538],"category_scores_gemma":[0.11593154,0.00015922464,0.00026347264,0.0047708284,0.0010319568,0.005542263,0.00035879904,0.0007607568,0.0002492222],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030257268,0.00009369468,0.0040189065,0.061144195,0.000020229692,4.7074354e-7,0.00023004379,0.000001137935,0.0000032514645,0.00025033284,0.058183085,0.87602437],"study_design_scores_gemma":[0.00007691131,0.00018559919,0.0011488473,0.11877302,0.00007276798,0.0000066520674,0.00005246864,0.00006632446,0.000021739103,0.00008571434,0.87938833,0.00012160546],"about_ca_topic_score_codex":0.00071597344,"about_ca_topic_score_gemma":0.000021374526,"teacher_disagreement_score":0.8759028,"about_ca_system_score_codex":0.00027402572,"about_ca_system_score_gemma":0.006814746,"threshold_uncertainty_score":0.9988157},"labels":[],"label_agreement":null},{"id":"W2314685856","doi":"10.2975/28.2004.55.62","title":"Conditions facilitating knowledge exchange between rehabilitation and research teams—A study.","year":2004,"lang":"en","type":"article","venue":"Psychiatric Rehabilitation Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Knowledge management; Process (computing); Quality (philosophy); Information exchange; Rehabilitation; Psychology; Computer science","score_opus":0.17421628038214132,"score_gpt":0.5481501127572728,"score_spread":0.37393383237513145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2314685856","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97150904,0.0005191737,0.0033705193,0.018916983,0.00081190414,0.0011890348,0.000021399075,0.0000456051,0.0036163332],"genre_scores_gemma":[0.9749504,0.00003092534,0.023830967,0.00004464241,0.0006769016,0.00012892071,0.0000075067796,0.000018907656,0.00031086468],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9902313,0.0033727963,0.0018841155,0.0007188441,0.0032874665,0.000505509],"domain_scores_gemma":[0.979021,0.016389927,0.00050912023,0.0005911949,0.0030983489,0.00039039535],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03978296,0.00022685577,0.00040731742,0.0022398194,0.0018749972,0.0007191751,0.0005309263,0.000114899725,0.0006697668],"category_scores_gemma":[0.018731048,0.00018045293,0.00018346997,0.0033122257,0.0003768096,0.0014433238,0.00009659534,0.00086674676,0.0005348816],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006062776,0.00078978407,0.78628916,0.00005772684,0.000045790177,0.0000014214695,0.09413552,0.0009158431,0.00004953473,0.006061053,0.0058062375,0.10578729],"study_design_scores_gemma":[0.0023326748,0.0031609666,0.636121,0.000034883044,0.000024482295,0.000015926462,0.11422882,0.00015814166,0.0000019572994,0.23669039,0.0070529594,0.00017782424],"about_ca_topic_score_codex":0.000042934607,"about_ca_topic_score_gemma":0.00012053398,"teacher_disagreement_score":0.23062934,"about_ca_system_score_codex":0.00048128644,"about_ca_system_score_gemma":0.00083477935,"threshold_uncertainty_score":0.9994244},"labels":[],"label_agreement":null},{"id":"W2315267983","doi":"10.1016/s1499-2671(11)52268-3","title":"Developing a performance measurement and evaluation framework for the Albert Obesity Program","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Diabetes","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Alberta Health Services","funders":"","keywords":"Medicine; Work (physics); Logic model; Outcome (game theory); Set (abstract data type); Obesity; Continuum of care; Service delivery framework; Service (business); Process management; Gerontology; Health care; Marketing; Economic growth; Engineering; Public administration; Computer science","score_opus":0.3967107575320211,"score_gpt":0.43854443832341033,"score_spread":0.041833680791389216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2315267983","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9914816,0.0012692633,0.0032041983,0.002315719,0.000616402,0.00055146165,0.0000020808066,0.0000030930937,0.00055619294],"genre_scores_gemma":[0.9844342,0.000016464302,0.014971444,0.00041004448,0.00009739036,0.000045254586,3.551358e-7,0.000005178166,0.000019702944],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9979839,0.000118881486,0.00046007015,0.000118545744,0.0010789817,0.00023966258],"domain_scores_gemma":[0.9967503,0.00047799546,0.00033621993,0.00018043588,0.0020317642,0.00022327848],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011985771,0.00008492327,0.00015325569,0.00018781914,0.00037378582,0.00018805255,0.00037583214,0.00004693551,0.00030963626],"category_scores_gemma":[0.0028950614,0.000049851857,0.00006094125,0.000263108,0.00008526381,0.00035197855,0.000011725775,0.00012732302,0.000009236187],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003175337,0.000011551747,0.48643512,0.00000868569,0.000042359523,1.0733087e-7,0.0017352249,0.000040345785,0.0000042458714,0.0022767521,0.00069788925,0.50874454],"study_design_scores_gemma":[0.0003028456,0.00027261578,0.93959475,0.000118493626,0.00006412357,0.0000016458143,0.0007127921,0.013396031,0.00037388704,0.030326566,0.014732805,0.00010343237],"about_ca_topic_score_codex":0.00006634658,"about_ca_topic_score_gemma":0.0044521107,"teacher_disagreement_score":0.5086411,"about_ca_system_score_codex":0.00018564642,"about_ca_system_score_gemma":0.002362479,"threshold_uncertainty_score":0.4190936},"labels":[],"label_agreement":null},{"id":"W231595241","doi":"10.3138/cjpe.0015.006","title":"Incorporating Stakeholders in Standard Setting: What’s at Stake?","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Representativeness heuristic; Stakeholder; Insider; Psychology; Scale (ratio); Decision maker; Applied psychology; Rating scale; Public relations; Social psychology; Political science; Management science; Economics","score_opus":0.5441481476401734,"score_gpt":0.5151732825914709,"score_spread":0.028974865048702503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W231595241","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9862941,0.0007581755,0.00057569164,0.0066544735,0.0011349017,0.00097272824,0.000005660514,0.000009094681,0.0035951836],"genre_scores_gemma":[0.99620086,0.000036664685,0.0030103237,0.0002986982,0.00013324695,0.0000345645,0.000013876926,0.000011709628,0.0002600263],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9943571,0.000723056,0.0013392075,0.00023894428,0.0029720352,0.00036965788],"domain_scores_gemma":[0.9954486,0.00026636157,0.0010495537,0.0002826304,0.002449964,0.00050287956],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.026334228,0.00013877972,0.00027417153,0.0010491449,0.0002453227,0.00092304783,0.00042210665,0.00008482926,0.0029944142],"category_scores_gemma":[0.0029605064,0.00011428598,0.00010202342,0.0012825395,0.00008887743,0.002007905,0.000017497112,0.00026481252,0.00006620224],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039750666,0.000018878067,0.16204154,0.000002172063,0.000009366272,0.00003314413,0.001593114,0.006900007,0.000027490525,0.00014298028,0.0022474977,0.82694405],"study_design_scores_gemma":[0.0068170764,0.0021628293,0.33944008,0.00054217654,0.00011735103,0.00035404923,0.045835357,0.15797001,0.00030144595,0.039977152,0.40574792,0.0007345328],"about_ca_topic_score_codex":0.00035681768,"about_ca_topic_score_gemma":0.13074769,"teacher_disagreement_score":0.82620955,"about_ca_system_score_codex":0.0014845455,"about_ca_system_score_gemma":0.0060980422,"threshold_uncertainty_score":0.99953645},"labels":[],"label_agreement":null},{"id":"W2316547733","doi":"10.3138/cjpe.016.002","title":"The Strong Focus on Output Information: A Threat to Evaluation in the Swedish State Sector?","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Public sector; Public interest; State (computer science); Quality (philosophy); Focus (optics); Business; Information management; Private sector; Management information systems; Information system; Public relations; Economics; Public economics; Political science; Economic growth; Computer science; Management","score_opus":0.39228625282051927,"score_gpt":0.5057903060285184,"score_spread":0.11350405320799911,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2316547733","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9296169,0.000359029,0.0020306783,0.03907496,0.0017417582,0.0048316983,0.00001234405,0.00001125497,0.022321353],"genre_scores_gemma":[0.9983776,0.000018702096,0.0002030232,0.0008177924,0.00019254774,0.0002749097,0.000009961344,0.0000062464696,0.000099175326],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9918308,0.0013920533,0.0011916717,0.00016154847,0.0050390232,0.00038485235],"domain_scores_gemma":[0.9945304,0.00070772396,0.0006494728,0.00046421489,0.003343447,0.0003047404],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.044585217,0.00014719686,0.00017811467,0.0007410806,0.0005064581,0.00136355,0.0008506008,0.00004887099,0.00065325544],"category_scores_gemma":[0.0045954734,0.0000795599,0.00010648688,0.0015213533,0.00006519064,0.001258406,0.000013384366,0.00030806946,0.00022845413],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048883117,0.000019308527,0.01053879,7.5301875e-7,0.000011268032,0.000002785667,0.00541638,0.02393267,6.030629e-7,0.0006096287,0.005417606,0.9540013],"study_design_scores_gemma":[0.0023976266,0.0016213286,0.524615,0.00008830272,0.000091105474,0.00008753352,0.01140397,0.17966206,0.00002099453,0.0547522,0.22499867,0.00026118488],"about_ca_topic_score_codex":0.00074987265,"about_ca_topic_score_gemma":0.08875212,"teacher_disagreement_score":0.9537401,"about_ca_system_score_codex":0.000839934,"about_ca_system_score_gemma":0.00406931,"threshold_uncertainty_score":0.9996731},"labels":[],"label_agreement":null},{"id":"W2317225213","doi":"10.1177/000841740907600101","title":"Extending an Invitation for Discussion and Debate","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Occupational Therapy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Sociology; Political science","score_opus":0.5046695147813165,"score_gpt":0.5740637033938376,"score_spread":0.06939418861252111,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2317225213","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97589254,0.00027385307,0.015216134,0.007907121,0.00034496418,0.00014753365,0.000017649896,0.0000023969,0.00019783182],"genre_scores_gemma":[0.9939563,0.000036825175,0.0038328117,0.0018297508,0.00016896611,0.0000017308615,0.00000929752,0.0000033027538,0.0001609946],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9988405,0.00008449776,0.00039208186,0.0001010547,0.00046888232,0.00011298871],"domain_scores_gemma":[0.99858,0.00017654408,0.00026714994,0.00008797012,0.00059197814,0.00029638442],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022333234,0.00006148142,0.00011008602,0.00039201003,0.00022219575,0.00019804348,0.00016692145,0.000031076,0.00026665334],"category_scores_gemma":[0.00034335817,0.000035011508,0.000047755533,0.00017989158,0.000026088022,0.00080796436,0.0000012431489,0.000054778582,0.0000033132926],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025092336,0.000023222672,0.050470907,7.3593185e-7,0.000009980537,0.0000032990524,0.0017825369,0.0007970055,0.001038999,0.008377052,0.0035706125,0.93367475],"study_design_scores_gemma":[0.00094806793,0.0007290164,0.8620139,0.000016317194,0.000003717662,0.000034955152,0.00054359075,0.0046341787,0.00019116756,0.07857118,0.052219126,0.00009483327],"about_ca_topic_score_codex":0.000029347317,"about_ca_topic_score_gemma":0.0008922888,"teacher_disagreement_score":0.9335799,"about_ca_system_score_codex":0.000056363315,"about_ca_system_score_gemma":0.0008069767,"threshold_uncertainty_score":0.2919667},"labels":[],"label_agreement":null},{"id":"W2317895816","doi":"10.1177/171516350714000301","title":"More than 100 Years of Leading Change","year":2007,"lang":"en","type":"article","venue":"Canadian Pharmacists Journal / Revue des Pharmaciens du Canada","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"History","score_opus":0.28739210589326497,"score_gpt":0.4677343953940254,"score_spread":0.18034228950076042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2317895816","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99115807,0.00053662056,0.0003216074,0.0002910697,0.0030048874,0.00027424746,0.00016707493,0.00001317387,0.0042332406],"genre_scores_gemma":[0.9940242,0.0007522159,0.00022655229,0.002591113,0.00094952865,0.000005934216,0.000009574325,0.000029190182,0.0014116884],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99545616,0.00016846492,0.0011267683,0.00037849764,0.0019097391,0.00096037536],"domain_scores_gemma":[0.9955229,0.0004284843,0.00058905344,0.00036471966,0.0011277305,0.0019671037],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0061600124,0.00024777825,0.00043031393,0.0010498585,0.0005102858,0.00022245859,0.0011746988,0.00006315808,0.0030919095],"category_scores_gemma":[0.0006485538,0.0002426561,0.000182542,0.0015659204,0.00021331664,0.0007879248,0.000055102697,0.0005055977,0.00006371023],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010369889,0.0000467718,0.0490191,0.000048866474,0.000110446665,0.018732341,0.0077740247,0.00082375645,0.0027351896,0.00019358139,0.029796565,0.89061564],"study_design_scores_gemma":[0.004772782,0.00021013385,0.017971925,0.000091649934,0.00021047491,0.2587114,0.00072261284,0.015922653,0.015100553,0.00081215147,0.68370396,0.0017697021],"about_ca_topic_score_codex":0.024053723,"about_ca_topic_score_gemma":0.2546875,"teacher_disagreement_score":0.888846,"about_ca_system_score_codex":0.001552059,"about_ca_system_score_gemma":0.0036166674,"threshold_uncertainty_score":0.9978194},"labels":[],"label_agreement":null},{"id":"W2318026979","doi":"10.15405/futureacademy/ejsbs(2301-2218).2012.2.13","title":"Why Consistency Is Not Possible In Experienced Teacher Evaluations","year":2012,"lang":"en","type":"article","venue":"The European Journal of Social & Behavioural Sciences","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Consistency (knowledge bases); Psychology; Task (project management); Principal (computer security); Performance appraisal; Process (computing); Christian ministry; Phenomenon; Grounded theory; Employee Performance Appraisal; Pedagogy; Applied psychology; Social psychology; Mathematics education; Computer science; Management; Qualitative research; Epistemology; Political science; Medicine; Nursing","score_opus":0.3937768503371043,"score_gpt":0.5170564721557023,"score_spread":0.12327962181859797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2318026979","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9539205,0.00016118032,0.00011922187,0.014991299,0.00073497696,0.000112025715,0.0000026066243,0.0000067017763,0.029951496],"genre_scores_gemma":[0.9966423,0.000010938569,0.00034845906,0.0017852886,0.00034915603,0.0000021927021,2.447887e-7,0.0000062560293,0.0008551667],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99335945,0.00223127,0.0010290397,0.00016884925,0.0028290665,0.00038235256],"domain_scores_gemma":[0.99815184,0.00029946773,0.00078882027,0.00017423862,0.00044907504,0.0001365336],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.033876266,0.00012559173,0.00022864858,0.00025716276,0.0010604507,0.0003696665,0.0013516434,0.000023661674,0.002915494],"category_scores_gemma":[0.00070256816,0.000066738685,0.00017124756,0.0012104632,0.0007603762,0.0014850124,0.00012024157,0.00029079829,0.0001829797],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005395821,0.0004106948,0.69654524,0.0000013307131,0.000015218885,0.0000109875655,0.13762535,0.00012949835,0.003114007,0.0023425298,0.028472742,0.13127843],"study_design_scores_gemma":[0.00043213874,0.00015916109,0.964356,0.000014811213,0.000024618348,0.000030495425,0.028540837,0.00017493544,0.00039265858,0.00060450676,0.0051387833,0.00013103384],"about_ca_topic_score_codex":0.000042722542,"about_ca_topic_score_gemma":0.000030162639,"teacher_disagreement_score":0.26781076,"about_ca_system_score_codex":0.000077337594,"about_ca_system_score_gemma":0.0002695987,"threshold_uncertainty_score":0.997996},"labels":[],"label_agreement":null},{"id":"W2318178033","doi":"10.1177/1098214013503698","title":"Managing Tensions Between Evaluation and Research","year":2013,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Université de Sherbrooke","funders":"","keywords":"Temporality; Psychological intervention; Software deployment; Process (computing); Management science; Psychology; Sociology; Engineering ethics; Computer science; Epistemology","score_opus":0.47772656074020564,"score_gpt":0.6157514516411698,"score_spread":0.1380248909009642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2318178033","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9802135,0.0001993876,0.0021741558,0.011756685,0.0002013404,0.0005508481,8.9548826e-7,0.0000049271616,0.004898242],"genre_scores_gemma":[0.9969881,0.000068875335,0.002331134,0.00019337679,0.00024846595,0.000028509889,0.0000033859014,0.00000810423,0.00013005408],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9870958,0.0031166677,0.0010039213,0.00024547332,0.008301758,0.00023641392],"domain_scores_gemma":[0.9841439,0.002339619,0.00093663693,0.00033900575,0.012052897,0.00018791875],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0714384,0.00009767957,0.00029961075,0.0010077792,0.00028249988,0.000345456,0.0002885809,0.000030883384,0.0026489745],"category_scores_gemma":[0.007943246,0.000068043286,0.000069343405,0.0014503445,0.0002749547,0.0011634958,0.00007774925,0.0003136753,0.00029543543],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009274296,0.000017721432,0.03604556,8.460693e-7,0.000020698044,2.9884407e-7,0.00085281115,0.00094839314,0.0004935671,0.00010987002,0.0026778397,0.95882314],"study_design_scores_gemma":[0.00074205676,0.00070182025,0.7268568,0.000042068714,0.00010182883,0.000025218918,0.009414387,0.16749005,0.00012892406,0.09252984,0.0018573366,0.00010962672],"about_ca_topic_score_codex":0.000083956744,"about_ca_topic_score_gemma":0.000010992133,"teacher_disagreement_score":0.9587135,"about_ca_system_score_codex":0.00020514267,"about_ca_system_score_gemma":0.0006851025,"threshold_uncertainty_score":0.99826276},"labels":[],"label_agreement":null},{"id":"W2319245188","doi":"10.7202/1024723ar","title":"Raîche, G., Paquette-Côté, K., &amp; Magis, D. (Eds.) (2011). Des mécanismes pour assurer la validité de l’interprétation de la mesure en éducation. Volume 1 – La mesure, et Volume 2 – L’évaluation. Québec, Qc : Presses de l’Université du Québec.","year":2012,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université du Québec à Rimouski","funders":"","keywords":"Philosophy","score_opus":0.06358612308384637,"score_gpt":0.4026810928921547,"score_spread":0.33909496980830833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2319245188","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5475694,0.017870141,0.21841535,0.18094312,0.003831583,0.0022085493,0.00026784965,0.00044777113,0.028446259],"genre_scores_gemma":[0.91997254,0.0076658423,0.020474585,0.00197127,0.00118484,0.00040931723,0.0009893199,0.00016972823,0.047162544],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9383207,0.053425394,0.0019879404,0.0013003052,0.0036023657,0.0013633104],"domain_scores_gemma":[0.97824806,0.01499723,0.0016696012,0.001352714,0.0030724043,0.0006599776],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.12462202,0.0009615011,0.00085720845,0.0009966011,0.00097297726,0.0013458581,0.0012524079,0.0011347801,0.04039145],"category_scores_gemma":[0.019897502,0.0010023024,0.000490965,0.0010956345,0.0005636182,0.0046724463,0.00023331221,0.0012195811,0.00410849],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000083849234,0.000996355,0.33486152,0.00014338971,0.00023944725,0.0000025409108,0.21476476,0.008722602,0.0014789066,0.0012907552,0.40145698,0.035958894],"study_design_scores_gemma":[0.0011186291,0.00008169697,0.6072183,0.00017425859,0.00064946583,0.0001439596,0.0052431007,0.016789172,0.0005437275,0.005506562,0.3618433,0.00068779],"about_ca_topic_score_codex":0.041394413,"about_ca_topic_score_gemma":0.04508874,"teacher_disagreement_score":0.37240317,"about_ca_system_score_codex":0.0048315604,"about_ca_system_score_gemma":0.028837295,"threshold_uncertainty_score":0.99969083},"labels":[],"label_agreement":null},{"id":"W2319861733","doi":"10.1177/1098214014542100","title":"Insights on Using Developmental Evaluation for Innovating","year":2014,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Conceptualization; Process (computing); Knowledge management; Process management; Rendering (computer graphics); Computer science; Psychology; Management science; Business; Engineering; Artificial intelligence","score_opus":0.35735194148799976,"score_gpt":0.5543062644225002,"score_spread":0.19695432293450044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2319861733","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9296078,0.000018883096,0.06633253,0.00050017354,0.0005733205,0.00041749162,9.793494e-7,0.000004641747,0.0025441882],"genre_scores_gemma":[0.9637597,0.0000015765262,0.03519446,0.00067376293,0.00031543098,0.00001922778,0.0000066798875,0.000010521649,0.00001860453],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9924273,0.0010994474,0.0012667668,0.00022748491,0.0048246393,0.00015435019],"domain_scores_gemma":[0.99017936,0.001384525,0.0021653955,0.0001898382,0.0060057556,0.000075152464],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.029487727,0.00012712482,0.00031081293,0.00067634234,0.00022378459,0.00013952403,0.00024986066,0.00003009329,0.0003482328],"category_scores_gemma":[0.010658501,0.00009235309,0.0001019309,0.0010812924,0.00007460052,0.00058750797,0.00002170007,0.00012430077,0.00003358059],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010116811,0.00004927513,0.0023402951,0.0000013822068,0.000024886182,8.615216e-8,0.000983902,0.034103595,0.0039117057,0.0009134166,0.000354244,0.957216],"study_design_scores_gemma":[0.0017467113,0.0012711562,0.023804335,0.00005997321,0.00008945526,0.00001832487,0.0027847898,0.9470034,0.0016494895,0.018363886,0.003052178,0.0001562494],"about_ca_topic_score_codex":0.000005514293,"about_ca_topic_score_gemma":0.000009420181,"teacher_disagreement_score":0.9570598,"about_ca_system_score_codex":0.00055104593,"about_ca_system_score_gemma":0.0013538746,"threshold_uncertainty_score":0.9993466},"labels":[],"label_agreement":null},{"id":"W2320227325","doi":"10.1097/psn.0000000000000079","title":"Sample Policies for Your Policy and Procedure Manual","year":2015,"lang":"en","type":"article","venue":"Plastic Surgical Nursing","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Thornhill Medical (Canada)","funders":"","keywords":"Confusion; Set (abstract data type); Sample (material); Computer science; Service (business); Resource (disambiguation); Quality (philosophy); Risk analysis (engineering); Process management; Operations research; Operations management; Management science; Business; Marketing; Psychology; Engineering","score_opus":0.3014895744846291,"score_gpt":0.5403804627032615,"score_spread":0.23889088821863236,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2320227325","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.947247,0.00017979696,0.028139379,0.010099902,0.0009777918,0.00034945077,0.000064434425,0.00006552335,0.012876692],"genre_scores_gemma":[0.99581224,0.000005287977,0.002621333,0.00018171301,0.00055138423,0.00001627018,0.000008954662,0.000008132955,0.0007946853],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981533,0.00006611726,0.00032925827,0.00026260683,0.0009063222,0.00028234604],"domain_scores_gemma":[0.99456745,0.0046577533,0.00009104964,0.00013948014,0.0002799967,0.00026427812],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0014484557,0.00010700776,0.0001958069,0.00020962466,0.00015828025,0.00022342446,0.00016089006,0.000056431847,0.0000962535],"category_scores_gemma":[0.009930193,0.00007444815,0.000044568416,0.00037432695,0.00012948112,0.00022040922,0.000030688858,0.00006811306,0.000046902012],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016271555,0.000684097,0.07674735,0.000055994304,0.00005439453,0.000010201869,0.024845287,0.00505998,0.00017418001,0.37843552,0.053144835,0.459161],"study_design_scores_gemma":[0.004924744,0.0008601986,0.05839891,0.00018464938,0.000054176067,0.00021799163,0.013838968,0.19137152,0.00019701489,0.26541597,0.46393573,0.000600123],"about_ca_topic_score_codex":0.000030805288,"about_ca_topic_score_gemma":0.0000076083384,"teacher_disagreement_score":0.45856088,"about_ca_system_score_codex":0.000088724286,"about_ca_system_score_gemma":0.0003333855,"threshold_uncertainty_score":0.99840957},"labels":[],"label_agreement":null},{"id":"W2320230425","doi":"10.3138/cjpe.29.1.104","title":"Contributing Factors to the Continued Blurring of Evaluation and Research: Strategies for Moving Forward","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Terminology; Confusion; Management science; Psychology; Control (management); Political science; Engineering ethics; Computer science; Economics; Engineering; Artificial intelligence","score_opus":0.5421588467804487,"score_gpt":0.5906286609896096,"score_spread":0.048469814209160966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2320230425","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97953,0.00024239607,0.014003947,0.0026591842,0.00042579215,0.0024519893,0.000009547482,0.000003598538,0.0006735432],"genre_scores_gemma":[0.99788874,0.0000019769625,0.0017386301,0.000055917426,0.00016429002,0.00011448382,0.00000697566,0.0000073973642,0.00002160553],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9942142,0.0014146653,0.00090703834,0.00018922237,0.0029119805,0.00036294176],"domain_scores_gemma":[0.98663133,0.002037655,0.00065569725,0.0002381924,0.010137632,0.00029946503],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10056718,0.000095159376,0.00024404033,0.0006575753,0.00050510105,0.00063874084,0.000334495,0.000059131336,0.00015092616],"category_scores_gemma":[0.029459981,0.00006113902,0.000087481356,0.000655,0.00010783433,0.0005497179,0.000023113083,0.00017927468,0.0000036831075],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033288747,0.000014849981,0.02605238,0.000011960439,0.000033120974,1.4831193e-7,0.007084948,0.013018862,0.00032541776,0.0036190965,0.0011431357,0.9486628],"study_design_scores_gemma":[0.0021678535,0.001574917,0.21031125,0.00018560466,0.00017803791,0.000008496697,0.033196025,0.6550601,0.0009971518,0.062370792,0.033762775,0.00018695624],"about_ca_topic_score_codex":0.0004938818,"about_ca_topic_score_gemma":0.015873937,"teacher_disagreement_score":0.94847584,"about_ca_system_score_codex":0.00024310997,"about_ca_system_score_gemma":0.003372903,"threshold_uncertainty_score":0.9787153},"labels":[],"label_agreement":null},{"id":"W232181897","doi":"10.3138/cjpe.025.005","title":"Using Web-Based Technologies to Increase Evaluation Capacity in Organizations Providing Child and Youth Mental Health Services","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa; Natural Sciences and Engineering Research Council of Canada; Ontario Centre of Excellence for Child and Youth Mental Health","funders":"","keywords":"Mental health; Excellence; Context (archaeology); Service provider; Process (computing); Capacity building; Face (sociological concept); Public relations; Medical education; Service (business); Business; Knowledge management; Psychology; Marketing; Computer science; Medicine; Sociology; Psychiatry; Political science","score_opus":0.31751165643650486,"score_gpt":0.4729386949800939,"score_spread":0.15542703854358902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W232181897","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98975414,0.00021621081,0.0003920675,0.006847814,0.000510157,0.0020271295,0.000037898215,0.00002119307,0.00019336447],"genre_scores_gemma":[0.9877934,0.000004120703,0.011704755,0.00035968862,0.000053238917,0.000036361333,0.000035243287,0.000010718032,0.000002496978],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962397,0.0005338735,0.00085228443,0.00026351368,0.0018258666,0.00028474754],"domain_scores_gemma":[0.995654,0.00006487312,0.0006482839,0.00025977605,0.0029929006,0.00038015566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018444592,0.00013693956,0.00023027345,0.0015421131,0.00046924868,0.00045987085,0.00034119186,0.000098770535,0.0002831296],"category_scores_gemma":[0.0028080428,0.00011614437,0.000035841895,0.0019116518,0.00008347077,0.00072113535,0.0000229571,0.00031723286,0.0000073439323],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000342751,0.00014291248,0.24977429,0.000033670818,0.000025348192,8.5186775e-7,0.013921872,0.019909954,0.0014371771,0.00046540928,0.0001264901,0.7141277],"study_design_scores_gemma":[0.0019830954,0.0003556137,0.07069842,0.00025408342,0.00008238053,0.000037765705,0.013714124,0.9077855,0.00038206147,0.0016837294,0.0028091834,0.00021407218],"about_ca_topic_score_codex":0.0040031737,"about_ca_topic_score_gemma":0.18764102,"teacher_disagreement_score":0.8878755,"about_ca_system_score_codex":0.00051885087,"about_ca_system_score_gemma":0.0072637806,"threshold_uncertainty_score":0.9983641},"labels":[],"label_agreement":null},{"id":"W2322332679","doi":"10.3138/cjpe.30.3.07","title":"Considering the Social Determinants of Equity in International Development Evaluation Guidance Documents","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Equity (law); Business; Social equality; Public economics; Public relations; Political science; Accounting; Economics","score_opus":0.5190978300383406,"score_gpt":0.6044219470048832,"score_spread":0.08532411696654252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2322332679","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99300736,0.0001533114,0.0005262038,0.0024774119,0.0010273333,0.00082037353,0.0000042209485,0.0000024931103,0.0019812654],"genre_scores_gemma":[0.998104,0.00000537997,0.001549777,0.00007174001,0.000105189836,0.00008388499,0.0000020562372,0.0000052553446,0.00007276611],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9939568,0.0006674063,0.0014199185,0.00017140535,0.0035514317,0.00023300966],"domain_scores_gemma":[0.9947978,0.0003092979,0.0011695749,0.0001756983,0.0034193825,0.00012821198],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.032936636,0.00009955501,0.000202913,0.0005178377,0.00017737434,0.00016476003,0.0006462141,0.000058203328,0.0019229718],"category_scores_gemma":[0.00478544,0.000056853067,0.00007592118,0.0004220617,0.00012709347,0.0007102801,0.000043820983,0.00009761336,0.00002754794],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014089771,0.000020998961,0.17414777,0.0000018578884,0.000013483015,0.0000012338978,0.0016906029,0.00018896173,0.00012951391,0.000077065175,0.00029544087,0.823419],"study_design_scores_gemma":[0.0021556842,0.0001159695,0.9532177,0.00020334468,0.00004060859,0.000017984077,0.0012823567,0.017832175,0.0015225625,0.009918388,0.0135628525,0.00013039229],"about_ca_topic_score_codex":0.00020459357,"about_ca_topic_score_gemma":0.030377697,"teacher_disagreement_score":0.82328856,"about_ca_system_score_codex":0.0010947026,"about_ca_system_score_gemma":0.007104039,"threshold_uncertainty_score":0.9989894},"labels":[],"label_agreement":null},{"id":"W2322729581","doi":"10.36510/learnland.v9i1.746","title":"The Promise of Action Research: Lessons Learned From the Indiana Principal Leadership Institute","year":2015,"lang":"en","type":"article","venue":"LEARNing Landscapes","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Principal (computer security); Action (physics); Action research; Professional development; Perception; Engineering ethics; Political science; Psychology; Public relations; Sociology; Pedagogy; Engineering; Computer science","score_opus":0.8306625739607959,"score_gpt":0.5682151335232001,"score_spread":0.2624474404375958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2322729581","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9376032,0.00038554097,0.0001926317,0.05170043,0.00046711467,0.00025385263,0.0000036180677,0.00003762452,0.009356017],"genre_scores_gemma":[0.99246454,0.000098790544,0.000086545726,0.000099471465,0.00023798781,0.000026314505,0.000010683645,0.0000080200925,0.006967616],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99506855,0.0015692916,0.0003964061,0.0002861265,0.0023758423,0.000303779],"domain_scores_gemma":[0.9953143,0.0032227954,0.00027035628,0.0005058193,0.0005813819,0.0001053592],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.016588103,0.00009443286,0.00015479758,0.0001136039,0.00080390944,0.0003925694,0.0008435963,0.00007634283,0.00020420851],"category_scores_gemma":[0.010011405,0.000044261673,0.00006420753,0.0007123975,0.00024148358,0.00037194113,0.00015188758,0.0006989958,0.0004319197],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00054488407,0.000101730446,0.3071236,0.000010065098,0.00009385089,0.000004465083,0.039249234,0.02339243,0.00082506775,0.007843833,0.026469316,0.5943415],"study_design_scores_gemma":[0.0008353841,0.00018380678,0.111950845,0.00004338959,0.0000133538115,0.0000019873194,0.051297333,0.01498947,0.0006642354,0.009355167,0.81054455,0.000120464494],"about_ca_topic_score_codex":0.0002343539,"about_ca_topic_score_gemma":0.002444943,"teacher_disagreement_score":0.78407526,"about_ca_system_score_codex":0.000046884114,"about_ca_system_score_gemma":0.0005265211,"threshold_uncertainty_score":0.9983277},"labels":[],"label_agreement":null},{"id":"W2324237053","doi":"10.3138/cjpe.30.3.390","title":"A Transcultural Global Systems Perspective: In Search of Blue Marble Evaluators","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Framing (construction); Reflexivity; Indigenous; Sociology; Praxis; Perspective (graphical); Epistemology; Political science; Management science; Public relations; Engineering ethics; Social science; Computer science; Geography; Engineering","score_opus":0.33164886305323843,"score_gpt":0.5492553374225089,"score_spread":0.21760647436927044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2324237053","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99112713,0.0009082091,0.00091585354,0.0024103057,0.0007942328,0.0011241458,0.000024749854,0.0000045002635,0.0026908845],"genre_scores_gemma":[0.9992231,0.000014564175,0.00045539925,0.000018007224,0.00009625235,0.00004054378,0.0000015123662,0.0000056139106,0.00014498078],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9939693,0.0012066663,0.0011310107,0.0002216023,0.0031493166,0.00032205897],"domain_scores_gemma":[0.9932659,0.00020554784,0.00049091806,0.00024751897,0.005405118,0.00038498966],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.020650186,0.00012084922,0.00031787474,0.00059450057,0.0000790579,0.00016751747,0.0004942995,0.0000973594,0.0013848356],"category_scores_gemma":[0.0023115037,0.000071008006,0.00015370618,0.0012201356,0.00014656576,0.0006938084,0.000008309102,0.00013741672,0.000040718878],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000098279015,0.00011047567,0.3165316,0.000014195636,0.00006840246,0.0000117154905,0.005554768,0.0072711003,0.00042594864,0.006080656,0.0011538665,0.662679],"study_design_scores_gemma":[0.006133266,0.0017109481,0.88598365,0.00049701985,0.0001473551,0.00018362366,0.030159296,0.05671376,0.00038649284,0.010838681,0.0068826936,0.00036319284],"about_ca_topic_score_codex":0.0038866482,"about_ca_topic_score_gemma":0.04323935,"teacher_disagreement_score":0.6623158,"about_ca_system_score_codex":0.0017430431,"about_ca_system_score_gemma":0.0070953383,"threshold_uncertainty_score":0.99952805},"labels":[],"label_agreement":null},{"id":"W2324490698","doi":"10.3138/cjpe.30.3.394","title":"Hood, S., Hopson, R., &amp; Frierson, H., (2015). <i>Continuing the journey to reposition culture and cultural context in evaluation theory and practice.</i>","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Sociology; Psychology; History; Archaeology","score_opus":0.22758183789853317,"score_gpt":0.5146177563723437,"score_spread":0.2870359184738106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2324490698","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9406097,0.0066019576,0.0031450544,0.04423142,0.00077077,0.0026982608,0.000011157706,0.000010074553,0.0019216392],"genre_scores_gemma":[0.9962666,0.00013445922,0.0019736106,0.0010101919,0.00019250202,0.00010445711,0.0000054179177,0.0000096507865,0.00030311104],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9925786,0.0036341632,0.0009932129,0.0003104241,0.0021794064,0.00030418474],"domain_scores_gemma":[0.9921193,0.0012456737,0.0009233295,0.00028753042,0.004950666,0.00047348344],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06348135,0.0001646732,0.00024615918,0.0004508399,0.00029456412,0.00083337835,0.0002766345,0.00010631492,0.0004119133],"category_scores_gemma":[0.032228265,0.000084714266,0.00006494987,0.0006099097,0.00015853927,0.0019151609,0.000023579687,0.00023875448,0.000030286443],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012749869,0.000018776878,0.006868336,0.0000021860174,0.000023752997,0.000002968759,0.017330674,0.00008167033,0.00057823875,0.0010642743,0.0060799206,0.9678217],"study_design_scores_gemma":[0.008430098,0.0017614338,0.29651257,0.0010827256,0.00077611115,0.0016493578,0.08648451,0.007212007,0.00032150926,0.060375374,0.53460306,0.00079124345],"about_ca_topic_score_codex":0.00026279452,"about_ca_topic_score_gemma":0.018726386,"teacher_disagreement_score":0.96703047,"about_ca_system_score_codex":0.0004718284,"about_ca_system_score_gemma":0.0012750459,"threshold_uncertainty_score":0.9991793},"labels":[],"label_agreement":null},{"id":"W232449294","doi":"","title":"Designing and Implementing the Next Generation of Teacher Evaluation Systems: Lessons Learned from Case Studies in Five Illinois Districts","year":2013,"lang":"en","type":"book","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Canadian Navy","funders":"","keywords":"Mathematics education; Engineering management; Political science; Computer science; Psychology; Engineering","score_opus":0.7586416864230355,"score_gpt":0.5506418792379232,"score_spread":0.20799980718511235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W232449294","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81008804,0.024803454,0.008265579,0.0033379893,0.002062665,0.007495415,0.00020859604,0.00006549443,0.14367275],"genre_scores_gemma":[0.81552887,0.00092796964,0.00084365986,0.00007449542,0.00035449042,0.00026079573,0.00016985863,0.000020032041,0.18181983],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99490523,0.0011483517,0.0012920076,0.0005330008,0.0019180467,0.00020336981],"domain_scores_gemma":[0.9948284,0.0023631258,0.0010432239,0.0004709507,0.0012524602,0.00004185684],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.012954573,0.00022839378,0.0004937837,0.00028709258,0.00030343395,0.00040520923,0.000246212,0.0001461727,0.0009832471],"category_scores_gemma":[0.0017341673,0.00013233112,0.00006577113,0.00022836083,0.00011178814,0.00050953793,0.00018730877,0.00023824228,0.000047327194],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030934072,0.0001182623,0.0043065553,0.00016514976,0.0007274233,0.000051470783,0.05077317,0.01738339,0.0021716934,0.010898786,0.21911928,0.69425386],"study_design_scores_gemma":[0.001272042,0.0001149685,0.0008311558,0.00033146667,0.000377656,0.00003671132,0.09864611,0.87358505,0.00022507136,0.011751248,0.012349186,0.00047935126],"about_ca_topic_score_codex":0.0011391559,"about_ca_topic_score_gemma":0.0024840308,"teacher_disagreement_score":0.85620165,"about_ca_system_score_codex":0.0002922114,"about_ca_system_score_gemma":0.0005302792,"threshold_uncertainty_score":0.99992996},"labels":[],"label_agreement":null},{"id":"W2324664192","doi":"10.1177/1356389014564248","title":"The institutionalization of evaluation matters: Updating the <i>International Atlas of Evaluation</i> 10 years later","year":2015,"lang":"en","type":"article","venue":"Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":114,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Institutionalisation; Political science; Regional science; Public administration; Geography; Law","score_opus":0.2102689892953537,"score_gpt":0.4898436435508309,"score_spread":0.2795746542554772,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2324664192","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9080491,0.0011072233,0.003734284,0.026082715,0.0046652746,0.003868282,0.000049803853,0.000038477603,0.052404813],"genre_scores_gemma":[0.9978589,0.00002755371,0.00040923254,0.00048209072,0.00022402499,0.00023464009,0.00025694477,0.000011003814,0.00049565325],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9822151,0.0020715038,0.0015023838,0.00038353654,0.013633656,0.00019379103],"domain_scores_gemma":[0.986153,0.001104237,0.0013322355,0.00073282607,0.010616667,0.000061013943],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.071788594,0.00014952618,0.00019909994,0.00024275074,0.000268019,0.00024386842,0.0006609633,0.000080972466,0.004859765],"category_scores_gemma":[0.010870377,0.000090525355,0.00011841597,0.00086915575,0.00022376583,0.00089328474,0.00013517065,0.000115561365,0.00036903162],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027431693,0.00021323812,0.014640591,0.000009817303,0.00019039285,2.5562437e-7,0.0063946275,0.41197252,0.0020958793,0.014199504,0.13778523,0.4122236],"study_design_scores_gemma":[0.0019615155,0.00007998525,0.052228473,0.00003409219,0.0001868774,0.000004835899,0.0024469874,0.86182547,0.0015806805,0.03365036,0.045869738,0.00013100257],"about_ca_topic_score_codex":0.000038117512,"about_ca_topic_score_gemma":0.0001409408,"teacher_disagreement_score":0.4498529,"about_ca_system_score_codex":0.00042021775,"about_ca_system_score_gemma":0.0020985885,"threshold_uncertainty_score":0.9974615},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W2324880020","doi":"10.3138/cjpe.30.3.391","title":"Goodyear, L., Jewiss, J., Usinger, J., &amp; Barela, E. (Eds.). (2014). <i>Qualitative inquiry in evaluation: From theory to practice.</i>","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Epistemology; Philosophy","score_opus":0.4800931468809325,"score_gpt":0.5926954103586337,"score_spread":0.11260226347770119,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2324880020","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8013842,0.018110374,0.07738004,0.07047283,0.012384353,0.00917961,0.00017229463,0.000058792924,0.010857473],"genre_scores_gemma":[0.95303106,0.00014292051,0.04248462,0.0023419894,0.00087911537,0.0003538522,0.000047453508,0.000040983155,0.0006780311],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.984703,0.0071596275,0.0018817144,0.0005356224,0.0051984466,0.0005215832],"domain_scores_gemma":[0.9853945,0.0040234914,0.0012782215,0.0006985114,0.007753608,0.0008517164],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.08635211,0.00025037728,0.0004468105,0.0013345778,0.00021269775,0.0004904669,0.000757431,0.000169272,0.013253012],"category_scores_gemma":[0.040946595,0.00017084052,0.0001623066,0.0013662134,0.0001869917,0.0021416221,0.000038926013,0.00030770226,0.0014947032],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012363946,0.00008546004,0.0029605746,0.0000021716749,0.0000531599,0.0000062577906,0.017413154,0.0009336385,0.00015510937,0.0005560148,0.020463094,0.95724773],"study_design_scores_gemma":[0.004300674,0.00079508533,0.033887308,0.0004707469,0.0003311462,0.000039474617,0.01598847,0.0027741448,0.00014464353,0.13410844,0.80662084,0.000539021],"about_ca_topic_score_codex":0.0009882561,"about_ca_topic_score_gemma":0.031014338,"teacher_disagreement_score":0.9567087,"about_ca_system_score_codex":0.001332277,"about_ca_system_score_gemma":0.009321745,"threshold_uncertainty_score":0.9992828},"labels":[],"label_agreement":null},{"id":"W2326397368","doi":"10.1177/097340821100600116","title":"Determining the ‘Essentials’ for an Undergraduate Sustainability Degree Program","year":2012,"lang":"en","type":"article","venue":"Journal of Education for Sustainable Development","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Sustainability; Delphi method; Curriculum; Delphi; Multitude; Inclusion (mineral); Engineering ethics; Curriculum development; Medical education; Pedagogy; Political science; Psychology; Sociology; Engineering; Computer science; Social science; Medicine","score_opus":0.21147649218818435,"score_gpt":0.5190298841131473,"score_spread":0.307553391924963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2326397368","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84542364,0.00024994294,0.13234405,0.011428365,0.0029464667,0.0049402434,0.0000021056665,0.000030400373,0.0026347996],"genre_scores_gemma":[0.95035243,0.0000042959446,0.040710505,0.00030645967,0.0003644173,0.00053663924,0.000013128607,0.0000150323185,0.0076971203],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99679226,0.0001994597,0.0012174245,0.00018727891,0.001050606,0.00055297907],"domain_scores_gemma":[0.9872126,0.00091111043,0.0011001497,0.0003311659,0.010206064,0.00023891155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014661778,0.00015434388,0.00025513896,0.00035223635,0.0007415805,0.0004825285,0.00063109025,0.00005864254,0.000058396858],"category_scores_gemma":[0.0054159453,0.00009361866,0.00015630909,0.00049239,0.00005882257,0.0018502343,0.00006133483,0.000115121715,0.000004572526],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001594024,0.0019044119,0.044318296,0.00014721825,0.000062154446,2.4466357e-7,0.007253021,0.0002145335,0.0000067444,0.032786023,0.036641024,0.8765069],"study_design_scores_gemma":[0.0007345149,0.00044473447,0.16317554,0.00001369634,0.000044791097,0.000009963004,0.07830224,0.00037686512,0.0003154719,0.06807052,0.68833435,0.00017730554],"about_ca_topic_score_codex":0.0000034309337,"about_ca_topic_score_gemma":0.000010982509,"teacher_disagreement_score":0.8763296,"about_ca_system_score_codex":0.0008238295,"about_ca_system_score_gemma":0.007165046,"threshold_uncertainty_score":0.9984634},"labels":[],"label_agreement":null},{"id":"W2326672695","doi":"10.1177/1049732310392386","title":"Considering the Qualitative–Quantitative Language Divide","year":2010,"lang":"en","type":"article","venue":"Qualitative Health Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Mohawk College","funders":"","keywords":"Qualitative research; Linguistics; Psychology; Sociology; Computer science; Anthropology","score_opus":0.9024482665202305,"score_gpt":0.8039551711135557,"score_spread":0.09849309540667472,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2326672695","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80973035,0.00070001255,0.0071723205,0.15849926,0.0007417891,0.0014097139,0.00010162677,0.00007066572,0.021574266],"genre_scores_gemma":[0.9830456,0.000049557777,0.0079889,0.002525338,0.0001567139,0.00021438763,0.000013580866,0.000022646107,0.005983304],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9614653,0.028374253,0.0014514799,0.0007860575,0.006802276,0.0011206341],"domain_scores_gemma":[0.9143238,0.080736965,0.00047987624,0.0011442265,0.0028846345,0.00043048253],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.19429651,0.00019766473,0.00043715868,0.0006220877,0.0017945034,0.00050292345,0.001156702,0.00008853778,0.0033153163],"category_scores_gemma":[0.0507159,0.0001145145,0.00012003089,0.002276319,0.0014725027,0.0005864581,0.00031214615,0.0019471903,0.0030614613],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006509416,0.000059762704,0.00019726613,0.000020612553,0.00001791581,0.0000023641285,0.71001357,0.000008737398,0.00080206257,0.24721129,0.024081446,0.017519882],"study_design_scores_gemma":[0.00040853219,0.00048795264,0.0028532366,0.000027681739,0.0000014649918,0.0000031524244,0.792512,0.0010116227,0.00035546662,0.13522883,0.06696343,0.00014663607],"about_ca_topic_score_codex":0.0010670549,"about_ca_topic_score_gemma":0.0039868904,"teacher_disagreement_score":0.17331523,"about_ca_system_score_codex":0.0001406438,"about_ca_system_score_gemma":0.0018697425,"threshold_uncertainty_score":0.99950504},"labels":[],"label_agreement":null},{"id":"W2327372734","doi":"10.1126/science.335.6074.1302-a","title":"IEG's Role in Evaluating Climate Financing—Response","year":2012,"lang":"en","type":"article","venue":"Science","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Credibility; Audit; Institution; Business; Financial institution; Accounting; Independence (probability theory); Corporate governance; Finance; Political science","score_opus":0.27676480019234506,"score_gpt":0.5754352199778733,"score_spread":0.2986704197855282,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2327372734","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9890949,0.00014890816,0.0001944671,0.0005880861,0.00060399156,0.00013069634,0.0000017143328,0.000018959094,0.009218292],"genre_scores_gemma":[0.9965518,0.0000066564176,0.0024602474,0.0004104768,0.000052102896,0.000016166356,2.4367242e-7,0.0000034479522,0.0004988735],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9952869,0.00033397134,0.00048118772,0.00035762208,0.002871349,0.00066898233],"domain_scores_gemma":[0.9980539,0.0008374472,0.000166828,0.0004988966,0.00028512013,0.00015781105],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.06440326,0.0000879534,0.00013384415,0.00048381859,0.00035680152,0.00024106343,0.0008333861,0.000028236449,0.00096693775],"category_scores_gemma":[0.0075030876,0.00006391802,0.000034323333,0.0025743744,0.00023871656,0.0019611444,0.0002357389,0.00011540873,0.0017381038],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001150709,0.000092766546,0.7723786,0.0000019741321,5.473986e-7,9.0524117e-7,0.0064043463,0.0016817024,0.052062165,0.002265005,0.00015232236,0.16484454],"study_design_scores_gemma":[0.000222331,0.00006621071,0.93613213,0.000013399956,0.0000011810636,0.000004038328,0.0017201471,0.051260855,0.0033238365,0.0016804608,0.005468161,0.000107240354],"about_ca_topic_score_codex":0.00000994942,"about_ca_topic_score_gemma":0.00002413872,"teacher_disagreement_score":0.16473731,"about_ca_system_score_codex":0.00014384168,"about_ca_system_score_gemma":0.00062466454,"threshold_uncertainty_score":0.9999463},"labels":[],"label_agreement":null},{"id":"W2328932467","doi":"10.4006/0836-1398-25.2.148","title":"Your Published Article: Making the Greatest Impact","year":2012,"lang":"en","type":"article","venue":"Physics Essays","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Physics","score_opus":0.3051399055196307,"score_gpt":0.524794196624513,"score_spread":0.21965429110488227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2328932467","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6624134,0.00015039205,0.010547176,0.0037675046,0.0008720714,0.00024642472,0.000012835991,0.00006968199,0.32192048],"genre_scores_gemma":[0.99784935,0.0000028377103,0.00019147064,0.00056590425,0.00063845376,0.000017885659,0.0000035961823,0.000009826123,0.0007206672],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99766123,0.00017550752,0.0003151135,0.00015782607,0.0013137662,0.00037652694],"domain_scores_gemma":[0.9982573,0.0005156919,0.0001943925,0.00065807777,0.00027164424,0.000102922655],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003937872,0.00011959956,0.00014621344,0.000063205414,0.00027753427,0.0006396476,0.0005652888,0.000029639328,0.0021366796],"category_scores_gemma":[0.00051213906,0.00006017621,0.00012002275,0.0010134612,0.000061022918,0.0018326842,0.000119823446,0.00016143071,0.0016401978],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015209079,0.00018683681,0.68441266,0.0000023335915,0.00003374387,3.9594616e-7,0.00562769,0.00090020325,0.0004274606,0.15796915,0.030317267,0.12010705],"study_design_scores_gemma":[0.0005625223,0.00006447008,0.5034689,0.000014503433,0.00004185715,0.000010300264,0.0025203286,0.03975662,0.00088909984,0.43743995,0.014885764,0.00034571637],"about_ca_topic_score_codex":0.000014620137,"about_ca_topic_score_gemma":0.0000026500331,"teacher_disagreement_score":0.33543593,"about_ca_system_score_codex":0.0000542451,"about_ca_system_score_gemma":0.00009089128,"threshold_uncertainty_score":0.99913716},"labels":[],"label_agreement":null},{"id":"W233084541","doi":"10.3138/cjpe.017.006","title":"Public Training Programs in Canada: A Meta-evaluation","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Summative assessment; Formative assessment; Training (meteorology); Program evaluation; Medical education; Political science; Public relations; Psychology; Pedagogy; Public administration; Medicine; Geography","score_opus":0.9006990989952361,"score_gpt":0.5282974646477141,"score_spread":0.37240163434752205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W233084541","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95176154,0.0044805794,0.00038953143,0.021945722,0.0020647643,0.004387647,0.0000110163755,0.000016725782,0.014942487],"genre_scores_gemma":[0.9975076,0.0000129305845,0.001590763,0.00028367026,0.00012555979,0.00034971564,0.000015469677,0.000012669992,0.0001016728],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9902838,0.0014958618,0.0016387617,0.00030869636,0.0057129962,0.0005598889],"domain_scores_gemma":[0.9930124,0.00026770963,0.0009877279,0.00035695813,0.004672662,0.00070249895],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.033242255,0.00018879346,0.00049217435,0.001144385,0.00018774414,0.00057723647,0.00063075434,0.00007882191,0.015695544],"category_scores_gemma":[0.00586014,0.00014375198,0.00020112119,0.0019555113,0.00006684631,0.001150254,0.000011219119,0.0003306842,0.00005078962],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000026508728,0.000039424176,0.02816503,0.0000019171475,0.00009709614,0.000009592594,0.0020124305,0.0025774606,0.0000022635004,0.00016523058,0.0022207813,0.9647061],"study_design_scores_gemma":[0.0024604027,0.00047759543,0.10485934,0.000047863487,0.0008388146,0.00011277623,0.009278659,0.7696825,0.000009431111,0.008765075,0.10308641,0.00038110942],"about_ca_topic_score_codex":0.34388363,"about_ca_topic_score_gemma":0.99592984,"teacher_disagreement_score":0.964325,"about_ca_system_score_codex":0.003129474,"about_ca_system_score_gemma":0.03065914,"threshold_uncertainty_score":0.99548054},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"grok","categories":["metaepi_broad"],"domain":null,"study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"opus","categories":["metaresearch","metaepi_broad"],"domain":"methods","study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":true,"confidence":"medium"}],"label_agreement":"split"},{"id":"W2331580938","doi":"10.3138/cjpe.30.3.02","title":"A Critical Exploration of Culture in International Development Evaluation","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sociology; Context (archaeology); Engineering ethics; Epistemology","score_opus":0.5144255173283512,"score_gpt":0.58370906981695,"score_spread":0.06928355248859885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2331580938","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9414468,0.00072937144,0.026706744,0.016119037,0.0036414035,0.0023938778,0.000015671487,0.000011827402,0.008935281],"genre_scores_gemma":[0.9922971,0.000011494132,0.0072883717,0.000059332186,0.0001225604,0.000107587424,0.000010887922,0.00000577642,0.000096896394],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99403024,0.0006491894,0.0013622788,0.00019152004,0.0035720891,0.00019467552],"domain_scores_gemma":[0.99089956,0.00029175053,0.0006338282,0.00018391843,0.0077624577,0.000228486],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.021487162,0.00010157171,0.00020021356,0.0009950374,0.00007270749,0.00014690246,0.00040700566,0.000086676235,0.0033710047],"category_scores_gemma":[0.01297649,0.000064457214,0.0000760071,0.00059806724,0.00009257394,0.0020562415,0.000012779809,0.00010647767,0.000053974618],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024764893,0.00006109762,0.023804948,0.0000026262137,0.000014421086,0.0000016466371,0.0031305512,0.0005945097,0.00036332203,0.00081298046,0.0006811216,0.97050804],"study_design_scores_gemma":[0.00889797,0.0013745489,0.58433175,0.0009779257,0.00019228934,0.00006606055,0.009168787,0.102784276,0.0062930565,0.13932641,0.14596222,0.0006247045],"about_ca_topic_score_codex":0.000070931026,"about_ca_topic_score_gemma":0.010202997,"teacher_disagreement_score":0.9698833,"about_ca_system_score_codex":0.000868365,"about_ca_system_score_gemma":0.0064564664,"threshold_uncertainty_score":0.999176},"labels":[],"label_agreement":null},{"id":"W2331822834","doi":"10.1177/0022466915613592","title":"A Socio-Cultural Analysis of Practitioner Perspectives on Implementation of Evidence-Based Practice in Special Education","year":2015,"lang":"en","type":"article","venue":"The Journal of Special Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"McMaster University","keywords":"Construct (python library); Variety (cybernetics); Evidence-based practice; Psychology; Special education; Work (physics); Pedagogy; Medicine","score_opus":0.3102764335004414,"score_gpt":0.5900387415306811,"score_spread":0.27976230803023977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2331822834","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96963346,0.00026807876,0.00023439611,0.02140424,0.0016222832,0.00027813856,0.0000049349537,0.0000016840484,0.0065527847],"genre_scores_gemma":[0.9951358,0.0002431819,0.0009408656,0.00031747296,0.0031792603,0.0000059549347,0.000008971856,0.000004113229,0.00016437829],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9955588,0.00095453527,0.0011609931,0.0001323994,0.0020961156,0.000097150914],"domain_scores_gemma":[0.9903693,0.0014787959,0.0028243647,0.0002467195,0.005009254,0.000071533155],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009139868,0.000097355856,0.00029958427,0.0010727199,0.000075726304,0.000076354256,0.00034179573,0.000044109584,0.0020727408],"category_scores_gemma":[0.0054160054,0.00005676837,0.00015542364,0.0020323638,0.00010076234,0.0019977253,0.000016341777,0.00018817758,0.00001972489],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0034118004,0.004441611,0.050696325,0.000016006998,0.00051239843,5.9033914e-7,0.47443756,0.024462475,0.0015282165,0.01728661,0.09021079,0.33299562],"study_design_scores_gemma":[0.0005741732,0.0005303969,0.22487499,0.00007572881,0.00055102,0.00000544078,0.76073515,0.0002509902,0.0010259317,0.0029534644,0.008332745,0.000089956164],"about_ca_topic_score_codex":0.00032301588,"about_ca_topic_score_gemma":0.00035974148,"teacher_disagreement_score":0.33290565,"about_ca_system_score_codex":0.00057717983,"about_ca_system_score_gemma":0.005775793,"threshold_uncertainty_score":0.9998605},"labels":[],"label_agreement":null},{"id":"W2332681108","doi":"10.3138/cjpe.30.2.228","title":"Trevisan, M. S., &amp; Walser, T. M. (2015) <i>Evaluability assessment: Improving evaluation quality and use.</i>","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Quality (philosophy); Psychology; Philosophy; Epistemology","score_opus":0.6893862509287247,"score_gpt":0.6140360373202267,"score_spread":0.07535021360849803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2332681108","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9811114,0.001815964,0.0037381942,0.0055870013,0.0017873165,0.003032283,0.000026616293,0.000025754174,0.0028754505],"genre_scores_gemma":[0.9850796,0.000018102492,0.013820823,0.0003948555,0.0002762434,0.00014152467,0.000058716698,0.000019472845,0.00019067478],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98495704,0.004638206,0.0022966436,0.0005485074,0.007064892,0.00049472245],"domain_scores_gemma":[0.9807506,0.00085298903,0.001878694,0.00077348016,0.014340102,0.001404121],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13153072,0.0002711448,0.00055679027,0.0007850798,0.0003508092,0.0014996793,0.0005510934,0.0001725865,0.0020038884],"category_scores_gemma":[0.028855763,0.00021619268,0.0001863378,0.0010244142,0.00023042252,0.002728225,0.0000464808,0.00042380608,0.00006949462],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034091274,0.00007699148,0.15844215,0.000011469184,0.000033417095,0.0000011665289,0.000994954,0.0016701261,0.00007902474,0.0003451781,0.0055084964,0.83280295],"study_design_scores_gemma":[0.004146789,0.00073458225,0.7006008,0.00006562821,0.0004392274,0.000069240916,0.001810032,0.15452753,0.00004128695,0.031854503,0.10525603,0.00045438175],"about_ca_topic_score_codex":0.002535575,"about_ca_topic_score_gemma":0.036347516,"teacher_disagreement_score":0.8323485,"about_ca_system_score_codex":0.0016678949,"about_ca_system_score_gemma":0.017653648,"threshold_uncertainty_score":0.9995369},"labels":[],"label_agreement":null},{"id":"W2335339537","doi":"10.7748/nr2009.01.16.2.4.c6758","title":"Action research","year":2009,"lang":"en","type":"article","venue":"Nurse Researcher","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Confederation College","funders":"","keywords":"Action (physics); Action research; Psychology; Computer science; Sociology; Pedagogy","score_opus":0.8571674905601864,"score_gpt":0.743545656250745,"score_spread":0.1136218343094414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2335339537","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38927835,0.0001059163,0.00039281815,0.04257768,0.00022075466,0.00034383897,0.000002136549,0.000052531705,0.56702596],"genre_scores_gemma":[0.92698014,0.000037953327,0.00029453036,0.0002835858,0.00021387523,0.000013952202,0.00000265514,0.0000050471403,0.07216826],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99173135,0.0011591052,0.00030134892,0.00035944124,0.005971621,0.0004771129],"domain_scores_gemma":[0.9968076,0.0008752825,0.000042605894,0.00067469565,0.0014008043,0.0001990458],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.024554815,0.00006745442,0.00011313395,0.0006068875,0.00032285549,0.00039715713,0.0006608644,0.00008081646,0.011761429],"category_scores_gemma":[0.0035303559,0.000046390436,0.00005763417,0.0017676188,0.00013380393,0.00051120267,0.000035612706,0.00055906037,0.00871793],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006361779,0.000120611054,0.0021781884,9.722686e-7,0.0000029534963,0.00000429541,0.00050730346,0.000030692936,0.0028970207,0.009682843,0.19297276,0.7915387],"study_design_scores_gemma":[0.00044002442,0.00038297515,0.33316067,0.000012101956,0.0000012797705,0.000004293242,0.003419791,0.0061064223,0.0025737602,0.10096598,0.55282265,0.00011006782],"about_ca_topic_score_codex":0.000026517784,"about_ca_topic_score_gemma":0.000037390757,"teacher_disagreement_score":0.7914287,"about_ca_system_score_codex":0.00015216543,"about_ca_system_score_gemma":0.00035831908,"threshold_uncertainty_score":0.9920539},"labels":[],"label_agreement":null},{"id":"W2336697119","doi":"10.4256/mio.2013.015","title":"The Blind Men and the Elephant: A Metaphor to Illuminate the Role of Researchers and Reviewers in Social Science","year":2013,"lang":"en","type":"article","venue":"Methodological Innovations Online","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ministère de l’Emploi et de la Solidarité Sociale (Québec); University of Saskatchewan","funders":"Fonds de Recherche du Québec-Société et Culture","keywords":"Metaphor; Confusion; Value (mathematics); Field (mathematics); Epistemology; Sociology; Social science; Psychology; Computer science; Psychoanalysis; Philosophy","score_opus":0.6408327611946647,"score_gpt":0.6155259409060417,"score_spread":0.025306820288622967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2336697119","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87067944,0.0012145046,0.0017547065,0.11895894,0.000062909174,0.0014102339,0.000012129573,0.000008080892,0.005899047],"genre_scores_gemma":[0.97413045,0.0005377106,0.022750357,0.0017285959,0.000049926937,0.00018185096,0.000001932379,0.0000035631622,0.00061563007],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.995186,0.0023910152,0.00072618097,0.0002807778,0.0011778757,0.0002381642],"domain_scores_gemma":[0.9865708,0.011352756,0.00024969227,0.0003935725,0.0013823386,0.00005089397],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0754016,0.000083700485,0.0002543823,0.0002470781,0.0008099684,0.0002611902,0.000825666,0.000040348452,0.0001313557],"category_scores_gemma":[0.037200734,0.000028852486,0.000032929333,0.0047263354,0.002376844,0.00022727404,0.0003903614,0.0002733464,0.000009631563],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014056025,0.00006208697,0.0033057258,0.0000030382325,0.000014608518,1.299634e-7,0.003837749,0.000022244922,0.006453084,0.15689208,0.0009382074,0.8283305],"study_design_scores_gemma":[0.0014843382,0.00018902875,0.4100264,0.0000202465,0.000021110554,0.0000041006674,0.050695397,0.026558904,0.0008449001,0.4338797,0.07610441,0.00017146353],"about_ca_topic_score_codex":0.0000577905,"about_ca_topic_score_gemma":0.00003311476,"teacher_disagreement_score":0.82815903,"about_ca_system_score_codex":0.000023198843,"about_ca_system_score_gemma":0.00012593018,"threshold_uncertainty_score":0.97090936},"labels":[],"label_agreement":null},{"id":"W2336718227","doi":"10.1080/0309877x.2015.1135882","title":"Multidisciplinary graduate training in social research methodology and computer-assisted qualitative data analysis: a hands-on/hands-off course design","year":2016,"lang":"en","type":"article","venue":"Journal of Further and Higher Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Reflexivity; Multidisciplinary approach; Social constructivism; Context (archaeology); Qualitative research; Instructional design; Qualitative property; Action research; Pedagogy; Computer science; Engineering ethics; Mathematics education; Medical education; Psychology; Sociology; Engineering","score_opus":0.9015824367923144,"score_gpt":0.6993465791985246,"score_spread":0.20223585759378981,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2336718227","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95849365,0.0004241789,0.017985407,0.021309592,0.00038994494,0.00018106542,0.000006732497,0.00000526694,0.0012041403],"genre_scores_gemma":[0.98783654,0.00010254412,0.010012628,0.00008647447,0.00033940523,0.0000063613934,0.000002527323,0.000007903456,0.0016056297],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9943657,0.0037149044,0.0006015179,0.000285306,0.0008680307,0.00016454983],"domain_scores_gemma":[0.99450606,0.004212102,0.0004298684,0.00022445395,0.000531445,0.00009606846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024318252,0.000092978575,0.00034286318,0.0009144678,0.00015994834,0.00012184287,0.00030001142,0.000061460225,0.0003508593],"category_scores_gemma":[0.0003320914,0.00005301131,0.000044469944,0.0007942034,0.00016536066,0.00041835703,0.0000780782,0.00018106005,0.000010247857],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005055459,0.00040972882,0.019458327,0.0000054580128,0.00028174775,0.0000037667971,0.13831823,0.00002872348,0.0002788369,0.0022817072,0.009426219,0.8290017],"study_design_scores_gemma":[0.0019013848,0.000751662,0.93100464,0.000075455864,0.0001180744,0.000012537974,0.037060488,0.0015214287,0.000020613043,0.026447007,0.0009725929,0.00011408163],"about_ca_topic_score_codex":0.000012758526,"about_ca_topic_score_gemma":0.00006681527,"teacher_disagreement_score":0.91154635,"about_ca_system_score_codex":0.000045068267,"about_ca_system_score_gemma":0.00060981413,"threshold_uncertainty_score":0.8428269},"labels":[],"label_agreement":null},{"id":"W2336770740","doi":"10.7202/1035199ar","title":"Le pari de l’accompagnement pour la formation de praticiens réflexifs de l’enseignement : possibilités et limites d’un système de stages","year":2016,"lang":"fr","type":"article","venue":"Approches inductives Travail intellectuel et construction des connaissances","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Humanities; Political science; Philosophy; Sociology","score_opus":0.10897634935211381,"score_gpt":0.3893437607751088,"score_spread":0.280367411422995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2336770740","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5210926,0.0043957154,0.44546852,0.015227406,0.00052238436,0.0007254966,0.00005909061,0.000146563,0.012362229],"genre_scores_gemma":[0.95252943,0.0026945702,0.041062318,0.0012458023,0.0001921507,0.0003154651,0.0000112832195,0.000050440907,0.0018985124],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99081665,0.004072134,0.0015658104,0.001027469,0.001219889,0.001298025],"domain_scores_gemma":[0.992637,0.0042549046,0.0009609544,0.0006542817,0.0010392528,0.0004536508],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011302177,0.00066270307,0.0006876978,0.0005404549,0.0009835718,0.000969214,0.0008343497,0.00046327055,0.0022168772],"category_scores_gemma":[0.004409725,0.0005361154,0.0002987097,0.0008784094,0.0071273395,0.0028937196,0.00019735056,0.0006451365,0.000109036046],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042716737,0.0009355228,0.013815259,0.00038121085,0.0004359071,0.000017591912,0.13383031,0.0013777781,0.027550228,0.3485464,0.004434025,0.46824864],"study_design_scores_gemma":[0.004265006,0.0014393381,0.07380894,0.0025970582,0.00038118497,0.0023202968,0.273646,0.026046092,0.2425448,0.32008648,0.05091515,0.001949645],"about_ca_topic_score_codex":0.00022064464,"about_ca_topic_score_gemma":0.00052142283,"teacher_disagreement_score":0.46629897,"about_ca_system_score_codex":0.0023283612,"about_ca_system_score_gemma":0.006638502,"threshold_uncertainty_score":0.999709},"labels":[],"label_agreement":null},{"id":"W2337090609","doi":"10.3138/cjpe.022.005","title":"A Participatory Approach to the Development of an Evaluation Framework: Process, Pitfalls, and Payoffs","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Alberta Health; Alberta Community Council on HIV; Public Health Agency of Canada","funders":"","keywords":"Citizen journalism; Participatory evaluation; Participatory GIS; Process (computing); Participatory development; Process management; Knowledge management; Business; Sociology; Management science; Computer science; Economics; Social science; World Wide Web","score_opus":0.5222899769278269,"score_gpt":0.5645426097571967,"score_spread":0.04225263282936986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2337090609","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97285044,0.00040723814,0.022461955,0.00065262493,0.00033616822,0.0017610419,0.0000020599987,0.0000052582204,0.00152322],"genre_scores_gemma":[0.96025497,0.0000015018416,0.03926586,0.00018929066,0.000137677,0.00012146643,0.000008410546,0.000008871774,0.000011927745],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99359846,0.0006548917,0.0013601047,0.00024941718,0.003802967,0.00033415295],"domain_scores_gemma":[0.9936635,0.00025290463,0.00077934033,0.00032926354,0.0043542664,0.0006207063],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07402125,0.00012914308,0.00022406182,0.0005709598,0.0003186923,0.00023861523,0.00048750802,0.00009441131,0.00028694895],"category_scores_gemma":[0.0043747555,0.00008326373,0.000051650855,0.0009651523,0.00009920448,0.0005361862,0.0000156395,0.00021649513,0.000013908587],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028651002,0.00009522614,0.014345506,0.000007770929,0.000023558094,3.8946752e-7,0.020334326,0.0040927506,0.000020993124,0.00041862344,0.00012777818,0.9605044],"study_design_scores_gemma":[0.001115249,0.00076306507,0.74541694,0.000118940894,0.00022056498,0.00003131912,0.019436192,0.19715771,0.00080608536,0.015920846,0.018714672,0.00029838597],"about_ca_topic_score_codex":0.00008177498,"about_ca_topic_score_gemma":0.015754929,"teacher_disagreement_score":0.96020603,"about_ca_system_score_codex":0.00030625545,"about_ca_system_score_gemma":0.007438188,"threshold_uncertainty_score":0.99818873},"labels":[],"label_agreement":null},{"id":"W2337817302","doi":"10.1177/0741713616643958","title":"Book Review: <i>Community-Based Participatory Research</i> , by K. Hacker","year":2016,"lang":"en","type":"article","venue":"Adult Education Quarterly","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Hacker; Sociology; Citizen journalism; Participatory action research; Engineering ethics; Media studies; Computer science; World Wide Web; Engineering; Computer security; Anthropology","score_opus":0.28634735965750024,"score_gpt":0.5469796021214901,"score_spread":0.26063224246398986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2337817302","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16778268,0.07842038,0.009245129,0.69075906,0.0043607904,0.0034535893,0.00015366127,0.0003729527,0.045451757],"genre_scores_gemma":[0.60676354,0.0023730574,0.00039806537,0.3033937,0.00032040227,0.0012520017,0.00009699117,0.000042525182,0.08535972],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.993122,0.0032137719,0.0007972011,0.00034935112,0.0021415579,0.00037615362],"domain_scores_gemma":[0.99341846,0.0021421968,0.00025429405,0.001396775,0.0025398938,0.00024840748],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0107353795,0.00014547366,0.00021773824,0.00024470148,0.0004950578,0.00016109119,0.000817659,0.000066466964,0.010526585],"category_scores_gemma":[0.001487134,0.00008873841,0.00009155557,0.00071616034,0.00020812897,0.0008733127,0.00002221121,0.00030451533,0.008963826],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007910179,0.0002490486,0.00082343485,0.000026549335,0.0000034484967,7.412252e-8,0.000651773,1.3022252e-7,0.00040988205,0.00034387645,0.86399186,0.13349204],"study_design_scores_gemma":[0.00033816264,0.0003148497,0.0015961819,0.00044378982,0.000008587065,8.824357e-7,0.0014791931,0.000040736533,0.00061933027,0.0028791984,0.992129,0.00015008546],"about_ca_topic_score_codex":0.00006335218,"about_ca_topic_score_gemma":0.000051029496,"teacher_disagreement_score":0.43898088,"about_ca_system_score_codex":0.00014389766,"about_ca_system_score_gemma":0.0013136035,"threshold_uncertainty_score":0.9918078},"labels":[],"label_agreement":null},{"id":"W2338361602","doi":"10.55016/ojs/ajer.v59i2.55613","title":"Research Mediation in Education: A Typology of Research Brokering Organizations That Exist Across Canada","year":2014,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Typology; Political science; Sociology; Humanities; Terminology; Library science","score_opus":0.3830017211334402,"score_gpt":0.6377082577611763,"score_spread":0.2547065366277361,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2338361602","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8816343,0.0003711263,0.000013290904,0.050381847,0.0010132763,0.00026770288,0.0000049083474,4.139646e-7,0.06631312],"genre_scores_gemma":[0.9816645,0.00017133896,0.00025905855,0.000111845795,0.00065530394,0.000036182304,0.000015544394,0.000015630043,0.017070616],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98529476,0.00408276,0.0013100671,0.00036725658,0.008214264,0.0007308834],"domain_scores_gemma":[0.89043444,0.088879675,0.00041184665,0.00063070585,0.019315425,0.0003279297],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.049590055,0.000107367676,0.00031729942,0.0016843196,0.000674764,0.0002294766,0.001595617,0.000118665695,0.009190297],"category_scores_gemma":[0.14020197,0.000088467496,0.00004934918,0.007036002,0.0006143076,0.0006271991,0.00028405417,0.001337412,0.0002658329],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012124816,0.00071848667,0.7471998,0.000048035097,0.000028753566,6.0548433e-7,0.0063294363,0.00067779043,0.0005413612,0.09271969,0.1423943,0.009220495],"study_design_scores_gemma":[0.0007450623,0.00040757906,0.7582748,0.00022333451,0.0000041077933,0.0000603444,0.044247564,0.000711266,0.001630647,0.031937238,0.16157979,0.0001782525],"about_ca_topic_score_codex":0.20857047,"about_ca_topic_score_gemma":0.76594657,"teacher_disagreement_score":0.5573761,"about_ca_system_score_codex":0.0011331813,"about_ca_system_score_gemma":0.027531914,"threshold_uncertainty_score":0.99171543},"labels":[],"label_agreement":null},{"id":"W2338777541","doi":"10.3138/cjpe.0023.011","title":"Understanding Organization Capacity for Evaluation: Synthesis and Integration","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Context (archaeology); Empirical examination; Capacity building; Capacity development; Political science; Regional science; Process management; Knowledge management; Sociology; Business; Environmental resource management; Computer science; Geography; Economics; Archaeology","score_opus":0.6461461480260806,"score_gpt":0.5144417351249825,"score_spread":0.13170441290109813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2338777541","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6423295,0.00043947255,0.33081377,0.015983721,0.0015119814,0.004953599,0.000020832065,0.000029234818,0.0039178627],"genre_scores_gemma":[0.9897749,0.000008999988,0.009760496,0.00018659688,0.0001715482,0.00005275838,0.000017307115,0.0000074130044,0.000019994792],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964657,0.0005089066,0.0007722218,0.00020335351,0.0018556863,0.000194145],"domain_scores_gemma":[0.99256045,0.00047460434,0.00065706036,0.00017997288,0.00583559,0.00029230895],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021255374,0.00011606143,0.00020583815,0.00066721183,0.00038403278,0.00059925043,0.00021131645,0.000075826916,0.0008957825],"category_scores_gemma":[0.014939678,0.00009311519,0.0000587075,0.00084473146,0.000062778105,0.0009497191,0.000003568893,0.000110922745,0.000007692732],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001906658,0.00003322135,0.0035787437,0.0000028859233,0.000016609618,3.0720742e-7,0.0009361584,0.0012196548,0.00018429346,0.0074181086,0.0019372235,0.9846537],"study_design_scores_gemma":[0.0034036036,0.0022968107,0.15119055,0.00017603331,0.0006380883,0.000091382855,0.004431694,0.52747685,0.0017980216,0.29901153,0.009065995,0.0004194475],"about_ca_topic_score_codex":0.000060889404,"about_ca_topic_score_gemma":0.004146175,"teacher_disagreement_score":0.9842343,"about_ca_system_score_codex":0.000996008,"about_ca_system_score_gemma":0.0027818903,"threshold_uncertainty_score":0.9933579},"labels":[],"label_agreement":null},{"id":"W2340330296","doi":"","title":"Cousins, J. B., & Chouinard, J. A. (Eds.). (2012). Participatory evaluation up close: An integration of research-based knowledge. IAP. Available in paperback (ISBN 978-1617358012)","year":2014,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Citizen journalism; Participatory GIS; Participatory action research; Scholarship; Transformative learning; Sociology; Reading (process); Political science; Computer science; Pedagogy; World Wide Web","score_opus":0.42450867747596555,"score_gpt":0.5530076508535396,"score_spread":0.1284989733775741,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2340330296","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8313486,0.0020381673,0.0040528015,0.0024100684,0.0014987692,0.0019994173,0.000015569809,0.00012466504,0.15651193],"genre_scores_gemma":[0.98491484,0.0001690002,0.0011805147,0.00028677343,0.0001541923,0.00021762378,0.00006456688,0.000024482546,0.012988006],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9874868,0.004591673,0.0015932611,0.0007700608,0.0049248566,0.00063334586],"domain_scores_gemma":[0.99212366,0.0016816306,0.00039740273,0.0014585598,0.0040817405,0.0002569985],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.06177346,0.00024937006,0.00048292047,0.00079398276,0.00029172955,0.00025624002,0.000817738,0.00021048718,0.030808685],"category_scores_gemma":[0.0049553984,0.000188128,0.00011005451,0.002126433,0.00042904925,0.0015464477,0.000112933056,0.00041902778,0.0054817647],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005459069,0.002084185,0.031250644,0.00008080524,0.000025472835,0.0000010193082,0.0042183055,0.005670607,0.018435776,0.016516985,0.31154972,0.6096206],"study_design_scores_gemma":[0.00263308,0.00085977296,0.03815221,0.00013009468,0.000027108688,8.678172e-7,0.002171309,0.7389123,0.011381339,0.011340131,0.19405241,0.00033939094],"about_ca_topic_score_codex":0.00022451972,"about_ca_topic_score_gemma":0.0052936114,"teacher_disagreement_score":0.7332417,"about_ca_system_score_codex":0.00030191505,"about_ca_system_score_gemma":0.0017817242,"threshold_uncertainty_score":0.9952926},"labels":[],"label_agreement":null},{"id":"W2340392036","doi":"10.3138/cjpe.0026.007","title":"Trois conceptions de la nature des programmes : implications pour l’évaluation de programmes complexes en santé publique","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Dysfunctional family; Epistemology; Program evaluation; Valuation (finance); Psychology; Sociology; Business; Political science; Philosophy; Psychotherapist","score_opus":0.22282856566803982,"score_gpt":0.5388556115237819,"score_spread":0.3160270458557421,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2340392036","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9710492,0.0024206177,0.015813714,0.0057942015,0.0003673683,0.001980186,0.00003052377,0.000052904146,0.0024912946],"genre_scores_gemma":[0.93746966,0.000052524458,0.06087284,0.00033873043,0.0005655908,0.00052601297,0.00006552429,0.00002264754,0.00008643794],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9931326,0.0031180878,0.0010668808,0.00025190163,0.0016219642,0.0008085561],"domain_scores_gemma":[0.9927992,0.0012504421,0.0008371411,0.00038816774,0.0037021928,0.0010228426],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.035775106,0.00022511606,0.0003117498,0.00087387214,0.00060496345,0.0010534236,0.0006815988,0.0003321453,0.0012027835],"category_scores_gemma":[0.009422355,0.00018440507,0.00024411769,0.0012831573,0.0003905484,0.0016416095,0.00002351294,0.0006569043,0.000039668663],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009124345,0.00015999371,0.3625515,0.0000063408893,0.000041232397,8.184947e-7,0.005786663,0.0005155909,0.0002469946,0.004594444,0.0033195126,0.62276775],"study_design_scores_gemma":[0.0008122669,0.00027616016,0.8737729,0.000050626466,0.00017808328,0.0002589808,0.0049905283,0.010287418,0.00025150008,0.05259086,0.056314256,0.00021641413],"about_ca_topic_score_codex":0.00087782764,"about_ca_topic_score_gemma":0.009699292,"teacher_disagreement_score":0.6225513,"about_ca_system_score_codex":0.0013731685,"about_ca_system_score_gemma":0.011233715,"threshold_uncertainty_score":0.99998355},"labels":[],"label_agreement":null},{"id":"W2346855372","doi":"10.29173/cais306","title":"Information Literacy and Education Policy: An Instrumental Case Study of the Ontario Public School Curriculum","year":2013,"lang":"fr","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Literacy; Rhetorical question; Curriculum; Information literacy; Political science; Public policy; Humanities; Sociology; Pedagogy; Art; Law","score_opus":0.06170490700017143,"score_gpt":0.36398620391274555,"score_spread":0.3022812969125741,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2346855372","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9854439,0.000095227275,0.0000027311685,0.008454038,0.00055847515,0.0013401223,0.00005808322,0.000009762349,0.004037659],"genre_scores_gemma":[0.99751526,0.000048514343,0.00022512014,0.0004219479,0.00009714476,0.000082915525,0.000004406703,0.000009105988,0.0015955716],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99669075,0.00013007829,0.0012445732,0.00026656664,0.0013216895,0.00034636256],"domain_scores_gemma":[0.94388956,0.00012479261,0.0019481272,0.00038182654,0.053394634,0.00026107475],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.001702578,0.00028105034,0.00042674036,0.00042168555,0.00034038376,0.0072191767,0.0016049371,0.00015115121,0.00047027195],"category_scores_gemma":[0.011384697,0.00018005937,0.00011975584,0.001076847,0.00049029227,0.05852739,0.0008147971,0.00039571951,0.000013628615],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001658404,0.00073050073,0.70846653,0.00009645329,0.000041697673,1.466284e-7,0.17465298,0.0000031918855,0.00014882674,0.003910856,0.0009373283,0.11099492],"study_design_scores_gemma":[0.0010184406,0.0009636097,0.7534974,0.0003122987,0.00009953301,0.00029200158,0.20675644,0.002272312,0.00070632424,0.0050356262,0.0287792,0.0002667807],"about_ca_topic_score_codex":0.08903018,"about_ca_topic_score_gemma":0.005484042,"teacher_disagreement_score":0.110728145,"about_ca_system_score_codex":0.00026841255,"about_ca_system_score_gemma":0.0034158248,"threshold_uncertainty_score":0.9969428},"labels":[],"label_agreement":null},{"id":"W2349084151","doi":"","title":"A Study on Provincial District Review in Canada——the Case of School District No.5 in British Columbia","year":2007,"lang":"en","type":"article","venue":"Comparative Education Review","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Christian ministry; School district; Enlightenment; Accountability; Political science; Public administration; Geography; Sociology; Pedagogy; Law","score_opus":0.24682101332419978,"score_gpt":0.5290981049031173,"score_spread":0.28227709157891745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2349084151","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9154035,0.072363324,0.000022895565,0.0011797266,0.00055399374,0.0046180035,0.000024589908,0.0000043095924,0.005829696],"genre_scores_gemma":[0.98661834,0.010153098,0.000021010137,0.0022205475,0.000052154617,0.0003042274,0.000015706191,0.0000041243397,0.0006107905],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99585575,0.0009735458,0.0016692264,0.00036281685,0.00094637705,0.00019229874],"domain_scores_gemma":[0.9969152,0.00096245634,0.0006668283,0.0005530582,0.0007883485,0.0001141054],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007287006,0.00011569865,0.0006542217,0.00008310725,0.00010640215,0.000106250955,0.0004618949,0.000017448965,0.001712844],"category_scores_gemma":[0.0033963555,0.00010559319,0.00006626571,0.002348207,0.0000420067,0.000171752,0.00004644723,0.0002463053,0.00012944084],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005779763,0.0008434278,0.559483,0.0004662186,0.0000069724106,0.000052639367,0.0002505269,0.0000057924135,2.6476187e-7,0.000031558448,0.26679942,0.17205444],"study_design_scores_gemma":[0.00024159276,0.00010053571,0.9318398,0.0050018933,0.000022095583,0.0000436756,0.0036862814,0.000028018563,7.4192826e-7,0.000028361525,0.058882475,0.00012448773],"about_ca_topic_score_codex":0.7153225,"about_ca_topic_score_gemma":0.9964842,"teacher_disagreement_score":0.37235686,"about_ca_system_score_codex":0.0007803329,"about_ca_system_score_gemma":0.006497605,"threshold_uncertainty_score":0.99919975},"labels":[],"label_agreement":null},{"id":"W2355906629","doi":"","title":"Research partnership and knowledge transfer in the development of a generic evaluation toolkit for health promotion interventions in primary care.","year":2010,"lang":"en","type":"article","venue":"International public health journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Health promotion; Public relations; Health policy; Health care; Medicine; General partnership; Public health; Nursing; Political science","score_opus":0.7677590715728929,"score_gpt":0.6584001051372363,"score_spread":0.10935896643565657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2355906629","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90104324,0.0005006285,0.012107306,0.08133501,0.00076665625,0.0012429229,0.000009998689,0.000004149597,0.0029900612],"genre_scores_gemma":[0.9960557,0.00006291262,0.00294825,0.0003729272,0.0001862027,0.00023406414,0.00004656305,0.000005529539,0.000087802815],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99253315,0.0020726894,0.0019085243,0.0002761332,0.0028189665,0.0003905204],"domain_scores_gemma":[0.99649245,0.0007812328,0.00029524753,0.00016231333,0.0021187356,0.00015003522],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.09643627,0.000082417304,0.00019805408,0.0013276438,0.00031797786,0.0003126544,0.00060369435,0.000054164808,0.00026236012],"category_scores_gemma":[0.0015015287,0.00005645859,0.0000736099,0.00079151837,0.00007114613,0.00059478945,0.000047367284,0.000615578,0.000006753775],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039148268,0.000525909,0.022961667,0.00011934255,0.000011806156,2.2937965e-7,0.044065718,0.000059130725,0.000050604922,0.0046868506,0.0012632934,0.9262163],"study_design_scores_gemma":[0.002751106,0.00051094417,0.8694206,0.00031114975,0.000002228058,0.000043441894,0.013570514,0.013078897,0.000021591355,0.005315096,0.09485739,0.000117039686],"about_ca_topic_score_codex":0.000021338124,"about_ca_topic_score_gemma":0.007117995,"teacher_disagreement_score":0.92609924,"about_ca_system_score_codex":0.0007978869,"about_ca_system_score_gemma":0.008800136,"threshold_uncertainty_score":0.996819},"labels":[],"label_agreement":null},{"id":"W2365117357","doi":"10.1007/978-3-319-23347-5_13","title":"First Nations Assessment Issues","year":2015,"lang":"en","type":"book-chapter","venue":"˜The œenabling power of assessment","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Political science; Engineering ethics; Engineering","score_opus":0.20582046363996587,"score_gpt":0.48932813609867615,"score_spread":0.2835076724587103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2365117357","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012001892,0.0013479678,0.006277354,0.00814447,0.002673894,0.0011817216,0.00015222475,0.00009685784,0.9800055],"genre_scores_gemma":[0.24385549,0.0007507515,0.0057512415,0.0004727869,0.00045073347,0.000109173445,0.00011515341,0.00011278049,0.7483819],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9879141,0.00023189704,0.0023150505,0.0010356779,0.007981728,0.00052157976],"domain_scores_gemma":[0.9895162,0.0023777261,0.0021084214,0.002438892,0.003282852,0.00027589945],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.011152591,0.0006885802,0.0011185496,0.0011706767,0.00079779496,0.0006124852,0.0022574433,0.000403574,0.013809471],"category_scores_gemma":[0.0003148552,0.00045571016,0.0005408158,0.000499627,0.0003582566,0.00048927404,0.0006445754,0.000939462,0.00079798524],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003906339,0.0003389682,0.0010048383,0.000093818795,0.0005608225,0.000017965323,0.0016033542,0.0076299836,0.000025582813,0.76733625,0.21211948,0.009229877],"study_design_scores_gemma":[0.00059135177,0.00033900148,0.0012463355,0.0002582428,0.00013153885,0.000007866316,0.0009094102,0.0034268976,0.000008255495,0.06564492,0.9269269,0.0005092786],"about_ca_topic_score_codex":0.00006401291,"about_ca_topic_score_gemma":0.0010750932,"teacher_disagreement_score":0.71480745,"about_ca_system_score_codex":0.0007386392,"about_ca_system_score_gemma":0.0028354651,"threshold_uncertainty_score":0.99998003},"labels":[],"label_agreement":null},{"id":"W237532803","doi":"10.3138/cjpe.26.006","title":"The Essential Skills Series in Evaluation: Assessing the Validity of the ESS Participant Workshop Evaluation Questionnaire","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Centre de Liaison Sur l'Intervention et la Prévention Psychosociales; Université du Québec à Montréal; Université de Montréal","funders":"","keywords":"Psychology; Medical education; Applied psychology; Medicine","score_opus":0.518137140465873,"score_gpt":0.548237636298514,"score_spread":0.03010049583264096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W237532803","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9836564,0.0011011629,0.0005890633,0.0067049586,0.0032204285,0.0031163853,0.0000037491461,0.0000067905776,0.0016010748],"genre_scores_gemma":[0.9988406,0.000026446105,0.00039092547,0.00008924334,0.00022861757,0.00033015394,0.0000049497603,0.000011973766,0.000077099496],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9838411,0.007246238,0.0019373316,0.0002855865,0.006257947,0.00043176225],"domain_scores_gemma":[0.9881095,0.00087532384,0.001996249,0.0008092596,0.0079968935,0.0002127336],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10130053,0.00019084217,0.00029769258,0.00032198027,0.0009840672,0.00070253067,0.0011894483,0.00012126301,0.0010210243],"category_scores_gemma":[0.01912317,0.000094300085,0.00022397765,0.0016418836,0.00054190605,0.001379401,0.000048823484,0.00043021239,0.0000126447785],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030712203,0.00014719395,0.15487787,0.000007096411,0.00006272527,0.0000015063703,0.011612259,0.014197379,0.000040564963,0.0013280927,0.000990496,0.8167041],"study_design_scores_gemma":[0.0009522966,0.00015919376,0.80145407,0.00022980102,0.00046351412,0.000030659037,0.007948485,0.14694789,0.00048052892,0.039612103,0.0015764547,0.00014497757],"about_ca_topic_score_codex":0.0006206697,"about_ca_topic_score_gemma":0.07303869,"teacher_disagreement_score":0.81655914,"about_ca_system_score_codex":0.000639029,"about_ca_system_score_gemma":0.011873252,"threshold_uncertainty_score":0.9998922},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W2385104559","doi":"","title":"The formation and enlightenment of America's program evaluation standard","year":2015,"lang":"en","type":"article","venue":"Journal of Chongqing University. English Edition","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Enlightenment; National standard; China; Quality (philosophy); Professional standards; Imitation; Political science; International standard; Evaluation methods; Quality standard; Control (management); Engineering management; Public administration; Public relations; Computer science; Engineering; Engineering ethics; Psychology; Law; Artificial intelligence","score_opus":0.11800238857940584,"score_gpt":0.41126419638218753,"score_spread":0.29326180780278166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2385104559","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9555602,0.0002762211,0.023697656,0.0029135167,0.0031496673,0.00072208943,0.0000134443,0.000023693796,0.01364353],"genre_scores_gemma":[0.9967703,0.00019552339,0.002557396,0.00002387609,0.0003321439,0.0000010884462,0.0000049371793,0.0000028033483,0.000111888665],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9966703,0.00033475106,0.00044199664,0.00008018071,0.002384054,0.000088738794],"domain_scores_gemma":[0.9938786,0.00035461565,0.0009776186,0.00012364097,0.004571198,0.000094298775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0066150357,0.000060126833,0.00014355764,0.00018496346,0.00016564142,0.00012936501,0.00020785438,0.00003533763,0.00003879221],"category_scores_gemma":[0.0017657934,0.0000398523,0.00005787319,0.0003905633,0.00008797909,0.0015994443,0.00003717651,0.000117419026,0.000002188959],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043071582,0.00009942546,0.0019223179,0.000007962839,0.000040487004,0.000003718031,0.009379653,0.003300338,0.0001116557,0.0007441463,0.04375778,0.9402018],"study_design_scores_gemma":[0.003030521,0.0015147529,0.0065268455,0.00008881538,0.00012406806,0.000018614153,0.074690156,0.042609137,0.0011973649,0.0061518615,0.8639234,0.00012449623],"about_ca_topic_score_codex":0.000002588486,"about_ca_topic_score_gemma":0.000006591139,"teacher_disagreement_score":0.9400773,"about_ca_system_score_codex":0.0002529609,"about_ca_system_score_gemma":0.0002975563,"threshold_uncertainty_score":0.22926526},"labels":[],"label_agreement":null},{"id":"W2396775442","doi":"","title":"Impact factors and the law of unintended consequences.","year":2005,"lang":"en","type":"editorial","venue":"PubMed","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Unintended consequences; Political science; Law; Law and economics; Economics","score_opus":0.14262324261299045,"score_gpt":0.44946816456325167,"score_spread":0.30684492195026125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2396775442","genre_codex":"editorial","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010179567,0.00080416177,0.000025638281,0.0035521819,0.9406892,0.0015665499,0.0004127086,0.00003474244,0.042735253],"genre_scores_gemma":[0.80626744,0.00024686908,0.0000164993,0.00008691682,0.19010869,0.00023660505,0.00003814265,0.000011604937,0.0029872423],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9952179,0.00042644245,0.0007683875,0.00034781432,0.0029505556,0.00028889702],"domain_scores_gemma":[0.992579,0.0052631367,0.0007197774,0.0005647634,0.0007460281,0.00012731926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007663355,0.00022028857,0.0005929422,0.00015974834,0.00011885235,0.00026888802,0.0007948678,0.00027727865,0.0003994174],"category_scores_gemma":[0.0068720547,0.00009452225,0.00021134535,0.00030996653,0.0022526933,0.0002461118,0.00012192345,0.00041266877,0.000017391449],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000112007736,0.000018267849,0.0013348906,0.0000050156673,0.000071969494,4.4252056e-7,0.00037353227,0.000014537778,4.2290813e-7,0.00411516,0.97213876,0.021814967],"study_design_scores_gemma":[0.0013769493,0.000026689086,0.03660286,0.000008745824,0.0000543142,9.4320126e-7,0.00031008356,0.00007056351,0.00003636286,0.008405026,0.9529456,0.00016189313],"about_ca_topic_score_codex":0.0006468251,"about_ca_topic_score_gemma":0.0005138172,"teacher_disagreement_score":0.79608786,"about_ca_system_score_codex":0.000091307644,"about_ca_system_score_gemma":0.00046184481,"threshold_uncertainty_score":0.8300142},"labels":[],"label_agreement":null},{"id":"W2401324600","doi":"10.14288/1.0055798","title":"Program evaluation in education : school district practice in British Columbia","year":2010,"lang":"en","type":"article","venue":"cIRcle (University of British Columbia)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"School district; Mathematics education; Pedagogy; Sociology; Psychology","score_opus":0.03935953827517552,"score_gpt":0.35738025682453384,"score_spread":0.3180207185493583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2401324600","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9889787,0.00010704118,0.000033950564,0.00037128213,0.0005476644,0.0013901098,0.000042764736,0.000034952984,0.008493548],"genre_scores_gemma":[0.99586505,0.00012272061,0.002249018,0.00010602146,0.0000429563,0.000023435077,0.00005811898,0.000008349501,0.0015243466],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99656606,0.00042034307,0.00044576998,0.0005790023,0.0017275793,0.00026126427],"domain_scores_gemma":[0.99721825,0.00036601044,0.00039304298,0.00045889456,0.001403002,0.00016081512],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005509364,0.00004125758,0.00026086607,0.00014630608,0.00020984923,0.0013529651,0.0006070796,0.00015851305,0.0035131813],"category_scores_gemma":[0.0039564143,0.00016820557,0.000082299135,0.001700019,0.00016664395,0.0020429678,0.000115387156,0.00041181114,0.00010515605],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003643599,0.00053476356,0.3023751,0.000006063812,0.0000034130055,0.000012536782,0.00012217954,0.000018121635,0.000024005143,5.309635e-7,0.0066215843,0.69027805],"study_design_scores_gemma":[0.0012967002,0.00008477809,0.97245663,0.00009776963,0.000020849711,0.000056601213,0.0073136836,0.0042905137,1.2113134e-7,0.0011676317,0.013041304,0.00017339745],"about_ca_topic_score_codex":0.6016107,"about_ca_topic_score_gemma":0.9936349,"teacher_disagreement_score":0.69010466,"about_ca_system_score_codex":0.00023176377,"about_ca_system_score_gemma":0.0017128584,"threshold_uncertainty_score":0.99968374},"labels":[],"label_agreement":null},{"id":"W2404873549","doi":"","title":"Report from the Director-at-Large-- Professional Practice.","year":2010,"lang":"en","type":"article","venue":"PubMed","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Association of Nurses in Oncology","funders":"","keywords":"Management; Economics","score_opus":0.1544821648554743,"score_gpt":0.470311997459725,"score_spread":0.3158298326042507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2404873549","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82713455,0.000091819165,0.00019690719,0.06221516,0.009143418,0.0009448168,0.000037479345,0.00006856353,0.100167304],"genre_scores_gemma":[0.9568061,0.0000065920794,0.00061050936,0.0033174914,0.00059725845,0.00085104373,0.000025221894,0.000007712859,0.037778046],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9962005,0.00031879568,0.00052716443,0.00037203627,0.0022883194,0.00029316102],"domain_scores_gemma":[0.9941205,0.0039947163,0.00043600483,0.00088745914,0.0004282227,0.00013310299],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.013729793,0.00009474043,0.00013070313,0.000046126217,0.00039632642,0.00021095993,0.0005937406,0.00007473623,0.0051866784],"category_scores_gemma":[0.01678747,0.0000474576,0.00007307823,0.00031987418,0.00006386517,0.00053682085,0.00023869121,0.00033522752,0.0008184261],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006816245,0.00017449346,0.41959727,5.494785e-7,0.000029863322,0.000026736781,0.0005931269,0.000004382311,0.00016263235,0.0013028292,0.36282688,0.21521306],"study_design_scores_gemma":[0.00012618475,0.0000014625692,0.505014,5.8942607e-7,0.0000058362953,0.000014305451,0.00015581783,0.00014905809,0.00012209066,0.0012831839,0.49308476,0.000042724645],"about_ca_topic_score_codex":0.00004830022,"about_ca_topic_score_gemma":0.0005839716,"teacher_disagreement_score":0.21517032,"about_ca_system_score_codex":0.000036070174,"about_ca_system_score_gemma":0.0001733647,"threshold_uncertainty_score":0.9999595},"labels":[],"label_agreement":null},{"id":"W2407144358","doi":"10.1186/s12961-016-0109-0","title":"A qualitative case study of evaluation use in the context of a collaborative program evaluation strategy in Burkina Faso","year":2016,"lang":"en","type":"article","venue":"Health Research Policy and Systems","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cégep Marie-Victorin; Université de Montréal","funders":"Canadian Institutes of Health Research","keywords":"Health services research; Qualitative research; Public health; Context (archaeology); Health administration; Medicine; Program evaluation; Medical education; Nursing; Environmental health; Political science; Sociology; Geography; Social science; Public administration","score_opus":0.8851314341190073,"score_gpt":0.758790436845812,"score_spread":0.12634099727319525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2407144358","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9857224,0.00047592857,0.000014518863,0.002372269,0.00003574371,0.010939151,0.000034187018,0.0000030092197,0.00040276058],"genre_scores_gemma":[0.9973154,0.0000800039,0.000009872527,0.000042053496,0.00003371438,0.0024393657,0.000002477766,0.000004277073,0.00007281097],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9294787,0.05915617,0.0021766485,0.0005033341,0.008153081,0.0005320684],"domain_scores_gemma":[0.9808924,0.0117606055,0.0005904304,0.00044984842,0.006205489,0.0001012325],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.18170068,0.00010035333,0.00040252545,0.0011845564,0.00016684935,0.00015426557,0.00020408837,0.00005839871,0.000022896786],"category_scores_gemma":[0.01981014,0.000050429375,0.000019076911,0.0038423098,0.00021775514,0.00048797016,0.00004501384,0.0001805772,0.000004504518],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026781505,0.0013094859,0.026764318,0.00014695576,0.000020562458,0.000016369237,0.6537382,0.0004489564,0.00005713763,0.0099485805,0.00056346477,0.30671817],"study_design_scores_gemma":[0.0034443303,0.0035263721,0.042700596,0.00024372176,0.0000034571285,0.000020355272,0.90715027,0.041142296,0.0000066280822,0.001446967,0.0002580441,0.000056957248],"about_ca_topic_score_codex":0.04837309,"about_ca_topic_score_gemma":0.07209955,"teacher_disagreement_score":0.30666122,"about_ca_system_score_codex":0.00046882883,"about_ca_system_score_gemma":0.0053364406,"threshold_uncertainty_score":0.9884464},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W2409542052","doi":"10.20452/pamw.1613","title":"Impact factor and study quality","year":2013,"lang":"en","type":"editorial","venue":"Polskie Archiwum Medycyny Wewnętrznej","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Quality (philosophy); Factor (programming language); Computer science; Physics","score_opus":0.3513820254119452,"score_gpt":0.6240069059100605,"score_spread":0.2726248804981153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2409542052","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1830654,0.0005333024,0.0004423958,0.00097516214,0.7928543,0.0029925248,0.0013079508,0.0002259951,0.017602976],"genre_scores_gemma":[0.43197963,0.00033946938,0.0008278039,0.00019353042,0.5492883,0.00037383175,0.00031388298,0.00014519102,0.016538417],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9828658,0.002232478,0.002399617,0.0018299217,0.00967019,0.0010019733],"domain_scores_gemma":[0.98299557,0.011100935,0.0013694464,0.0023187937,0.0014058583,0.00080938713],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.009522786,0.00092251506,0.0016864807,0.0009085406,0.0004917188,0.0015163216,0.0021398794,0.0006387915,0.0074104755],"category_scores_gemma":[0.011738676,0.0006094886,0.00044721822,0.0007570954,0.00029949285,0.00091949647,0.00093139085,0.0017436579,0.0030100415],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008309747,0.00044217092,0.020149408,0.00002407044,0.00018756806,0.000005830659,0.002995966,0.000004924199,0.00003127117,0.00012426675,0.8912588,0.08469265],"study_design_scores_gemma":[0.0014655471,0.00086083997,0.2214199,0.000037868973,0.000059977705,0.0000018669751,0.0011019064,0.00016329327,0.0000042606257,0.0058163865,0.76833516,0.00073296175],"about_ca_topic_score_codex":0.002227958,"about_ca_topic_score_gemma":0.00094989804,"teacher_disagreement_score":0.24891421,"about_ca_system_score_codex":0.0002730992,"about_ca_system_score_gemma":0.0017808739,"threshold_uncertainty_score":0.99963564},"labels":[],"label_agreement":null},{"id":"W2410304144","doi":"10.3928/01484834-20050301-05","title":"Participatory Inquiry with a Colleague: An Innovative Faculty Development Process","year":2005,"lang":"en","type":"article","venue":"Journal of Nursing Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cargill (Canada)","funders":"","keywords":"Scholarship; Commit; Citizen journalism; Nurse educator; Process (computing); Work (physics); Sociology; Medical education; Engineering ethics; Participatory action research; Pedagogy; Nurse education; Psychology; Nursing; Medicine; Political science; Computer science","score_opus":0.5710031227578791,"score_gpt":0.6336520683877865,"score_spread":0.06264894562990742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2410304144","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99229014,0.000041589872,0.0017482045,0.0033451254,0.0006533239,0.00010437171,3.970483e-7,0.0000063157195,0.0018105048],"genre_scores_gemma":[0.98593706,0.000001506231,0.012746764,0.00042303567,0.00043946182,0.000009417768,0.0000040260206,0.000005988458,0.00043273985],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99753666,0.00012679677,0.0007184248,0.00013557024,0.0013538593,0.0001286723],"domain_scores_gemma":[0.99575996,0.00007085387,0.0008400826,0.00014002706,0.0030713184,0.00011777062],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027799904,0.000085368905,0.00015882285,0.00034892894,0.00015900217,0.0001412596,0.00024042263,0.000035018507,0.00018142698],"category_scores_gemma":[0.00028893183,0.00005429716,0.000018805262,0.00092989573,0.00007216588,0.0012868599,0.00000450902,0.00014323005,0.000032219927],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015634699,0.0016159741,0.018868774,0.0000042350493,0.000019195457,4.561148e-7,0.20006981,0.002023027,0.0001823225,0.00016444117,0.011713686,0.7651817],"study_design_scores_gemma":[0.0013618456,0.00093543413,0.6792945,0.0006808785,0.000042837968,0.00017396657,0.24127805,0.0022382922,0.008014237,0.0021393488,0.06350319,0.00033736866],"about_ca_topic_score_codex":4.8806305e-7,"about_ca_topic_score_gemma":0.000008665407,"teacher_disagreement_score":0.76484436,"about_ca_system_score_codex":0.00038170256,"about_ca_system_score_gemma":0.0046657063,"threshold_uncertainty_score":0.8276763},"labels":[],"label_agreement":null},{"id":"W2414340625","doi":"","title":"Integrated Programs Paradigm As a Response to Harm Reduction Shortcomings in Quebec.","year":2016,"lang":"en","type":"article","venue":"Dutch Crossing","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Reduction (mathematics); Harm reduction; Harm; Political science; Risk analysis (engineering); Psychology; Business; Medicine; Social psychology; Mathematics; Nursing","score_opus":0.16605584680923213,"score_gpt":0.48516837428765563,"score_spread":0.3191125274784235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2414340625","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98073775,0.000015969661,0.0027619242,0.014723927,0.00044712736,0.00035480206,0.0000027676235,0.000063403575,0.0008923198],"genre_scores_gemma":[0.97967976,0.000001751067,0.0012890509,0.00035278522,0.00005952814,0.000057709454,0.0000026279465,0.000011912026,0.018544877],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99700165,0.00036949248,0.0006856731,0.00049836887,0.001093005,0.00035180332],"domain_scores_gemma":[0.998588,0.00041185238,0.00015533532,0.00044412471,0.00024384024,0.00015680211],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0067006866,0.00014786678,0.00022074468,0.0004316114,0.00029420966,0.0016441555,0.00035226162,0.00007955776,0.0007316165],"category_scores_gemma":[0.002037147,0.000088335444,0.000066846595,0.0012922847,0.0001819576,0.00094733713,0.000069056594,0.00011434257,0.0010868418],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012918996,0.00009915072,0.019357167,0.0000018881755,0.000005368641,0.000011232646,0.011778753,0.000065324966,0.062549174,0.0005279404,0.0020419555,0.90227014],"study_design_scores_gemma":[0.0023297719,0.00047297394,0.26348835,0.00057404797,0.000010114602,0.000062046434,0.009148308,0.0030727834,0.022554876,0.010687514,0.6869468,0.000652385],"about_ca_topic_score_codex":0.002057337,"about_ca_topic_score_gemma":0.0024174121,"teacher_disagreement_score":0.90161777,"about_ca_system_score_codex":0.00039328815,"about_ca_system_score_gemma":0.0008120146,"threshold_uncertainty_score":0.99969095},"labels":[],"label_agreement":null},{"id":"W2415836739","doi":"","title":"Developmental evaluation exemplars : principles in practice","year":2016,"lang":"en","type":"book","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":154,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Indigenous; Sociology; Watson; Management; Library science","score_opus":0.3816857263393895,"score_gpt":0.533974536343964,"score_spread":0.15228881000457445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2415836739","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004141703,0.0001058943,0.0004518877,0.0032681164,0.0004448799,0.00076196843,0.000011124634,0.000027102467,0.9945149],"genre_scores_gemma":[0.001868953,0.00013400867,0.0051509826,0.0009853023,0.00013725286,0.00009877544,0.00004118574,0.000019202953,0.99156433],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9912925,0.00048856396,0.0012731309,0.0006732607,0.006015476,0.00025709326],"domain_scores_gemma":[0.99510026,0.002492341,0.00068818737,0.0003831416,0.0012478103,0.00008828203],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.021220893,0.00024525297,0.00034135708,0.0006685382,0.0001143168,0.00022438534,0.000662261,0.00024740052,0.028868526],"category_scores_gemma":[0.005534299,0.00015250956,0.00008216701,0.00025662372,0.000056152345,0.0010523393,0.00020727474,0.0002449865,0.009748576],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008313494,0.00010606122,0.0020443678,0.0000089954165,0.0000593694,0.000011924272,0.0012511986,0.00015100613,0.000030688945,0.046012778,0.27456754,0.67567295],"study_design_scores_gemma":[0.000647228,0.0000319511,0.0030643842,0.00009813105,0.000025879177,0.000014312244,0.0004956858,0.0012850385,0.000022874316,0.022543324,0.9715081,0.00026310747],"about_ca_topic_score_codex":0.000008767757,"about_ca_topic_score_gemma":0.0006375279,"teacher_disagreement_score":0.69694054,"about_ca_system_score_codex":0.0022654582,"about_ca_system_score_gemma":0.007963419,"threshold_uncertainty_score":0.9976605},"labels":[],"label_agreement":null},{"id":"W2417257911","doi":"10.1177/0829573516652992","title":"Saskatchewan Revisited","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of School Psychology","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Psychology; Foundation (evidence); Professional psychology; Set (abstract data type); Affect (linguistics); Engineering ethics; Applied psychology; Medical education; Political science; Law; Clinical psychology; Medicine; Burnout; Engineering","score_opus":0.21624783215170293,"score_gpt":0.5020217960991932,"score_spread":0.2857739639474902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2417257911","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82574314,0.00076509133,0.012300002,0.10143697,0.0036897522,0.000154634,0.000028233133,0.0000096103695,0.055872545],"genre_scores_gemma":[0.9894617,0.00003121176,0.00078814593,0.0053963526,0.0003514146,9.328426e-7,3.0926435e-7,0.000006735925,0.0039631943],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99788254,0.00025334215,0.0008438468,0.00018247568,0.0005590323,0.00027875367],"domain_scores_gemma":[0.99696857,0.00026326097,0.0004555567,0.00043453806,0.0008567274,0.0010213527],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.004294273,0.00008755718,0.00023993586,0.000764376,0.00009472087,0.00009319467,0.0007605159,0.00008881187,0.027686797],"category_scores_gemma":[0.002259789,0.00004776353,0.000113213304,0.0004748328,0.00012447781,0.00042559917,0.000008380148,0.00018262939,0.0023574033],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003521393,0.000010294026,0.32176775,7.8553836e-7,0.000025669748,0.00007817092,0.00024143902,0.000005710407,0.0014253919,0.00072359486,0.49243933,0.18324666],"study_design_scores_gemma":[0.0009779192,0.00021273123,0.3762993,0.00004140828,0.000008415276,0.00020797073,0.000491193,0.000004934458,0.00006946913,0.018338887,0.6032459,0.000101882266],"about_ca_topic_score_codex":0.00018970064,"about_ca_topic_score_gemma":0.009885508,"teacher_disagreement_score":0.18314478,"about_ca_system_score_codex":0.00011638234,"about_ca_system_score_gemma":0.0028076526,"threshold_uncertainty_score":0.9984194},"labels":[],"label_agreement":null},{"id":"W2417527718","doi":"","title":"Scaffolding good practices.","year":2007,"lang":"en","type":"article","venue":"PubMed","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Forming Technologies (Canada)","funders":"","keywords":"Scaffold; Computer science; Business; Programming language","score_opus":0.3856509411932347,"score_gpt":0.5101007304628821,"score_spread":0.12444978926964739,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2417527718","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5046416,0.000118164535,0.0035054823,0.003515868,0.0010598865,0.00044180878,0.0000012005704,0.000060800405,0.48665518],"genre_scores_gemma":[0.9887223,0.000008688514,0.00065042905,0.00081328413,0.0002009195,0.00009955314,9.438054e-7,0.0000048911897,0.009498957],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9973464,0.00007576608,0.0004237833,0.00025028258,0.0015651162,0.00033866634],"domain_scores_gemma":[0.99773836,0.001058866,0.00049702724,0.00034514265,0.00020902867,0.00015157527],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019259507,0.0000667371,0.00010356199,0.00020624087,0.000121561316,0.0002453429,0.0003739242,0.000040611536,0.000781674],"category_scores_gemma":[0.0040321467,0.000047894304,0.000049239537,0.00065765093,0.000026822665,0.0007021324,0.000062674335,0.00008200866,0.00063439395],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001375421,0.00003203151,0.09752437,9.0411055e-7,0.000005841472,0.0000027430237,0.00012018593,0.000019005138,0.000024206724,0.003149196,0.0047136443,0.8943941],"study_design_scores_gemma":[0.00017962462,0.000005688436,0.7188879,7.604052e-7,0.0000042199367,0.000004175856,0.00034883356,0.00023296889,0.00063791964,0.0016261938,0.2780093,0.00006240933],"about_ca_topic_score_codex":0.000012442617,"about_ca_topic_score_gemma":0.00008748356,"teacher_disagreement_score":0.8943317,"about_ca_system_score_codex":0.000056057455,"about_ca_system_score_gemma":0.000048685084,"threshold_uncertainty_score":0.85587823},"labels":[],"label_agreement":null},{"id":"W2422794107","doi":"10.55016/ojs/ajer.v47i3.54882","title":"Perspectives on the Unity and Integration of Knowledge by Garth Benson, Ronald Glasberg, and Bryant Griffith (Eds.)","year":2001,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Epistemology; Psychology; Philosophy; Sociology","score_opus":0.26437165272879876,"score_gpt":0.5390030449779506,"score_spread":0.27463139224915184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2422794107","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92019033,0.002144271,0.0000129329665,0.05057942,0.00008188737,0.00011888404,0.000002970956,2.0527388e-7,0.026869074],"genre_scores_gemma":[0.980701,0.002103539,0.000069948925,0.00011726382,0.00013739066,0.0000056090057,0.00000234946,0.000004574139,0.0168583],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9969445,0.00070966006,0.00049227837,0.00017697319,0.0015170312,0.00015958256],"domain_scores_gemma":[0.9690046,0.027895398,0.00026417468,0.00019738391,0.0025015832,0.00013691715],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006521962,0.0000843639,0.0001600775,0.00036329695,0.000301231,0.00014425657,0.00034117652,0.00003364997,0.005949646],"category_scores_gemma":[0.015612083,0.000045694,0.00003983317,0.0006572262,0.00034284816,0.00034111174,0.000054487216,0.0003846248,0.000055192435],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010311888,0.0025960892,0.27631554,0.000019289744,0.00017026252,6.0676166e-7,0.03317035,0.000068156856,0.0065194843,0.32753372,0.31201392,0.04056141],"study_design_scores_gemma":[0.0010557453,0.002175456,0.79936475,0.00020641276,0.000025404837,0.00015713762,0.037206594,0.0019505777,0.0012421805,0.023133907,0.13329023,0.00019158413],"about_ca_topic_score_codex":0.0002444422,"about_ca_topic_score_gemma":0.0012979748,"teacher_disagreement_score":0.52304924,"about_ca_system_score_codex":0.000071844785,"about_ca_system_score_gemma":0.00081024674,"threshold_uncertainty_score":0.99495906},"labels":[],"label_agreement":null},{"id":"W2424957842","doi":"","title":"Conducting policy research children with special needs.","year":2000,"lang":"en","type":"article","venue":"PubMed","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Psychology; Political science","score_opus":0.5372514726051199,"score_gpt":0.5194326730824923,"score_spread":0.01781879952262755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2424957842","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70143515,0.000014205519,0.0000049456776,0.004538523,0.00008171617,0.0004175974,0.000003083017,0.000019870664,0.29348487],"genre_scores_gemma":[0.95867956,0.000017501048,0.000095299314,0.00042841028,0.0030074848,0.0002491724,0.0000033358779,0.000008130946,0.037511088],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9961371,0.00029300753,0.00031007017,0.00027145943,0.0024781039,0.00051025883],"domain_scores_gemma":[0.99872905,0.00031768225,0.00006201126,0.0004131218,0.0003063981,0.0001717213],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.007730448,0.00008207752,0.0001349749,0.0005894902,0.00031221707,0.0003787836,0.0005086857,0.00004020168,0.007860542],"category_scores_gemma":[0.0008015107,0.00005259374,0.000034849025,0.0024084414,0.00015141143,0.00044040786,0.000049668215,0.00022784136,0.0014227018],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031963522,0.000027379132,0.055918194,3.2392506e-7,0.000009248898,7.780006e-7,0.0005665504,0.000112968286,0.000001211898,0.0014070957,0.01399731,0.92792696],"study_design_scores_gemma":[0.00048692134,0.00003177713,0.87160635,0.000001818085,0.0000026167268,0.000016375778,0.0005903825,0.000073983116,0.00013067017,0.0025970633,0.12436489,0.00009713902],"about_ca_topic_score_codex":0.00012833538,"about_ca_topic_score_gemma":0.00008253579,"teacher_disagreement_score":0.92782986,"about_ca_system_score_codex":0.00008430501,"about_ca_system_score_gemma":0.00024564314,"threshold_uncertainty_score":0.9993548},"labels":[],"label_agreement":null},{"id":"W242703065","doi":"10.3138/cjpe.0014.005","title":"Organizational Development and Evaluation","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Organization development; Organizational learning; Organizational effectiveness; Organizational culture; Organizational behavior and human resources; Knowledge management; Facilitation; Organizational commitment; Organizational performance; Organizational studies; Organizational engineering; Process (computing); Psychology; Process management; Business; Computer science; Public relations; Political science; Social psychology","score_opus":0.3470470019193243,"score_gpt":0.5167326550286309,"score_spread":0.16968565310930656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W242703065","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9848315,0.00059873913,0.00020943723,0.0015919893,0.0003473457,0.000852512,0.0000021949875,0.000006861273,0.011559385],"genre_scores_gemma":[0.99203706,0.0000105148965,0.007120703,0.00019346764,0.00013930512,0.000044271692,0.000025046242,0.000008064774,0.00042155443],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99511397,0.000479311,0.00086574914,0.00018701941,0.0031608173,0.00019313527],"domain_scores_gemma":[0.994701,0.00013147466,0.0003607743,0.00016478283,0.004245061,0.00039685983],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.018886132,0.00010251714,0.00015921968,0.00049297005,0.00029217592,0.00039247482,0.0002472586,0.000064020045,0.030043043],"category_scores_gemma":[0.0016846117,0.00008153411,0.000039175357,0.0007273301,0.0000671318,0.0005667342,0.0000058724786,0.0001169412,0.00022470689],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000066792977,0.000019406772,0.016743524,0.0000012194348,0.00001476917,0.0000010737588,0.0012953348,0.0015426663,0.000008297396,0.00028805315,0.000943133,0.9791359],"study_design_scores_gemma":[0.002336901,0.0003609886,0.45420936,0.00005719761,0.00015846833,0.00014092268,0.00118837,0.18080038,0.000297725,0.02987434,0.33027124,0.0003040879],"about_ca_topic_score_codex":0.00006852469,"about_ca_topic_score_gemma":0.0047591617,"teacher_disagreement_score":0.97883177,"about_ca_system_score_codex":0.0003954455,"about_ca_system_score_gemma":0.008964811,"threshold_uncertainty_score":0.99665344},"labels":[],"label_agreement":null},{"id":"W2428903417","doi":"10.1016/j.aap.2016.05.024","title":"An exemplum and its road safety morals","year":2016,"lang":"en","type":"article","venue":"Accident Analysis & Prevention","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":28,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Causation; Poison control; Occupational safety and health; Accident (philosophy); Human factors and ergonomics; Injury prevention; State (computer science); Position (finance); Suicide prevention; Computer security; Engineering; Public relations; Psychology; Business; Political science; Law; Computer science; Medicine; Environmental health","score_opus":0.1408927365800541,"score_gpt":0.5063235803534554,"score_spread":0.3654308437734013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2428903417","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9742546,0.0001652798,0.022376865,0.0016508317,0.000105057276,0.00018267483,8.284951e-7,0.000034093384,0.0012297593],"genre_scores_gemma":[0.9879917,0.0002633177,0.00027250405,0.0001047232,0.00006546335,0.000017923297,0.000019525312,0.0000056319213,0.011259217],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9966769,0.0004990944,0.00077783497,0.0005082061,0.0013450682,0.00019290033],"domain_scores_gemma":[0.9983358,0.00018375652,0.0003944751,0.00057671755,0.00037465597,0.00013462512],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005480265,0.0001278633,0.0003110834,0.0005733657,0.00018341605,0.00025272905,0.00039627374,0.00006253575,0.01019169],"category_scores_gemma":[0.0003401912,0.00007648877,0.00024206932,0.0012455628,0.000025658253,0.0018333377,0.00008634944,0.000045490266,0.0006833661],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025590742,0.00006389736,0.7002108,2.8441764e-7,0.00019391962,6.839444e-7,0.00015016554,0.00017300525,0.0031312222,0.0010054694,0.0003889982,0.29465598],"study_design_scores_gemma":[0.00044420979,0.000083205836,0.9764366,0.000012911267,0.0004033465,0.0000010675502,0.00017273641,0.010598999,0.0010101259,0.00874207,0.0019459914,0.00014871523],"about_ca_topic_score_codex":0.000025792075,"about_ca_topic_score_gemma":0.0019689112,"teacher_disagreement_score":0.29450727,"about_ca_system_score_codex":0.00005540648,"about_ca_system_score_gemma":0.00005359557,"threshold_uncertainty_score":0.9907131},"labels":[],"label_agreement":null},{"id":"W2430466294","doi":"10.1108/jpcc-03-2016-0004","title":"Developing professional capital in policy and practice","year":2016,"lang":"en","type":"article","venue":"Journal of Professional Capital and Community","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Professional learning community; Professional development; Government (linguistics); Originality; Value (mathematics); Teacher leadership; Pedagogy; Psychology; Public relations; Faculty development; Political science; Educational leadership; Sociology; Qualitative research; Computer science","score_opus":0.2434268403466248,"score_gpt":0.5369826068248024,"score_spread":0.2935557664781776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2430466294","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9606535,0.0003369472,0.00025795025,0.0367957,0.00057223125,0.00010452198,0.0000065982267,0.0000040562836,0.0012685183],"genre_scores_gemma":[0.9951361,0.00024673057,0.0017898125,0.0012276281,0.00016442685,0.0000048140473,9.0004e-7,0.000006002189,0.0014236044],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99470675,0.0027174456,0.00088794803,0.00012443263,0.0013550632,0.00020837387],"domain_scores_gemma":[0.99055696,0.0075404784,0.0006839588,0.00020300629,0.00084731984,0.00016830613],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013360518,0.00013779479,0.00029409162,0.0004194592,0.0005952601,0.0000844229,0.00042539233,0.00009582534,0.00018512685],"category_scores_gemma":[0.0089933155,0.0000682862,0.000052974865,0.00032732834,0.00021679638,0.0016632681,0.00047511692,0.0008117218,0.000019572619],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0029813487,0.0027641435,0.24670774,0.00010933197,0.0001392652,0.00009645303,0.08976757,0.000012180305,0.011299746,0.2337916,0.0056257085,0.4067049],"study_design_scores_gemma":[0.0021418813,0.00046379416,0.7327784,0.00056987454,0.000010844183,0.0005584926,0.061440006,0.00003582696,0.00018800373,0.19384784,0.0077488,0.00021627739],"about_ca_topic_score_codex":0.00006810777,"about_ca_topic_score_gemma":0.00013080635,"teacher_disagreement_score":0.48607063,"about_ca_system_score_codex":0.00013897216,"about_ca_system_score_gemma":0.0013040021,"threshold_uncertainty_score":0.99935436},"labels":[],"label_agreement":null},{"id":"W2438874508","doi":"","title":"Evaluating the Impacts of Media Assistance: Problems and Principles","year":2014,"lang":"en","type":"article","venue":"Common Library Network (Der Gemeinsame Bibliotheksverbund)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"RMIT University; International Development Research Centre; Consejo Latinoamericano de Ciencias Sociales; World Bank Group","keywords":"Computer science; Data science","score_opus":0.22600457967221052,"score_gpt":0.43549587840451376,"score_spread":0.20949129873230324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2438874508","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9137797,0.0063189617,0.0027955214,0.008171693,0.0011229577,0.000988071,0.00002223614,0.00019774215,0.066603124],"genre_scores_gemma":[0.9889045,0.00093322137,0.0052678105,0.0023280843,0.00065529236,0.000041614425,0.000018269371,0.00004584936,0.0018053591],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99384296,0.001354704,0.0013499773,0.00059420936,0.002303876,0.0005542954],"domain_scores_gemma":[0.9916109,0.0056108045,0.0009387107,0.0013968411,0.0002073473,0.00023538664],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009246056,0.00031593582,0.00057954213,0.0009888544,0.00047527018,0.0009286583,0.0014584814,0.00013644755,0.0029899718],"category_scores_gemma":[0.0010201639,0.00018779037,0.00015261563,0.006106642,0.0003981147,0.0021529335,0.00067444314,0.0003517673,0.000073526666],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000250618,0.00023096375,0.68988526,0.0001160185,0.00012718046,0.0000013805505,0.0027813604,0.04700323,0.00017453126,0.062942326,0.07633299,0.12015417],"study_design_scores_gemma":[0.0011828878,0.0006734743,0.39953348,0.00029333576,0.00005390733,0.000009318386,0.00032052628,0.2954821,0.00018090331,0.10664976,0.19518934,0.0004309587],"about_ca_topic_score_codex":0.00001674576,"about_ca_topic_score_gemma":0.00009799054,"teacher_disagreement_score":0.29035175,"about_ca_system_score_codex":0.000017300776,"about_ca_system_score_gemma":0.00021878062,"threshold_uncertainty_score":0.9979214},"labels":[],"label_agreement":null},{"id":"W2460202963","doi":"","title":"Practising Critical Reflection","year":2007,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":40,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Education and Early Childhood Development","funders":"","keywords":"Reflection (computer programming); Critical reflection; Computer science; Sociology; Pedagogy","score_opus":0.4946179770867682,"score_gpt":0.6745244743406964,"score_spread":0.1799064972539282,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2460202963","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.065540515,0.000010246783,0.33233958,0.00486834,0.00069580565,0.000042705225,1.422504e-7,0.000041881936,0.59646076],"genre_scores_gemma":[0.97991455,0.0000017071559,0.010950657,0.0011718445,0.00012021028,8.162538e-7,3.5848848e-7,0.0000022168445,0.007837629],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.998214,0.00005684,0.00031409453,0.00015989623,0.0011159919,0.00013915647],"domain_scores_gemma":[0.9978613,0.0015169594,0.000047294256,0.00018739744,0.00032026382,0.000066732624],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008349568,0.00003814996,0.00005802301,0.00014522714,0.00013737111,0.00016155995,0.00011089348,0.00003154126,0.007460253],"category_scores_gemma":[0.0035795125,0.000025561376,0.00002808825,0.0004302667,0.000028521852,0.0005426823,0.000021337799,0.00007449029,0.0016268238],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056857723,0.00010449003,0.035202473,0.0000016551473,0.000004483592,0.000007137027,0.00049600453,0.00005182227,0.006668117,0.1659615,0.032969695,0.7584758],"study_design_scores_gemma":[0.0003037032,0.00015946227,0.26360035,0.0000066929365,0.0000066352286,0.000048169168,0.0031613747,0.008754598,0.01202846,0.07026458,0.6414801,0.00018589133],"about_ca_topic_score_codex":0.000010126593,"about_ca_topic_score_gemma":0.00010797733,"teacher_disagreement_score":0.91437405,"about_ca_system_score_codex":0.000035469828,"about_ca_system_score_gemma":0.00005352774,"threshold_uncertainty_score":0.9991505},"labels":[],"label_agreement":null},{"id":"W2463300067","doi":"","title":"A \"Step-Back\" Is Actually a \"Step-Forward\" When Attempting to Make the Transition from Administrator to Faculty within the Canadian College Environment.","year":2015,"lang":"en","type":"article","venue":"The College Quarterly","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Transition (genetics); Higher education; Public relations; Psychology; Mathematics education; Pedagogy; Sociology; Political science; Law","score_opus":0.14885447087539092,"score_gpt":0.3861885014128269,"score_spread":0.23733403053743599,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2463300067","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.732601,0.000041265095,0.0036127293,0.24622734,0.00083530997,0.003239251,0.00408318,0.00004365952,0.009316276],"genre_scores_gemma":[0.96783936,5.9777057e-7,0.0020279693,0.021285664,0.00027530314,0.0002466626,0.000038509716,0.000026367938,0.008259571],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9944839,0.0008058329,0.00091339566,0.00061697577,0.0026402432,0.00053968304],"domain_scores_gemma":[0.9965428,0.0007449178,0.0002865657,0.0014008353,0.00030278714,0.00072209025],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.006514988,0.00033018654,0.0003556697,0.00016322527,0.0012408562,0.000668413,0.001855062,0.00012433884,0.0021369976],"category_scores_gemma":[0.00019696045,0.00016099255,0.00015768826,0.00075039285,0.00014983647,0.00028445703,0.0000580998,0.00032329926,0.005266105],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004469614,0.00009311251,0.0005441278,0.0000040118402,0.00013754684,0.000021686916,0.29293257,0.000762339,0.0002019103,0.0026457452,0.6862493,0.015960682],"study_design_scores_gemma":[0.0016359407,0.0018117346,0.0067211543,0.000052619365,0.00010436496,0.000028244578,0.2493975,0.019472873,0.00016537262,0.0050441558,0.71498954,0.0005765225],"about_ca_topic_score_codex":0.014761471,"about_ca_topic_score_gemma":0.38935983,"teacher_disagreement_score":0.37459835,"about_ca_system_score_codex":0.00044393094,"about_ca_system_score_gemma":0.0016585389,"threshold_uncertainty_score":0.9987752},"labels":[],"label_agreement":null},{"id":"W2467101919","doi":"","title":"A brief introduction to identifying a \"good\" qualitative study when you see one.","year":2001,"lang":"en","type":"article","venue":"PubMed","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Qualitative research; Computer science; Psychology; Sociology; Social science","score_opus":0.3865793226444442,"score_gpt":0.5086347152414692,"score_spread":0.12205539259702497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2467101919","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.961989,0.00003091436,0.0067054904,0.018613838,0.001085589,0.0018531119,0.0000044601484,0.00007083103,0.009646797],"genre_scores_gemma":[0.9726822,0.000004867025,0.000687579,0.00070850365,0.00069762237,0.0014284012,0.000003985613,0.000009989969,0.0237769],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9954492,0.0007098998,0.00065771583,0.00060020067,0.0022141442,0.00036886864],"domain_scores_gemma":[0.99816126,0.0003423545,0.00020255102,0.0005903048,0.0004999528,0.00020357974],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.013281889,0.00012588232,0.00024062855,0.00041276665,0.00021027963,0.0004855579,0.00044867463,0.000035366018,0.0015987107],"category_scores_gemma":[0.0023617789,0.00010372262,0.000063669715,0.0011185372,0.000030535462,0.00078977575,0.00013610511,0.00012730506,0.0010482155],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016621081,0.0006792225,0.03981082,0.0000039657857,0.00008066263,0.0000051234283,0.1895461,0.00021593667,0.000046973193,0.0009602589,0.04070292,0.72778183],"study_design_scores_gemma":[0.00097649096,0.00014572295,0.7405707,0.0000038292437,0.000030100302,0.0000056825434,0.12915291,0.00026767995,0.00009030806,0.010369785,0.11814415,0.00024260036],"about_ca_topic_score_codex":0.00013388907,"about_ca_topic_score_gemma":0.0005474944,"teacher_disagreement_score":0.72753924,"about_ca_system_score_codex":0.00014119866,"about_ca_system_score_gemma":0.000055522843,"threshold_uncertainty_score":0.9997296},"labels":[],"label_agreement":null},{"id":"W2468395910","doi":"10.1080/14739879.2010.11493885","title":"Consensus paper: resources for teaching critical appraisal","year":2010,"lang":"en","type":"article","venue":"Education for Primary Care","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Toronto; McMaster University","keywords":"Critical appraisal; Medical education; Psychology; Computer science; Management science; Medicine; Engineering; Alternative medicine; Pathology","score_opus":0.07157440703489197,"score_gpt":0.5014564327842065,"score_spread":0.4298820257493145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2468395910","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8327227,0.00034911587,0.004615732,0.026699007,0.01689189,0.0012346024,0.00020127588,0.00010990846,0.11717577],"genre_scores_gemma":[0.94865745,0.0000012211129,0.044918373,0.0021651008,0.0012198063,0.00036048493,0.00016334753,0.00001759231,0.0024966234],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982273,0.00009609733,0.00044204065,0.00036997357,0.0006544436,0.0002101608],"domain_scores_gemma":[0.9921963,0.0060062506,0.00012663977,0.00044718792,0.0010990772,0.00012451944],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0022588912,0.00011350905,0.00016598473,0.0001469648,0.00051869446,0.00025647838,0.00036493846,0.00009151449,0.00055870024],"category_scores_gemma":[0.010118273,0.000091898895,0.00013229818,0.00011256856,0.00012427426,0.00025513626,0.000038047903,0.00020734903,0.000069373826],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011802462,0.00022989632,0.0071423687,0.00013613963,0.000012239332,1.0295815e-7,0.013150751,0.000018391953,0.0055831205,0.10174371,0.25390822,0.61795706],"study_design_scores_gemma":[0.00034169262,0.0000971714,0.015148731,0.0000099819,0.000019103123,0.0000050025433,0.01706731,0.00025016308,0.00020342653,0.0070774974,0.9596333,0.00014662746],"about_ca_topic_score_codex":0.000009330593,"about_ca_topic_score_gemma":0.000047147834,"teacher_disagreement_score":0.7057251,"about_ca_system_score_codex":0.00005955441,"about_ca_system_score_gemma":0.0011234127,"threshold_uncertainty_score":0.9982199},"labels":[],"label_agreement":null},{"id":"W2468646665","doi":"","title":"The Business of Placing Canadian Children and","year":2016,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Politics; Sociology; Political science; Humanities","score_opus":0.09247581151201939,"score_gpt":0.4201605192062073,"score_spread":0.3276847076941879,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2468646665","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95454997,0.000042449283,0.0006518506,0.013472507,0.0000971374,0.00006578883,0.000004940351,0.0000038112564,0.03111153],"genre_scores_gemma":[0.99548304,0.000042694275,0.000078601326,0.00015292087,0.000014365275,9.874693e-7,1.7634422e-7,0.0000010430447,0.004226191],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9993194,0.000029015042,0.00015216533,0.00007725103,0.00034311722,0.0000790627],"domain_scores_gemma":[0.99913096,0.00042105143,0.00004361881,0.00016075383,0.00018956397,0.000054042714],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015041205,0.000025886944,0.00004452032,0.000058556663,0.00011979942,0.000050709208,0.00015090255,0.000011656426,0.0007247223],"category_scores_gemma":[0.00043780275,0.000008894255,0.000008160909,0.0001797206,0.00005342343,0.00012280284,0.000020239837,0.000010935299,0.00006831995],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034375958,0.0000020251596,0.499462,2.1580101e-7,0.000004171786,7.036652e-8,0.00008595029,0.0000052913465,0.00019158046,0.013684958,0.006695273,0.479865],"study_design_scores_gemma":[0.00011264812,0.0000058420205,0.9843001,0.0000037286813,8.727037e-7,0.0000015602026,0.00006905236,0.00008396505,0.0002490919,0.0019230355,0.013227703,0.00002240147],"about_ca_topic_score_codex":0.011889182,"about_ca_topic_score_gemma":0.16751552,"teacher_disagreement_score":0.4848381,"about_ca_system_score_codex":0.000011162665,"about_ca_system_score_gemma":0.00024292893,"threshold_uncertainty_score":0.9946907},"labels":[],"label_agreement":null},{"id":"W2472004567","doi":"10.1177/0008417416655557","title":"Book Review: Evaluation in occupational therapy: Obtaining and interpreting data","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Occupational Therapy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Occupational therapy; Psychology; Medicine; Medical physics; Physical therapy","score_opus":0.5845288343661743,"score_gpt":0.5763907881709734,"score_spread":0.008138046195200865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2472004567","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5054553,0.43860435,0.00570545,0.045160994,0.0015753204,0.0012543751,0.00027454703,0.000011465568,0.0019581714],"genre_scores_gemma":[0.9490927,0.023631804,0.0008125946,0.025765652,0.00027817104,0.000016505533,0.00004564298,0.000014987089,0.0003419642],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962666,0.0005782073,0.0010496606,0.00027756763,0.0016238422,0.00020410636],"domain_scores_gemma":[0.9961382,0.0011300768,0.00067670987,0.00040958647,0.0013886872,0.0002567402],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.013624292,0.00013035805,0.00026125918,0.00062644004,0.00013729751,0.00013344146,0.0007300778,0.000052510946,0.009869926],"category_scores_gemma":[0.0032173754,0.000079055644,0.000056643596,0.00041436445,0.00009397598,0.0015358749,0.000026445412,0.00013238883,0.000031840267],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002082254,0.000017294076,0.33016038,0.0000034090488,0.000028912844,0.0000045552315,0.00040856135,0.00007226478,0.00009899831,0.00019373788,0.14026406,0.5285396],"study_design_scores_gemma":[0.0016426403,0.00012887087,0.46939462,0.0005723008,0.0000059026074,0.000035792884,0.00009134185,0.0029158334,0.00003083323,0.001511553,0.523532,0.0001383502],"about_ca_topic_score_codex":0.00014782719,"about_ca_topic_score_gemma":0.0014958207,"teacher_disagreement_score":0.52840126,"about_ca_system_score_codex":0.00022592145,"about_ca_system_score_gemma":0.0047559934,"threshold_uncertainty_score":0.99103516},"labels":[],"label_agreement":null},{"id":"W2473520880","doi":"10.1186/s13012-016-0428-0","title":"Proceedings of the 3rd Biennial Conference of the Society for Implementation Research Collaboration (SIRC) 2015: advancing efficient methodologies through community partnerships and team science","year":2016,"lang":"en","type":"article","venue":"Implementation Science","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children; Veterans Affairs Canada; Institut Universitaire de Gériatrie de Montréal; Université de Montréal; CARE Canada; Toronto Metropolitan University","funders":"Congressionally Directed Medical Research Programs; National Center for Advancing Translational Sciences; National Center for PTSD, U.S. Department of Veterans Affairs; National Institute of Mental Health; Université de Montréal; University of Queensland; Centers for Disease Control and Prevention; Georgia Clinical and Translational Science Alliance; U.S. Department of Veterans Affairs; Hellman Foundation; National Institutes of Health; U.S. Department of Health and Human Services; Medical Research and Materiel Command; Good Samaritan Foundation; Quality Enhancement Research Initiative; U.S. Department of Defense","keywords":"Sociology; Health services research; Library science; Art history; Media studies; Medicine; Public health; Art; Nursing; Computer science","score_opus":0.7702988517591058,"score_gpt":0.6968625830024563,"score_spread":0.07343626875664955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2473520880","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98282814,0.000011919835,0.00609946,0.008734621,0.00033522162,0.0014945754,0.000063449144,0.000010626388,0.0004219587],"genre_scores_gemma":[0.9881445,0.000020514844,0.011508965,0.00013834826,0.000020728643,0.00010863086,8.4356066e-7,0.0000043839,0.000053053558],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9933773,0.00048047127,0.0009328825,0.0004715536,0.0042411345,0.0004966457],"domain_scores_gemma":[0.98831314,0.0028708624,0.0009701137,0.00050182047,0.0072723497,0.00007172103],"candidate_categories":["metaresearch","sts"],"consensus_categories":["sts"],"category_scores_codex":[0.056380816,0.00012190384,0.00019842412,0.00022882337,0.0026602505,0.00039663227,0.001840809,0.000033518063,0.00008608635],"category_scores_gemma":[0.0063442974,0.00005863501,0.00010220485,0.0048617455,0.0044788034,0.0024491071,0.0007870131,0.00014844711,0.000001628438],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006296085,0.00004716828,0.06034111,0.000031962947,0.000009173102,4.686783e-9,0.034774303,0.000041962787,0.77761215,0.090492174,0.0027191094,0.033867933],"study_design_scores_gemma":[0.0010848225,0.00026640235,0.13689509,0.000047552214,0.00001652829,0.0000012235862,0.17754908,0.0013143696,0.65952086,0.021159602,0.0020319556,0.000112530855],"about_ca_topic_score_codex":0.00010123449,"about_ca_topic_score_gemma":0.00047436258,"teacher_disagreement_score":0.14277478,"about_ca_system_score_codex":0.00030667413,"about_ca_system_score_gemma":0.0023963465,"threshold_uncertainty_score":0.99863815},"labels":[],"label_agreement":null},{"id":"W2475092493","doi":"10.15402/esj.v1i2.117","title":"Charting the Trajectory of a Flexible Community-University Collaboration in an Applied Learning Ecosystem","year":2016,"lang":"en","type":"article","venue":"Engaged Scholar Journal Community-Engaged Research Teaching and Learning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Toronto Metropolitan University; Centre for Advancing Health Outcomes","funders":"","keywords":"General partnership; Community engagement; Context (archaeology); Experiential learning; Flexibility (engineering); Public relations; Service-learning; Service (business); Community organization; Sociology; Knowledge management; Political science; Business; Pedagogy; Marketing; Management; Computer science; Economics","score_opus":0.334630157187209,"score_gpt":0.4936869298633171,"score_spread":0.15905677267610807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2475092493","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99342185,0.000110798464,0.0018178436,0.0006416698,0.00010832931,0.00027608988,0.0000025773363,0.00005823066,0.0035625913],"genre_scores_gemma":[0.9980434,0.00007227427,0.00065621134,0.000030756604,0.00007639977,0.00000602794,0.000004380857,0.000024732866,0.0010858062],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.17770009,0.8190444,0.0007490451,0.00020962972,0.0018177892,0.00047905193],"domain_scores_gemma":[0.68283343,0.31485495,0.0005496281,0.00069765537,0.00083705445,0.00022726566],"candidate_categories":["metaresearch","sts","scholarly_communication","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.91644365,0.00019923697,0.00040616008,0.0012689984,0.2958488,0.0010665898,0.0015592615,0.00014806233,0.00018786742],"category_scores_gemma":[0.4786078,0.00012592884,0.00008635672,0.001290447,0.00025519545,0.001988518,0.00046575407,0.4307733,0.000028923469],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002314278,0.00020901854,0.030154238,0.000024627876,0.000035234145,0.0000058844953,0.80886513,0.0043367133,0.047379285,0.00017301508,0.00005872238,0.108526684],"study_design_scores_gemma":[0.0012975904,0.0005277308,0.041990127,0.0002394118,0.000008369534,0.000021972084,0.9453058,0.0023027319,0.00032056362,0.00027898027,0.007550198,0.00015651909],"about_ca_topic_score_codex":0.00023900965,"about_ca_topic_score_gemma":0.00079084997,"teacher_disagreement_score":0.5051334,"about_ca_system_score_codex":0.00031544678,"about_ca_system_score_gemma":0.0003443128,"threshold_uncertainty_score":0.9999704},"labels":[],"label_agreement":null},{"id":"W2482243048","doi":"","title":"L’étude d’évaluabilité : Une approche d’évaluation de programmes encore mal connue et peu utilisée","year":2016,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.2956668829198084,"score_gpt":0.49993669500760696,"score_spread":0.20426981208779854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2482243048","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84755886,0.008271438,0.019218737,0.107952565,0.005464288,0.0056339735,0.00009491484,0.000057193713,0.005748027],"genre_scores_gemma":[0.9667224,0.00035978152,0.028513476,0.0008119783,0.00069095497,0.0004063413,0.000039539405,0.000054755506,0.002400723],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9863536,0.004523845,0.0024510573,0.00069219567,0.004750431,0.0012288808],"domain_scores_gemma":[0.98660856,0.0013625527,0.0018346827,0.0007539352,0.007857041,0.0015832015],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06195263,0.0004960501,0.0007093857,0.0010970439,0.00048491723,0.0010352039,0.001097182,0.0004918058,0.0073642298],"category_scores_gemma":[0.012353503,0.00036082193,0.00049284636,0.0018550681,0.00083830545,0.0022893583,0.000051299987,0.00064052735,0.00035821303],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008038972,0.00026965357,0.032408644,0.00004108818,0.00012737114,0.000021879972,0.010388147,0.0012549561,0.00026927848,0.003314676,0.005019215,0.9468047],"study_design_scores_gemma":[0.0075732116,0.004314231,0.21177459,0.0014785578,0.0013026352,0.0007320699,0.012364976,0.121984825,0.0008162179,0.09693653,0.53962046,0.0011017121],"about_ca_topic_score_codex":0.0037618002,"about_ca_topic_score_gemma":0.07189041,"teacher_disagreement_score":0.94570297,"about_ca_system_score_codex":0.002115037,"about_ca_system_score_gemma":0.035790008,"threshold_uncertainty_score":0.99988437},"labels":[],"label_agreement":null},{"id":"W2482388446","doi":"10.1057/9780230289925_19","title":"Strategy Analysis – Logical Framework","year":2010,"lang":"en","type":"book-chapter","venue":"Palgrave Macmillan UK eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"European commission; Principal (computer security); Perspective (graphical); Commission; Management science; Logical framework; Process management; Political science; Business; Regional science; Computer science; Economics; Finance; Geography; Economic policy","score_opus":0.15061992101823407,"score_gpt":0.42293428071339156,"score_spread":0.2723143596951575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2482388446","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00048096164,0.00022589449,0.005260914,0.00018538626,0.00066718145,0.00039386554,0.0001328905,0.00008640895,0.9925665],"genre_scores_gemma":[0.9394479,0.000055501256,0.002178629,0.00064088084,0.0005221169,0.000022842803,0.00008322421,0.000045128036,0.057003774],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99319744,0.00012997109,0.0014483813,0.0012174458,0.0035015806,0.00050520775],"domain_scores_gemma":[0.99459356,0.0013025688,0.0008940471,0.0020839735,0.0007295988,0.00039625305],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002904473,0.00064511964,0.0012212399,0.0011670141,0.00029896095,0.00054783165,0.0014634905,0.0011959041,0.060288627],"category_scores_gemma":[0.00041853896,0.00045586852,0.0010378764,0.00020872416,0.0003615948,0.0000017356807,0.00029798326,0.0014290032,0.004059677],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000227896,5.597607e-7,0.0010840377,0.000004095536,0.00040700374,0.000028199667,0.00013944595,0.00005057286,0.00003538957,0.9538549,0.000046384488,0.044326574],"study_design_scores_gemma":[0.00016385727,0.00011662829,0.0043870304,0.000024717345,0.0004873602,0.000007802707,0.00005273672,0.0005326924,0.00004977695,0.97472584,0.018874794,0.000576736],"about_ca_topic_score_codex":0.000019388026,"about_ca_topic_score_gemma":0.0005333512,"teacher_disagreement_score":0.93896693,"about_ca_system_score_codex":0.00006674034,"about_ca_system_score_gemma":0.0003189035,"threshold_uncertainty_score":0.9997893},"labels":[],"label_agreement":null},{"id":"W248337343","doi":"10.4324/9781315849072.ch40","title":"Mixing Quantitative and Qualitative Research","year":2015,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Mixing (physics); Physics","score_opus":0.6396218325078998,"score_gpt":0.6718821311761145,"score_spread":0.03226029866821467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W248337343","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93654084,0.00444351,0.02584273,0.013263603,0.00032260953,0.00017987081,0.0000020026337,0.000015769272,0.019389039],"genre_scores_gemma":[0.99212813,0.0006660364,0.0011075593,0.00008759813,0.00014021214,0.0000048924394,7.3376816e-7,0.000007479241,0.0058573587],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9928861,0.0023104888,0.0004592241,0.00024668244,0.0027200256,0.0013774813],"domain_scores_gemma":[0.99577856,0.0019438348,0.00018314942,0.00017595396,0.0017254448,0.00019306093],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.10761579,0.00008690411,0.00016950167,0.00042878411,0.00038592028,0.00033137653,0.00037846604,0.000043133336,0.00009337558],"category_scores_gemma":[0.005928379,0.000058997928,0.000042723426,0.0007499453,0.00016845856,0.00067054864,0.000083473446,0.0015815411,0.00036612758],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011392695,0.000027777009,0.0022200397,9.0187814e-7,0.000044020555,0.0000018930401,0.04364532,0.000063826825,0.00009841835,0.9002392,0.0021726135,0.051372018],"study_design_scores_gemma":[0.0004305367,0.0005537524,0.00038835558,0.000006169498,0.0000028423192,0.000059705584,0.29748628,0.0011611845,0.00002312572,0.6925864,0.007239683,0.00006198097],"about_ca_topic_score_codex":0.0000560643,"about_ca_topic_score_gemma":0.0008088813,"teacher_disagreement_score":0.25384095,"about_ca_system_score_codex":0.0006231417,"about_ca_system_score_gemma":0.0050456603,"threshold_uncertainty_score":0.91889733},"labels":[],"label_agreement":null},{"id":"W2483463161","doi":"10.3138/cjpe.31.1.122","title":"Hallie Preskill et Darlene Russ-Eft. (2016). <i>Building evaluation capacity: Activities for teaching and training</i> (2nd ed.).","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Training (meteorology); Sociology; Physics","score_opus":0.4310966052308271,"score_gpt":0.5106947102029149,"score_spread":0.0795981049720878,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2483463161","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9487782,0.0010010388,0.033041246,0.009747823,0.0014442954,0.0028359815,0.000062532505,0.000022941254,0.0030659314],"genre_scores_gemma":[0.9755666,0.000044128108,0.023150036,0.00035013625,0.00036865735,0.00025075473,0.000010927974,0.00002260661,0.00023613824],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99377304,0.0015919245,0.0010787868,0.00038068314,0.0027248398,0.00045071877],"domain_scores_gemma":[0.9939671,0.0017234499,0.0010808184,0.00031896244,0.0023933935,0.0005162567],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05778622,0.00021299481,0.00036596265,0.000732569,0.00055735995,0.0006699086,0.00038787458,0.00012912623,0.00080816867],"category_scores_gemma":[0.01237312,0.00014287452,0.00014909786,0.00022190389,0.0002011748,0.0021509628,0.000019845202,0.0002774537,0.000008418449],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030954365,0.000027679951,0.0016858528,0.000007374379,0.000045966943,6.720422e-7,0.0038653598,0.00043278598,0.00097090943,0.0018964856,0.003866011,0.9871699],"study_design_scores_gemma":[0.012782238,0.003457099,0.050992634,0.0013072153,0.0010532798,0.00027938592,0.013058447,0.16627775,0.0019340436,0.1936308,0.5539788,0.0012482888],"about_ca_topic_score_codex":0.00030980588,"about_ca_topic_score_gemma":0.0075110765,"teacher_disagreement_score":0.9859217,"about_ca_system_score_codex":0.0005972922,"about_ca_system_score_gemma":0.0058150305,"threshold_uncertainty_score":0.99982107},"labels":[],"label_agreement":null},{"id":"W2484421087","doi":"10.4018/978-1-4666-7409-7.ch006","title":"The Civic University, the Engaged Scholar","year":2014,"lang":"en","type":"book-chapter","venue":"Advances in knowledge acquisition, transfer, and management book series/Advances in knowledge acquisition, transfer and management book series","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Scholarship; Ivory tower; Criticism; Face (sociological concept); Political science; Sociology; Engaged scholarship; Public relations; Media studies; Engineering ethics; Social science; Law; Engineering","score_opus":0.02441464359163219,"score_gpt":0.3172655215032895,"score_spread":0.2928508779116573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2484421087","genre_codex":"other","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017764703,0.26633227,0.012836657,0.0024431206,0.0019979256,0.0041282238,0.00013586157,0.00023502976,0.71171325],"genre_scores_gemma":[0.016384337,0.669569,0.00023133402,0.0011025703,0.00031965144,0.00035011908,0.0001409892,0.000123922,0.3117781],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9898346,0.0018850687,0.002533429,0.0025395863,0.001810308,0.0013969737],"domain_scores_gemma":[0.99479324,0.0018991292,0.0002829413,0.0019197119,0.00075134425,0.00035366273],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.009146577,0.001685196,0.0015932848,0.0015828356,0.0048590098,0.0009770484,0.0023444707,0.00047813126,0.001430643],"category_scores_gemma":[0.00004857075,0.0013022674,0.00047516674,0.001056391,0.002373685,0.010457508,0.0006676457,0.0018698681,0.00025673848],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010561483,0.00021888959,0.00019760295,0.0016194285,0.00031919184,0.00007689979,0.005440255,0.00022947427,0.0000064252736,0.8868177,0.0029681853,0.10104978],"study_design_scores_gemma":[0.003586634,0.000527565,0.0012579767,0.0012864092,0.00046128457,0.00002978948,0.007176814,0.00009928099,0.000045547884,0.06305475,0.92104393,0.0014299923],"about_ca_topic_score_codex":0.0000062892946,"about_ca_topic_score_gemma":0.00442123,"teacher_disagreement_score":0.91807574,"about_ca_system_score_codex":0.00045616826,"about_ca_system_score_gemma":0.0001535661,"threshold_uncertainty_score":0.9995895},"labels":[],"label_agreement":null},{"id":"W2485244308","doi":"10.1017/cbo9781139507684.018","title":"Choosing model-building methods","year":2014,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science","score_opus":0.22071460836194393,"score_gpt":0.4317894419491312,"score_spread":0.2110748335871873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2485244308","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000475608,0.000043584703,0.32551932,0.000040799783,0.00032585434,0.00020064024,0.00003391047,0.00007101391,0.6737173],"genre_scores_gemma":[0.0014524125,0.000039181105,0.025125079,0.0002703477,0.0001609335,6.4931737e-7,0.000012086158,0.000038466176,0.97290087],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965873,0.0002663273,0.0005260109,0.00083777297,0.0014586147,0.00032399222],"domain_scores_gemma":[0.9966994,0.00066387234,0.000633022,0.0011456453,0.0006136269,0.00024442296],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0033466704,0.0003875795,0.00062074105,0.00053376175,0.0003998641,0.0002531736,0.0013155778,0.0003759871,0.00007104033],"category_scores_gemma":[0.0001637265,0.00037629795,0.00035606057,0.000025251193,0.00019291951,0.00020601571,0.000622442,0.00055418425,0.00009204991],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027707227,0.000003039472,0.0000025492564,0.000012545067,0.000042822077,0.0000095569,0.000054913155,0.001140908,0.00011801604,0.91718876,0.029783167,0.05161602],"study_design_scores_gemma":[0.00033769745,0.0000271662,0.000008714031,0.00008036731,0.00010640569,0.000005344589,0.000028877721,0.11165891,0.00035998004,0.000619103,0.88637054,0.00039690014],"about_ca_topic_score_codex":0.000020640578,"about_ca_topic_score_gemma":0.0000014273363,"teacher_disagreement_score":0.91656965,"about_ca_system_score_codex":0.00026604775,"about_ca_system_score_gemma":0.00031794628,"threshold_uncertainty_score":0.99986887},"labels":[],"label_agreement":null},{"id":"W2487684520","doi":"10.1057/9781403982872_4","title":"What You Don’t Know about Evaluation","year":2006,"lang":"en","type":"book-chapter","venue":"Palgrave Macmillan US eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Ignorance; Need to know; Limiting; Foolishness; Set (abstract data type); Public relations; Law; Political science; Computer science; Engineering; Psychology; Computer security; Social psychology","score_opus":0.09961152326540613,"score_gpt":0.39384089459825794,"score_spread":0.2942293713328518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2487684520","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00067298167,0.0047754426,0.00023356295,0.00029990615,0.002985119,0.0013547394,0.00008831503,0.0001095643,0.9894804],"genre_scores_gemma":[0.44166172,0.0008724144,0.00024040513,0.0009777508,0.0010702848,0.00012012846,0.0004131571,0.000113286515,0.55453086],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9893701,0.0002887375,0.0017711628,0.001329396,0.006669595,0.0005710098],"domain_scores_gemma":[0.99419343,0.0005517889,0.0012381311,0.0018852797,0.0018739789,0.00025736718],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0069179432,0.0007573366,0.0008932082,0.0008570619,0.0003534081,0.0012589032,0.0011594879,0.00060711993,0.015310496],"category_scores_gemma":[0.00025278065,0.00060346967,0.00053608336,0.0000814772,0.00025791567,0.000041256266,0.00026637703,0.0005549193,0.003794444],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004674417,0.0000038740586,0.00059669453,0.000024877789,0.00010550654,0.000016387436,0.00046873704,0.00031098595,0.00004901046,0.16503172,0.00844195,0.8249035],"study_design_scores_gemma":[0.0007416833,0.00010938153,0.0023953782,0.00027986732,0.00015939731,0.000015741876,0.00012494845,0.0045143366,0.00008738651,0.5796425,0.41123646,0.0006929632],"about_ca_topic_score_codex":0.00006720621,"about_ca_topic_score_gemma":0.00069943845,"teacher_disagreement_score":0.8242105,"about_ca_system_score_codex":0.0003664703,"about_ca_system_score_gemma":0.0007616474,"threshold_uncertainty_score":0.9997779},"labels":[],"label_agreement":null},{"id":"W2487975284","doi":"10.1093/med:psych/9780195310641.003.0001","title":"Developing Criteria for Evidence-Based Assessment","year":2008,"lang":"en","type":"book-chapter","venue":"Oxford University Press eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":94,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; University of Ottawa","funders":"","keywords":"Computer science","score_opus":0.4388937843731766,"score_gpt":0.4515329646806724,"score_spread":0.012639180307495779,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2487975284","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008749552,0.000082617495,0.06994136,0.00051828497,0.0005864317,0.0009687209,0.00012954642,0.00008448069,0.92760104],"genre_scores_gemma":[0.0015558393,0.000500827,0.022867365,0.00054400536,0.00015985059,0.000008260527,0.0000476402,0.00003673577,0.97427946],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9963813,0.0001234978,0.0005945179,0.00079820055,0.0017651205,0.0003374079],"domain_scores_gemma":[0.995769,0.0014044329,0.00066269626,0.0008486025,0.0011498966,0.00016534669],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016386238,0.0003918161,0.00057251856,0.00048057668,0.00057828036,0.00022656124,0.0012557859,0.00033751258,0.00056404737],"category_scores_gemma":[0.00014592306,0.00036994164,0.00038101728,0.000029026645,0.0001872009,0.0004314858,0.0003016439,0.00030416902,0.000008257012],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032685726,0.000020340185,0.0000748796,0.00010761192,0.0001282118,0.000050472077,0.0002803678,0.00018683287,0.000026230484,0.883107,0.052423548,0.06326765],"study_design_scores_gemma":[0.0007280726,0.00014306123,0.00014982905,0.00038035162,0.00008018423,0.00000357743,0.000054136144,0.004359717,0.00010016773,0.0024591614,0.99107736,0.000464393],"about_ca_topic_score_codex":0.00001175827,"about_ca_topic_score_gemma":0.000022279313,"teacher_disagreement_score":0.9386538,"about_ca_system_score_codex":0.0005859723,"about_ca_system_score_gemma":0.0020233744,"threshold_uncertainty_score":0.99987525},"labels":[],"label_agreement":null},{"id":"W2488422952","doi":"10.1007/978-3-319-29188-8_3","title":"Researcher as Practitioner: Practitioner as Researcher","year":2016,"lang":"en","type":"book-chapter","venue":"SpringerBriefs in family therapy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Practitioner research; Psychology; Medical education; Engineering ethics; Medicine; Pedagogy; Engineering","score_opus":0.34159609619148534,"score_gpt":0.5137590266741612,"score_spread":0.17216293048267584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2488422952","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031910138,0.0017700864,0.00016388217,0.010351323,0.00080446055,0.0011242004,0.00005939783,0.00009748105,0.98243815],"genre_scores_gemma":[0.012649903,0.015458029,0.00044345384,0.004925105,0.00085622637,0.00019291614,0.000040361403,0.00015136627,0.9652826],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9883329,0.0007127624,0.0014720481,0.0014661661,0.0071744393,0.0008416836],"domain_scores_gemma":[0.9923413,0.0026840016,0.00083814864,0.0021063131,0.0016515126,0.00037875687],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.015256862,0.00059615134,0.0007534719,0.0015051592,0.00033464527,0.0006698496,0.0015826143,0.0007375956,0.05996966],"category_scores_gemma":[0.002526626,0.00042429176,0.00034964096,0.00043407254,0.00048607326,0.0013460945,0.0003690668,0.0017328548,0.029409291],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012627451,0.00027097797,0.00061359233,0.00001943882,0.0002229536,0.00020100597,0.0009256711,0.000035952802,0.0021961217,0.59786314,0.10949335,0.28689504],"study_design_scores_gemma":[0.0011056731,0.00028257485,0.003209061,0.00021234364,0.0000048890515,0.000011180844,0.00015675183,0.000022398395,0.00017965534,0.2661108,0.72827387,0.00043083684],"about_ca_topic_score_codex":0.0002765546,"about_ca_topic_score_gemma":0.00022767247,"teacher_disagreement_score":0.6187805,"about_ca_system_score_codex":0.00071456574,"about_ca_system_score_gemma":0.0022775852,"threshold_uncertainty_score":0.9998209},"labels":[],"label_agreement":null},{"id":"W2489127426","doi":"","title":"La planification globale comme stratégie pour favoriser l’évaluation comme aide à l’apprentissage","year":2015,"lang":"fr","type":"article","venue":"Érudit (Université de Montréal)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cégep de l'Abitibi Témiscamingue","funders":"","keywords":"Political science; Humanities; Philosophy","score_opus":0.21207974367404261,"score_gpt":0.3535066072929607,"score_spread":0.14142686361891807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2489127426","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5548675,0.0316155,0.041234493,0.23019521,0.0032576646,0.0010969533,0.00046617448,0.00023749052,0.13702898],"genre_scores_gemma":[0.82247156,0.003621704,0.0044088624,0.00069155014,0.00028625244,0.000012602196,0.00026039395,0.000035061927,0.168212],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99488324,0.0013077726,0.000613769,0.00060067745,0.0020166757,0.000577851],"domain_scores_gemma":[0.99661463,0.00071879046,0.00054416043,0.00085112726,0.0007022636,0.0005690384],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0053123236,0.00034281184,0.00040321125,0.0002988759,0.00059913535,0.00023893718,0.00090300356,0.00037976936,0.0021455467],"category_scores_gemma":[0.00035021023,0.00036750862,0.00019206501,0.00089524366,0.00018798646,0.0011539708,0.00034486977,0.00039757587,0.0036272858],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021753735,0.0004117934,0.020330943,0.000024944336,0.00010565561,0.00025187104,0.0039195884,0.007463018,0.00023107715,0.047465768,0.6200342,0.29954356],"study_design_scores_gemma":[0.0025616642,0.0001854259,0.024547987,0.00008117226,0.00017863876,0.00022778014,0.011881747,0.06253065,0.00013861366,0.015915254,0.88135225,0.0003987979],"about_ca_topic_score_codex":0.0034166998,"about_ca_topic_score_gemma":0.024631886,"teacher_disagreement_score":0.29914477,"about_ca_system_score_codex":0.0071134875,"about_ca_system_score_gemma":0.0007978862,"threshold_uncertainty_score":0.9998777},"labels":[],"label_agreement":null},{"id":"W2489879551","doi":"","title":"Evidence-based Principles to Guide Collaborative Approaches to Evaluation: Technical Report","year":2015,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Management science; Engineering ethics; Data science; Engineering","score_opus":0.9049027782050624,"score_gpt":0.5776800492054441,"score_spread":0.32722272899961824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2489879551","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09726898,0.00025617104,0.18592983,0.16178644,0.0009874827,0.004535439,0.000010576281,0.00023783691,0.54898727],"genre_scores_gemma":[0.8296793,0.0000023530524,0.1446094,0.004611113,0.00017942494,0.00071428163,0.000010778185,0.000011782689,0.02018152],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99117297,0.0005613143,0.0011736039,0.00075440435,0.0060834703,0.00025425715],"domain_scores_gemma":[0.99316883,0.0009876023,0.00025844754,0.0011875482,0.0038330841,0.0005644786],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.036306858,0.00016816429,0.00028921574,0.00037928013,0.0001294387,0.000396475,0.0007429154,0.00007740955,0.0022579017],"category_scores_gemma":[0.03370766,0.00011188209,0.00006468932,0.0026660312,0.000052952066,0.0006313503,0.000225258,0.000090161404,0.002209999],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003519961,0.00030517994,0.059928287,0.000005750746,0.000026338776,0.000029440349,0.0029311853,0.22841872,0.000611104,0.021107726,0.56835973,0.11792452],"study_design_scores_gemma":[0.00082350627,0.00083604886,0.05074651,0.000102524275,0.000036692905,0.000029225626,0.005770158,0.09213318,0.004916011,0.0038203436,0.84029907,0.00048669978],"about_ca_topic_score_codex":0.000025219659,"about_ca_topic_score_gemma":0.00047302476,"teacher_disagreement_score":0.7324104,"about_ca_system_score_codex":0.00047453222,"about_ca_system_score_gemma":0.0048363465,"threshold_uncertainty_score":0.9986542},"labels":[],"label_agreement":null},{"id":"W2492161979","doi":"10.1002/9780470592663.indsub2","title":"Subject Index: Volume 3","year":2009,"lang":"en","type":"other","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Subject (documents); Index (typography); Volume (thermodynamics); Mathematics; Computer science; Library science; Thermodynamics; World Wide Web; Physics","score_opus":0.14562302104131936,"score_gpt":0.48553383814802037,"score_spread":0.339910817106701,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2492161979","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000146137345,0.00014378231,0.003361619,0.000930381,0.0005345662,0.0001629687,0.0000068026297,0.00014631695,0.99469894],"genre_scores_gemma":[0.0027749285,0.000051383988,0.00072437007,0.0015054048,0.00032790567,0.0000055649584,0.000009500083,0.0000713512,0.9945296],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99699754,0.000099080156,0.00036899713,0.00037313392,0.0019870515,0.00017420088],"domain_scores_gemma":[0.9987901,0.00008251959,0.0002442637,0.0007060072,0.00009897647,0.00007816888],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0016769997,0.00015993146,0.00027573312,0.00053997245,0.00003595386,0.00019044362,0.00061855384,0.00020044956,0.4093365],"category_scores_gemma":[0.00019648421,0.00010177786,0.000099498735,0.00044590735,0.000031598272,0.00007975592,0.000045459885,0.00013847195,0.03189282],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014514145,0.000012988268,0.0036757214,8.0188596e-7,0.000005085522,8.998173e-7,0.000014387721,0.000004659468,4.88018e-7,0.0005172472,0.90846974,0.087296516],"study_design_scores_gemma":[0.00014046616,0.000034130142,0.010178157,0.000012565239,0.0000039478864,0.0000012910327,0.000043334036,0.0011035468,0.0000026080393,0.0018988218,0.9864318,0.00014933561],"about_ca_topic_score_codex":0.00011412238,"about_ca_topic_score_gemma":0.0008801808,"teacher_disagreement_score":0.3774437,"about_ca_system_score_codex":0.000026819827,"about_ca_system_score_gemma":0.00021363131,"threshold_uncertainty_score":0.968861},"labels":[],"label_agreement":null},{"id":"W2494134454","doi":"","title":"Book Review: S. HASINOFF & D. MANDZUK. (2015). Case Studies in Educational Foundations: Canadian Perspectives","year":2016,"lang":"en","type":"article","venue":"McGill Journal of Education / Revue des sciences de l'éducation de McGill","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University","funders":"","keywords":"Political science; Sociology","score_opus":0.5190109827126098,"score_gpt":0.5812342909061801,"score_spread":0.06222330819357025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2494134454","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17570086,0.26870415,0.000999781,0.50272,0.012016478,0.0017893347,0.00021322932,0.00004793067,0.037808247],"genre_scores_gemma":[0.8576802,0.065381564,0.016033232,0.032337703,0.0008546486,0.00020540376,0.000008263,0.00003596824,0.02746299],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9954928,0.00084641366,0.0015697302,0.00051152677,0.0010659582,0.0005135374],"domain_scores_gemma":[0.99215484,0.0017500982,0.0012394595,0.00045959305,0.0039036025,0.0004924223],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0113833165,0.00023625542,0.00042714836,0.001823893,0.0014820329,0.00015745817,0.00087029196,0.000084982144,0.0052243876],"category_scores_gemma":[0.012934392,0.00016663157,0.00017769616,0.0019787934,0.00084464625,0.002615965,0.00004868329,0.00021347847,0.00020633142],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00003238811,0.0008510099,0.011345163,0.00023857623,0.00007912423,0.00006613571,0.011561779,0.00057342625,0.00023238892,0.032194275,0.8687828,0.07404292],"study_design_scores_gemma":[0.00049466867,0.00026748236,0.0106895985,0.002183666,0.00007345222,0.010844657,0.030805849,0.00023728577,0.00015558713,0.044270102,0.8995606,0.00041708903],"about_ca_topic_score_codex":0.001240202,"about_ca_topic_score_gemma":0.013627473,"teacher_disagreement_score":0.68197936,"about_ca_system_score_codex":0.005865521,"about_ca_system_score_gemma":0.007052152,"threshold_uncertainty_score":0.9998179},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":true,"confidence":"low"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":true,"confidence":"low"}],"label_agreement":"agree"},{"id":"W2494669165","doi":"10.3138/cjpe.0026.001","title":"How Does Complexity Impact Evaluation? An Introduction to the Special Issue","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Montréal; Université de Sherbrooke; Université du Québec à Montréal; McGill University; École Nationale d'Administration Publique; York University","funders":"Canadian Institutes of Health Research; U.S. Public Health Service","keywords":"Psychological intervention; Impact evaluation; Management science; Program evaluation; Evaluation methods; Psychology; Computer science; Political science; Medicine; Economics; Engineering","score_opus":0.410774152797953,"score_gpt":0.5566967272910203,"score_spread":0.14592257449306728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2494669165","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82219225,0.00033659238,0.0020082525,0.15809229,0.0114581315,0.003975544,0.000032304986,0.000016605361,0.0018880237],"genre_scores_gemma":[0.96717614,0.000002458034,0.0019426612,0.00032175882,0.030109828,0.00009610709,0.000037409725,0.0000116824085,0.00030196432],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99217016,0.0020760472,0.00075970945,0.00024704653,0.0042784535,0.00046858838],"domain_scores_gemma":[0.99186444,0.00014654883,0.0006965695,0.0005905262,0.0056878277,0.0010140728],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.045736507,0.00017082704,0.0002506859,0.0006743331,0.0005274036,0.0013160515,0.000675114,0.00007454296,0.016031774],"category_scores_gemma":[0.0060512535,0.000090018795,0.00016215185,0.0011241763,0.0001240743,0.0027227579,0.00001800521,0.00025936187,0.00021428558],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028411596,0.000071321956,0.0149643505,0.0000013064491,0.000026109548,3.7704845e-7,0.003253714,0.0037188022,0.000042882526,0.00043637012,0.09615621,0.88130015],"study_design_scores_gemma":[0.0005868735,0.00066062645,0.25603443,0.000008250027,0.00015604153,0.000058572325,0.0048321295,0.03136617,0.00014691734,0.0059028277,0.70007163,0.00017551913],"about_ca_topic_score_codex":0.0004171657,"about_ca_topic_score_gemma":0.048126027,"teacher_disagreement_score":0.8811246,"about_ca_system_score_codex":0.0011238743,"about_ca_system_score_gemma":0.0031818,"threshold_uncertainty_score":0.9997207},"labels":[],"label_agreement":null},{"id":"W249659815","doi":"10.3138/cjpe.17.005","title":"New Partnerships Require New Approaches to Participatory Program Evaluations: Planning for the Future","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Participatory evaluation; Independence (probability theory); Citizen journalism; Work (physics); Government (linguistics); Affect (linguistics); Power (physics); Civil society; Public relations; Program evaluation; Process management; Business; Political science; Psychology; Public administration; Engineering; Politics","score_opus":0.8918311256608674,"score_gpt":0.5795271091974086,"score_spread":0.31230401646345884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W249659815","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11190089,0.049305055,0.2114975,0.56085294,0.014240603,0.043164,0.000052168383,0.00025145515,0.008735387],"genre_scores_gemma":[0.93700635,0.000020840991,0.05421546,0.001051659,0.0035694982,0.0011782877,0.000016830969,0.000034850087,0.0029062137],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9945733,0.0006070521,0.0011873926,0.00033466867,0.0027555819,0.0005420107],"domain_scores_gemma":[0.9954454,0.00069252757,0.000733914,0.00052714784,0.001328437,0.0012725935],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017652106,0.00020627584,0.00029551436,0.00054344797,0.000611891,0.000954235,0.00084432674,0.00012558498,0.0031221781],"category_scores_gemma":[0.003632237,0.00013519984,0.00023102587,0.0012385987,0.00006771985,0.0009552875,0.000017281189,0.00027970597,0.00013678687],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022005259,0.00003484679,0.0027474377,0.0000038172893,0.000043944943,0.0000010326477,0.0045527597,0.010978329,0.0000018308783,0.0014988804,0.099831484,0.88028365],"study_design_scores_gemma":[0.0011533241,0.0010026951,0.011826763,0.000058768135,0.00022625532,0.00001997032,0.0045896317,0.23951,0.000022561697,0.011694651,0.729694,0.00020137931],"about_ca_topic_score_codex":0.000096111595,"about_ca_topic_score_gemma":0.008737331,"teacher_disagreement_score":0.88008225,"about_ca_system_score_codex":0.00038570593,"about_ca_system_score_gemma":0.0053229057,"threshold_uncertainty_score":0.9977891},"labels":[],"label_agreement":null},{"id":"W2497444116","doi":"10.4000/ere.5501","title":"Au-delà du développement durable, une éducation à la compétence éthique dans la diversité et la complexité des cultures","year":2003,"lang":"fr","type":"article","venue":"Éducation relative à l environnement","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Political science; Humanities; Philosophy","score_opus":0.12149514922565213,"score_gpt":0.42258379258612305,"score_spread":0.3010886433604709,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2497444116","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16295318,0.0007398048,0.09401798,0.08700223,0.0019220272,0.001300531,0.0000801403,0.00007093845,0.65191317],"genre_scores_gemma":[0.9439518,0.0025735628,0.013921682,0.0013698089,0.00009271416,0.00019040446,0.0001640251,0.000036069945,0.03769995],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.98949087,0.006068195,0.0011561644,0.0009255166,0.001791918,0.000567331],"domain_scores_gemma":[0.9949138,0.0026914827,0.0008220063,0.000690258,0.0005587924,0.00032366713],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.009459838,0.0005269866,0.0004406627,0.0002957724,0.0013527556,0.00038426172,0.0006043276,0.0003330022,0.005233417],"category_scores_gemma":[0.0012770826,0.0004787721,0.00020108157,0.0010253803,0.0013700124,0.0013641095,0.00018730886,0.0006445842,0.0011999815],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001727565,0.0012602207,0.04087713,0.00004741723,0.00013359591,0.000006193521,0.09488707,0.004872641,0.00029481878,0.84508514,0.008325967,0.004192507],"study_design_scores_gemma":[0.0012444246,0.00018085462,0.33775383,0.00022862774,0.00013778993,0.00004622365,0.068608806,0.002059936,0.00051140995,0.055845853,0.53284085,0.0005413777],"about_ca_topic_score_codex":0.0009106788,"about_ca_topic_score_gemma":0.0025356167,"teacher_disagreement_score":0.7892393,"about_ca_system_score_codex":0.0024545463,"about_ca_system_score_gemma":0.0017125382,"threshold_uncertainty_score":0.99994737},"labels":[],"label_agreement":null},{"id":"W2498848778","doi":"10.3138/cjpe.307","title":"Evaluating a Prison-Based Intervention Program: Approaches and Challenges","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université du Québec à Trois-Rivières; Université Laval","funders":"","keywords":"Prison; Government (linguistics); Intervention (counseling); Process (computing); Face (sociological concept); Public relations; Psychology; Business; Process management; Political science; Sociology; Computer science; Criminology; Psychiatry","score_opus":0.7617709376605948,"score_gpt":0.5696057253886638,"score_spread":0.19216521227193095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2498848778","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9572402,0.007538209,0.0050552716,0.023732292,0.0008836167,0.0035161672,0.000007865205,0.000043925345,0.0019824253],"genre_scores_gemma":[0.98300123,0.00006455795,0.01635922,0.000048402857,0.00015053808,0.00027207876,0.0000039419733,0.000012871901,0.000087183675],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9949832,0.0010781356,0.0010600215,0.00031486602,0.0022497256,0.00031404753],"domain_scores_gemma":[0.99555457,0.00051336864,0.0009673466,0.00030107857,0.0022032107,0.00046041864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027472114,0.00015561651,0.00026559032,0.0007244074,0.00019259717,0.0003893023,0.00036445816,0.00009752443,0.0008613683],"category_scores_gemma":[0.0053286045,0.00009457686,0.00015381904,0.0004072026,0.00015906067,0.0007400686,0.000016349783,0.00013429607,0.000035131237],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024511099,0.000080587575,0.007431304,0.000015203084,0.000022464248,0.000001334068,0.00046043593,0.00018385056,0.000036127887,0.00035381835,0.00012774332,0.9912626],"study_design_scores_gemma":[0.009573988,0.008346784,0.38325873,0.0010014374,0.00037732054,0.0001047928,0.00472745,0.4740058,0.0006142023,0.031431355,0.08589619,0.0006619702],"about_ca_topic_score_codex":0.00010932353,"about_ca_topic_score_gemma":0.007145909,"teacher_disagreement_score":0.99060065,"about_ca_system_score_codex":0.0003221289,"about_ca_system_score_gemma":0.002514481,"threshold_uncertainty_score":0.95213413},"labels":[],"label_agreement":null},{"id":"W2498866013","doi":"10.4135/9781506335124.n6","title":"From Discrete Evaluations to a More Holistic Organizational Approach: The Case of the Public Health Agency of Canada","year":2014,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Agency (philosophy); Sociology; Public relations; Political science; Social science","score_opus":0.30383321795997464,"score_gpt":0.4647437315501253,"score_spread":0.16091051359015068,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2498866013","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029843145,0.00018505097,0.0892469,0.08317347,0.0013646167,0.002218797,0.0021878076,0.000018978619,0.8186201],"genre_scores_gemma":[0.7614779,0.0000071354625,0.0011835787,0.003238561,0.0001614166,0.00002152286,0.00013058256,0.0000224374,0.23375688],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9952519,0.0002811107,0.0011168938,0.00037645546,0.0027906212,0.00018303748],"domain_scores_gemma":[0.995071,0.0010406261,0.0009616333,0.001248736,0.0015102957,0.0001677002],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0040054983,0.00019430244,0.00039472143,0.00014772237,0.0003608444,0.00007888202,0.0010466554,0.00007547363,0.011332104],"category_scores_gemma":[0.001885498,0.000091801216,0.00010924706,0.00037330593,0.00015352273,0.000066424574,0.0002505235,0.00018414792,0.00002914752],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000058820165,0.00002936503,0.00031272872,0.000023582472,0.00010629457,0.0000021928531,0.0046660528,0.002870017,0.0000052153114,0.83026683,0.14471263,0.01699922],"study_design_scores_gemma":[0.0012757211,0.00029263095,0.028205723,0.00024668197,0.00031708909,0.00018143356,0.010555845,0.14594296,0.000045926874,0.38059714,0.43110085,0.001237998],"about_ca_topic_score_codex":0.06375753,"about_ca_topic_score_gemma":0.3257784,"teacher_disagreement_score":0.75849354,"about_ca_system_score_codex":0.0001903858,"about_ca_system_score_gemma":0.008227786,"threshold_uncertainty_score":0.9973946},"labels":[],"label_agreement":null},{"id":"W2499544124","doi":"10.1057/9781403980939_10","title":"Practice, Practice, Practice","year":2005,"lang":"en","type":"book-chapter","venue":"Palgrave Macmillan US eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Capstone; Curriculum; Presentation (obstetrics); Medical education; Political science; Public service; Public relations; Pedagogy; Medicine; Psychology","score_opus":0.10418735057195316,"score_gpt":0.4285272690446612,"score_spread":0.32433991847270804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2499544124","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000009591008,0.0017194119,0.0005304161,0.008152268,0.0014057208,0.0012338675,0.00011070004,0.00018848617,0.9866495],"genre_scores_gemma":[0.09451409,0.002621451,0.028118795,0.040601462,0.0034639277,0.00013879738,0.0001624186,0.00032321736,0.83005583],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9867301,0.000822813,0.0025009774,0.0017658725,0.0073403874,0.00083985884],"domain_scores_gemma":[0.9763451,0.011720339,0.00402354,0.0027497592,0.004611074,0.0005501848],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.012185905,0.0010310657,0.0011558263,0.00095764914,0.0005298874,0.0011210443,0.0017152021,0.0008255743,0.008871041],"category_scores_gemma":[0.0168058,0.0008464839,0.0005563803,0.00014770536,0.00033330946,0.00018352072,0.0005757322,0.0016425612,0.015997825],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000467092,0.000020146808,0.000027103648,0.000018613495,0.0004212052,0.00027561787,0.0010007004,0.00005506875,0.000019156063,0.7101918,0.011005961,0.27649754],"study_design_scores_gemma":[0.0007687595,0.00029279524,0.00007417708,0.00008696005,0.00050843874,0.00062216714,0.0007809047,0.00028920927,0.000030260384,0.13817136,0.85748094,0.0008940461],"about_ca_topic_score_codex":0.00007996096,"about_ca_topic_score_gemma":0.00014630806,"teacher_disagreement_score":0.84647495,"about_ca_system_score_codex":0.0003970938,"about_ca_system_score_gemma":0.0013739615,"threshold_uncertainty_score":0.9999159},"labels":[],"label_agreement":null},{"id":"W2503808664","doi":"10.1093/acprof:oso/9780199658039.003.0003","title":"Coalition advocacy action and research for policy development","year":2013,"lang":"en","type":"book-chapter","venue":"Oxford University Press eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Conceptualization; Pooling; Political science; Process (computing); Action (physics); Structuring; Public relations; Field (mathematics); Public administration; Computer science; Law","score_opus":0.45367141080899726,"score_gpt":0.48379264472803446,"score_spread":0.030121233919037205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2503808664","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00088132324,0.000021148977,0.002158397,0.00039983419,0.000139147,0.0009709224,0.00003371675,0.000035352114,0.99536014],"genre_scores_gemma":[0.0041880794,0.00019837209,0.0015562804,0.00007170312,0.00015371479,0.000009152458,0.000043947322,0.000017951486,0.9937608],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973439,0.00011181509,0.0003271045,0.00051306444,0.0014247257,0.00027940044],"domain_scores_gemma":[0.99743325,0.00060089293,0.00025956743,0.00040645807,0.0011346353,0.00016521882],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020692423,0.00019448363,0.00025999988,0.00076821947,0.000613372,0.00024396487,0.00045623875,0.00026839273,0.00027520373],"category_scores_gemma":[0.00012598117,0.00018129959,0.00008392552,0.000029095425,0.00020111815,0.00030878797,0.00033834798,0.00030301607,0.000022375052],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009974387,0.0000090476915,0.0000086604705,0.000035911788,0.000036870362,0.000001537555,0.00061583676,0.000005346383,0.000018871955,0.74744785,0.01830912,0.23341118],"study_design_scores_gemma":[0.0005099843,0.000084197316,0.00014705573,0.000056013156,0.000016934173,0.000002094682,0.00034357308,0.00042524972,0.00012973738,0.016788647,0.98130167,0.0001948495],"about_ca_topic_score_codex":0.00008508845,"about_ca_topic_score_gemma":0.00006375998,"teacher_disagreement_score":0.96299255,"about_ca_system_score_codex":0.00040098644,"about_ca_system_score_gemma":0.0011011765,"threshold_uncertainty_score":0.73931825},"labels":[],"label_agreement":null},{"id":"W2505652211","doi":"10.3138/cjpe.225","title":"Improving Interprofessional Education and Collaborative Practice Through Evaluation: An Exploration of Current Trends","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Centre for Interdisciplinary Research in Rehabilitation; University of British Columbia","funders":"","keywords":"Political science; Humanities; Psychology; Sociology; Philosophy","score_opus":0.4583917648546845,"score_gpt":0.6133023389854954,"score_spread":0.15491057413081083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2505652211","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88807213,0.011767515,0.053219575,0.024606602,0.009396067,0.004382689,0.00007388969,0.000028182294,0.00845336],"genre_scores_gemma":[0.98749137,0.00006916527,0.01174718,0.00010415066,0.0002991462,0.00017032007,0.000028021928,0.000009606104,0.000081038655],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99365866,0.0018668069,0.0011803437,0.00027954247,0.0028295654,0.000185086],"domain_scores_gemma":[0.9839836,0.00050261494,0.0019006621,0.0002911148,0.013005108,0.00031689837],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.018372267,0.00014122047,0.00023911834,0.00074622984,0.00020715677,0.00023994886,0.00028396194,0.00007848933,0.0013522033],"category_scores_gemma":[0.0074808123,0.00009069195,0.00006257361,0.0010184187,0.00014480014,0.008666548,0.000017493892,0.00014388311,0.0000114423],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007057975,0.00014437886,0.002405762,0.0000045581164,0.000016446824,2.408491e-7,0.0041187876,0.0000990781,0.00026830778,0.0017363355,0.00071999716,0.9904155],"study_design_scores_gemma":[0.01427121,0.010620908,0.11866328,0.002495168,0.001986494,0.00022407403,0.120829985,0.1528864,0.0037643632,0.24163616,0.33104157,0.0015803997],"about_ca_topic_score_codex":0.00024391602,"about_ca_topic_score_gemma":0.00533397,"teacher_disagreement_score":0.98883516,"about_ca_system_score_codex":0.0004815928,"about_ca_system_score_gemma":0.020579588,"threshold_uncertainty_score":0.9995607},"labels":[],"label_agreement":null},{"id":"W2507161591","doi":"10.1177/0829573516655003","title":"La Psychologie Scolaire au Québec Français- <i>School Psychology in French Quebec</i>","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of School Psychology","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University","funders":"","keywords":"School psychology; Psychology; Professional psychology; Economic shortage; Pedagogy; Medical education; Clinical psychology; Medicine","score_opus":0.15322759372869,"score_gpt":0.4798461440746556,"score_spread":0.3266185503459656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2507161591","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87214494,0.0011340708,0.002091877,0.07121985,0.003775584,0.00024859793,0.000023261047,0.000016528309,0.049345296],"genre_scores_gemma":[0.9832017,0.00013779003,0.00053038914,0.013860743,0.00050428574,0.00001875563,0.0000010831163,0.000028452336,0.0017168182],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.994016,0.0012427617,0.0021643362,0.0007164458,0.0009170906,0.0009434037],"domain_scores_gemma":[0.9943761,0.0009379519,0.000875739,0.0011784432,0.0007433482,0.0018883729],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008365845,0.0003337349,0.0007297254,0.0021889445,0.00021714091,0.00016286357,0.0021803533,0.0005417804,0.018914387],"category_scores_gemma":[0.0049559386,0.00021848547,0.00026818455,0.0012457765,0.00068157015,0.0009372218,0.000036245998,0.0010696084,0.0036983318],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006917967,0.000058043126,0.7289238,0.0000017673979,0.00002535486,0.0002358985,0.00046379634,0.00001222586,0.00038463995,0.00017112942,0.1565352,0.113118984],"study_design_scores_gemma":[0.0025397628,0.00029312266,0.73035127,0.00007886315,0.000010121403,0.00027914514,0.0003204198,0.000002967169,0.00001817369,0.004208115,0.2616805,0.00021750793],"about_ca_topic_score_codex":0.13308345,"about_ca_topic_score_gemma":0.9613123,"teacher_disagreement_score":0.82822883,"about_ca_system_score_codex":0.0009882621,"about_ca_system_score_gemma":0.0151606165,"threshold_uncertainty_score":0.9970774},"labels":[],"label_agreement":null},{"id":"W2507236586","doi":"10.1016/j.evalprogplan.2016.08.005","title":"The use of Outcome Harvesting in learning-oriented and collaborative inquiry approaches to evaluation: An example from Calgary, Alberta","year":2016,"lang":"en","type":"article","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary","funders":"University of Toronto; United Way","keywords":"Neighbourhood (mathematics); Outcome (game theory); Work (physics); Collaborative learning; Process (computing); Community development; Knowledge management; Sociology; Public relations; Engineering; Computer science; Political science","score_opus":0.7616272255532968,"score_gpt":0.5431760229740711,"score_spread":0.21845120257922568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2507236586","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9941355,0.0003005318,0.0022883655,0.0011025924,0.00017641521,0.0014888895,0.0000035765263,0.000020692478,0.0004834134],"genre_scores_gemma":[0.99220836,0.000015222492,0.006763698,0.00008514335,0.00005184448,0.0003490173,0.000039836144,0.000009142062,0.00047776147],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99474126,0.0018577221,0.0008270397,0.0005112936,0.0018486595,0.00021403102],"domain_scores_gemma":[0.9939826,0.0043878616,0.00039847256,0.00031506552,0.0007831889,0.00013279752],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014981024,0.00014995672,0.0002459016,0.00017294029,0.00033549842,0.00041788982,0.00016280921,0.00007029088,0.00017200844],"category_scores_gemma":[0.006929794,0.000084661595,0.000021889398,0.000739175,0.00014778259,0.0009246831,0.00009575722,0.000118552285,0.000008950003],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000081210776,0.000027966025,0.3209282,0.0000013968729,0.000010032029,1.8828125e-7,0.014557156,0.0029643287,0.000051600164,0.00035876824,0.00006178792,0.6609574],"study_design_scores_gemma":[0.001690517,0.00039574172,0.39708105,0.00009385637,0.000036351717,0.0000014383022,0.008697741,0.56343776,0.00006862132,0.00095784746,0.027366009,0.00017310273],"about_ca_topic_score_codex":0.0010330473,"about_ca_topic_score_gemma":0.002256067,"teacher_disagreement_score":0.6607843,"about_ca_system_score_codex":0.000060910497,"about_ca_system_score_gemma":0.00021138226,"threshold_uncertainty_score":0.8296111},"labels":[],"label_agreement":null},{"id":"W2508682278","doi":"10.3138/cjpe.258","title":"Capturing the Imagination: Arts-Informed Inquiry as a Method in Program Evaluation","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"The arts; Context (archaeology); Representation (politics); Field (mathematics); Qualitative research; Arts in education; Sociology; Psychology; Pedagogy; Engineering ethics; Social science; Visual arts; Political science; Engineering; Art","score_opus":0.5462734858006425,"score_gpt":0.6255805119329582,"score_spread":0.07930702613231566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2508682278","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.867189,0.0019301404,0.012254197,0.07502822,0.0051064272,0.015573493,0.000010993402,0.00006756597,0.022839954],"genre_scores_gemma":[0.98820513,0.00002061981,0.0098293135,0.00037052165,0.00037125868,0.0009824877,0.000008908917,0.000014567161,0.00019720578],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99151146,0.0015716273,0.0015180697,0.00031390568,0.0046264245,0.0004585065],"domain_scores_gemma":[0.9916491,0.0009755034,0.001097801,0.0004844608,0.005399245,0.00039392477],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.052481346,0.00019032322,0.0002876194,0.0011435916,0.00026893767,0.0006548511,0.0007318885,0.00010959618,0.0030947712],"category_scores_gemma":[0.0126695195,0.00010234848,0.00016438804,0.0013904249,0.00018458533,0.0017687884,0.000024602417,0.00026665552,0.00018586763],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021075834,0.000043489166,0.007238515,0.0000029726957,0.000019326302,0.0000037565355,0.0039458894,0.00095571333,0.000035127556,0.0007084125,0.0015761501,0.98544955],"study_design_scores_gemma":[0.0069494937,0.0014366265,0.37518585,0.00042020658,0.0003104818,0.0002883561,0.012816513,0.20319165,0.00062534417,0.09800104,0.30020377,0.0005706648],"about_ca_topic_score_codex":0.00063890463,"about_ca_topic_score_gemma":0.03447505,"teacher_disagreement_score":0.9848789,"about_ca_system_score_codex":0.0015684015,"about_ca_system_score_gemma":0.012386379,"threshold_uncertainty_score":0.99781656},"labels":[],"label_agreement":null},{"id":"W2509408492","doi":"10.1111/capa.12177","title":"Commissions of inquiry and policy change: Comparative analysis and future research frontiers","year":2016,"lang":"en","type":"article","venue":"Canadian Public Administration","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Public administration; Policy analysis; Research policy; Public relations","score_opus":0.5222528378572118,"score_gpt":0.5705598099184708,"score_spread":0.048306972061259,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2509408492","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.536632,0.0004268836,0.0015861965,0.4529067,0.00024950804,0.0004311014,0.00017976933,0.000011473987,0.0075763664],"genre_scores_gemma":[0.9981681,0.00013901896,0.00031332613,0.00024485608,0.0002555788,0.000022045753,0.000021118498,0.0000023501789,0.00083361985],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9981206,0.00034288687,0.00032013236,0.00026017465,0.00072368,0.00023252779],"domain_scores_gemma":[0.9980083,0.00028841512,0.00012432404,0.00029780038,0.00068808475,0.0005930739],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026483368,0.000075878386,0.00020000125,0.0018977068,0.00031226227,0.00019509523,0.0001937469,0.00008144303,0.0005075844],"category_scores_gemma":[0.000535554,0.000048744936,0.00003153921,0.0022036475,0.00034675267,0.0006378993,0.0000302723,0.00008264892,0.000009901175],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030854204,0.000038627906,0.3409905,0.000006346938,0.00014588791,0.000002786685,0.0054706894,1.4196523e-7,0.00013314499,0.21802822,0.04093116,0.3942216],"study_design_scores_gemma":[0.0002734125,0.00015730037,0.5028249,0.000007473967,0.000022484026,0.0000030228605,0.009357509,0.0006344838,0.00009013971,0.0035571584,0.4829727,0.00009941299],"about_ca_topic_score_codex":0.001298831,"about_ca_topic_score_gemma":0.18676919,"teacher_disagreement_score":0.4615361,"about_ca_system_score_codex":0.00012127706,"about_ca_system_score_gemma":0.0021211742,"threshold_uncertainty_score":0.82807016},"labels":[],"label_agreement":null},{"id":"W2509640135","doi":"10.3138/cjpe.31.1.125","title":"Huey T. Chen. (2015). <i>Practical program evaluation: Theory-driven evaluation and the integrated evaluation perspective</i> (2nd ed.).","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Chen; Perspective (graphical); Evaluation methods; Sociology; Program evaluation; Epistemology; Management science; Psychology; Computer science; Mathematics; Philosophy; Statistics; Artificial intelligence; Economics; Engineering; Reliability engineering","score_opus":0.27595033564129184,"score_gpt":0.5513600661607184,"score_spread":0.2754097305194266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2509640135","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.65918225,0.021510176,0.019441085,0.18542649,0.009565019,0.07203196,0.00012837427,0.00023332158,0.03248132],"genre_scores_gemma":[0.9910821,0.00014351899,0.0045386725,0.0004073518,0.0006501154,0.0028707988,0.00005607779,0.000040887622,0.000210505],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9688457,0.014479715,0.0023460402,0.0009061513,0.012649585,0.00077277207],"domain_scores_gemma":[0.95830166,0.002838117,0.0021412184,0.0009535472,0.034954075,0.0008113919],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.17340463,0.00046183052,0.0006789795,0.0010393655,0.0008388877,0.0013898443,0.0008613431,0.0003016062,0.014546612],"category_scores_gemma":[0.05666442,0.000251587,0.00034172204,0.001612539,0.0010695326,0.0023935928,0.00006079161,0.00060951174,0.00021376446],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031300946,0.00018413222,0.0030873283,0.000004336839,0.00019029071,0.0000025093202,0.0022469421,0.0008656066,0.000079921185,0.008036325,0.007862286,0.9771273],"study_design_scores_gemma":[0.020416437,0.0016949156,0.047296062,0.00029086057,0.0032756026,0.00029956692,0.011533669,0.64388853,0.00015000057,0.20111299,0.06935454,0.000686817],"about_ca_topic_score_codex":0.00051356567,"about_ca_topic_score_gemma":0.010346884,"teacher_disagreement_score":0.9764405,"about_ca_system_score_codex":0.0032465705,"about_ca_system_score_gemma":0.022618946,"threshold_uncertainty_score":0.9999936},"labels":[],"label_agreement":null},{"id":"W2511230851","doi":"10.4000/ripes.1094","title":"Processus de coconstruction d’une grille critériée pour l’évaluation de productions écrites complexes à l’université","year":2016,"lang":"fr","type":"article","venue":"Revue internationale de pédagogie de l’enseignement supérieur","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université Laval","funders":"","keywords":"Humanities; Philosophy; Art","score_opus":0.11038961593035931,"score_gpt":0.387016316919996,"score_spread":0.2766267009896367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2511230851","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7986048,0.0016511763,0.06624937,0.11997198,0.0017451453,0.00088085164,0.0003212913,0.00014321253,0.010432182],"genre_scores_gemma":[0.8844801,0.0036611266,0.018130599,0.001239222,0.0016123153,0.00021296834,0.00016555737,0.00006297716,0.09043514],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9945076,0.0007721811,0.0011700692,0.0009387105,0.0016153546,0.0009960714],"domain_scores_gemma":[0.9949134,0.0013845817,0.000673673,0.0006409919,0.0020125967,0.0003747717],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004232158,0.00044774672,0.00044934175,0.0006793718,0.00073170697,0.00040973374,0.00095501955,0.00027887785,0.010568324],"category_scores_gemma":[0.0030884098,0.00041993312,0.0003033129,0.00087395683,0.00037658322,0.001305719,0.00022625006,0.00035437025,0.0006103335],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047366193,0.0016355378,0.14327341,0.00052204676,0.0006406476,0.00017233852,0.105339184,0.013554641,0.064075045,0.038775384,0.16738942,0.46414867],"study_design_scores_gemma":[0.006451915,0.00082852895,0.21505488,0.002479632,0.0006613582,0.0029056028,0.124134265,0.12768131,0.039547715,0.108687595,0.369735,0.0018321906],"about_ca_topic_score_codex":0.0006067802,"about_ca_topic_score_gemma":0.00085734,"teacher_disagreement_score":0.46231648,"about_ca_system_score_codex":0.002959742,"about_ca_system_score_gemma":0.0033467691,"threshold_uncertainty_score":0.99982524},"labels":[],"label_agreement":null},{"id":"W2511585254","doi":"10.1177/2158244016663800","title":"Developing a Framework for Research Evaluation in Complex Contexts Such as Action Research","year":2016,"lang":"en","type":"article","venue":"SAGE Open","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Roads University","funders":"","keywords":"Reflexivity; Accountability; Action research; Underpinning; Process (computing); Process management; Knowledge management; Action (physics); Conceptual framework; Dialogical self; Formative assessment; Computer science; Management science; Sociology; Psychology; Business; Political science; Engineering; Pedagogy; Social psychology","score_opus":0.9352271401275563,"score_gpt":0.7701994661372427,"score_spread":0.1650276739903136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2511585254","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.72088706,0.00017180602,0.12590635,0.08162721,0.0007449673,0.010721057,0.000027062786,0.000032674434,0.05988184],"genre_scores_gemma":[0.98236126,0.000059870465,0.011145965,0.00028772722,0.00011988775,0.00096911326,0.000010477955,0.000012003103,0.005033697],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9901243,0.003165796,0.0006397652,0.00062490656,0.004877862,0.0005673572],"domain_scores_gemma":[0.9865182,0.009448196,0.00012561014,0.0006561989,0.0031537,0.00009809953],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.11230117,0.00009123104,0.00021492719,0.0007357294,0.00059516606,0.0008516003,0.0014544509,0.00012302693,0.0075580208],"category_scores_gemma":[0.024990391,0.000057905003,0.000037773327,0.0018494799,0.00014385472,0.0011218028,0.0005419673,0.00030827316,0.0020256932],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026545045,0.00004582666,0.0069260243,0.0000053192725,0.000006073418,9.266449e-7,0.0010367355,0.000010740228,0.0014446687,0.10167789,0.006441589,0.8821388],"study_design_scores_gemma":[0.0014859219,0.00019035443,0.111390285,0.00024432776,0.0000017047176,0.0000012194171,0.0033917814,0.002182009,0.0015650147,0.7888893,0.0905403,0.000117776035],"about_ca_topic_score_codex":0.00025424856,"about_ca_topic_score_gemma":0.0028102524,"teacher_disagreement_score":0.882021,"about_ca_system_score_codex":0.00078429235,"about_ca_system_score_gemma":0.0018798212,"threshold_uncertainty_score":0.99875134},"labels":[],"label_agreement":null},{"id":"W2511650799","doi":"10.1007/s40955-016-0070-0","title":"Plus ça change – The failure of PIAAC to drive evidence-based policy in Canada","year":2016,"lang":"de","type":"article","venue":"Zeitschrift für Weiterbildungsforschung","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Business","score_opus":0.11669331729371056,"score_gpt":0.4132206735656929,"score_spread":0.29652735627198235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2511650799","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5495794,0.01009318,0.0036481724,0.42238143,0.0051184352,0.0055947355,0.0005450647,0.00007771707,0.0029619108],"genre_scores_gemma":[0.985795,0.0009020674,0.00051804277,0.010319619,0.0011593662,0.00030825508,0.000009558446,0.000056384928,0.0009317082],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9894693,0.0012000639,0.0022836432,0.0012521667,0.004386605,0.001408214],"domain_scores_gemma":[0.99076515,0.0046040327,0.0010378663,0.0020267316,0.0009304045,0.0006358107],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.006099532,0.00070054183,0.0010721115,0.0012054837,0.00032774836,0.00027111295,0.0027011572,0.00025774227,0.0028519519],"category_scores_gemma":[0.0035373976,0.0003782819,0.0003213564,0.0039023326,0.00027048276,0.0015928422,0.00059405714,0.00050773553,0.0011550264],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012358985,0.0003077191,0.46112517,0.00038974753,0.00028450138,0.000102112106,0.021722827,0.0042761457,0.0059517743,0.0160239,0.053125344,0.43545488],"study_design_scores_gemma":[0.0037447077,0.00080503034,0.273795,0.0059993505,0.00011838131,0.0000074589093,0.004950366,0.010648279,0.009848875,0.00021008198,0.68855256,0.0013199132],"about_ca_topic_score_codex":0.6335457,"about_ca_topic_score_gemma":0.8423874,"teacher_disagreement_score":0.6354272,"about_ca_system_score_codex":0.0007394922,"about_ca_system_score_gemma":0.017347129,"threshold_uncertainty_score":0.9998669},"labels":[],"label_agreement":null},{"id":"W2512095165","doi":"10.3138/cjpe.274","title":"Evaluate This! A Case for Developing Evaluation Competencies","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Competition (biology); Psychology; Business; Medical education; Public relations; Political science; Medicine; Ecology","score_opus":0.5723191234277859,"score_gpt":0.562928248525481,"score_spread":0.009390874902304946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2512095165","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9254388,0.0012358942,0.037165463,0.022738542,0.003605374,0.006586937,0.000050531555,0.000032152308,0.0031463031],"genre_scores_gemma":[0.9771815,0.000012671166,0.021445166,0.0002544582,0.0003356656,0.00043724466,0.000010650665,0.000017352106,0.00030527433],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99282396,0.0011560787,0.0014971939,0.00033371523,0.003743916,0.00044515383],"domain_scores_gemma":[0.98371226,0.0010746154,0.001204151,0.00039257243,0.013183756,0.0004326463],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.054492533,0.0001920546,0.0003415507,0.00070901704,0.0004894453,0.00045208808,0.0005054364,0.00011085585,0.0039134813],"category_scores_gemma":[0.012808461,0.0001180008,0.00022255366,0.00074934796,0.00017750065,0.0011784332,0.000017006436,0.000115057504,0.00012724644],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026716452,0.000019944773,0.0037242358,0.00000539601,0.000041424537,0.000016237831,0.00066140364,0.00034356074,0.00018481929,0.0010835944,0.0042374963,0.9896552],"study_design_scores_gemma":[0.013358807,0.0026190882,0.043988932,0.00060781755,0.0011579697,0.003604011,0.0045608715,0.41630852,0.0018791155,0.14576338,0.365082,0.0010694948],"about_ca_topic_score_codex":0.00030665618,"about_ca_topic_score_gemma":0.026465822,"teacher_disagreement_score":0.98858565,"about_ca_system_score_codex":0.0015667378,"about_ca_system_score_gemma":0.0128331585,"threshold_uncertainty_score":0.99699706},"labels":[],"label_agreement":null},{"id":"W2512462080","doi":"","title":"CONFLICTING VISIONS, COMPETING EXPECTATIONS: CONTROL AND DE-SKILLING OF EDUCATION - A PERSPECTIVE FROM ONTARIO","year":2002,"lang":"en","type":"article","venue":"McGill Journal of Education / Revue des sciences de l'éducation de McGill","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Western University","funders":"","keywords":"Political science; Vision; Excellence; Humanities; Restructuring; Public administration; Sociology; Law; Art","score_opus":0.3763883207719101,"score_gpt":0.5216406186977925,"score_spread":0.14525229792588246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2512462080","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9754994,0.0014379685,0.0029761237,0.004161375,0.0015131262,0.00028922508,0.000026066142,0.000015510712,0.014081208],"genre_scores_gemma":[0.9529388,0.00019758304,0.044773713,0.001064785,0.00022769485,0.000025930844,0.000003321281,0.000012300292,0.00075587875],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99623436,0.0006154285,0.0014151247,0.00042178546,0.0009807491,0.00033254022],"domain_scores_gemma":[0.99244314,0.0019542547,0.0020312439,0.00030183763,0.002971218,0.00029828682],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005803476,0.00019779448,0.0003958775,0.0008985736,0.001447393,0.00024377697,0.00062756526,0.00009777536,0.0010320832],"category_scores_gemma":[0.0055395626,0.00017785175,0.00015014024,0.0010794409,0.0004089383,0.0013514196,0.000040764746,0.00031216693,0.000024077206],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017609738,0.003819521,0.286733,0.00011350238,0.00023973238,0.00000452199,0.37319338,0.019281197,0.015623424,0.08395712,0.0056928964,0.2111656],"study_design_scores_gemma":[0.0016324292,0.000914123,0.15373076,0.0013689874,0.00029879765,0.0009044412,0.59619755,0.07754696,0.0034690718,0.12622856,0.036891576,0.0008167688],"about_ca_topic_score_codex":0.0032176445,"about_ca_topic_score_gemma":0.002263677,"teacher_disagreement_score":0.22300416,"about_ca_system_score_codex":0.0024843456,"about_ca_system_score_gemma":0.00225066,"threshold_uncertainty_score":0.9998811},"labels":[],"label_agreement":null},{"id":"W2512463988","doi":"10.1002/ev.20199","title":"Building Evaluation Capacity Through CLIPs: Communities of Learning, Inquiry, and Practice","year":2016,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"CLIPS; Context (archaeology); Work (physics); Community of practice; Medical education; Professional development; Higher education; Pedagogy; Knowledge management; Computer science; Sociology; Public relations; Psychology; Political science; Medicine; Engineering","score_opus":0.5953867694134086,"score_gpt":0.5760182223031797,"score_spread":0.01936854711022895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2512463988","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7530027,0.0004714587,0.22322667,0.0063555953,0.0014649073,0.0018853132,0.000015053681,0.00007808533,0.013500206],"genre_scores_gemma":[0.97594464,0.00026138744,0.022255298,0.00011085566,0.00021743223,0.00025958437,0.000015032424,0.000013472286,0.0009223027],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9939329,0.00223033,0.00076347834,0.00031110697,0.0025807538,0.00018142596],"domain_scores_gemma":[0.98803496,0.0068095415,0.00074501685,0.00043368884,0.003912688,0.00006411213],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.027903566,0.00013928166,0.00023189605,0.00030110104,0.00051679177,0.00013040236,0.00020788885,0.0000971628,0.0010881282],"category_scores_gemma":[0.026964903,0.0000980987,0.00008998557,0.00054928235,0.00016458565,0.0020252913,0.000056985857,0.0001096805,0.000031152675],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017888854,0.00011236208,0.008914937,0.000011895924,0.00006578926,1.6732297e-8,0.010674404,0.003148324,0.004252719,0.011055281,0.0052791378,0.9563062],"study_design_scores_gemma":[0.009569176,0.0011183295,0.06909404,0.000244745,0.0009758353,0.000032002987,0.027924566,0.19454497,0.0061150747,0.2463345,0.44347987,0.00056688866],"about_ca_topic_score_codex":0.00039491645,"about_ca_topic_score_gemma":0.0006101837,"teacher_disagreement_score":0.9557394,"about_ca_system_score_codex":0.00026677427,"about_ca_system_score_gemma":0.00057234656,"threshold_uncertainty_score":0.999825},"labels":[],"label_agreement":null},{"id":"W2513225428","doi":"10.4000/ripes.1073","title":"Bilan de pratiques évaluatives des apprentissages à distance en contexte de formation universitaire","year":2016,"lang":"fr","type":"article","venue":"Revue internationale de pédagogie de l’enseignement supérieur","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Montréal; Université de Sherbrooke","funders":"","keywords":"Political science; Humanities; Art","score_opus":0.10624118780867237,"score_gpt":0.3983688716331716,"score_spread":0.2921276838244992,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2513225428","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.570172,0.0026526854,0.40128472,0.016954036,0.00044880252,0.00050171337,0.00023775609,0.000086948494,0.007661315],"genre_scores_gemma":[0.8784816,0.0063651195,0.010787562,0.0006539506,0.00033707128,0.00011433396,0.000059641996,0.000036708505,0.10316397],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99456286,0.0015752582,0.0010335565,0.0006310766,0.0013081509,0.0008890743],"domain_scores_gemma":[0.99495834,0.0025383558,0.0006706427,0.0005227716,0.0009770364,0.0003328434],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0056961323,0.0004044368,0.00040698363,0.00037393163,0.00049898546,0.0004464875,0.0010568616,0.0002437475,0.0035802163],"category_scores_gemma":[0.0028483474,0.00034934617,0.00027341372,0.00041361252,0.0004412681,0.0022605867,0.00023944414,0.00027513283,0.0003855639],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031810562,0.0006365393,0.111376345,0.00041239883,0.00037392197,0.00016856607,0.20299491,0.0028413816,0.0100216335,0.037722584,0.02782508,0.60530853],"study_design_scores_gemma":[0.005242301,0.0012400474,0.29118392,0.0057847328,0.00036637267,0.00058675307,0.1554605,0.15263577,0.03162717,0.08283281,0.2713868,0.001652828],"about_ca_topic_score_codex":0.00014309301,"about_ca_topic_score_gemma":0.0013916316,"teacher_disagreement_score":0.6036557,"about_ca_system_score_codex":0.003992408,"about_ca_system_score_gemma":0.001685435,"threshold_uncertainty_score":0.9998959},"labels":[],"label_agreement":null},{"id":"W2513931290","doi":"10.5539/mas.v10n11p248","title":"Development of a Self-Assessment, Performance Measurement and Quality Insurance Repository Case of Two Higher Education Institutions in Morocco","year":2016,"lang":"en","type":"article","venue":"Modern Applied Science","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Computer science; Identification (biology); Quality (philosophy); Self-assessment; Higher education; Perspective (graphical); Process management; Engineering management; Business; Psychology; Political science; Artificial intelligence; Pedagogy; Engineering","score_opus":0.27666086987809885,"score_gpt":0.48216096370543693,"score_spread":0.20550009382733808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2513931290","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97174233,0.000040272207,0.013613381,0.00009251603,0.00019999545,0.00029225915,0.0000026731018,0.0000147495375,0.0140018305],"genre_scores_gemma":[0.98226607,0.0000100889865,0.017486,0.000042570435,0.000012226746,0.00008460759,2.6457795e-7,0.0000034546783,0.00009473995],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99606144,0.00007761144,0.0010407646,0.000504259,0.0020986656,0.00021725496],"domain_scores_gemma":[0.9978793,0.000110940004,0.000514989,0.00051640143,0.0008766204,0.000101746904],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008135212,0.00012357158,0.00024252129,0.0003769465,0.00030944915,0.000053813674,0.00045157588,0.000032667827,0.000029238712],"category_scores_gemma":[0.00007373547,0.00008163365,0.00001983665,0.0011324357,0.00042267237,0.00066187687,0.00014847325,0.000072437935,0.0000059558347],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025540352,0.00038024771,0.21957587,0.000038445196,0.0000061033365,8.735526e-7,0.0028750268,0.00023417812,0.5920141,0.025643986,0.000007479773,0.15919818],"study_design_scores_gemma":[0.0008853343,0.000025760715,0.9480154,0.00008741004,0.0000044987532,0.0000139159765,0.00035814906,0.005245557,0.04314749,0.0016556408,0.0003872402,0.00017360588],"about_ca_topic_score_codex":0.00004686771,"about_ca_topic_score_gemma":0.00017947928,"teacher_disagreement_score":0.7284395,"about_ca_system_score_codex":0.00045403026,"about_ca_system_score_gemma":0.004733005,"threshold_uncertainty_score":0.8396148},"labels":[],"label_agreement":null},{"id":"W2515878609","doi":"","title":"Book Review: A. L. LAVIGNE & T. L. GOOD. (2014). Teacher and Student Evaluation: Moving Beyond the Failure of School Reform.","year":2015,"lang":"en","type":"article","venue":"McGill Journal of Education / Revue des sciences de l'éducation de McGill","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Political science; Sociology; Management; Economics","score_opus":0.3834619295578525,"score_gpt":0.5385322126661344,"score_spread":0.15507028310828186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2515878609","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4444601,0.21764927,0.0011744157,0.19743842,0.0076135187,0.0030431598,0.0000609031,0.000052860196,0.12850738],"genre_scores_gemma":[0.912503,0.0156193115,0.017539663,0.038909685,0.00091965316,0.0001867853,0.000013300052,0.00003999101,0.014268636],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9937539,0.0012906366,0.0015800586,0.00037268814,0.002689119,0.00031356813],"domain_scores_gemma":[0.9919313,0.00046595858,0.002042175,0.00056410336,0.0045757247,0.00042073178],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.034364212,0.00020182431,0.00039893028,0.0004911356,0.00088504766,0.00019781356,0.0012019317,0.00008425485,0.0022549217],"category_scores_gemma":[0.005558663,0.00013013193,0.00014364833,0.001249379,0.0004936895,0.0018216617,0.00011676646,0.00031895164,0.00006547994],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042613945,0.00075254386,0.0197106,0.00019262896,0.00007171196,0.000001322608,0.006682243,0.0034692266,0.00053531537,0.0073362943,0.8983351,0.062870376],"study_design_scores_gemma":[0.00075153995,0.00064746325,0.035508595,0.0008862403,0.00026523205,0.00078335305,0.03466606,0.0035716116,0.00060798746,0.01927167,0.9026954,0.00034484864],"about_ca_topic_score_codex":0.00005835354,"about_ca_topic_score_gemma":0.000090325266,"teacher_disagreement_score":0.4680429,"about_ca_system_score_codex":0.0020316953,"about_ca_system_score_gemma":0.0031444523,"threshold_uncertainty_score":0.99865717},"labels":[],"label_agreement":null},{"id":"W2517081630","doi":"10.35502/jcswb.7","title":"How can we help? An educator’s perspective on the Situation Table Model in Ontario","year":2016,"lang":"en","type":"article","venue":"Journal of Community Safety and Well-Being","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Truancy; Perspective (graphical); Agency (philosophy); Mandate; Harm; Table (database); Public relations; Psychology; Sociology; Pedagogy; Social psychology; Political science; Computer science; Social science; Criminology","score_opus":0.11174178825149511,"score_gpt":0.39489466617616237,"score_spread":0.28315287792466726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2517081630","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8867921,0.000025480023,0.0031785232,0.09465436,0.00014652063,0.00009231384,0.0000010760033,0.000003061351,0.015106568],"genre_scores_gemma":[0.9962191,0.00020599822,0.00018804528,0.0009092256,0.000052064413,0.0000013086112,5.3157686e-7,0.0000047942954,0.0024189188],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99743515,0.0010446884,0.0004492466,0.0000833142,0.0008380336,0.0001495497],"domain_scores_gemma":[0.99699354,0.0015964747,0.00040550466,0.00039203168,0.0005164767,0.00009597837],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008458413,0.0001044727,0.0002126901,0.00022584516,0.0005862515,0.00023029167,0.0005306769,0.00005046157,0.0002206262],"category_scores_gemma":[0.0005789508,0.00005194794,0.000057749105,0.0002167444,0.00007447121,0.000985192,0.000076356766,0.0006982194,0.0000065129625],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014406047,0.0011170958,0.113503784,0.000009618509,0.00010334113,0.0000062348327,0.48162836,0.019877097,0.0019794758,0.23784766,0.0029296356,0.1395571],"study_design_scores_gemma":[0.0017863942,0.0007582664,0.19460769,0.0003231235,0.000028610408,0.000035284065,0.17750229,0.0119102355,0.0007543953,0.60024667,0.011790603,0.0002564465],"about_ca_topic_score_codex":0.004071033,"about_ca_topic_score_gemma":0.1205763,"teacher_disagreement_score":0.362399,"about_ca_system_score_codex":0.00054035935,"about_ca_system_score_gemma":0.0007219893,"threshold_uncertainty_score":0.8954709},"labels":[],"label_agreement":null},{"id":"W2517204597","doi":"10.1057/978-1-137-52712-7","title":"Forms of Practitioner Reflexivity","year":2016,"lang":"en","type":"book","venue":"Palgrave Macmillan US eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University","funders":"","keywords":"Reflexivity; Reflective practice; Sociology; Psychology; Epistemology; Pedagogy; Philosophy; Social science","score_opus":0.13128133461497388,"score_gpt":0.436147653264595,"score_spread":0.3048663186496211,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2517204597","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000606351,0.00010693006,0.0008742148,0.0002110377,0.00057098764,0.0005161626,0.00028203794,0.000051763374,0.9967805],"genre_scores_gemma":[0.5265898,0.000057281177,0.00029074552,0.00040986846,0.00031685934,0.000038178612,0.000057362562,0.00004034438,0.47219956],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9941578,0.00021945003,0.0013785778,0.0007036119,0.0031621887,0.00037837937],"domain_scores_gemma":[0.9945776,0.0011169781,0.0016421161,0.0014924018,0.0009817571,0.00018914457],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0038356017,0.0004047981,0.00079773203,0.00056728674,0.00014857073,0.00010778732,0.0009254174,0.00038898236,0.005392338],"category_scores_gemma":[0.0005509382,0.00024009829,0.00040674445,0.000083845116,0.00029307662,0.000017223356,0.00025745982,0.00032391123,0.0016980523],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016084228,0.0000080634,0.0014113836,0.00008564843,0.00017812834,0.00001659851,0.00047928924,0.0000061349688,0.00068310753,0.74032,0.02166189,0.23498891],"study_design_scores_gemma":[0.00043576746,0.00013717682,0.0017098471,0.00013307414,0.00003753325,0.000011714898,0.000028439596,0.000037062768,0.00070967316,0.76476777,0.2316774,0.00031452876],"about_ca_topic_score_codex":0.000009248267,"about_ca_topic_score_gemma":0.000120397744,"teacher_disagreement_score":0.52598345,"about_ca_system_score_codex":0.00021485807,"about_ca_system_score_gemma":0.0012230977,"threshold_uncertainty_score":0.9990792},"labels":[],"label_agreement":null},{"id":"W2517356492","doi":"10.3138/cjpe.267","title":"Process Flow Mapping for Systems Improvement: Lessons Learned","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Process (computing); Computer science; Context (archaeology); Process management; Flow (mathematics); Risk analysis (engineering); Management science; Engineering; Business; Mathematics; Geography","score_opus":0.5733614912876671,"score_gpt":0.5667968770536289,"score_spread":0.006564614234038202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2517356492","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67975587,0.0021538548,0.2191912,0.074308544,0.00861209,0.010969184,0.00017213993,0.0000636096,0.0047735195],"genre_scores_gemma":[0.99661094,0.000012199016,0.0019579178,0.00010368187,0.00034072113,0.00032527748,0.000006668448,0.000012601399,0.0006299932],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99631023,0.00024981456,0.0010032711,0.00023727628,0.0018523172,0.00034709246],"domain_scores_gemma":[0.9930999,0.0003451296,0.0008954168,0.00026018196,0.0049664862,0.0004328437],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017333744,0.00012055005,0.00024416434,0.00063582166,0.0002692112,0.00043906938,0.0004762207,0.00007775728,0.0005370318],"category_scores_gemma":[0.0040663723,0.00007250821,0.00013400699,0.0005095955,0.00006262938,0.0007833258,0.0000072500484,0.00008944472,0.000055099328],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000149941225,0.000018784753,0.0020936423,0.000009823179,0.000027202716,9.1096405e-7,0.0005844937,0.0017683861,0.00039896287,0.00047702703,0.0026165184,0.99198925],"study_design_scores_gemma":[0.00726273,0.0023868098,0.015621893,0.00052603014,0.0002156044,0.00006003752,0.008122462,0.4517606,0.0011317829,0.06464644,0.4476783,0.0005873206],"about_ca_topic_score_codex":0.000096418364,"about_ca_topic_score_gemma":0.002513491,"teacher_disagreement_score":0.9914019,"about_ca_system_score_codex":0.00044686408,"about_ca_system_score_gemma":0.005278585,"threshold_uncertainty_score":0.93639827},"labels":[],"label_agreement":null},{"id":"W2520223558","doi":"10.3138/cjpe.261","title":"Data Quality Evaluation for Program Evaluators","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Quality (philosophy); Psychology; Computer science; Philosophy; Epistemology","score_opus":0.8261497658997451,"score_gpt":0.6791874459859031,"score_spread":0.146962319913842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2520223558","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.898655,0.00245797,0.030731468,0.029141763,0.007745378,0.024527026,0.0007696941,0.000111835434,0.0058598644],"genre_scores_gemma":[0.9789172,0.000015721245,0.018944863,0.00019119329,0.00061030226,0.0008631262,0.0001633669,0.000024939394,0.000269304],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9880323,0.0021830683,0.0021908917,0.0006101159,0.0064362846,0.000547372],"domain_scores_gemma":[0.9813163,0.0013152628,0.00180972,0.0013874767,0.013430304,0.00074093597],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1198193,0.00022411389,0.00042955423,0.0008411665,0.00035928361,0.0005976603,0.0017351159,0.00015514827,0.0041519892],"category_scores_gemma":[0.036143035,0.00013812805,0.00022075255,0.0009224303,0.00018800801,0.0020836121,0.000050461542,0.0001535728,0.00013343655],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046323297,0.00008894667,0.014200328,0.0000059348513,0.000046061665,5.2487866e-7,0.00019809695,0.0001756776,0.00008467055,0.0004989415,0.013851008,0.9708035],"study_design_scores_gemma":[0.0064687054,0.001899504,0.15116438,0.00015611218,0.0005924234,0.000031470674,0.00096984016,0.21215537,0.00020082238,0.057284456,0.5685998,0.00047711233],"about_ca_topic_score_codex":0.00020050054,"about_ca_topic_score_gemma":0.020488763,"teacher_disagreement_score":0.97032636,"about_ca_system_score_codex":0.0009769184,"about_ca_system_score_gemma":0.0158549,"threshold_uncertainty_score":0.9973848},"labels":[],"label_agreement":null},{"id":"W2520519417","doi":"10.1177/1098214016668401","title":"Introducing Reflexivity to Evaluation Practice","year":2016,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Reflexivity; Action (physics); Psychology; Thematic analysis; Action research; Engineering ethics; Action plan; Competence (human resources); Sociology; Qualitative research; Pedagogy; Social psychology; Social science","score_opus":0.27423114310164076,"score_gpt":0.5920985262212245,"score_spread":0.31786738311958374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2520519417","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.854856,0.00007019765,0.07263486,0.063474126,0.0012167996,0.00052083674,0.0000027060346,0.000010444642,0.007214026],"genre_scores_gemma":[0.9784046,0.000024374136,0.019235848,0.001618274,0.0005298529,0.00001915708,9.498153e-7,0.000009457117,0.00015751865],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9863702,0.0033564335,0.001315626,0.00033978443,0.008401768,0.00021619529],"domain_scores_gemma":[0.98238623,0.002962429,0.0022346552,0.00054672675,0.011668981,0.00020096652],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.090552494,0.0001257669,0.00032590612,0.0006271381,0.00012232487,0.00014762046,0.00038687454,0.000027271557,0.00290052],"category_scores_gemma":[0.06624832,0.00007161531,0.00011355462,0.001342331,0.000092781534,0.0018785786,0.000054722095,0.00012443413,0.0005750011],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022500106,0.00005731218,0.0015911344,3.925302e-7,0.000026427197,7.1038596e-7,0.0009156074,0.0042401706,0.007446389,0.00022066446,0.0042161453,0.98106],"study_design_scores_gemma":[0.01141051,0.014073159,0.46234757,0.0005768739,0.0016930517,0.00068141916,0.027281988,0.101581424,0.014888053,0.07719248,0.28682002,0.0014534465],"about_ca_topic_score_codex":0.00001592721,"about_ca_topic_score_gemma":0.00002255696,"teacher_disagreement_score":0.9796066,"about_ca_system_score_codex":0.0006600155,"about_ca_system_score_gemma":0.0013744475,"threshold_uncertainty_score":0.998011},"labels":[],"label_agreement":null},{"id":"W2521476639","doi":"10.1097/acm.0000000000001389","title":"It’s a Story, Not a Study: Writing an Effective Research Paper","year":2016,"lang":"en","type":"article","venue":"Academic Medicine","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":27,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Psychology; Medical education; Medicine","score_opus":0.5371340376603417,"score_gpt":0.6453653655370287,"score_spread":0.10823132787668699,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2521476639","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8988549,0.000114554074,0.0006087141,0.08783578,0.00046347824,0.0009385347,0.0000023843597,0.000044957662,0.011136657],"genre_scores_gemma":[0.985892,0.00009842797,0.000025144094,0.0052352576,0.0010436691,0.00016214942,0.0000010636411,0.000013056546,0.007529211],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9900628,0.002900435,0.00078136154,0.00067261176,0.0051221373,0.00046068293],"domain_scores_gemma":[0.98803544,0.009927953,0.00018863773,0.000717363,0.0008457264,0.00028488948],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.06696375,0.00014546122,0.00034763664,0.00051798084,0.0003687977,0.000027412028,0.0009586583,0.00014052633,0.0054554646],"category_scores_gemma":[0.016295886,0.00006897464,0.000029820114,0.0008697907,0.0003687725,0.0007898737,0.00018246991,0.0009233717,0.00129547],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019934548,0.000063699044,0.10750608,0.0000064960595,0.000031635802,0.000015835234,0.048537526,0.0000030976305,0.03605105,0.0019487235,0.15463239,0.65100414],"study_design_scores_gemma":[0.0064493963,0.004194134,0.4861823,0.00051514537,0.000038156024,0.000020169276,0.11855541,0.00071735296,0.00095812185,0.011781745,0.37023884,0.0003492079],"about_ca_topic_score_codex":0.000048117163,"about_ca_topic_score_gemma":0.000070107715,"teacher_disagreement_score":0.6506549,"about_ca_system_score_codex":0.00016132265,"about_ca_system_score_gemma":0.00017375337,"threshold_uncertainty_score":0.99948215},"labels":[],"label_agreement":null},{"id":"W2523068226","doi":"10.1097/acm.0000000000001393","title":"The Tools of the Qualitative Research Trade","year":2016,"lang":"en","type":"article","venue":"Academic Medicine","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Wilson Centre; University Health Network","funders":"","keywords":"Qualitative research; Psychology; Medical education; Medicine; Sociology; Social science","score_opus":0.8162214891387137,"score_gpt":0.730245568857723,"score_spread":0.08597592028099077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2523068226","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34667382,0.0008931069,0.00078546203,0.6230206,0.00079763,0.00042150164,0.0000067652013,0.000009818151,0.027391324],"genre_scores_gemma":[0.98115474,0.00065166317,0.000009606337,0.00092081877,0.00023067351,0.000019275503,2.1492866e-7,0.0000034067962,0.017009608],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99267775,0.0021840215,0.0007393028,0.00019446669,0.0039695944,0.0002348495],"domain_scores_gemma":[0.9708416,0.027946476,0.0002462235,0.00057538506,0.00032706797,0.000063256804],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.051103782,0.00006148816,0.00015639042,0.00008910789,0.00028979854,0.000011118129,0.0013650872,0.0000732519,0.00093957264],"category_scores_gemma":[0.033258535,0.000016213611,0.000036874066,0.0008527937,0.001242011,0.0001801196,0.00012556517,0.0004180666,0.000148216],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007645424,0.000005028876,0.004667799,0.0000036729464,0.00001816149,2.2708461e-7,0.07605249,0.0000017466195,0.016411625,0.17204997,0.46479496,0.26591787],"study_design_scores_gemma":[0.0009067869,0.0002358086,0.038926117,0.00022954318,0.000008218938,0.0000030027804,0.08250337,0.00010852318,0.005210175,0.27327466,0.59852815,0.00006563766],"about_ca_topic_score_codex":0.000011519541,"about_ca_topic_score_gemma":0.000011438041,"teacher_disagreement_score":0.63448095,"about_ca_system_score_codex":0.000042527587,"about_ca_system_score_gemma":0.00021284781,"threshold_uncertainty_score":0.9999737},"labels":[],"label_agreement":null},{"id":"W2523734706","doi":"10.3138/cjpe.207","title":"L’étude d’évaluabilité : utilité et pertinence pour l’évaluation de programme","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Political science","score_opus":0.42773972430882595,"score_gpt":0.52477615985024,"score_spread":0.097036435541414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2523734706","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9543561,0.00036969795,0.016759222,0.023960596,0.000696046,0.0016074997,0.000009676367,0.000031506006,0.0022096948],"genre_scores_gemma":[0.9812846,0.000026225673,0.017405497,0.00050917995,0.00023529131,0.00018452173,0.000006085873,0.000019649522,0.00032891],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9916922,0.0020542957,0.0015267972,0.00039070993,0.0036763682,0.0006596354],"domain_scores_gemma":[0.99085265,0.0010185918,0.0010178129,0.00054059096,0.005703886,0.00086646376],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05709461,0.00021634795,0.00032161074,0.0007730405,0.00023786451,0.00048190178,0.0007778425,0.00014165422,0.0043397294],"category_scores_gemma":[0.021103842,0.00013405112,0.00024699076,0.00090395275,0.0001762252,0.0011829665,0.000024583374,0.00023805181,0.00023523692],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026427773,0.000062616935,0.09455938,0.0000035949565,0.00002257299,0.000004378011,0.0018902178,0.00043608787,0.0008905025,0.00074349064,0.0012601895,0.9001005],"study_design_scores_gemma":[0.0031872771,0.0012137297,0.7899452,0.00021220124,0.00017407497,0.00018216955,0.0018697662,0.054465503,0.0011177043,0.08929368,0.057940476,0.00039825405],"about_ca_topic_score_codex":0.0005371649,"about_ca_topic_score_gemma":0.014728337,"teacher_disagreement_score":0.8997023,"about_ca_system_score_codex":0.0009470432,"about_ca_system_score_gemma":0.015905267,"threshold_uncertainty_score":0.99657047},"labels":[],"label_agreement":null},{"id":"W2524551678","doi":"","title":"THE STANDARDIZED TESTING MOVEMENT: EQUITABLE OR EXCESSIVE?","year":2003,"lang":"en","type":"article","venue":"McGill Journal of Education / Revue des sciences de l'éducation de McGill","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Humanities; Legitimacy; Political science; Philosophy; Politics; History; Law","score_opus":0.6006801436383168,"score_gpt":0.5533757529947877,"score_spread":0.04730439064352909,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2524551678","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6267589,0.0021440363,0.016701011,0.017636763,0.014158918,0.0011320112,0.00007338986,0.000076319,0.32131872],"genre_scores_gemma":[0.93424237,0.00036179437,0.050460026,0.002886525,0.00026474558,0.000048484035,0.0000012959258,0.000019366184,0.011715416],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9946625,0.0010787605,0.0014857291,0.00036655675,0.0017880215,0.0006184164],"domain_scores_gemma":[0.99080944,0.0031560683,0.0018623858,0.0004588363,0.003395205,0.00031806872],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.027458237,0.00019936897,0.00030546275,0.0005081816,0.004383992,0.000643018,0.001284774,0.000072144445,0.0011033615],"category_scores_gemma":[0.025412507,0.00012118982,0.00014700386,0.0026680934,0.00050428504,0.0015399528,0.00006622697,0.00026347616,0.00006184585],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003464793,0.0016426543,0.038052313,0.00012906612,0.00014512283,0.000014721073,0.009372438,0.03430199,0.008680957,0.297279,0.06773154,0.54230374],"study_design_scores_gemma":[0.0008464541,0.0007651277,0.009549249,0.00028021287,0.000070171656,0.0007970765,0.03186158,0.0048539327,0.006068015,0.25099134,0.6935078,0.00040901525],"about_ca_topic_score_codex":0.00003417951,"about_ca_topic_score_gemma":0.00014268691,"teacher_disagreement_score":0.6257763,"about_ca_system_score_codex":0.0015422439,"about_ca_system_score_gemma":0.0043758354,"threshold_uncertainty_score":0.99980974},"labels":[],"label_agreement":null},{"id":"W2525451845","doi":"","title":"Évaluation de l’efficacité des systèmes d’assurance qualité des collèges québécois : orientations et cadre de référence","year":2013,"lang":"fr","type":"article","venue":"Bibliothèque et Archives nationales du Québec (Québec government)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Business","score_opus":0.05910149409475992,"score_gpt":0.3503991417044509,"score_spread":0.291297647609691,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2525451845","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88297415,0.010556437,0.0373316,0.040502768,0.0003143525,0.0010222568,0.00023761774,0.00013337274,0.026927425],"genre_scores_gemma":[0.9127066,0.0048976354,0.017603964,0.0033221177,0.00023711374,0.0008464709,0.000030508983,0.00007057681,0.060285013],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99038494,0.002477724,0.001641599,0.0009782419,0.0035519786,0.00096553133],"domain_scores_gemma":[0.96440506,0.03250934,0.0009992634,0.00070726505,0.0008044315,0.00057460926],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0052443147,0.0006293731,0.00059893465,0.0011319709,0.0011951431,0.0019687884,0.001347822,0.00017542804,0.01460028],"category_scores_gemma":[0.0205139,0.00059941097,0.0003908524,0.0026813971,0.0014877081,0.0038070153,0.0003497355,0.00051884894,0.0015730703],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000151256,0.0010713835,0.73823977,0.00038777266,0.00029468682,0.000011773897,0.09253401,0.025197344,0.0048324997,0.046613894,0.04204852,0.04861707],"study_design_scores_gemma":[0.001193117,0.00024490865,0.8998943,0.0005528651,0.00011028631,0.00008835603,0.006545473,0.038387027,0.0012018748,0.02221202,0.028909545,0.0006602416],"about_ca_topic_score_codex":0.49863252,"about_ca_topic_score_gemma":0.96945816,"teacher_disagreement_score":0.47082567,"about_ca_system_score_codex":0.00847107,"about_ca_system_score_gemma":0.11616132,"threshold_uncertainty_score":0.9996457},"labels":[],"label_agreement":null},{"id":"W2527468053","doi":"10.56645/jmde.v2i2.131","title":"An Update on Evaluation in Canada","year":2005,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Psychology","score_opus":0.19928177835078514,"score_gpt":0.5200236305055952,"score_spread":0.32074185215481005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2527468053","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9900646,0.0001438624,0.00033647218,0.006594589,0.0008240904,0.00045332522,0.000004663811,0.0000035369533,0.0015748331],"genre_scores_gemma":[0.9976199,0.00002804698,0.001601378,0.0002949967,0.0003710942,0.000018547342,0.000016158085,0.000009661601,0.00004019902],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98746514,0.001742262,0.0016770656,0.0002983282,0.008595182,0.00022200536],"domain_scores_gemma":[0.9950003,0.00052284193,0.0011671494,0.00046875997,0.0026793752,0.00016156488],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.038977165,0.00015470931,0.00030001253,0.0006601571,0.00013613398,0.000102857,0.0005614682,0.00005729958,0.0032481744],"category_scores_gemma":[0.0016544543,0.00011270343,0.000082023034,0.0006610126,0.000021285769,0.0016513354,0.000036487072,0.00028795394,0.00012947542],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015249154,0.00014623484,0.038615786,0.0000010099876,0.000006978877,0.0000024870785,0.000752893,0.5586497,0.00040791946,0.00005270478,0.001234282,0.39997748],"study_design_scores_gemma":[0.0015289213,0.00021704397,0.39366388,0.000025517968,0.000026385986,0.000010073101,0.0014377781,0.5999073,0.00037465367,0.002061993,0.000656168,0.0000902962],"about_ca_topic_score_codex":0.0069668232,"about_ca_topic_score_gemma":0.56667966,"teacher_disagreement_score":0.5597128,"about_ca_system_score_codex":0.002849146,"about_ca_system_score_gemma":0.0073863408,"threshold_uncertainty_score":0.9996459},"labels":[],"label_agreement":null},{"id":"W2529497696","doi":"10.1177/160940690700600203","title":"Book Review: How to do a Research Project: A Guide for Undergraduate Students, by Colin Robson. Oxford, UK: Blackwell, 2007","year":2007,"lang":"en","type":"article","venue":"International Journal of Qualitative Methods","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Library science; Sociology; Media studies; Computer science","score_opus":0.7623579334947574,"score_gpt":0.7761237534126141,"score_spread":0.013765819917856637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2529497696","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00081708666,0.039109718,0.89098674,0.06354993,0.0014932385,0.0012016525,0.00007724139,0.00000747141,0.002756901],"genre_scores_gemma":[0.0018599875,0.02191835,0.8304277,0.03965654,0.0011354248,0.00015527982,0.000022966375,0.000048647173,0.104775086],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98022926,0.0075377137,0.0025218227,0.0004927791,0.008693976,0.0005244285],"domain_scores_gemma":[0.9645326,0.019929761,0.001401875,0.00033720268,0.013518871,0.00027966718],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.22294247,0.00021125056,0.00058420264,0.0012484738,0.00017267447,0.00057005486,0.002303518,0.00007591543,0.001053921],"category_scores_gemma":[0.038411144,0.00015001859,0.0003335917,0.001050309,0.00016877124,0.00069279864,0.00025732923,0.0004726184,0.000050577342],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004181473,0.00014949568,0.000196476,0.0000200397,0.0001892147,0.000008324642,0.005973277,0.000021926619,0.0005714079,0.001527787,0.9485228,0.04240111],"study_design_scores_gemma":[0.0011378829,0.00072321214,0.00029270563,0.00048276866,0.000024827641,0.0000235754,0.011879641,0.0001364616,0.0014532144,0.013982586,0.96969134,0.00017176043],"about_ca_topic_score_codex":0.000019379984,"about_ca_topic_score_gemma":0.000019796751,"teacher_disagreement_score":0.18453133,"about_ca_system_score_codex":0.00058266445,"about_ca_system_score_gemma":0.0007911438,"threshold_uncertainty_score":0.9998593},"labels":[],"label_agreement":null},{"id":"W2540424390","doi":"10.1057/978-1-137-40523-4_7","title":"Action Research in the Canadian Context","year":2016,"lang":"en","type":"book-chapter","venue":"Palgrave Macmillan US eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Nipissing University","funders":"","keywords":"Contextualization; Scholarship; Context (archaeology); Action (physics); Function (biology); Action research; Political science; Vanguard; Sociology; Public relations; Geography; Interpretation (philosophy); Computer science; Law; Pedagogy","score_opus":0.3787559937240198,"score_gpt":0.4819089544770406,"score_spread":0.10315296075302077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2540424390","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004751698,0.0001678133,0.000009178154,0.0025818148,0.000509097,0.0007487714,0.000070281756,0.000014315676,0.99542356],"genre_scores_gemma":[0.8154515,0.000053647782,0.00000990118,0.0012689522,0.0003320378,0.00005076518,0.000012052429,0.00002583237,0.1827953],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99369544,0.0005569775,0.0007535861,0.0006354093,0.0037653227,0.0005932893],"domain_scores_gemma":[0.99585724,0.0016350235,0.000248095,0.0012415904,0.00077524397,0.00024277931],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.012613884,0.00028368327,0.00036444518,0.0014811809,0.0005504603,0.00044843063,0.0013691258,0.00037885984,0.0040636747],"category_scores_gemma":[0.00027069752,0.0001548787,0.0001608992,0.00009538673,0.00035212445,0.000007933857,0.00010419895,0.000855979,0.004644563],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016736341,4.5217143e-7,0.00059329794,0.00000423252,0.0000122807305,0.000031007025,0.0007272544,5.886453e-7,0.00000756848,0.70882857,0.0016572099,0.28812078],"study_design_scores_gemma":[0.00020933984,0.000054309825,0.0026605441,0.000070962065,0.000004769625,0.0000122642405,0.00028876893,0.000031862717,0.0000124850485,0.58637476,0.41011703,0.00016288534],"about_ca_topic_score_codex":0.019548047,"about_ca_topic_score_gemma":0.8145399,"teacher_disagreement_score":0.81497633,"about_ca_system_score_codex":0.00058578775,"about_ca_system_score_gemma":0.0017026246,"threshold_uncertainty_score":0.99684674},"labels":[],"label_agreement":null},{"id":"W2540625698","doi":"10.7202/1036904ar","title":"Durand, M.-J. et Loye, N. (2015). L’instrumentation pour l’évaluation : la boîte à outils de l’enseignant évaluateur. Montréal, Québec : Marcel Didier","year":2016,"lang":"fr","type":"article","venue":"Revue des sciences de l éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Valuation (finance); Economics","score_opus":0.46292064490149437,"score_gpt":0.5115384617199273,"score_spread":0.04861781681843297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2540625698","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8023561,0.0048378734,0.06224605,0.10785929,0.0023330704,0.000749701,0.00004725789,0.000074405674,0.019496232],"genre_scores_gemma":[0.9330413,0.007714149,0.015559525,0.0011083597,0.00034102902,0.00014022626,0.00001777108,0.000031463216,0.042046193],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99182415,0.0031346555,0.0012113245,0.0009701192,0.0019417311,0.0009180461],"domain_scores_gemma":[0.99509543,0.002202801,0.0008108922,0.00062845193,0.0008998667,0.00036255532],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.025525033,0.00038621738,0.00039429349,0.0005403865,0.0012447045,0.0008944728,0.0008259712,0.0002463489,0.0036070964],"category_scores_gemma":[0.0031483832,0.00028596687,0.00021326932,0.0013182756,0.0014756473,0.002893919,0.0001260788,0.00022357673,0.0020884937],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008082818,0.0004665881,0.04662578,0.00011316495,0.000043971508,0.000007333666,0.04805135,0.00456027,0.012332299,0.015949594,0.024118666,0.8476502],"study_design_scores_gemma":[0.0033679444,0.0009627016,0.4481252,0.0018852142,0.0003268233,0.0005664686,0.02356057,0.2372476,0.005633694,0.120430715,0.15657637,0.0013166976],"about_ca_topic_score_codex":0.007634176,"about_ca_topic_score_gemma":0.017179392,"teacher_disagreement_score":0.84633344,"about_ca_system_score_codex":0.002845417,"about_ca_system_score_gemma":0.010501015,"threshold_uncertainty_score":0.99995923},"labels":[],"label_agreement":null},{"id":"W2541009371","doi":"","title":"Finding the right frame: What is the problem represented to be in a national tuberculosis strategy","year":2015,"lang":"en","type":"article","venue":"Global Health: Annual Review","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McMaster University","funders":"","keywords":"Framing (construction); Tuberculosis; Population; Public health; Political science; Agency (philosophy); Social issues; Economic growth; Medicine; Sociology; Environmental health; Law; Geography; Economics; Social science","score_opus":0.29057467607282034,"score_gpt":0.5704808608183355,"score_spread":0.27990618474551515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2541009371","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0051043723,0.10384919,0.00015464437,0.86404973,0.00046726866,0.0026951535,0.0001982174,0.000028520382,0.02345291],"genre_scores_gemma":[0.22798528,0.1309994,0.0013854073,0.63554764,0.00039415693,0.0007647146,0.00007035927,0.000021945445,0.0028310888],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99347436,0.0011558058,0.0011548948,0.000463833,0.0033485433,0.00040258036],"domain_scores_gemma":[0.99704874,0.0005946849,0.00033732803,0.00058486883,0.0011502893,0.00028407082],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01848495,0.00016412853,0.00038326965,0.00006812213,0.00027298572,0.00039039328,0.0009135367,0.000054794826,0.0007881332],"category_scores_gemma":[0.0015163943,0.00007702657,0.000113710994,0.0024507642,0.0000612428,0.00085177,0.0001877198,0.00023667223,0.00089254125],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016254979,0.000050477847,0.0012220794,0.00009805706,0.000010612413,0.0000010078306,0.0027003586,0.00025886772,8.0476305e-8,0.01272678,0.6843293,0.29858613],"study_design_scores_gemma":[0.00020564339,0.00013388509,0.0053765927,0.0010973158,0.00000715282,0.000016212056,0.004498429,0.0007709141,7.6130505e-7,0.020400679,0.96738136,0.00011103111],"about_ca_topic_score_codex":0.00046926615,"about_ca_topic_score_gemma":0.0015122632,"teacher_disagreement_score":0.2984751,"about_ca_system_score_codex":0.00057239446,"about_ca_system_score_gemma":0.0019219893,"threshold_uncertainty_score":0.9998854},"labels":[],"label_agreement":null},{"id":"W2546479954","doi":"10.15353/cjds.v5i3.295","title":"Stories of Methodology: Interviewing Sideways, Crooked and Crip","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Disability Studies","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":87,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Interdependence; Interview; Argument (complex analysis); Focus (optics); Gaze; Qualitative research; Sociology; Disability studies; Psychology; Epistemology; Computer science; Gender studies; Social science; Psychoanalysis; Medicine","score_opus":0.7243396936077868,"score_gpt":0.5843992306938741,"score_spread":0.1399404629139127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2546479954","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9763858,0.004314663,0.0007111882,0.017379269,0.00076080224,0.00006417534,0.0000143609905,0.000001806528,0.00036795807],"genre_scores_gemma":[0.9977838,0.00018862038,0.0016165777,0.00015649472,0.00006693332,0.0000015803417,5.2443074e-8,0.00000301557,0.00018295832],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9977517,0.0005998949,0.00088713266,0.0001491316,0.00044710818,0.00016502215],"domain_scores_gemma":[0.9941977,0.003709642,0.00043939814,0.0002455069,0.0011809713,0.00022672894],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009605523,0.0000907321,0.00048042898,0.00014986112,0.00013839183,0.000036014735,0.00028562898,0.000032982854,0.0003351933],"category_scores_gemma":[0.020585304,0.000046758425,0.000104311905,0.00019593192,0.0011563768,0.00037623488,0.000046517067,0.00007602374,0.00000480456],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022805503,0.000012078999,0.8529197,0.0000251283,0.00011586654,0.0000024483002,0.012957226,0.0000052846194,0.00025563574,0.0016163898,0.003624258,0.1284432],"study_design_scores_gemma":[0.00070591236,0.00043006282,0.81129485,0.00023706512,0.00007118478,0.000026776437,0.0785202,0.000010147544,0.0012687102,0.07990351,0.027372308,0.00015929074],"about_ca_topic_score_codex":0.0006479167,"about_ca_topic_score_gemma":0.06542935,"teacher_disagreement_score":0.1282839,"about_ca_system_score_codex":0.00021718514,"about_ca_system_score_gemma":0.00048130966,"threshold_uncertainty_score":0.9876647},"labels":[],"label_agreement":null},{"id":"W2547939750","doi":"10.5751/es-00422-0602r07","title":"Priorities for Priorities: Where to Locate the First FLONAs?","year":2002,"lang":"en","type":"article","venue":"Conservation Ecology","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Environmental resource management; Geography; Environmental planning; Environmental science","score_opus":0.2778708268363284,"score_gpt":0.4299709037528654,"score_spread":0.15210007691653699,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2547939750","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.56117153,0.0002750924,0.008357066,0.4187404,0.0022634289,0.0016158557,0.000029696703,0.00008351001,0.0074633984],"genre_scores_gemma":[0.9179645,0.000087733606,0.0015271186,0.038693305,0.00026037166,0.0005477545,0.000004426127,0.000013668736,0.040901083],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99831504,0.00011423794,0.000546798,0.00029050998,0.00048122086,0.000252197],"domain_scores_gemma":[0.9958547,0.0027364204,0.00017264888,0.0004314812,0.00074433105,0.000060415572],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0020295696,0.00010940204,0.00019249145,0.00013906833,0.0005284536,0.0001921714,0.0005151833,0.000081277154,0.004492651],"category_scores_gemma":[0.0018364615,0.000074587515,0.000067341076,0.00042812902,0.0001158122,0.0003002629,0.00007244756,0.00008089529,0.0013233628],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039628256,0.000041972962,0.27976677,0.000021080281,0.000021762597,8.4479484e-7,0.0035541626,0.00071636424,0.000032291973,0.019450996,0.6685512,0.027802905],"study_design_scores_gemma":[0.00035682216,0.00014522646,0.2138999,0.0000059908602,0.000006445723,0.000003092079,0.0008868998,0.0264086,0.000031545103,0.0044023143,0.7537624,0.0000907762],"about_ca_topic_score_codex":0.000022350285,"about_ca_topic_score_gemma":0.0042259735,"teacher_disagreement_score":0.38004708,"about_ca_system_score_codex":0.00007604286,"about_ca_system_score_gemma":0.00014162641,"threshold_uncertainty_score":0.9994542},"labels":[],"label_agreement":null},{"id":"W2547943964","doi":"","title":"Making sense, discovering what works… Cross-agency collaboration in Child Welfare and Protection in Norway and Quebec","year":2016,"lang":"en","type":"article","venue":"BIBSYS Brage (BIBSYS (Norway))","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Agency (philosophy); Scope (computer science); Public relations; Welfare; Set (abstract data type); Child protection; Political science; Sociology; Business; Knowledge management; Law; Computer science; Social science","score_opus":0.08398374794122555,"score_gpt":0.4185410092362026,"score_spread":0.33455726129497704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2547943964","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.986059,0.0010578046,0.0030089088,0.0056682965,0.00064637995,0.0011433703,0.00002218816,0.000034547607,0.0023594697],"genre_scores_gemma":[0.9967739,0.00089969777,0.0002642445,0.00016827421,0.0001401047,0.00014357718,0.0000053213803,0.000028108283,0.0015767863],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.995817,0.00045270016,0.0010984112,0.000946782,0.0011968602,0.00048823055],"domain_scores_gemma":[0.9982909,0.00034382072,0.0004239258,0.0005502145,0.00026021633,0.00013095583],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0034383505,0.00033225777,0.00043435793,0.0012324599,0.00048858294,0.002729766,0.0002590736,0.00022704131,0.0011283502],"category_scores_gemma":[0.0007941911,0.00023668085,0.00005632364,0.0025179235,0.0001595947,0.0073584025,0.00023295697,0.0002865388,0.00017262789],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003160944,0.00015639045,0.15387546,0.00010402441,0.0000188698,0.000066718596,0.006380918,0.0011426044,0.006172018,0.0015588749,0.00011155176,0.8300965],"study_design_scores_gemma":[0.0024199341,0.00012479156,0.97814506,0.0015376142,0.000008446034,0.000050334562,0.0044097216,0.0052216365,0.00052113173,0.0011107498,0.005936254,0.0005143141],"about_ca_topic_score_codex":0.0006512403,"about_ca_topic_score_gemma":0.05298927,"teacher_disagreement_score":0.82958215,"about_ca_system_score_codex":0.000301312,"about_ca_system_score_gemma":0.00013230773,"threshold_uncertainty_score":0.99978477},"labels":[],"label_agreement":null},{"id":"W2548281546","doi":"10.55016/ojs/ajer.v47i2.54860","title":"The Art of Evaluation. A Handbook for Educators and Trainers by Tara Fenwick and Jim Parsons","year":2001,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Sociology; Gerontology; Medicine","score_opus":0.3379541857309786,"score_gpt":0.5962496267436449,"score_spread":0.2582954410126663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2548281546","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81895727,0.006875079,0.00008987958,0.15899329,0.0003633859,0.0005707847,0.000008286199,2.261379e-7,0.014141779],"genre_scores_gemma":[0.87220496,0.0018834429,0.00056268217,0.0002884606,0.00026610174,0.00008411601,0.000009006972,0.000009767243,0.12469144],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9963563,0.00035706247,0.0006525728,0.00017037055,0.0022388913,0.00022476536],"domain_scores_gemma":[0.9626865,0.03389008,0.00032810133,0.0001886825,0.0027172354,0.00018941407],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0133067295,0.000075848104,0.00016423475,0.00029785934,0.00043595702,0.00020689353,0.00031286047,0.0000371087,0.0035546247],"category_scores_gemma":[0.022689123,0.000045200177,0.00006232632,0.00045201185,0.00036998163,0.00034308477,0.00003629211,0.00017997679,0.000031286254],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018870001,0.0001855512,0.052384097,0.000007884093,0.00006106731,4.7254748e-8,0.0018921655,0.00003544696,0.00039931794,0.006584885,0.9161044,0.022156486],"study_design_scores_gemma":[0.0012993566,0.0005232175,0.06466159,0.00007269111,0.000042881853,0.000100124635,0.006358196,0.0031965221,0.000257515,0.040843513,0.8825291,0.000115328716],"about_ca_topic_score_codex":0.000051823878,"about_ca_topic_score_gemma":0.00041377416,"teacher_disagreement_score":0.15870483,"about_ca_system_score_codex":0.00007449578,"about_ca_system_score_gemma":0.0022562242,"threshold_uncertainty_score":0.99735624},"labels":[],"label_agreement":null},{"id":"W2548378115","doi":"10.1177/0739456x16675930","title":"Evaluation Theory and Practice: Comparing Program Evaluation and Evaluation in Planning","year":2016,"lang":"en","type":"article","venue":"Journal of Planning Education and Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":123,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Program evaluation; Evaluation methods; Outcome (game theory); Management science; Impact evaluation; Theory of change; Process management; Political science; Computer science; Business; Engineering; Public administration; Economics; Management; Medicine","score_opus":0.6508698838348513,"score_gpt":0.7143752125896877,"score_spread":0.06350532875483639,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2548378115","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9829497,0.0057807467,0.00032172128,0.004335065,0.00038074618,0.0010308856,4.8173763e-7,0.0000050340855,0.005195671],"genre_scores_gemma":[0.99803954,0.00021444469,0.0012362617,0.00006585731,0.00018413704,0.00010862611,0.000002765039,0.0000066835787,0.00014169532],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9835698,0.0083188005,0.00088595203,0.0003343568,0.0066417623,0.0002493528],"domain_scores_gemma":[0.9860083,0.0064497446,0.00055831217,0.00017688291,0.0066514057,0.00015534184],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.22706836,0.0001001195,0.00020668717,0.001244786,0.00026476724,0.0004352937,0.00016092551,0.0000825408,0.0002052202],"category_scores_gemma":[0.039628644,0.00006119938,0.000021606378,0.0005898369,0.0001543567,0.0014192282,0.00006866404,0.00032865093,0.000006344019],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022550565,0.00016298186,0.09130771,0.000008905349,0.000018587827,7.379317e-7,0.008856738,0.0004814627,0.0005880463,0.00053747377,0.0009843089,0.8968275],"study_design_scores_gemma":[0.002702998,0.00047274114,0.8192401,0.000729217,0.00010926336,0.00017923406,0.032785743,0.09441547,0.00008058509,0.040552523,0.008591017,0.00014110803],"about_ca_topic_score_codex":0.00000939084,"about_ca_topic_score_gemma":0.000008265448,"teacher_disagreement_score":0.89668643,"about_ca_system_score_codex":0.00031293035,"about_ca_system_score_gemma":0.0022213173,"threshold_uncertainty_score":0.968461},"labels":[],"label_agreement":null},{"id":"W2548483712","doi":"10.12927/hcq.2016.24866","title":"Evaluating Innovations in Home Care for Performance Accountability","year":2016,"lang":"en","type":"article","venue":"Healthcare Quarterly","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Alberta Health Services","funders":"","keywords":"Accountability; Service delivery framework; Sustainability; Business; Health care; Service (business); Healthcare service; Process management; Performance measurement; Best practice; Public relations; Nursing; Medicine; Marketing; Political science; Economic growth; Management; Economics","score_opus":0.2958161199956969,"score_gpt":0.5538304110776189,"score_spread":0.258014291081922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2548483712","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.983832,0.00010182239,0.0021762343,0.011856424,0.0006009714,0.00090126984,0.00006551992,0.000042763942,0.00042299242],"genre_scores_gemma":[0.9968065,0.000009522917,0.0017760624,0.0006188077,0.0001405642,0.00037345843,0.0000150877295,0.0000119522365,0.00024801615],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9963364,0.0002777112,0.0011199109,0.0005452658,0.0013032955,0.000417444],"domain_scores_gemma":[0.995816,0.0012029759,0.00028575608,0.0006873459,0.0019121579,0.00009579157],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0060050697,0.00014796617,0.00028520677,0.00038081742,0.0002813008,0.00010504798,0.00041595942,0.000097247124,0.00039122056],"category_scores_gemma":[0.00053579384,0.00009352995,0.00006993052,0.00096613535,0.00005657658,0.00085683324,0.000019130885,0.0001185097,0.00022388103],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004776455,0.000021696427,0.19962458,0.00004880676,0.0000014985461,1.0666108e-7,0.0049845595,0.0000117134,0.000190457,0.0013930796,0.00014029827,0.7935354],"study_design_scores_gemma":[0.0021073034,0.0021971746,0.9540961,0.00016766181,0.000004208084,0.0000027843141,0.012438684,0.004785074,0.00012947664,0.011887964,0.011878949,0.00030464662],"about_ca_topic_score_codex":0.000119939556,"about_ca_topic_score_gemma":0.0027205383,"teacher_disagreement_score":0.7932308,"about_ca_system_score_codex":0.00038150075,"about_ca_system_score_gemma":0.0009776319,"threshold_uncertainty_score":0.4283591},"labels":[],"label_agreement":null},{"id":"W2549653386","doi":"","title":"Pushing the Boundaries: Examining the Role of Advisory Committees in Fringe Planning, A Kelowna Case Study","year":2011,"lang":"en","type":"article","venue":"QSpace (Queen's University Library)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.09848480932020795,"score_gpt":0.322070014489053,"score_spread":0.22358520516884503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2549653386","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.962011,0.00002837558,0.00008159034,0.0054081813,0.00009749616,0.00038205925,0.0000066794796,0.000044804165,0.031939846],"genre_scores_gemma":[0.99287003,0.000008703294,0.00033250096,0.00017738168,0.000018448975,0.0000022955064,0.000001442924,0.000010218033,0.006579005],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99748534,0.00085419766,0.0003180319,0.00031777006,0.0007813691,0.0002433041],"domain_scores_gemma":[0.9975415,0.001278948,0.00030938373,0.00071866583,0.00007954677,0.000071975985],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015449177,0.00015552425,0.00023650487,0.00033922022,0.0007347987,0.00028918462,0.001172883,0.000058706562,0.0014392898],"category_scores_gemma":[0.00021494583,0.00009633496,0.00006767708,0.0009812909,0.00031072204,0.0018214949,0.0005807853,0.00034479983,0.000046539313],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006155268,0.00014533948,0.8818059,0.000002571755,0.000029098097,0.00029645138,0.10285314,0.00008215636,0.0000017047173,0.0028034917,0.01082035,0.0010982527],"study_design_scores_gemma":[0.00046384873,0.00022995475,0.23862293,0.000035458015,0.00002309207,0.0000041682856,0.6646866,0.00031423103,0.00020620463,0.0013600856,0.09388977,0.00016364917],"about_ca_topic_score_codex":0.009749405,"about_ca_topic_score_gemma":0.00069662434,"teacher_disagreement_score":0.64318293,"about_ca_system_score_codex":0.000036977133,"about_ca_system_score_gemma":0.00031890586,"threshold_uncertainty_score":0.9994735},"labels":[],"label_agreement":null},{"id":"W2553028960","doi":"10.1111/capa.12195","title":"A developing context: Evaluation and FedNor's evolving institutional context","year":2016,"lang":"en","type":"article","venue":"Canadian Public Administration","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mandate; Context (archaeology); Political science; Public administration; Environmental planning; Regional science; Environmental resource management; Geography; Economics; Law","score_opus":0.25343218592313804,"score_gpt":0.4492039141471447,"score_spread":0.19577172822400668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2553028960","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.63986593,0.00038489536,0.038527537,0.30206487,0.0011044567,0.0009354685,0.000086992004,0.000055434473,0.016974406],"genre_scores_gemma":[0.99661666,0.000010321579,0.00041711205,0.001879028,0.00011557642,0.000061315084,0.000038975944,0.0000061295373,0.0008548977],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99730355,0.00021702418,0.0005302754,0.00039506677,0.0012639759,0.0002900897],"domain_scores_gemma":[0.99724156,0.0003691192,0.00019396341,0.00026498444,0.0014853701,0.0004450226],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0044420217,0.00012665517,0.00014250448,0.0004474937,0.0005669771,0.00066430634,0.00023493059,0.000095450945,0.003261859],"category_scores_gemma":[0.004840291,0.000089348854,0.000034127235,0.00041723033,0.00014851456,0.001771041,0.00002339039,0.000066052984,0.00027995996],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005614337,0.0000060737507,0.021850433,0.0000016681321,0.000008538948,0.000002181897,0.00010598845,3.9624302e-7,0.000059550337,0.36203778,0.0031881966,0.6127336],"study_design_scores_gemma":[0.0014448249,0.00013129984,0.15929401,0.00006662474,0.000015559954,0.00006743334,0.0017177345,0.009809198,0.00027161886,0.02408969,0.8027184,0.0003736083],"about_ca_topic_score_codex":0.0005096507,"about_ca_topic_score_gemma":0.41820148,"teacher_disagreement_score":0.7995302,"about_ca_system_score_codex":0.0008904504,"about_ca_system_score_gemma":0.013359226,"threshold_uncertainty_score":0.9976493},"labels":[],"label_agreement":null},{"id":"W2553254625","doi":"10.56645/jmde.v12i27.454","title":"Debate on the Appropriate Methods for Conducting Impact Evaluation of Programs within the Development Context","year":2016,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Impact evaluation; Context (archaeology); Program evaluation; Computer science; Management science; Intervention (counseling); Impact assessment; Process management; Evaluation methods; Risk analysis (engineering); Psychology; Political science; Business; Engineering; Medicine","score_opus":0.6229679264758866,"score_gpt":0.6137793347535752,"score_spread":0.009188591722311457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2553254625","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9423179,0.00017759087,0.048267674,0.005905836,0.00090082665,0.0021947178,0.0000030839917,0.0000056180625,0.000226741],"genre_scores_gemma":[0.98133403,0.0000060917682,0.018143686,0.00004163829,0.00016110657,0.00019586844,0.0000036878334,0.000013808723,0.000100053716],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9867742,0.00504862,0.0022749947,0.0002908922,0.005380057,0.00023124058],"domain_scores_gemma":[0.98128766,0.0063530956,0.0037430755,0.00051294564,0.008023367,0.000079851045],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.19909209,0.00019636091,0.00036904853,0.0002604434,0.00049437507,0.00012657487,0.00071121927,0.00007742583,0.0004060477],"category_scores_gemma":[0.015513158,0.0000673592,0.00029359906,0.0004838099,0.00014337769,0.00063356216,0.000089848894,0.00018346816,0.000022909006],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038998207,0.00015418616,0.0026795752,0.0000048380143,0.00012454027,7.330209e-8,0.008254159,0.010419583,0.011445856,0.0003549402,0.00013155668,0.96604073],"study_design_scores_gemma":[0.0067610266,0.0019558806,0.07345316,0.00048636447,0.0005341875,0.00003306768,0.022764971,0.76465076,0.05936598,0.069183625,0.0005078907,0.00030307268],"about_ca_topic_score_codex":0.000002580683,"about_ca_topic_score_gemma":0.000032631557,"teacher_disagreement_score":0.96573764,"about_ca_system_score_codex":0.00049820496,"about_ca_system_score_gemma":0.002289622,"threshold_uncertainty_score":0.9927796},"labels":[],"label_agreement":null},{"id":"W2555346440","doi":"10.5130/pmrp.v3i0.5122","title":"Adopting Results Based Management in the Non-Profit Sector: Trócaire’s Experience","year":2016,"lang":"en","type":"article","venue":"Project Management Research and Practice","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact","funders":"","keywords":"Accountability; Profit (economics); Process (computing); Process management; Business; Quality (philosophy); Computer science; Political science; Economics","score_opus":0.5884840723353073,"score_gpt":0.6200703303048057,"score_spread":0.03158625796949843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2555346440","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041671805,0.0002097526,0.0061838813,0.06323436,0.00025473782,0.004153945,0.000011723473,0.000052377054,0.8842274],"genre_scores_gemma":[0.971936,0.0013623785,0.009931879,0.001351867,0.00007837922,0.0008009208,0.0000038069281,0.000011783004,0.014523013],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99154365,0.0021211784,0.0006578238,0.00078606623,0.0042453157,0.00064596185],"domain_scores_gemma":[0.98998004,0.008350326,0.00021584015,0.00095775304,0.00041433747,0.00008168288],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04548217,0.00016199189,0.00015725146,0.0008668022,0.00048296322,0.0008134652,0.0011469789,0.000043035783,0.00024151085],"category_scores_gemma":[0.0040275585,0.00007975863,0.00004051187,0.0022488309,0.00019177709,0.0014826861,0.0004904451,0.00028722157,0.00033352379],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026039367,0.00036839803,0.00447599,0.000096855045,0.00006274263,0.00026250049,0.007958304,0.000029811214,0.00008070563,0.019196384,0.04494197,0.9199224],"study_design_scores_gemma":[0.002647626,0.00045669664,0.027589723,0.00015002907,0.000014854796,0.000009570906,0.044719823,0.0021070153,0.00008439681,0.001621782,0.9203822,0.00021629581],"about_ca_topic_score_codex":0.0001502828,"about_ca_topic_score_gemma":0.00009292984,"teacher_disagreement_score":0.9302642,"about_ca_system_score_codex":0.00011720595,"about_ca_system_score_gemma":0.00009852988,"threshold_uncertainty_score":0.98287696},"labels":[],"label_agreement":null},{"id":"W2557668569","doi":"","title":"The History of Compliance, Non Compliance, and Alienation of Ontario Educators between 1969 and 1999","year":2013,"lang":"en","type":"dissertation","venue":"TSpace","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Compliance (psychology); Alienation; Psychology; Political science; Social psychology; Law","score_opus":0.21837629257988433,"score_gpt":0.4842583551483614,"score_spread":0.2658820625684771,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2557668569","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9174268,0.0016939667,0.00003414204,0.00022107185,0.0013566881,0.00042464343,0.0000066346724,0.0000063847187,0.07882962],"genre_scores_gemma":[0.6872158,0.00021108863,0.0003828984,0.000035005825,0.000050794162,0.000026557287,0.00008926473,0.0000121692465,0.3119764],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9977072,0.00008915495,0.00065403274,0.00031480647,0.0010873046,0.0001475022],"domain_scores_gemma":[0.99723935,0.00059368764,0.0010465563,0.000411677,0.00063090643,0.000077799894],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014177597,0.00017624955,0.0004340376,0.00019967175,0.00012034782,0.000057554716,0.0003423775,0.00012544465,0.00048694978],"category_scores_gemma":[0.0001409219,0.000120778575,0.000057438607,0.00018579334,0.00018843997,0.00017397529,0.000039520935,0.00020135118,0.000035063065],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002285181,0.00018324875,0.32749802,0.0007561189,0.00023180805,4.7508044e-7,0.16560858,0.00003721651,0.0018517268,0.003947564,0.23466335,0.26499334],"study_design_scores_gemma":[0.0003154318,0.00010172269,0.7681234,0.0002619608,0.000050114748,5.8805864e-7,0.008575515,0.0004217327,0.00028017364,0.00088459835,0.2208124,0.00017237321],"about_ca_topic_score_codex":0.012227853,"about_ca_topic_score_gemma":0.024395434,"teacher_disagreement_score":0.44062537,"about_ca_system_score_codex":0.00031887586,"about_ca_system_score_gemma":0.0013658393,"threshold_uncertainty_score":0.9943498},"labels":[],"label_agreement":null},{"id":"W2557681684","doi":"10.4102/aej.v4i1.178","title":"Evaluation involvement of local HIV/AIDS non-governmental organisations in Benin","year":2016,"lang":"en","type":"article","venue":"African Evaluation Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Civil society; Monitoring and evaluation; Human immunodeficiency virus (HIV); Task (project management); Political science; Public relations; Capacity building; Pandemic; Descriptive research; Business; Economic growth; Medicine; Sociology; Coronavirus disease 2019 (COVID-19); Politics; Management; Family medicine; Economics; Social science; Disease; Law","score_opus":0.1574875201533343,"score_gpt":0.4484900314840136,"score_spread":0.29100251133067934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2557681684","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8843382,0.00007684513,0.0963335,0.005268536,0.00062812975,0.0008097264,0.00002942975,0.000009938253,0.01250571],"genre_scores_gemma":[0.9975737,0.000024824929,0.0015535755,0.00012561488,0.0001682936,0.00006876065,0.00000896733,0.000013110988,0.0004631535],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9845324,0.0016631478,0.0016799539,0.00037886843,0.011447507,0.00029811857],"domain_scores_gemma":[0.9945516,0.00073384494,0.0010867203,0.00044730975,0.00300534,0.00017521459],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.045475107,0.00017784223,0.00030951292,0.00070278015,0.00018908817,0.00011982192,0.00053438294,0.000076174765,0.022234347],"category_scores_gemma":[0.0027490035,0.00011409951,0.00013017312,0.0011450333,0.0001608674,0.0010555125,0.00008802194,0.00017224827,0.00034393105],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000086676664,0.0002952973,0.09444159,0.0000027336932,0.00006751355,0.0000014243055,0.0045279195,0.0066241296,0.013586779,0.0017675635,0.004600854,0.8739975],"study_design_scores_gemma":[0.013498025,0.0011428645,0.5287915,0.00023588388,0.00036198104,0.000048556703,0.083026215,0.2842534,0.016250247,0.06690794,0.0048913322,0.0005920694],"about_ca_topic_score_codex":0.000017291713,"about_ca_topic_score_gemma":0.00018530477,"teacher_disagreement_score":0.87340546,"about_ca_system_score_codex":0.002790851,"about_ca_system_score_gemma":0.002429944,"threshold_uncertainty_score":0.9828842},"labels":[],"label_agreement":null},{"id":"W2559455505","doi":"10.1016/j.polsoc.2016.11.001","title":"The MPA/MPP in the Anglo-democracies: Australia, Canada, New Zealand, the United Kingdom, and the United States","year":2016,"lang":"en","type":"article","venue":"Policy and Society","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto; Carleton University","funders":"","keywords":"Convergence (economics); Diversity (politics); Scope (computer science); Kingdom; Political science; Sociology; Political economy; Law; Economics; Economic growth; Computer science","score_opus":0.17789108485329178,"score_gpt":0.4523342574007833,"score_spread":0.2744431725474915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2559455505","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7362828,0.00006118861,0.00003735263,0.26292574,0.0000748213,0.00022931743,0.00002493764,0.0000064520405,0.0003573708],"genre_scores_gemma":[0.96805704,0.0010544593,0.000013698371,0.017060706,0.00018479604,0.00001824908,0.0000060718403,0.0000048579445,0.0136001455],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.997588,0.0006554774,0.000352323,0.0001842553,0.00089725695,0.00032273435],"domain_scores_gemma":[0.99289435,0.0063021365,0.0001583567,0.0004340288,0.00013102949,0.00008009134],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0059544356,0.00013031371,0.00014012028,0.00004777104,0.0010037253,0.00042412558,0.00064119406,0.00005124473,0.00007937089],"category_scores_gemma":[0.0009070361,0.000036193076,0.00006693005,0.0011354057,0.00063699565,0.00013196247,0.000100215235,0.00020106121,0.000008398205],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000071452305,0.000020316009,0.031772383,0.0000043717096,0.00007646299,9.767251e-7,0.06887595,0.00022814832,0.00001638163,0.08991361,0.79612064,0.01289932],"study_design_scores_gemma":[0.0013130652,0.000024122755,0.13473676,0.000014118339,0.000014968355,0.0000063079424,0.017634204,0.0038467646,0.000010530996,0.039227106,0.80307186,0.00010019044],"about_ca_topic_score_codex":0.603558,"about_ca_topic_score_gemma":0.3134679,"teacher_disagreement_score":0.29009014,"about_ca_system_score_codex":0.00006369516,"about_ca_system_score_gemma":0.0004832526,"threshold_uncertainty_score":0.77199453},"labels":[],"label_agreement":null},{"id":"W2559640429","doi":"10.4300/jgme-d-16-00540.1","title":"Using Data From Program Evaluations for Qualitative Research","year":2016,"lang":"en","type":"article","venue":"Journal of Graduate Medical Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Wilson Centre; University of Toronto","funders":"","keywords":"Computer science; Qualitative research; Constructive; Flexibility (engineering); Data science; Qualitative property; Quality (philosophy); Research program; Management science; Process (computing); Epistemology; Sociology","score_opus":0.952474250576773,"score_gpt":0.8161911414528664,"score_spread":0.13628310912390662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2559640429","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69053316,0.00032462145,0.15337133,0.15055999,0.0035519553,0.0008492637,0.00007564368,0.000012606691,0.0007213973],"genre_scores_gemma":[0.9357293,0.00013291412,0.0611864,0.00047315416,0.001604817,0.000045037857,0.000044708922,0.000011834828,0.0007717832],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9899004,0.001835347,0.0011777866,0.0002691738,0.0066089807,0.00020831777],"domain_scores_gemma":[0.98296887,0.008663792,0.0007808179,0.0006498304,0.0065822965,0.000354378],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05893738,0.00007646662,0.00022192173,0.00043224246,0.00021831723,0.00015270626,0.0012346397,0.00007213275,0.0020697543],"category_scores_gemma":[0.09004665,0.000039427265,0.00007563989,0.0006511335,0.00021223298,0.0010099167,0.00011455844,0.00023820183,0.00010199798],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006764074,0.0005285211,0.0006425341,0.000003323374,0.000031327607,3.5036317e-7,0.0037572435,0.000004006332,0.00032781062,0.0012393255,0.12449016,0.86890775],"study_design_scores_gemma":[0.002861595,0.0010137104,0.015714051,0.0007538229,0.00011514249,0.000030469551,0.039343663,0.07441708,0.00044441284,0.6558953,0.20916077,0.00024997804],"about_ca_topic_score_codex":0.000046227164,"about_ca_topic_score_gemma":0.000057023513,"teacher_disagreement_score":0.86865777,"about_ca_system_score_codex":0.0001871106,"about_ca_system_score_gemma":0.009236262,"threshold_uncertainty_score":0.9988425},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"qualitative","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W2559869212","doi":"10.3138/cjpe.304","title":"Étude d’évaluabilité d’une intervention visant à prévenir l’usage de substances psychoactives lors de la transition primaire-secondaire","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Logbook; Psychology; Intervention (counseling); Medical education; Program evaluation; Logic model; Data collection; Pedagogy; Medicine; Political science; Sociology; Psychiatry","score_opus":0.13013536005876167,"score_gpt":0.47886784992876436,"score_spread":0.3487324898700027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2559869212","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9736783,0.0005173434,0.01900536,0.0038126907,0.0004773959,0.000788537,0.000013302783,0.000018134613,0.0016889614],"genre_scores_gemma":[0.9966599,0.000053155287,0.002756067,0.00014150969,0.00018122961,0.000106937216,0.000006229996,0.000016262627,0.0000787367],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99433494,0.0021139719,0.0011118692,0.000295911,0.0017343643,0.0004089709],"domain_scores_gemma":[0.99621356,0.0006419744,0.00083941926,0.00029237705,0.0015019217,0.00051073683],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.027809678,0.0001762921,0.00028408822,0.0006277158,0.00023183807,0.00037152084,0.00045488216,0.00014441044,0.0026111617],"category_scores_gemma":[0.0020191725,0.00011954152,0.00029207382,0.00068020116,0.0002898999,0.0013005509,0.000006777476,0.00022750086,0.000037552036],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008729866,0.00013256026,0.030518308,0.000011915529,0.000048782338,0.00000868099,0.007310072,0.00059639616,0.0013457905,0.00024964882,0.0006054279,0.9590851],"study_design_scores_gemma":[0.0035573274,0.0012258978,0.9081154,0.00047283087,0.00018097428,0.0001835168,0.0061498526,0.013718489,0.0025217028,0.051669747,0.01188294,0.00032133353],"about_ca_topic_score_codex":0.00042078967,"about_ca_topic_score_gemma":0.01833103,"teacher_disagreement_score":0.9587638,"about_ca_system_score_codex":0.001126812,"about_ca_system_score_gemma":0.0036858476,"threshold_uncertainty_score":0.9995819},"labels":[],"label_agreement":null},{"id":"W2559871496","doi":"10.3138/cjpe.263","title":"Evaluating System Change Initiatives: Advancing the Need for Adapting Evaluation Practices","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"PolicyWise for Children & Families; University of Alberta","funders":"","keywords":"Process management; Plan (archaeology); Context (archaeology); Strategic planning; Government (linguistics); Key (lock); Business; Outcome (game theory); Program evaluation; Monitoring and evaluation; Knowledge management; Political science; Management science; Computer science; Public administration; Engineering; Marketing; Economics; Computer security","score_opus":0.771827991309673,"score_gpt":0.6310206511420624,"score_spread":0.14080734016761054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2559871496","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89291674,0.0034419452,0.035508383,0.036229856,0.006170598,0.01954091,0.000058825706,0.00007173341,0.0060609863],"genre_scores_gemma":[0.98673975,0.000012826906,0.010465026,0.00026563153,0.0010327884,0.0013997878,0.000009128088,0.000021601392,0.00005343167],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9896707,0.0031312462,0.0016314887,0.00036126177,0.004688583,0.0005167065],"domain_scores_gemma":[0.9782064,0.0041848132,0.0048265983,0.00045317604,0.011952314,0.0003766958],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11777359,0.00020017252,0.00033205858,0.0006886445,0.00079448434,0.0005933375,0.00070499,0.00010020795,0.0007003974],"category_scores_gemma":[0.058747627,0.00010583737,0.00020604482,0.0008723181,0.00010815818,0.0031155285,0.000022248769,0.00018671843,0.000048773807],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046182624,0.000017396707,0.005813794,0.00001403642,0.000045780136,8.1560336e-7,0.002586119,0.00082785706,0.00028277075,0.0007842796,0.00044717462,0.9891338],"study_design_scores_gemma":[0.004080933,0.0016724253,0.042394914,0.000756664,0.0006563582,0.00008014601,0.027310919,0.89414895,0.00029774092,0.006125252,0.022146452,0.00032925082],"about_ca_topic_score_codex":0.00032122337,"about_ca_topic_score_gemma":0.009110141,"teacher_disagreement_score":0.9888045,"about_ca_system_score_codex":0.0014824657,"about_ca_system_score_gemma":0.0074361037,"threshold_uncertainty_score":0.9981908},"labels":[],"label_agreement":null},{"id":"W2560013324","doi":"10.3138/cjpe.339","title":"La production de la théorie du programme dans le cadre d’une évaluation participative : une étude de cas","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Process management; Business","score_opus":0.2661443501415783,"score_gpt":0.4849594687576983,"score_spread":0.21881511861612002,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2560013324","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95953166,0.00009904118,0.016410893,0.019077558,0.00046525925,0.0011531352,0.000005994387,0.000025717862,0.0032307405],"genre_scores_gemma":[0.995279,0.00002699596,0.0037281765,0.000079766156,0.0003691497,0.00028439763,0.000008018103,0.000019911078,0.00020457755],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9928341,0.003313486,0.0009616999,0.00031733868,0.0020514121,0.0005219711],"domain_scores_gemma":[0.99469936,0.00072386063,0.0008521174,0.00032733093,0.0027839208,0.00061342464],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.042368006,0.0001807821,0.00026071112,0.00048898713,0.0004045258,0.00041617698,0.00039976748,0.00016537598,0.00040889223],"category_scores_gemma":[0.010366895,0.00012357,0.00014219143,0.001208333,0.00035987466,0.0009754188,0.000015212237,0.00025468346,0.000040905972],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003905803,0.00012767258,0.137877,0.000004960563,0.000046801986,0.000017406142,0.013235081,0.003056702,0.001398433,0.00157955,0.0012727886,0.84134454],"study_design_scores_gemma":[0.0024948695,0.00088657177,0.8424893,0.00017335518,0.0002590237,0.0004205042,0.012264493,0.02425306,0.004261663,0.096190445,0.01597106,0.00033565192],"about_ca_topic_score_codex":0.003278734,"about_ca_topic_score_gemma":0.05796284,"teacher_disagreement_score":0.8410089,"about_ca_system_score_codex":0.0013806053,"about_ca_system_score_gemma":0.01202589,"threshold_uncertainty_score":0.9979692},"labels":[],"label_agreement":null},{"id":"W2560249367","doi":"10.3138/cjpe.31.2.262","title":"Kenneth Bush and Colleen Duggan (eds.). (2015). <i>Evaluation in the Extreme: Research, Impact and Politics in Violently Divided Societies</i> .","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Politics; Political science; Environmental ethics; Psychology; Criminology; Sociology; Law; Philosophy","score_opus":0.48133458098590837,"score_gpt":0.5657556512806122,"score_spread":0.08442107029470386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2560249367","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9800959,0.0036701285,0.00005146585,0.013566724,0.00018649615,0.0017012823,0.000015114736,0.0000028928348,0.000709996],"genre_scores_gemma":[0.9987014,0.0004472969,0.00028351677,0.00021410109,0.00013608928,0.00010518462,0.0000059176036,0.000009064906,0.00009743636],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9910818,0.0033295813,0.0009676086,0.00027533234,0.0038345759,0.0005111413],"domain_scores_gemma":[0.9946375,0.0014593217,0.0004018201,0.00030135902,0.00281748,0.0003825237],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0757867,0.00014056965,0.00024994093,0.0010801313,0.00027631974,0.0005299657,0.00042219413,0.000112720874,0.00065226527],"category_scores_gemma":[0.0069184885,0.000077122866,0.00006490805,0.0011695974,0.00032498685,0.0007828825,0.000028330769,0.00032792374,0.000013560209],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002339624,0.00005345539,0.11350302,0.000004597925,0.00001332319,0.0000051769393,0.003345285,0.00013093643,0.00009469483,0.00018040142,0.013912382,0.86873335],"study_design_scores_gemma":[0.0036586057,0.0009442669,0.8634307,0.0002318935,0.000053860134,0.000058911257,0.00447557,0.023700928,0.000040195926,0.07755379,0.02566306,0.00018822149],"about_ca_topic_score_codex":0.001294187,"about_ca_topic_score_gemma":0.041365746,"teacher_disagreement_score":0.8685451,"about_ca_system_score_codex":0.0008570418,"about_ca_system_score_gemma":0.00583716,"threshold_uncertainty_score":0.99979883},"labels":[],"label_agreement":null},{"id":"W2560370233","doi":"10.3138/cjpe.306","title":"Measuring Evaluation Capacity in Ontario Public Health Units","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"École Nationale d'Administration Publique","funders":"","keywords":"Business; Capacity building; Process (computing); Evaluation methods; Knowledge management; Process management; Public health; Program evaluation; Public relations; Nursing; Medicine; Political science; Computer science; Public administration; Engineering","score_opus":0.9060914930214881,"score_gpt":0.5182209136786268,"score_spread":0.3878705793428613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2560370233","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9806124,0.00023792054,0.0013748645,0.012621835,0.00103512,0.0014308174,0.000004369182,0.000007589852,0.002675085],"genre_scores_gemma":[0.9982151,0.0000064168657,0.0011822461,0.00023464802,0.00009159034,0.00008308589,0.0000067043343,0.000008786118,0.00017142587],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99085605,0.002211713,0.0014925163,0.00027815666,0.004652212,0.00050935464],"domain_scores_gemma":[0.9899289,0.0002872569,0.0010617184,0.00034354388,0.00760336,0.00077524455],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.077727795,0.0001388744,0.000297573,0.0014863774,0.00021464693,0.00036799957,0.00048811946,0.000084007916,0.004825947],"category_scores_gemma":[0.010347604,0.00009199527,0.00008091174,0.0013751683,0.00008610649,0.00149792,0.000012362616,0.00026512716,0.00009180222],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.0000053747385,0.000028484468,0.20235527,0.0000013765864,0.000010463935,0.000001053058,0.0024405052,0.0003909313,0.000022614267,0.00026843854,0.0006094369,0.79386604],"study_design_scores_gemma":[0.0023968369,0.00046165957,0.90920156,0.00015611225,0.000025575511,0.000033163353,0.0009303371,0.011100992,0.000043314416,0.01139984,0.06407487,0.00017573532],"about_ca_topic_score_codex":0.045580003,"about_ca_topic_score_gemma":0.96183324,"teacher_disagreement_score":0.9162532,"about_ca_system_score_codex":0.0063032643,"about_ca_system_score_gemma":0.051754877,"threshold_uncertainty_score":0.99798864},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"opus","categories":["metaresearch"],"domain":"methods","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"low"}],"label_agreement":"split"},{"id":"W2560370905","doi":"10.3138/cjpe.31.2.265","title":"Katherine Eve Hay and Shubh Kumar-Range (eds.). (2014). <i>Making Evaluation Matter: Writings from South Asia</i> .","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Hay; Range (aeronautics); South asia; History; Ancient history; Animal science; Engineering; Biology","score_opus":0.20613094438966154,"score_gpt":0.46084156104524177,"score_spread":0.25471061665558026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2560370905","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9725852,0.00311442,0.0029961274,0.013137939,0.0010504998,0.0019025642,0.00005937711,0.000023571081,0.0051302942],"genre_scores_gemma":[0.996488,0.00003863603,0.0021406405,0.00053242594,0.0003948792,0.00010684695,0.000013968732,0.000024013483,0.00026060242],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9933762,0.001013759,0.0012697254,0.0004331162,0.0034862459,0.00042094965],"domain_scores_gemma":[0.99376434,0.00048686904,0.0012426764,0.00043552349,0.0035576313,0.00051293283],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02152673,0.00022742181,0.00036464934,0.0006554706,0.00030103567,0.00064943486,0.0004810976,0.0001324924,0.013173599],"category_scores_gemma":[0.002750609,0.00015234674,0.00013949734,0.0004503465,0.00015826705,0.00121136,0.00003150729,0.00019889454,0.0004590436],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027398817,0.000020120355,0.14430743,0.000003368855,0.000035691268,0.000003353031,0.0012149574,0.000062245075,0.00025300914,0.00005604223,0.005486047,0.84853035],"study_design_scores_gemma":[0.006357458,0.0007057474,0.8020369,0.0006239148,0.0005918453,0.00010966459,0.0027383065,0.050395988,0.0002940298,0.02937071,0.10607703,0.0006984224],"about_ca_topic_score_codex":0.0004010148,"about_ca_topic_score_gemma":0.0044858954,"teacher_disagreement_score":0.8478319,"about_ca_system_score_codex":0.00049411407,"about_ca_system_score_gemma":0.002883094,"threshold_uncertainty_score":0.9877285},"labels":[],"label_agreement":null},{"id":"W2560535401","doi":"10.3138/cjpe.276","title":"Canada’s National Alcohol Strategy: It’s Time to Assess Progress","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Canadian Centre on Substance Use and Addiction","funders":"","keywords":"Moderation; Harm; Alcohol; Political science; Risk analysis (engineering); Psychology; Business; Public relations; Social psychology","score_opus":0.5170074637952967,"score_gpt":0.5469577318808765,"score_spread":0.029950268085579768,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2560535401","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5049042,0.0004942961,0.0026779324,0.39561102,0.004215536,0.0073386836,0.0003831287,0.00005511354,0.08432007],"genre_scores_gemma":[0.9935736,0.0000015198505,0.0014799314,0.0015321162,0.00030477185,0.000095913834,0.000009563011,0.000012768825,0.0029897878],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9923806,0.00051331124,0.0010980604,0.000266021,0.00535149,0.00039050748],"domain_scores_gemma":[0.9898163,0.0003785065,0.00063906185,0.0002522869,0.00795514,0.0009586854],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01528773,0.0001539403,0.0002504027,0.0006628329,0.0002126381,0.0004706822,0.0007078612,0.000072955256,0.0154230315],"category_scores_gemma":[0.0041657398,0.00009709021,0.000091746566,0.0007434394,0.000079490106,0.00078396226,0.000016953913,0.00012591227,0.00061818433],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014049906,0.000024311228,0.0063014547,0.0000014032901,0.000028613686,0.000007985156,0.0000954657,0.0009915716,0.000068682995,0.00034863202,0.28824207,0.7038758],"study_design_scores_gemma":[0.0012867539,0.0005423818,0.13660274,0.000110223955,0.000049875314,0.000065500106,0.00031611885,0.010991308,0.00022109796,0.004319595,0.84521276,0.00028167252],"about_ca_topic_score_codex":0.02584108,"about_ca_topic_score_gemma":0.7997829,"teacher_disagreement_score":0.7739418,"about_ca_system_score_codex":0.001788921,"about_ca_system_score_gemma":0.06714829,"threshold_uncertainty_score":0.98547703},"labels":[],"label_agreement":null},{"id":"W2560834949","doi":"10.1007/978-94-024-0878-2_8","title":"A Citizen-Led Approach to Enhancing Community Well-Being","year":2016,"lang":"en","type":"book-chapter","venue":"International handbooks of quality-of-life","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Trillium Foundation; Headwaters Health Care Centre; York University","funders":"","keywords":"Publication; Poverty; Community organization; Public relations; Community development; Political science; Publishing; Geography","score_opus":0.2953411978686673,"score_gpt":0.4869036544790429,"score_spread":0.19156245661037558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2560834949","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019980218,0.00010530841,0.032137062,0.0006959076,0.00084290694,0.0004201218,0.0002448296,0.000023186121,0.94555044],"genre_scores_gemma":[0.799997,0.000056891142,0.0028206098,0.0010569801,0.00025922284,0.000025010606,0.000056495664,0.000038762613,0.19568904],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9912747,0.00054821343,0.0033540684,0.0004554574,0.004148054,0.00021947193],"domain_scores_gemma":[0.9894105,0.0042065987,0.0026532505,0.001069507,0.0024234308,0.00023668542],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011321393,0.00035052648,0.0012039704,0.0009134697,0.00013895887,0.0000660415,0.0020459497,0.00026537522,0.0029154702],"category_scores_gemma":[0.0041615716,0.00027182276,0.0004808231,0.00009699936,0.00029821528,0.00023432498,0.0005879766,0.00047204745,0.00021608121],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006401385,0.00023397928,0.0010853092,0.0002430845,0.0005506106,4.953298e-7,0.0046863365,0.00017738953,0.004316537,0.9674559,0.0025243296,0.018085858],"study_design_scores_gemma":[0.00707421,0.000757813,0.004360698,0.0058002654,0.00016245995,0.000006210612,0.0034829185,0.0012875963,0.026879432,0.7963819,0.1518001,0.0020064365],"about_ca_topic_score_codex":0.00014098789,"about_ca_topic_score_gemma":0.00013484231,"teacher_disagreement_score":0.7800168,"about_ca_system_score_codex":0.00012772989,"about_ca_system_score_gemma":0.00074207113,"threshold_uncertainty_score":0.9999734},"labels":[],"label_agreement":null},{"id":"W2561874864","doi":"10.3138/cjpe.0023.009","title":"A Bumpy Journey to Evaluation Capacity: A Case Study of Evaluation Capacity Building in a Private Foundation","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Foundation (evidence); Officer; Capacity building; Process (computing); Function (biology); Business; Sample (material); Evaluation methods; Public relations; Knowledge management; Engineering; Political science; Computer science","score_opus":0.6621746987407026,"score_gpt":0.5495807547365068,"score_spread":0.11259394400419576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2561874864","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9886587,0.00009321041,0.0019081263,0.0012367854,0.0007471892,0.0068983044,0.0000046539612,0.000010443494,0.00044253888],"genre_scores_gemma":[0.9933648,0.0000028685017,0.0059666545,0.00017489908,0.0001792805,0.00027659457,0.000010859995,0.00001530462,0.000008733707],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9844244,0.0039313426,0.0028009661,0.00053592806,0.0077960375,0.0005112903],"domain_scores_gemma":[0.98513615,0.00033728703,0.00201976,0.0006288432,0.011216745,0.00066123623],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08249955,0.00028530322,0.00059726456,0.0032319082,0.00034594486,0.00057627755,0.0005058338,0.00015100148,0.0012511249],"category_scores_gemma":[0.012535421,0.0002535303,0.00016338324,0.0032376419,0.00006780003,0.0017206399,0.000020457363,0.00039286184,0.000021843789],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006498079,0.0005214632,0.031022979,0.0000062778213,0.000043615953,0.000044396074,0.017936418,0.056328576,0.00056880957,0.00019403276,0.00017033578,0.8930981],"study_design_scores_gemma":[0.007834966,0.005344123,0.26259652,0.00028200247,0.00064947194,0.0010131788,0.018155582,0.67467844,0.00036806043,0.02747486,0.0011267532,0.0004760599],"about_ca_topic_score_codex":0.0043537845,"about_ca_topic_score_gemma":0.12585863,"teacher_disagreement_score":0.89262205,"about_ca_system_score_codex":0.0026127647,"about_ca_system_score_gemma":0.005930187,"threshold_uncertainty_score":0.9999917},"labels":[],"label_agreement":null},{"id":"W256235996","doi":"10.1093/oxfordhb/9780199548453.003.0015","title":"The Politics of Policy Evaluation","year":2009,"lang":"en","type":"book-chapter","venue":"Oxford University Press eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":136,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute on Governance","funders":"","keywords":"Politics; Political science; Policy analysis; Public administration; Public policy; Key (lock); Computer science; Law; Computer security","score_opus":0.17103137773699942,"score_gpt":0.4025742096289181,"score_spread":0.23154283189191868,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W256235996","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001637202,0.000085145955,0.00012051874,0.00037271314,0.00015686438,0.00040550999,0.00005175664,0.000018324981,0.99862546],"genre_scores_gemma":[0.0063125757,0.00027189447,0.00008371516,0.00010360215,0.00013785077,4.846332e-7,0.000012168075,0.000010138476,0.99306756],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99638456,0.00015382047,0.0004503349,0.00030480785,0.0024970858,0.00020940525],"domain_scores_gemma":[0.99647325,0.0006336524,0.000679924,0.00086083927,0.0012555914,0.000096726166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023631053,0.0001921762,0.00028084902,0.0003279778,0.0004330761,0.00010036166,0.0010296756,0.00020263127,0.00021044878],"category_scores_gemma":[0.00027212608,0.00014135228,0.0002090319,0.00003032554,0.00024334308,0.00012123132,0.00020114341,0.00023311841,0.000007631521],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002107107,0.0000043630666,0.0000042857946,0.0000026258315,0.00002624627,9.95358e-7,0.00016698168,0.00006302742,0.000002236275,0.79988366,0.002892311,0.1969322],"study_design_scores_gemma":[0.00032351317,0.000072326846,0.00011844322,0.000028139328,0.00008390522,0.0000014063379,0.00013830024,0.0014460139,0.000041332885,0.07433396,0.9232799,0.0001328],"about_ca_topic_score_codex":0.000029511597,"about_ca_topic_score_gemma":0.000035288675,"teacher_disagreement_score":0.92038757,"about_ca_system_score_codex":0.00028362792,"about_ca_system_score_gemma":0.0011335632,"threshold_uncertainty_score":0.5764179},"labels":[],"label_agreement":null},{"id":"W2563555348","doi":"10.1080/07294360.2016.1263937","title":"Strengthening collaborative capacity: experiences from a short, intensive field course on ecosystems, health and society","year":2016,"lang":"en","type":"article","venue":"Higher Education Research & Development","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Public Health Ontario; University of Toronto; Université du Québec à Montréal; Simon Fraser University; University of Northern British Columbia","funders":"International Development Research Centre","keywords":"Course (navigation); Field (mathematics); Psychology; Political science; Business; Sociology; Environmental resource management; Environmental science; Engineering","score_opus":0.2475815552421443,"score_gpt":0.535144278403018,"score_spread":0.2875627231608737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2563555348","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9632717,0.00043033055,0.00015322697,0.032252632,0.0010056222,0.0005120545,0.000013370965,0.0000235313,0.0023375822],"genre_scores_gemma":[0.9867682,0.00020372427,0.00287348,0.0031384612,0.00018393452,0.0005183916,0.000014644978,0.000008689471,0.006290517],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99523205,0.0006739574,0.0006396353,0.0005948507,0.0024775353,0.000381948],"domain_scores_gemma":[0.9941782,0.0024938104,0.00017375559,0.00037686998,0.0024196466,0.00035776486],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0045440965,0.0001506834,0.00023975917,0.00019914168,0.0006187044,0.00031349843,0.0003551992,0.000070907096,0.0031926115],"category_scores_gemma":[0.00080570875,0.00008979508,0.00003278427,0.0006703584,0.00015297931,0.00033874743,0.00011942289,0.00019914714,0.00025731916],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006797118,0.0002560668,0.03271548,0.000011861545,0.000072050956,6.0744276e-7,0.1856116,0.0000015070435,0.00030447106,0.0037924685,0.45242628,0.3247396],"study_design_scores_gemma":[0.00041406974,0.0003636785,0.07882158,0.0003769687,0.0000024148792,0.0000010808998,0.3117735,0.00007471332,0.003904592,0.0020504105,0.60195637,0.00026062268],"about_ca_topic_score_codex":0.0001296235,"about_ca_topic_score_gemma":0.00013963868,"teacher_disagreement_score":0.32447898,"about_ca_system_score_codex":0.0004205469,"about_ca_system_score_gemma":0.005616967,"threshold_uncertainty_score":0.99771863},"labels":[],"label_agreement":null},{"id":"W2564563180","doi":"10.56645/jmde.v2i3.107","title":"Evaluation in Canada","year":2005,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"World Bank Group","keywords":"Political science; Business","score_opus":0.23999870031305678,"score_gpt":0.5137436117701629,"score_spread":0.2737449114571061,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2564563180","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98746866,0.0005236888,0.00045065334,0.006564054,0.00091076636,0.0004331495,0.0000025139352,0.0000024369049,0.0036440506],"genre_scores_gemma":[0.99760216,0.000030374305,0.0017966053,0.00010697563,0.0003287549,0.00001765416,0.0000049156124,0.000007198002,0.0001053523],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9842972,0.0016375739,0.0018950865,0.00023754904,0.011718586,0.00021401215],"domain_scores_gemma":[0.9929475,0.0007047929,0.0012111575,0.00032268377,0.0046981694,0.00011565015],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.061072104,0.00012824949,0.00029265002,0.00056630623,0.000103659695,0.00007235225,0.0004630363,0.00004956297,0.0037616158],"category_scores_gemma":[0.0042766556,0.00009407204,0.00009366534,0.0007518908,0.000020858059,0.0012916261,0.00006143937,0.00024445434,0.00008532499],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00005620988,0.000072948955,0.07212818,0.0000012956395,0.00001193035,0.0000022677325,0.0010194544,0.36309075,0.00035145818,0.000024021045,0.0020933542,0.5611481],"study_design_scores_gemma":[0.0014922902,0.00006583078,0.41661492,0.000023302882,0.000045368473,0.000017273474,0.0018171805,0.5760356,0.00023207012,0.00259726,0.0009834322,0.00007546236],"about_ca_topic_score_codex":0.015731765,"about_ca_topic_score_gemma":0.7698318,"teacher_disagreement_score":0.7541,"about_ca_system_score_codex":0.0038662492,"about_ca_system_score_gemma":0.0134458,"threshold_uncertainty_score":0.99995774},"labels":[],"label_agreement":null},{"id":"W2564980420","doi":"10.35502/jcswb.30","title":"Canada’s Hub Model: Calling for Perceptions and Feedback from those Clients at the Focus of Collaborative Risk-Driven Intervention","year":2016,"lang":"en","type":"article","venue":"Journal of Community Safety and Well-Being","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Intervention (counseling); Focus (optics); Perception; Psychology; Computer science","score_opus":0.063792154017629,"score_gpt":0.3983528986253132,"score_spread":0.3345607446076842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2564980420","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94201076,0.00014563111,0.05178056,0.0047862795,0.00012309621,0.00014521187,0.000093342285,0.0000017432967,0.00091337605],"genre_scores_gemma":[0.9972567,0.0012380173,0.0010034501,0.00012887364,0.000034617908,0.0000017304051,0.0000031309519,0.000004840929,0.00032866927],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9975194,0.00094138656,0.0007744133,0.00007296749,0.00058434554,0.00010753755],"domain_scores_gemma":[0.9948171,0.003201066,0.00090885593,0.00024584192,0.0007471511,0.00008001742],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004651839,0.000090020134,0.00025080665,0.00007649584,0.00089764193,0.000059727372,0.00032858353,0.000044533994,0.00013511645],"category_scores_gemma":[0.00063308346,0.000047358906,0.000088610876,0.00012287931,0.00012385668,0.00038316456,0.00016413817,0.00025342198,0.0000013803825],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003525422,0.00043923923,0.2508451,0.000050007293,0.00055066793,0.0000019088307,0.08066092,0.03678149,0.003981934,0.0043541575,0.010956093,0.60785306],"study_design_scores_gemma":[0.00786383,0.0010098899,0.66904116,0.001110144,0.00035238668,0.000019410665,0.060989946,0.112626374,0.0020128204,0.119061016,0.025516748,0.00039629638],"about_ca_topic_score_codex":0.015131816,"about_ca_topic_score_gemma":0.28534472,"teacher_disagreement_score":0.60745674,"about_ca_system_score_codex":0.00012761242,"about_ca_system_score_gemma":0.0003092493,"threshold_uncertainty_score":0.9914265},"labels":[],"label_agreement":null},{"id":"W2565032618","doi":"10.13033/ijahp.v8i3.446","title":"MCDM 2017 is in Ottawa, Canada","year":2016,"lang":"en","type":"article","venue":"International Journal of the Analytic Hierarchy Process","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Multiple-criteria decision analysis; Computer science; Operations research; Mathematics","score_opus":0.09207599738649472,"score_gpt":0.4629284079082877,"score_spread":0.37085241052179296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2565032618","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86650723,0.000103014456,0.0013076232,0.12198936,0.002139914,0.00008592121,0.000024774601,0.0000026451094,0.007839511],"genre_scores_gemma":[0.9907995,0.000032744887,0.000057367273,0.002394165,0.00020731984,0.0000015985837,1.8406304e-7,0.0000042592196,0.0065028644],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9949788,0.00012393153,0.0009545183,0.00015457171,0.003634222,0.00015394702],"domain_scores_gemma":[0.9965394,0.00053049397,0.00079841766,0.0002622094,0.0017837926,0.000085686435],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002931857,0.00009054395,0.00019586502,0.00036134146,0.000047960315,0.00011656223,0.0022279387,0.000029063685,0.0014771124],"category_scores_gemma":[0.0020639075,0.000040034218,0.00012644609,0.0004369698,0.000066914734,0.0005784811,0.000094493065,0.00016509916,0.00004149639],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002213071,0.000177696,0.68678504,0.000007803505,0.00026208712,0.00017536392,0.0023687924,0.0032894427,0.0005146431,0.0019471346,0.15143363,0.15281709],"study_design_scores_gemma":[0.004918439,0.00015033645,0.42065576,0.0007336555,0.00005587885,0.0006668353,0.0018547906,0.012668926,0.0067029595,0.13043119,0.42066225,0.0004989633],"about_ca_topic_score_codex":0.00375542,"about_ca_topic_score_gemma":0.075954676,"teacher_disagreement_score":0.2692286,"about_ca_system_score_codex":0.00035880276,"about_ca_system_score_gemma":0.0023856272,"threshold_uncertainty_score":0.99943566},"labels":[],"label_agreement":null},{"id":"W2565401354","doi":"10.7202/1038240ar","title":"Les évaluations de l’enseignement par les étudiants : vers une démarche abrégée","year":2016,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Rimouski","funders":"","keywords":"Humanities; Psychology; Art","score_opus":0.2695073214114779,"score_gpt":0.5013435240190546,"score_spread":0.2318362026075767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2565401354","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45914957,0.0014862727,0.14658342,0.35669976,0.005226843,0.0016348576,0.00015110787,0.00014004216,0.028928123],"genre_scores_gemma":[0.97077787,0.0018134678,0.006824496,0.000629759,0.0005988327,0.00030911356,0.00017789108,0.00005045117,0.01881809],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98231226,0.0105826445,0.0016085512,0.000994656,0.003756423,0.00074547244],"domain_scores_gemma":[0.9914993,0.004354178,0.00086182036,0.0010111231,0.001990059,0.0002835388],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.05722589,0.00046559976,0.0004527324,0.0006286572,0.0009910886,0.00035475643,0.00068133534,0.00042194466,0.017225543],"category_scores_gemma":[0.0066063995,0.00036411057,0.00025759835,0.0015291218,0.0003365194,0.0017345619,0.00011272506,0.0003658762,0.003063704],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050351868,0.00042906578,0.035078764,0.000044128465,0.000116730116,0.0000014413333,0.057291422,0.0021965818,0.0035535141,0.0116106365,0.032475825,0.85715157],"study_design_scores_gemma":[0.0020204908,0.00023948707,0.8357172,0.0003947241,0.00025710443,0.000011990684,0.0072395983,0.01044423,0.001582031,0.018668827,0.12288773,0.00053660665],"about_ca_topic_score_codex":0.0013967557,"about_ca_topic_score_gemma":0.005069649,"teacher_disagreement_score":0.85661495,"about_ca_system_score_codex":0.003603318,"about_ca_system_score_gemma":0.008070528,"threshold_uncertainty_score":0.9998811},"labels":[],"label_agreement":null},{"id":"W2569543923","doi":"10.4018/978-1-5225-2315-4.les9","title":"Cross-Cultural Design-Based Research (CC-DBR) Strategies &amp; Activities","year":2017,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University","funders":"","keywords":"Computer science; Sociology","score_opus":0.578314913784136,"score_gpt":0.5761870116866764,"score_spread":0.002127902097459611,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2569543923","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023859937,0.00017163753,0.0013025111,0.00026431325,0.0009008639,0.00064041576,0.00020085667,0.000101398895,0.994032],"genre_scores_gemma":[0.4214364,0.000007063872,0.0010331705,0.00018497359,0.0003938662,0.000048860722,0.000012037184,0.000028385908,0.57685524],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99130833,0.00032332752,0.00090323994,0.0010290357,0.0057211667,0.00071487215],"domain_scores_gemma":[0.9934643,0.0011704842,0.0007029771,0.0020150186,0.0023769261,0.00027032453],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0068262606,0.0005454945,0.0007055963,0.0003086682,0.0014002037,0.00710006,0.002276778,0.00059992593,0.0022565213],"category_scores_gemma":[0.00081601273,0.00039618948,0.00037290488,0.000044263154,0.0015783394,0.0008918086,0.0003471488,0.0008527115,0.0028588115],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024178684,0.00005156973,0.00014962038,0.000022024948,0.00006834757,0.00002851338,0.00029039217,0.00037726402,0.000053852327,0.9415362,0.031355068,0.025825385],"study_design_scores_gemma":[0.0011474891,0.00018774084,0.00031580482,0.00016688596,0.000022989647,0.000011260929,0.00028085444,0.000351283,0.00013394472,0.63271195,0.36414337,0.00052643154],"about_ca_topic_score_codex":0.00016789026,"about_ca_topic_score_gemma":0.0010964205,"teacher_disagreement_score":0.41905043,"about_ca_system_score_codex":0.0005059664,"about_ca_system_score_gemma":0.0036234537,"threshold_uncertainty_score":0.99989986},"labels":[],"label_agreement":null},{"id":"W2574130935","doi":"10.56645/jmde.v2i2.141","title":"Canadian Journal of Program Evaluation, Volume 19(2), Fall 2004","year":2005,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Volume (thermodynamics); Psychology; Physics; Thermodynamics","score_opus":0.22543288998314084,"score_gpt":0.5251932649418456,"score_spread":0.2997603749587048,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2574130935","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9713532,0.002738246,0.0030427335,0.016386501,0.0023983107,0.001437274,0.000011633008,0.000009595961,0.0026225592],"genre_scores_gemma":[0.98282766,0.0000556545,0.014790956,0.00012599041,0.0012697987,0.000031931242,0.000012955354,0.000018757255,0.00086627895],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98604506,0.001627094,0.0031656963,0.0002775746,0.008487716,0.00039688428],"domain_scores_gemma":[0.97937226,0.00047278052,0.0036278274,0.00047401615,0.015364289,0.0006888162],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.06369709,0.00023750316,0.00053613546,0.0015912163,0.00044837344,0.00039796124,0.0010218997,0.0001652243,0.005568292],"category_scores_gemma":[0.007507977,0.00017189891,0.0003927723,0.0010783639,0.000120716,0.0024137727,0.00005541645,0.00049956713,0.00026982112],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013232867,0.00035656054,0.10523536,0.000006839627,0.00008291553,0.000009071239,0.0051799873,0.21776882,0.00020674609,0.00003910989,0.033926528,0.63705575],"study_design_scores_gemma":[0.0038764465,0.0012833365,0.33017465,0.000105314786,0.00036162863,0.0003483484,0.0031145017,0.59765434,0.00013645452,0.0065436596,0.056149818,0.0002515274],"about_ca_topic_score_codex":0.00025174275,"about_ca_topic_score_gemma":0.013134108,"teacher_disagreement_score":0.6368042,"about_ca_system_score_codex":0.0018102385,"about_ca_system_score_gemma":0.014269216,"threshold_uncertainty_score":0.99534076},"labels":[],"label_agreement":null},{"id":"W2576058593","doi":"10.56645/jmde.v3i4.77","title":"Taking Evaluation Contexts Seriously: A Cross-Cultural Evaluation in Extreme Unpredictability","year":2006,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Psychology; Sociology","score_opus":0.3547556918813846,"score_gpt":0.5431977453023824,"score_spread":0.1884420534209978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2576058593","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9875534,0.001057614,0.0010256598,0.0015182595,0.0017350232,0.0019761657,0.0000110293,0.00002000757,0.005102837],"genre_scores_gemma":[0.99762475,0.000020316556,0.0013124204,0.00003936384,0.00063397974,0.0001375618,0.00008782414,0.000020848554,0.00012292998],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97485805,0.0046717986,0.0040098256,0.0007250709,0.015263999,0.0004712826],"domain_scores_gemma":[0.9777062,0.0011591057,0.0039147753,0.0006744469,0.016401023,0.00014446834],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.117622264,0.00034730323,0.0006445102,0.0010335137,0.00041626795,0.0006114856,0.0007184701,0.00023087341,0.0049127396],"category_scores_gemma":[0.013225877,0.00026023228,0.00034373588,0.0015186587,0.00020798355,0.004420624,0.00014602368,0.0004993116,0.000098172226],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040764068,0.0004851742,0.42600638,0.000011325831,0.000024514093,0.0000042630604,0.0025619625,0.3383353,0.0046365336,0.00011643283,0.00047251355,0.22693795],"study_design_scores_gemma":[0.004011939,0.00017700897,0.5174589,0.00007240122,0.00011492587,0.000029182285,0.0010775749,0.4588423,0.00026692223,0.017705169,0.00008835511,0.00015529017],"about_ca_topic_score_codex":0.000113622395,"about_ca_topic_score_gemma":0.0013410401,"teacher_disagreement_score":0.22678266,"about_ca_system_score_codex":0.0023145971,"about_ca_system_score_gemma":0.0024086596,"threshold_uncertainty_score":0.999985},"labels":[],"label_agreement":null},{"id":"W2579700397","doi":"","title":"L'alignement stratégique des projets/programmes de développement de l'ACDI","year":2013,"lang":"fr","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Humanities; Political science; Library science; Art","score_opus":0.15866486152870685,"score_gpt":0.4947029236317271,"score_spread":0.33603806210302023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2579700397","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68478864,0.0024125353,0.13852832,0.09972081,0.0010614338,0.0022874177,0.000011497088,0.00014215133,0.071047194],"genre_scores_gemma":[0.72628033,0.0016178035,0.19857083,0.004213563,0.00024415323,0.00067871716,0.000010234222,0.000026235342,0.068358116],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9948556,0.0006163728,0.0010619865,0.0005950627,0.0016546126,0.0012163856],"domain_scores_gemma":[0.9973806,0.00038262882,0.0002504797,0.0006091883,0.0008228469,0.0005542433],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0067097438,0.0003473785,0.0003272529,0.00021575466,0.0004442163,0.0013439291,0.0007616855,0.00021506801,0.07715865],"category_scores_gemma":[0.00032794586,0.00026843863,0.00018134127,0.00071328424,0.00035051306,0.0009905157,0.00020585027,0.000253738,0.0054360866],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010092195,0.00050368224,0.12316452,0.000062541185,0.000059418897,0.0000057613197,0.0053108954,0.0002392494,0.00097033166,0.019398553,0.0603764,0.7898986],"study_design_scores_gemma":[0.0016035319,0.0012121203,0.356942,0.00026071194,0.00009108222,0.000061103055,0.028878782,0.06025661,0.016856803,0.24993216,0.28295872,0.000946381],"about_ca_topic_score_codex":0.0032254304,"about_ca_topic_score_gemma":0.0022219268,"teacher_disagreement_score":0.7889522,"about_ca_system_score_codex":0.0009898664,"about_ca_system_score_gemma":0.002334909,"threshold_uncertainty_score":0.99997675},"labels":[],"label_agreement":null},{"id":"W2586085861","doi":"","title":"Leadership in British Columbia's K to 12 international programs: where are we now?","year":2017,"lang":"en","type":"dissertation","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Educational leadership; Political science; Public administration; Library science; Computer science; Law","score_opus":0.43489784148225913,"score_gpt":0.49911481343765635,"score_spread":0.06421697195539722,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2586085861","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25034487,0.0006306912,0.000109832974,0.036564056,0.010455689,0.0025253817,0.000092683025,0.00016195576,0.6991148],"genre_scores_gemma":[0.19611086,0.00044458735,0.00047212656,0.000577546,0.00023986907,0.00023397637,0.0003855553,0.00002457561,0.80151093],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9951719,0.00011109803,0.0008461941,0.0007426764,0.0027791827,0.00034897047],"domain_scores_gemma":[0.99760556,0.00014834838,0.00062709657,0.0006466829,0.0008138621,0.00015847344],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0023831755,0.00017126364,0.0004081588,0.0002906877,0.00021020147,0.00543427,0.0017322948,0.0002890935,0.02322824],"category_scores_gemma":[0.0005469347,0.00022287235,0.00014689016,0.00027280542,0.000035425266,0.00063087593,0.00005687002,0.00035382752,0.0016493979],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021018195,0.00011513643,0.21177764,0.000039442228,0.000017363698,0.000017576582,0.0007641501,0.000015062112,0.000004881424,0.000021560287,0.30148527,0.48572087],"study_design_scores_gemma":[0.0004438598,0.000053618576,0.43038663,0.0010224201,0.000007651297,0.0000044925173,0.028503302,0.00035562876,0.0000059338868,0.00091161963,0.5379809,0.00032393332],"about_ca_topic_score_codex":0.005456024,"about_ca_topic_score_gemma":0.96858126,"teacher_disagreement_score":0.9631252,"about_ca_system_score_codex":0.00016297727,"about_ca_system_score_gemma":0.00044852408,"threshold_uncertainty_score":0.9991279},"labels":[],"label_agreement":null},{"id":"W2586091975","doi":"10.33524/cjar.v17i3.288","title":"PARTICIPATORY ACTION RESEARCH AND PAYING IT FORWARD","year":2016,"lang":"en","type":"article","venue":"The Canadian Journal of Action Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Northern British Columbia","funders":"","keywords":"Institution; Action (physics); Sociology; Citizen journalism; Action research; Pedagogy; Participatory action research; Personal life; Management; Public relations; Media studies; Political science; Social science; Law","score_opus":0.9249743192767562,"score_gpt":0.7030402588843554,"score_spread":0.22193406039240082,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2586091975","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8843243,0.00012264203,0.00029535822,0.10941701,0.0005119498,0.00017068369,0.0000033478675,0.0000027615392,0.0051519442],"genre_scores_gemma":[0.99178374,0.00018808662,0.00003472,0.0001815996,0.00031393365,0.00000887544,1.301842e-7,0.0000070842248,0.007481814],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9937873,0.0019564577,0.00050224195,0.0001723984,0.0030424157,0.0005392173],"domain_scores_gemma":[0.99189246,0.003301782,0.00017110446,0.00035350863,0.0036245654,0.0006565824],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.05829071,0.00006328591,0.00013290058,0.0013088355,0.0016088386,0.0005813981,0.00058453315,0.00007158995,0.002927424],"category_scores_gemma":[0.005268729,0.000030263283,0.000049245693,0.0010189709,0.0006436008,0.00080882723,0.00004779763,0.00073809293,0.00040611802],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027068358,0.000037256355,0.06506481,0.00001157369,0.000059783055,0.000036124682,0.0044260724,0.00007054256,0.008715576,0.0060611446,0.29756323,0.61768323],"study_design_scores_gemma":[0.0008310153,0.00077998004,0.11753143,0.00011024851,0.000008613376,0.0001381576,0.01987661,0.0006227711,0.0054692617,0.064303294,0.79019964,0.00012899328],"about_ca_topic_score_codex":0.0030799173,"about_ca_topic_score_gemma":0.12726152,"teacher_disagreement_score":0.6175542,"about_ca_system_score_codex":0.0006315697,"about_ca_system_score_gemma":0.0035786687,"threshold_uncertainty_score":0.99969095},"labels":[],"label_agreement":null},{"id":"W2586534219","doi":"10.1080/0142159x.2017.1286310","title":"Twelve tips for planning and conducting a participatory evaluation","year":2017,"lang":"en","type":"article","venue":"Medical Teacher","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Children's Hospital of Eastern Ontario; University of Ottawa","funders":"","keywords":"Participatory evaluation; Participatory GIS; Citizen journalism; General partnership; Stakeholder; Participatory planning; Stakeholder engagement; Participatory action research; Sociology; Process management; Medical education; Knowledge management; Management science; Public relations; Computer science; Medicine; Political science; Business; Environmental planning; Engineering; World Wide Web","score_opus":0.8526421026490272,"score_gpt":0.6614250633989234,"score_spread":0.1912170392501038,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2586534219","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97562534,0.00018328705,0.0035756943,0.0056648306,0.0004756421,0.00028678475,8.3582637e-7,0.000016577858,0.01417102],"genre_scores_gemma":[0.99702144,0.0000022361116,0.0002555621,0.00031057376,0.00029407535,0.00009642107,0.000002647625,0.0000054888415,0.0020115443],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969428,0.00021876063,0.00034028848,0.00022481324,0.0020968125,0.00017650716],"domain_scores_gemma":[0.9986106,0.00038129557,0.0002252007,0.00038612887,0.0002246219,0.00017211391],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.021979509,0.00007073618,0.00014981037,0.00004813912,0.00052565173,0.00025805295,0.00033720856,0.00008505556,0.0055959094],"category_scores_gemma":[0.024413237,0.00004821369,0.000037677954,0.000034561173,0.00015392457,0.00033047787,0.00009095992,0.00014390956,0.000068028385],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026332187,0.000047857928,0.4664966,0.0000068369336,0.000020536816,0.0000015264475,0.0045830645,0.000019364283,0.00004590277,0.0006959903,0.018756876,0.50929916],"study_design_scores_gemma":[0.002099497,0.00009795765,0.118470915,0.00006597439,0.00004672632,0.000007642785,0.004164958,0.7787536,0.000114617644,0.012455339,0.083542265,0.00018055961],"about_ca_topic_score_codex":0.000009521596,"about_ca_topic_score_gemma":0.000016664573,"teacher_disagreement_score":0.7787342,"about_ca_system_score_codex":0.000026895103,"about_ca_system_score_gemma":0.00023145752,"threshold_uncertainty_score":0.9953131},"labels":[],"label_agreement":null},{"id":"W2586887829","doi":"","title":"Pourquoi des différences dans les résultats des examens PISA entre les élèves des écoles publiques et privées","year":2016,"lang":"fr","type":"article","venue":"Archipelago (Université du Québec à Montréal)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Humanities; Political science; Art","score_opus":0.05157191180063006,"score_gpt":0.2990846878801473,"score_spread":0.24751277607951724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2586887829","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91694874,0.01821185,0.02732839,0.030162407,0.0003254438,0.0004643791,0.00018784316,0.00022134492,0.0061496333],"genre_scores_gemma":[0.9547969,0.017670002,0.011774651,0.00033866204,0.00017422227,0.000022697937,0.000013922734,0.00005586516,0.015153061],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99344164,0.0015382952,0.00094234047,0.001175841,0.0017044921,0.0011974195],"domain_scores_gemma":[0.9913614,0.005349669,0.0006496484,0.00086894346,0.0010734734,0.0006968634],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["sts"],"category_scores_codex":[0.0023236321,0.0007561909,0.0007630443,0.00073263445,0.0028068582,0.00066154037,0.0016841613,0.00028998082,0.0056886794],"category_scores_gemma":[0.0021389443,0.0005425899,0.00047674353,0.0010252189,0.0053698267,0.004001981,0.0008067004,0.0003931668,0.0005475572],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013328643,0.0002718502,0.24708581,0.00006272498,0.0001420017,0.00005621594,0.17744349,0.00018497702,0.0015506698,0.01242962,0.0014142686,0.5592251],"study_design_scores_gemma":[0.0019482138,0.00071344327,0.5812323,0.0010853503,0.00022175621,0.00010022743,0.27817774,0.0022557788,0.0013711542,0.063548036,0.06834735,0.0009986586],"about_ca_topic_score_codex":0.19197287,"about_ca_topic_score_gemma":0.84964645,"teacher_disagreement_score":0.65767354,"about_ca_system_score_codex":0.0009895739,"about_ca_system_score_gemma":0.0023659554,"threshold_uncertainty_score":0.9997026},"labels":[],"label_agreement":null},{"id":"W2587059332","doi":"10.29173/cais867","title":"‘Collaboration’ is the New Black: Independent Pharmacist Prescribing in a Collaborative Environment","year":2016,"lang":"fr","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Pharmacist; Sociology; Theme (computing); Humanities; Medicine; Nursing; Art; Computer science; Pharmacy; World Wide Web","score_opus":0.0742549560785676,"score_gpt":0.3637349930125252,"score_spread":0.28948003693395763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2587059332","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84260625,0.0012676647,0.00019928307,0.14331692,0.0006969065,0.0013704081,0.0005790644,0.000014700361,0.0099488],"genre_scores_gemma":[0.9756157,0.0023361805,0.00037142294,0.0008852101,0.00018866126,0.00005803959,0.0000016355972,0.000022442826,0.020520708],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9947749,0.00020342838,0.001420777,0.00064283115,0.002362552,0.0005955174],"domain_scores_gemma":[0.9628773,0.00085786625,0.0018690155,0.00045118137,0.033700123,0.00024455626],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0039534657,0.00041654194,0.00062917825,0.00028003106,0.00024305384,0.0039529614,0.002784892,0.00023019762,0.0016217885],"category_scores_gemma":[0.015153685,0.0002294179,0.0001961695,0.001494164,0.001185619,0.015241635,0.00088440283,0.00038196027,0.00011377174],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00086589856,0.00069602794,0.31101537,0.00022408087,0.0003148023,0.000003222726,0.36305773,0.00022300037,0.040610127,0.033882517,0.12048381,0.1286234],"study_design_scores_gemma":[0.0033838588,0.0005661465,0.06641776,0.0011197511,0.00017402013,0.000015306181,0.035338815,0.0033764786,0.09294349,0.020219555,0.7758591,0.0005857166],"about_ca_topic_score_codex":0.00023286387,"about_ca_topic_score_gemma":0.000140907,"teacher_disagreement_score":0.6553753,"about_ca_system_score_codex":0.00036585872,"about_ca_system_score_gemma":0.0025989045,"threshold_uncertainty_score":0.9992909},"labels":[],"label_agreement":null},{"id":"W2587275352","doi":"10.1016/j.evalprogplan.2017.02.005","title":"Concept mapping internal validity: A case of misconceived mapping?","year":2017,"lang":"en","type":"article","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cégep Marie-Victorin; Université de Montréal","funders":"Canadian Institutes of Health Research","keywords":"Internal validity; Engineering; Psychology; Computer science; Mathematics; Statistics","score_opus":0.49797449573113756,"score_gpt":0.5785909440871707,"score_spread":0.08061644835603315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2587275352","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9770821,0.00035892447,0.005276906,0.0007840182,0.0005098569,0.0006865867,0.000009311154,0.000037723574,0.015254598],"genre_scores_gemma":[0.9935855,0.000008294409,0.0055332896,0.00012068396,0.0001138178,0.00006123848,0.000013109796,0.000006384838,0.0005576419],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99706036,0.0004077161,0.00066725694,0.00036157016,0.0013062507,0.00019683244],"domain_scores_gemma":[0.997266,0.00044599787,0.00088133186,0.0005303793,0.00076673337,0.000109548506],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00959699,0.00013511186,0.00026923604,0.00020340557,0.00065732986,0.0007386549,0.00038051858,0.000069934984,0.0010599309],"category_scores_gemma":[0.0026712415,0.0001071661,0.00007508673,0.0001432789,0.00021260085,0.0005965514,0.000134139,0.00014863549,0.000026587571],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022834975,0.000042908916,0.12102782,0.000010847473,0.000028427057,0.000037358386,0.009306656,0.00023984177,0.00017301987,0.00025146632,0.0009030397,0.8679558],"study_design_scores_gemma":[0.0027606313,0.00037975342,0.32248136,0.00035656415,0.000059736292,0.00037624055,0.014634889,0.6146403,0.0006511993,0.006115142,0.037194245,0.00034993977],"about_ca_topic_score_codex":0.000072977826,"about_ca_topic_score_gemma":0.000019555655,"teacher_disagreement_score":0.86760587,"about_ca_system_score_codex":0.00002991707,"about_ca_system_score_gemma":0.00017407343,"threshold_uncertainty_score":0.99985325},"labels":[],"label_agreement":null},{"id":"W2588201730","doi":"","title":"Les effets de la standardisation, de la normalisation et de la pondération des indicateurs sur la robustesse d'une cote globale : le cas de l'évaluation sommative de la performance des écoles","year":2002,"lang":"fr","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.09735974484122759,"score_gpt":0.4399673199780079,"score_spread":0.3426075751367803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2588201730","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.780821,0.00090479973,0.16533473,0.0013384287,0.00009439045,0.00044448837,0.0000486347,0.00010862597,0.05090487],"genre_scores_gemma":[0.965065,0.0032963075,0.027810799,0.0003769909,0.00012407862,0.00013770195,0.000059693564,0.000045438588,0.0030839948],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9821584,0.013750197,0.0010515415,0.00056369166,0.0016638259,0.0008123192],"domain_scores_gemma":[0.9884868,0.009290324,0.0006753329,0.0004001901,0.00081312814,0.00033422338],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03705794,0.00045597396,0.00043164968,0.00042096648,0.0012672492,0.0016577954,0.0005276772,0.0006837458,0.001192384],"category_scores_gemma":[0.0042996625,0.00043660437,0.00016895412,0.0011924623,0.0018711475,0.0030528638,0.00011335734,0.0006255042,0.00009109112],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012622344,0.0005832181,0.5795328,0.0001611247,0.00007801583,0.00001747375,0.051587477,0.20742063,0.0020836229,0.016694354,0.0025233433,0.1391917],"study_design_scores_gemma":[0.0019665791,0.00016076147,0.65551746,0.0002658159,0.000117556985,0.00027878588,0.0057500885,0.30656606,0.009515014,0.013317315,0.006154643,0.00038993967],"about_ca_topic_score_codex":0.005053231,"about_ca_topic_score_gemma":0.004065349,"teacher_disagreement_score":0.18424398,"about_ca_system_score_codex":0.0022364657,"about_ca_system_score_gemma":0.0034445315,"threshold_uncertainty_score":0.99980855},"labels":[],"label_agreement":null},{"id":"W2588856153","doi":"10.5553/bo/221335502017000002001","title":"Bespreking van: S.B. Nielsen, R. Turksema &amp; P. van der Knaap (Eds.), Success in evaluation: Focusing on the positives, New Brunswick/London: Transaction Publishers 2015","year":2017,"lang":"nl","type":"article","venue":"Beleidsonderzoek Online","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Database transaction; Theology; Philosophy; Computer science; Database","score_opus":0.18107815977515088,"score_gpt":0.46559463913773175,"score_spread":0.28451647936258084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2588856153","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7392051,0.010494863,0.013083387,0.20464572,0.006683655,0.0035745883,0.00013176074,0.00016795723,0.022012945],"genre_scores_gemma":[0.9677246,0.0010550793,0.0014554481,0.0028841307,0.0018418608,0.000049141632,0.00024725357,0.00010621299,0.024636239],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9863231,0.0019570182,0.0022290174,0.0018363391,0.006377398,0.0012771084],"domain_scores_gemma":[0.99061906,0.0020649664,0.0018808019,0.0032659394,0.0016061172,0.0005631192],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.014166813,0.0009402824,0.0010510043,0.0008970487,0.0026647018,0.0062119667,0.0030050701,0.0006084189,0.020483414],"category_scores_gemma":[0.0032117562,0.00070865813,0.00048375825,0.0012324239,0.00046053165,0.006422719,0.0003037947,0.0016581133,0.0014661668],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007986199,0.0016134575,0.04527068,0.00006445817,0.00030546103,0.00003372812,0.005109798,0.015713716,0.0007320728,0.0012414989,0.04999785,0.8791187],"study_design_scores_gemma":[0.011386399,0.00082611275,0.46916753,0.0017358637,0.0007654447,0.00008564586,0.0056413906,0.15825987,0.0012505082,0.011674462,0.33683607,0.0023707238],"about_ca_topic_score_codex":0.0032731781,"about_ca_topic_score_gemma":0.0498526,"teacher_disagreement_score":0.8767479,"about_ca_system_score_codex":0.0007899932,"about_ca_system_score_gemma":0.005532043,"threshold_uncertainty_score":0.99953645},"labels":[],"label_agreement":null},{"id":"W2588949029","doi":"10.1093/eurpub/ckv171.031","title":"Qualitative Evaluation: Partners in Inner-city Integrated Prenatal Care Project in Winnipeg, Canada","year":2015,"lang":"en","type":"article","venue":"European Journal of Public Health","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Winnipeg Regional Health Authority; University of Manitoba","funders":"","keywords":"Inner city; Prenatal care; Qualitative research; Sociology; Nursing; Gerontology; Political science; Medicine; Environmental health; Socioeconomics; Social science","score_opus":0.642102486092122,"score_gpt":0.5970568549626996,"score_spread":0.04504563112942239,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2588949029","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9563043,0.0007204023,0.0014658697,0.02127918,0.00088897924,0.00048543175,0.00002381144,0.0000076202696,0.01882437],"genre_scores_gemma":[0.9978782,0.000015316971,0.0008401752,0.00095191,0.00010387911,0.000003840374,0.0000203155,0.000009855499,0.00017652551],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9592001,0.032341342,0.0026345314,0.00033908762,0.0049654073,0.00051957177],"domain_scores_gemma":[0.99460256,0.0004545183,0.0010700552,0.0002618925,0.0031755327,0.00043544764],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14134859,0.00013876388,0.00037908182,0.0008164953,0.00006650948,0.00018866351,0.00063166465,0.000020492947,0.00021032446],"category_scores_gemma":[0.010749427,0.000096509924,0.00004576043,0.002010101,0.00005697249,0.0008975275,0.00006593276,0.0005158991,0.000017543236],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000633827,0.00017447458,0.08153222,0.000023148326,0.000020920097,0.00010760177,0.3059492,0.0027475585,0.0000013739352,0.0002685373,0.06381319,0.5452984],"study_design_scores_gemma":[0.004822045,0.0010235887,0.20205057,0.00019642472,0.0000039764655,0.000046548234,0.5750471,0.006125006,0.000007157293,0.00026410108,0.2101653,0.0002481871],"about_ca_topic_score_codex":0.040102944,"about_ca_topic_score_gemma":0.45390114,"teacher_disagreement_score":0.5450502,"about_ca_system_score_codex":0.0022946454,"about_ca_system_score_gemma":0.043033473,"threshold_uncertainty_score":0.99758345},"labels":[],"label_agreement":null},{"id":"W2590790663","doi":"","title":"Lectures 10 : program 16 : the slogan of evidence based policy practice education in Canada : whom does it serve?","year":2008,"lang":"en","type":"article","venue":"OAR@UM (University of Malta)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Slogan; Political science; Public relations; Pedagogy; Sociology; Law","score_opus":0.19378393175044412,"score_gpt":0.43815292147235685,"score_spread":0.24436898972191273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2590790663","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91238517,0.00007377335,0.00018656613,0.07966517,0.00013905972,0.00035341235,0.000007673631,0.00000884755,0.007180305],"genre_scores_gemma":[0.991238,0.000085170665,0.0019580324,0.0009952417,0.000026654974,0.000001187253,0.0000035679554,0.000002900187,0.005689251],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.997775,0.00038890934,0.00023427978,0.00022062303,0.0012226239,0.00015856858],"domain_scores_gemma":[0.9970861,0.0012607545,0.00042286035,0.0004252787,0.0007373067,0.00006767402],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016339069,0.00008453699,0.00017373175,0.00023774183,0.00026952883,0.000026777743,0.0006946082,0.00003941314,0.001766165],"category_scores_gemma":[0.0016413638,0.00005526122,0.00005477868,0.001018863,0.00018236315,0.00073300075,0.00008563219,0.0001231475,0.000020610983],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00067374407,0.0007999448,0.24854493,0.00009842797,0.00004869276,0.000019417857,0.012299285,0.0045869756,0.0003872639,0.0013508861,0.10293497,0.6282554],"study_design_scores_gemma":[0.000439298,0.00016819371,0.64485216,0.000100788486,0.000023451967,0.000005891391,0.034789734,0.0057458994,0.00027859345,0.00029729595,0.31316417,0.0001345108],"about_ca_topic_score_codex":0.71449965,"about_ca_topic_score_gemma":0.9085455,"teacher_disagreement_score":0.62812096,"about_ca_system_score_codex":0.00034843976,"about_ca_system_score_gemma":0.015566065,"threshold_uncertainty_score":0.99914634},"labels":[],"label_agreement":null},{"id":"W2591620871","doi":"10.3138/cjpe.0026.008","title":"Discussion: Practice-Based Evaluation as a Response to Adress Intervention Complexity","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Université de Montréal; Université du Québec à Montréal; McGill University; École Nationale d'Administration Publique","funders":"","keywords":"Intervention (counseling); Context (archaeology); Psychological intervention; Reading (process); Field (mathematics); Psychology; Management science; Computer science; Knowledge management; Political science; Engineering; History; Mathematics","score_opus":0.5295924933400027,"score_gpt":0.6233783243564389,"score_spread":0.09378583101643623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2591620871","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92752945,0.0006886818,0.009906607,0.04954772,0.0036148771,0.0043626395,0.000017761025,0.000024622448,0.0043076267],"genre_scores_gemma":[0.9896529,0.0000010950235,0.008610821,0.00092859013,0.00033986478,0.00023497407,0.000029713792,0.000014458063,0.00018762695],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98636687,0.00596091,0.001374991,0.00026019546,0.005572952,0.0004640821],"domain_scores_gemma":[0.9883575,0.00078523654,0.0012399629,0.0004842369,0.00793279,0.0012002806],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10586144,0.00017739073,0.00027733698,0.001226073,0.00035332385,0.000587415,0.0005304305,0.000104477695,0.008595042],"category_scores_gemma":[0.039588194,0.000116423485,0.00022428267,0.0012894633,0.00009964091,0.0021172776,0.000024234863,0.0002680081,0.00056722463],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00078265363,0.00027542023,0.010059043,0.0000047012236,0.000033134984,0.0000029640225,0.0030417994,0.004060116,0.00010911019,0.0003531621,0.0047143754,0.9765635],"study_design_scores_gemma":[0.004782185,0.0030207592,0.41693148,0.0002870315,0.0005278156,0.00014268707,0.010173282,0.1267363,0.00050292205,0.008757734,0.42768154,0.00045628575],"about_ca_topic_score_codex":0.0005553988,"about_ca_topic_score_gemma":0.0052941465,"teacher_disagreement_score":0.97610724,"about_ca_system_score_codex":0.0013299799,"about_ca_system_score_gemma":0.006673217,"threshold_uncertainty_score":0.99895805},"labels":[],"label_agreement":null},{"id":"W2593018669","doi":"10.4212/cjhp.v70i1.1636","title":"The Pursuit of Professional Practice Excellence and the Achievement of Peer Recognition","year":2017,"lang":"en","type":"article","venue":"The Canadian Journal of Hospital Pharmacy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Excellence; Psychology; Medical education; Medicine; Political science; Law","score_opus":0.1554398694588703,"score_gpt":0.48517224064548353,"score_spread":0.32973237118661325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2593018669","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6622957,0.0007539416,0.000025484836,0.32990393,0.001732704,0.000300016,0.000016926115,6.497154e-7,0.004970648],"genre_scores_gemma":[0.9976444,0.00029107224,0.00008016956,0.00060347834,0.00013755854,0.0000044558406,4.167808e-7,0.0000036793517,0.0012347414],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968184,0.00042564326,0.00062911306,0.00008184971,0.0018959098,0.00014905196],"domain_scores_gemma":[0.99397117,0.0017047062,0.0018115499,0.0003639646,0.002001434,0.00014717883],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019282887,0.00007388931,0.00015545444,0.00006446665,0.0012822293,0.0004319185,0.0015764417,0.000016386257,0.00027874458],"category_scores_gemma":[0.0058144187,0.000028946319,0.000086843655,0.00008681961,0.00085199496,0.0007173355,0.000084512234,0.00028362832,0.000013081588],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00217049,0.00032721425,0.061517637,0.000030491838,0.00053191086,0.00003584224,0.03237909,0.00018706733,0.00049153174,0.014668981,0.16228932,0.7253704],"study_design_scores_gemma":[0.009485223,0.0010609229,0.28593284,0.00030007807,0.00040467852,0.00014168775,0.027958902,0.0027083685,0.0043562185,0.08713046,0.58017397,0.00034668538],"about_ca_topic_score_codex":0.0023294245,"about_ca_topic_score_gemma":0.0035381638,"teacher_disagreement_score":0.72502375,"about_ca_system_score_codex":0.00003712385,"about_ca_system_score_gemma":0.0012740871,"threshold_uncertainty_score":0.9862001},"labels":[],"label_agreement":null},{"id":"W2593467741","doi":"10.1353/book20095","title":"Jugement professionnel en évaluation: Pratiques enseignantes au Québec et à Genève","year":2007,"lang":"fr","type":"book","venue":"Presses de l'Université du Québec eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Valuation (finance); Geography; Business","score_opus":0.08804810887010212,"score_gpt":0.3528987592482066,"score_spread":0.26485065037810446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2593467741","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13419266,0.0034572608,0.030730827,0.017858105,0.0019453578,0.0033408615,0.00014548961,0.00037526808,0.8079542],"genre_scores_gemma":[0.37171403,0.0009021474,0.004985904,0.0034313807,0.0010936762,0.00012837606,0.00015891435,0.00013841734,0.61744714],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.989808,0.002434313,0.0017427165,0.0014309514,0.0034612343,0.0011227622],"domain_scores_gemma":[0.988745,0.0057893647,0.0015852863,0.0013892156,0.0018963434,0.0005948274],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008743997,0.0010506009,0.0010925661,0.0008895225,0.0015503021,0.00048382606,0.0022367565,0.00086781225,0.035284366],"category_scores_gemma":[0.0013328823,0.0009389711,0.00057363644,0.0002552694,0.0008324353,0.0009031116,0.0012855812,0.0012736152,0.0039662914],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00070993166,0.0006187423,0.070507124,0.0006167725,0.0008977197,0.000301844,0.25870392,0.0018464009,0.00078713405,0.016890366,0.112880275,0.53523976],"study_design_scores_gemma":[0.0018420982,0.0006012096,0.028264234,0.0012192768,0.000670433,0.000083782616,0.019100929,0.0066066496,0.0015700064,0.0020097005,0.93678385,0.0012478248],"about_ca_topic_score_codex":0.20187134,"about_ca_topic_score_gemma":0.76836926,"teacher_disagreement_score":0.82390356,"about_ca_system_score_codex":0.0064776465,"about_ca_system_score_gemma":0.073260985,"threshold_uncertainty_score":0.99974954},"labels":[],"label_agreement":null},{"id":"W2598054673","doi":"","title":"Ontario budget 2009 & addressing the challenges of the future and crime prevention","year":2009,"lang":"en","type":"article","venue":"Docs.school Publications","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Business; Political science","score_opus":0.23541120644019262,"score_gpt":0.468669296727589,"score_spread":0.23325809028739639,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2598054673","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23022291,0.0063494677,0.0013666176,0.5502139,0.0008207508,0.0012740622,0.000038301405,0.000076282566,0.20963772],"genre_scores_gemma":[0.98958623,0.00018714582,0.00056884345,0.0011360757,0.00018415315,0.000034765566,0.000007931123,0.0000036651722,0.008291182],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99795485,0.00024485312,0.00045653907,0.0002585581,0.00093697995,0.00014819886],"domain_scores_gemma":[0.9979626,0.00019407262,0.0003422247,0.00089319947,0.0005266715,0.000081243095],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0022890312,0.00009778689,0.00012978143,0.00012583961,0.00046259156,0.00033075525,0.0007032924,0.00006211869,0.00138783],"category_scores_gemma":[0.00052628765,0.000049562754,0.000085331194,0.00056991505,0.00007806072,0.0007093465,0.000072207644,0.0002325473,0.000060252256],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018116145,0.00034651047,0.040627144,0.000007055882,0.000040022267,8.997821e-8,0.005408643,0.00011776105,0.00040632763,0.40133482,0.18539461,0.3662989],"study_design_scores_gemma":[0.00013726426,0.000029962697,0.7425713,0.000011507124,0.000013196018,0.0000031648544,0.0010994509,0.00018667776,0.000048559017,0.031195369,0.22465116,0.000052387233],"about_ca_topic_score_codex":0.00012955813,"about_ca_topic_score_gemma":0.0064257775,"teacher_disagreement_score":0.75936335,"about_ca_system_score_codex":0.000054253702,"about_ca_system_score_gemma":0.0004967408,"threshold_uncertainty_score":0.999525},"labels":[],"label_agreement":null},{"id":"W2600360485","doi":"","title":"Profession based research through Action research. Framing knowledge production in an interdisciplinary perspective","year":2014,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Framing (construction); Knowledge production; Action research; Perspective (graphical); Sociology; Knowledge management; Political science; Geography; Pedagogy; Computer science","score_opus":0.7650458582160211,"score_gpt":0.7232141524456882,"score_spread":0.041831705770332905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2600360485","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87099344,0.00003263038,0.0042879637,0.013392789,0.00091838866,0.0007883667,5.20167e-7,0.00006067918,0.10952524],"genre_scores_gemma":[0.9901631,0.000006715415,0.0015941738,0.000048836548,0.00042481502,0.0001317361,0.0000054035613,0.00001289149,0.0076123103],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9891409,0.0057714204,0.00054385356,0.0009085865,0.003143368,0.0004918365],"domain_scores_gemma":[0.993319,0.0018875678,0.00009567324,0.00085696933,0.0037379125,0.000102876256],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.052581992,0.000118064396,0.00019032112,0.0013383138,0.0010717103,0.00029347753,0.0006005122,0.00013315701,0.0013351177],"category_scores_gemma":[0.0047844653,0.0000813995,0.000045334822,0.003156862,0.00027024778,0.0020594841,0.00046012568,0.0010255435,0.00077864656],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013555933,0.003829508,0.079127796,0.000086569504,0.000014050215,0.0000044455505,0.19043446,0.0032266336,0.029234177,0.05498272,0.06436312,0.57334095],"study_design_scores_gemma":[0.0008681211,0.001354212,0.118330374,0.00024011913,0.0000021437513,0.0000022663328,0.37274343,0.23892544,0.017117264,0.2404341,0.009705283,0.00027726914],"about_ca_topic_score_codex":0.00014337973,"about_ca_topic_score_gemma":0.004217221,"teacher_disagreement_score":0.5730637,"about_ca_system_score_codex":0.0007367684,"about_ca_system_score_gemma":0.0005577243,"threshold_uncertainty_score":0.99999934},"labels":[],"label_agreement":null},{"id":"W2600614567","doi":"","title":"Participatory community Action Research process addressing employment integration of internationally trained professionals (ITPs) in Canada","year":2016,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary; University of Alberta","funders":"","keywords":"Participatory action research; Context (archaeology); Public relations; Community engagement; Underemployment; Community mobilization; Citizen journalism; Action research; Variety (cybernetics); Political science; Unemployment; Business; Sociology; Economic growth; Economics; Pedagogy; Geography","score_opus":0.8436846887584326,"score_gpt":0.6717842832093761,"score_spread":0.1719004055490565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2600614567","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98948604,0.000007262007,0.0016867106,0.0045431475,0.00020546104,0.00027666576,0.000008973075,0.000008265174,0.0037774502],"genre_scores_gemma":[0.99770945,0.0000044792946,0.0001242236,0.00019655864,0.000022355105,0.0000920852,0.0000051763645,0.00000497637,0.0018406893],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99381,0.0018530107,0.000839079,0.00019320652,0.0030864708,0.00021823586],"domain_scores_gemma":[0.9953523,0.0025033618,0.00024884197,0.00033016762,0.0014905123,0.00007477782],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.014095031,0.000083042636,0.000174812,0.00037671402,0.00018365878,0.00004288344,0.0005013117,0.000040671544,0.0025029923],"category_scores_gemma":[0.0026868428,0.00004504933,0.00002688873,0.00063124654,0.000082076425,0.00062309625,0.000083226674,0.0002671182,0.000023898578],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000404986,0.0009135518,0.38412455,0.000046834954,0.000031518197,0.000002638717,0.013578553,0.00057771633,0.06122817,0.006048916,0.011191179,0.5218514],"study_design_scores_gemma":[0.001082401,0.0001268865,0.8653586,0.0005272673,0.0000029995297,0.00000102946,0.044607773,0.009045404,0.06423371,0.014175484,0.00068656186,0.00015189036],"about_ca_topic_score_codex":0.21016273,"about_ca_topic_score_gemma":0.9399022,"teacher_disagreement_score":0.7297395,"about_ca_system_score_codex":0.0007756498,"about_ca_system_score_gemma":0.003850843,"threshold_uncertainty_score":0.99840885},"labels":[],"label_agreement":null},{"id":"W2603069932","doi":"10.31581/jbs-21.1-4.3(2011)","title":"Identity, Discourse, and Policy","year":2011,"lang":"en","type":"article","venue":"The Journal of Bahá’í Studies","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Dialogical self; Identity (music); Sociology; Consciousness; Character (mathematics); Epistemology; Social psychology; Psychology; Aesthetics","score_opus":0.5861317831417903,"score_gpt":0.6212557299200748,"score_spread":0.035123946778284565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2603069932","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9732851,0.004166332,0.00072515896,0.010146987,0.00048378596,0.000059547227,0.000001298625,0.0000035909063,0.011128223],"genre_scores_gemma":[0.99427,0.0038221888,0.00034436924,0.0004260096,0.00021940039,5.786824e-7,1.8586201e-8,0.0000027927226,0.00091460056],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99815947,0.00016466988,0.0004824853,0.000059000577,0.0010278744,0.000106504514],"domain_scores_gemma":[0.99827135,0.0004984987,0.00044680276,0.00017357396,0.00056290824,0.000046869794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0067020073,0.00006763768,0.00020761514,0.00018645714,0.00022115083,0.000058959267,0.0004311641,0.00001318811,0.00018622998],"category_scores_gemma":[0.0011951685,0.00002939585,0.00005425074,0.0003087698,0.00025039449,0.00071970647,0.00019774496,0.000108766784,0.0000506107],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048224314,0.00035831763,0.29863974,0.000033155407,0.0012655016,0.00003065586,0.25517803,0.0001287323,0.000813537,0.12189747,0.10646748,0.21470514],"study_design_scores_gemma":[0.0005942396,0.00040485847,0.62410986,0.00004896554,0.00011887614,0.0001480675,0.07920133,0.00008001955,0.00036005577,0.29001078,0.004809186,0.00011375177],"about_ca_topic_score_codex":0.000021054213,"about_ca_topic_score_gemma":0.00008961645,"teacher_disagreement_score":0.32547012,"about_ca_system_score_codex":0.000022860835,"about_ca_system_score_gemma":0.000096352356,"threshold_uncertainty_score":0.23227954},"labels":[],"label_agreement":null},{"id":"W2603662470","doi":"","title":"Implementing Evidence-informed Practice: International Perspectives","year":2012,"lang":"en","type":"article","venue":"Research Portal (Queen's University Belfast)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Engineering ethics; Political science; Public relations; Engineering","score_opus":0.21505255040363808,"score_gpt":0.5393075750106522,"score_spread":0.3242550246070141,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2603662470","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31486902,0.000114202645,0.001314329,0.05136732,0.00078171206,0.0008113138,0.000045378787,0.00011459255,0.63058215],"genre_scores_gemma":[0.96656126,0.00051263405,0.0014718035,0.000097902805,0.00032347522,0.0000028158297,0.000016026848,0.000008795461,0.031005284],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9920661,0.0007770242,0.000421915,0.0004275054,0.0053147958,0.0009926452],"domain_scores_gemma":[0.9926116,0.0032910004,0.00029704013,0.0005138326,0.0028822487,0.0004042939],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.016702604,0.00014455391,0.00018724255,0.0009924776,0.00097155024,0.0003507432,0.0011691112,0.00008299413,0.016151505],"category_scores_gemma":[0.010067015,0.00012782765,0.00013857584,0.0013970735,0.00024396634,0.0070080487,0.0009852909,0.00054460164,0.0013349976],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00064932794,0.0009315323,0.4402815,0.00002772858,0.00036983343,0.00017466943,0.03129021,0.00008631196,0.00025133404,0.28220624,0.20363197,0.04009935],"study_design_scores_gemma":[0.00044580371,0.000109377506,0.07398376,0.00003513501,0.000014226613,0.000010742487,0.20950714,0.00025009154,0.00012077907,0.0002500043,0.7151081,0.00016485465],"about_ca_topic_score_codex":0.00046068983,"about_ca_topic_score_gemma":0.000061214894,"teacher_disagreement_score":0.6516923,"about_ca_system_score_codex":0.0005222285,"about_ca_system_score_gemma":0.001031696,"threshold_uncertainty_score":0.9994426},"labels":[],"label_agreement":null},{"id":"W2603692242","doi":"","title":"An exploration of the use of an online Delphi method within an advocacy group","year":2003,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Delphi method; Delphi; Public relations; Computer science; Political science; Knowledge management; Data science; Internet privacy; World Wide Web; Artificial intelligence","score_opus":0.6584448704482336,"score_gpt":0.5643210461641252,"score_spread":0.09412382428410848,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2603692242","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83372694,0.0000032243822,0.16530329,0.00021891629,0.0001615959,0.00017976329,0.000007002872,0.000012685696,0.00038661493],"genre_scores_gemma":[0.77145517,0.0000034370478,0.22786918,0.00039383455,0.000016465185,0.0000042292827,0.000014025839,0.000004839977,0.00023884322],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99636704,0.0013229866,0.0007106749,0.00024771114,0.001258569,0.0000930435],"domain_scores_gemma":[0.997802,0.0003171162,0.00039082314,0.0008813082,0.00052920275,0.00007952803],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0056039807,0.00008515297,0.00017230582,0.00012557184,0.00008259008,0.00008170742,0.00041866102,0.000046352965,0.0008873445],"category_scores_gemma":[0.00079083047,0.000045653636,0.000049501974,0.0006255944,0.000054557084,0.004119509,0.000023250068,0.000071797454,0.0000070163414],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028425368,0.004873542,0.060495473,0.000018754223,0.0000476865,0.0000010308494,0.050961096,0.25329065,0.07251871,0.18495202,0.0009705507,0.37158623],"study_design_scores_gemma":[0.0009974517,0.0013424846,0.10565676,0.00001710473,0.00003106961,0.000004098397,0.030168584,0.7760016,0.044904128,0.035927024,0.004710447,0.00023926522],"about_ca_topic_score_codex":0.00015954048,"about_ca_topic_score_gemma":0.0024140954,"teacher_disagreement_score":0.5227109,"about_ca_system_score_codex":0.000012993643,"about_ca_system_score_gemma":0.0002029574,"threshold_uncertainty_score":0.97157997},"labels":[],"label_agreement":null},{"id":"W2604136236","doi":"","title":"Knowledge Translation / La traduction des connaissances - Getting Efficacious Interventions Incorporated Into Practice: Lessons Learned","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Nursing Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychological intervention; Psychology; Medicine; Nursing","score_opus":0.7981214960109292,"score_gpt":0.6753249993119925,"score_spread":0.12279649669893666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2604136236","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7150838,0.012098049,0.021062225,0.18742014,0.0015996803,0.000538196,0.000008500744,0.000031403168,0.062158026],"genre_scores_gemma":[0.99590147,0.000093677605,0.0034018618,0.0000367623,0.00020178701,0.0000018519246,0.0000031620652,0.000008386621,0.0003510616],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9951334,0.002173815,0.0008364754,0.00021819286,0.0012630746,0.00037504375],"domain_scores_gemma":[0.993454,0.002020603,0.0004204347,0.00021101738,0.003354561,0.00053938193],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021472147,0.00010034776,0.00021685103,0.0017055887,0.0010598642,0.0007715754,0.00048702979,0.00010240941,0.00025647494],"category_scores_gemma":[0.008507422,0.00008480792,0.00014965297,0.00194443,0.0006460806,0.0013401092,0.000004285928,0.00077877287,0.00005376207],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000062630934,0.00012974444,0.00034835542,0.000006687038,0.000011109703,0.000024635347,0.022638278,0.00076826994,0.0007816622,0.0025634295,0.0061954204,0.96646976],"study_design_scores_gemma":[0.0034967694,0.0037661314,0.09170663,0.006502897,0.00015235745,0.0013014901,0.1490817,0.016476156,0.0015125116,0.61548275,0.10985024,0.0006703399],"about_ca_topic_score_codex":0.00026414648,"about_ca_topic_score_gemma":0.0032471544,"teacher_disagreement_score":0.96579945,"about_ca_system_score_codex":0.0007954162,"about_ca_system_score_gemma":0.0030196891,"threshold_uncertainty_score":0.9998443},"labels":[],"label_agreement":null},{"id":"W2604282250","doi":"10.7202/1039183ar","title":"L’évaluation des pratiques en protection de l’enfance","year":2017,"lang":"fr","type":"article","venue":"Nouvelles pratiques sociales","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Centre intégré universitaire de santé et de services sociaux de la Capitale-Nationale; Centre Intégré Universitaire de Santé et de Services Sociaux du Centre-Sud-de-l'Île-de-Montréal; Centre Intégré Universitaire de Santé et de Services Sociaux du Saguenay–Lac-Saint-Jean; Université Laval","funders":"","keywords":"Humanities; Political science; Art","score_opus":0.28927065102011423,"score_gpt":0.5184123323962858,"score_spread":0.22914168137617158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2604282250","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8830094,0.0028460112,0.03480048,0.03915255,0.0021138291,0.0015291392,0.00005446396,0.00016034156,0.03633382],"genre_scores_gemma":[0.91776973,0.0050931615,0.03460515,0.00050655723,0.0014813092,0.00026971786,0.000015140789,0.000041217576,0.04021799],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99348354,0.00251666,0.0010308208,0.00068695314,0.0016355577,0.0006464443],"domain_scores_gemma":[0.9954545,0.0008088589,0.0013132056,0.0009514865,0.0012798291,0.00019211041],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01143967,0.00039902012,0.0004864223,0.00018291493,0.0036054377,0.0023396886,0.0011372874,0.00065759843,0.0022173687],"category_scores_gemma":[0.007754574,0.00037502465,0.00022879345,0.00024395084,0.001566138,0.0030204423,0.00025977867,0.0005823394,0.0005879687],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007502886,0.00029341766,0.017073154,0.00014126317,0.000086376705,0.000007264458,0.12630962,0.00022833062,0.0023591346,0.10748194,0.0038337526,0.7421107],"study_design_scores_gemma":[0.0013843875,0.0009338597,0.45915908,0.0008940362,0.00017920371,0.000034832905,0.051236123,0.055655945,0.022169763,0.24229491,0.16488822,0.0011696499],"about_ca_topic_score_codex":0.0021631636,"about_ca_topic_score_gemma":0.013676511,"teacher_disagreement_score":0.74094105,"about_ca_system_score_codex":0.0009951034,"about_ca_system_score_gemma":0.0138905225,"threshold_uncertainty_score":0.9998702},"labels":[],"label_agreement":null},{"id":"W2604745329","doi":"","title":"Mixed Methods for Higher Education Research: Opportunities and Challenges","year":2015,"lang":"en","type":"article","venue":"Canadian Society for the Study of Higher Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Exploratory research; Multimethodology; Presentation (obstetrics); Higher education; Qualitative research; Sociology; Educational research; Political science; Pedagogy; Social science; Medicine","score_opus":0.8212401770877109,"score_gpt":0.6186108686431202,"score_spread":0.2026293084445907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2604745329","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34859335,0.07688769,0.00070388505,0.49858934,0.024429819,0.012394725,0.00012786362,0.00006155054,0.03821178],"genre_scores_gemma":[0.9119431,0.00060746865,0.010429034,0.001294809,0.00074687175,0.0018219873,0.00003093108,0.000023683371,0.07310211],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99806064,0.00038112572,0.00037283992,0.00029970228,0.0006332385,0.00025242128],"domain_scores_gemma":[0.9951003,0.0018572335,0.0001785704,0.0004817466,0.0020774573,0.0003046921],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011030468,0.000107770975,0.00018345451,0.0001877566,0.0005353014,0.00013939939,0.00042849104,0.000073004696,0.00017153156],"category_scores_gemma":[0.0003444927,0.00007579964,0.00010881097,0.00032478163,0.00015946779,0.00025247314,0.00003686268,0.00009279312,0.0000045620272],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017312916,0.00027030462,0.000529377,0.000030405054,0.00008046162,7.81467e-9,0.022616627,0.000008695802,0.000007858526,0.06376793,0.4544236,0.45824742],"study_design_scores_gemma":[0.00030109865,0.00023888143,0.028951079,0.0000071878903,0.00003780569,2.6441742e-7,0.21060681,0.000109066066,0.000008992549,0.026140962,0.73352545,0.000072362134],"about_ca_topic_score_codex":0.0054211146,"about_ca_topic_score_gemma":0.007044199,"teacher_disagreement_score":0.5633498,"about_ca_system_score_codex":0.0002608344,"about_ca_system_score_gemma":0.0045574806,"threshold_uncertainty_score":0.819514},"labels":[],"label_agreement":null},{"id":"W2604904726","doi":"10.1057/palcomms.2017.17","title":"Evaluating policy-relevant research: lessons from a series of theory-based outcomes assessments","year":2017,"lang":"en","type":"article","venue":"Palgrave Communications","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Roads University","funders":"Centre de Coopération Internationale en Recherche Agronomique pour le Développement; Centre for International Forestry Research; Social Sciences and Humanities Research Council of Canada; Canada Research Chairs; International Development Research Centre","keywords":"Context (archaeology); Theory of change; Documentation; Monitoring and evaluation; Quality (philosophy); Psychological intervention; Environmental resource management; Management science; Political science; Process management; Business; Sociology; Psychology; Computer science; Engineering; Geography; Economics","score_opus":0.8128656375162506,"score_gpt":0.702614926171458,"score_spread":0.11025071134479258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2604904726","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5413474,0.00073930674,0.02020881,0.24613364,0.00068883447,0.0020343997,0.0010458325,0.00014741374,0.1876544],"genre_scores_gemma":[0.96012884,0.0001624697,0.03820757,0.0002340644,0.000035581263,0.00015111137,0.000057071018,0.000015686319,0.0010076021],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9924936,0.0030486537,0.00097027724,0.0003880738,0.0027561798,0.00034320742],"domain_scores_gemma":[0.97839326,0.009572518,0.0009727592,0.008886258,0.0020411457,0.0001340663],"candidate_categories":["metaresearch","sts","open_science"],"consensus_categories":[],"category_scores_codex":[0.020098548,0.00016808743,0.00040381282,0.0005167516,0.0026725873,0.00071649434,0.006178787,0.00008992818,0.0007457363],"category_scores_gemma":[0.022610104,0.00012642954,0.00018004258,0.00051505456,0.0011635046,0.000308653,0.0015853066,0.0004376169,0.0002844718],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005553583,0.00020281528,0.16188522,0.0000061312103,0.00009373034,4.2882704e-7,0.0015842766,0.00016803262,0.0021886274,0.74015456,0.00020159893,0.09345904],"study_design_scores_gemma":[0.0005649344,0.00010498413,0.43114313,0.000061828134,0.000024461582,2.830709e-7,0.0017003549,0.019649908,0.00074574305,0.54324275,0.0026347071,0.00012692671],"about_ca_topic_score_codex":0.0012964384,"about_ca_topic_score_gemma":0.002121966,"teacher_disagreement_score":0.4187815,"about_ca_system_score_codex":0.00011299966,"about_ca_system_score_gemma":0.001231474,"threshold_uncertainty_score":0.99919826},"labels":[],"label_agreement":null},{"id":"W2605706618","doi":"10.1177/1356389017697620","title":"Evaluability assessment of a small NGO in water-based development","year":2017,"lang":"en","type":"article","venue":"Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Waterloo","funders":"Mitacs","keywords":"Accountability; Context (archaeology); Political science; Public relations; Water development; Face (sociological concept); Qualitative research; Baseline (sea); Psychology; Sociology; Water resources; Geography; Social science","score_opus":0.4462252381466189,"score_gpt":0.5827030978504076,"score_spread":0.13647785970378873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2605706618","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9783971,0.00001108007,0.0060170037,0.001561852,0.00037060858,0.00079419516,0.0000018044892,0.000010699163,0.012835661],"genre_scores_gemma":[0.9893357,0.0000011084741,0.010132974,0.00008154628,0.000027979153,0.00016896622,0.000025564303,0.000006244187,0.0002198929],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9935225,0.00083791156,0.0011472378,0.00046289215,0.0037911467,0.00023831133],"domain_scores_gemma":[0.99638367,0.00034759982,0.0005687114,0.001271999,0.0013631391,0.0000648564],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.04582828,0.00013442134,0.00028529888,0.00030582037,0.00031477617,0.0002223635,0.0007757697,0.00007334439,0.0038971938],"category_scores_gemma":[0.0028727537,0.00009035523,0.00007416601,0.00015335137,0.00009105515,0.00041467822,0.00013077489,0.000117579344,0.000153893],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044410113,0.0003992253,0.6240411,0.000021212876,0.0000127869025,5.595517e-7,0.0015256848,0.040380202,0.0033028491,0.00029814697,0.000095128235,0.32987872],"study_design_scores_gemma":[0.001043278,0.00005030922,0.6518721,0.000021292131,0.000009286129,1.3771889e-7,0.00009806313,0.3366754,0.0061176424,0.0032073467,0.0008218672,0.00008328992],"about_ca_topic_score_codex":0.00006404194,"about_ca_topic_score_gemma":0.0008674607,"teacher_disagreement_score":0.32979542,"about_ca_system_score_codex":0.00039145295,"about_ca_system_score_gemma":0.0017292053,"threshold_uncertainty_score":0.9970134},"labels":[],"label_agreement":null},{"id":"W2605831918","doi":"10.1017/s000842391700004x","title":"Towards a More Collaborative Political Science: A Partnership Approach","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Political Science","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McMaster University; University of Toronto","funders":"","keywords":"General partnership; Politics; Field (mathematics); Inclusion (mineral); Indigenous; Political science; Public relations; Value (mathematics); Sociology; Engineering ethics; Social science; Engineering; Computer science; Law","score_opus":0.2545015171666257,"score_gpt":0.5257059581158848,"score_spread":0.2712044409492591,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2605831918","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6765227,0.000043894895,0.0012850664,0.04431976,0.0011660735,0.00021946241,0.000034665813,0.0000072659336,0.27640113],"genre_scores_gemma":[0.99499464,5.803374e-7,0.0024142056,0.0017845113,0.00034256122,0.0000032060693,2.490572e-7,0.0000055717524,0.00045447345],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.991317,0.00014162551,0.0008013531,0.0004929021,0.0047531174,0.0024940541],"domain_scores_gemma":[0.9857433,0.00025870974,0.00045912122,0.0009437657,0.004576892,0.008018207],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":["sts"],"category_scores_codex":[0.022648882,0.00016929659,0.00036145496,0.0011457131,0.0029052424,0.0038660986,0.0049418146,0.00007433089,0.00056075666],"category_scores_gemma":[0.03825085,0.00011358083,0.00011644273,0.0019001467,0.013350431,0.0028641263,0.0001687593,0.00038922403,0.00009707036],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000058800915,0.000019585015,0.020659223,0.0000017152116,0.0000028770448,0.000028327117,0.00075532094,0.000013234771,0.000092478156,0.97554433,0.00079797604,0.0020790705],"study_design_scores_gemma":[0.00042298262,0.00020992613,0.9124385,0.00002909526,0.000014706212,0.00018225318,0.009082395,0.0046553286,0.0012154082,0.06773202,0.0037944734,0.00022287994],"about_ca_topic_score_codex":0.0072722724,"about_ca_topic_score_gemma":0.0035072793,"teacher_disagreement_score":0.9078123,"about_ca_system_score_codex":0.0015326876,"about_ca_system_score_gemma":0.06556567,"threshold_uncertainty_score":0.9993384},"labels":[],"label_agreement":null},{"id":"W2606229491","doi":"10.3138/cjpe.325","title":"Influential Mentoring Practices for Navigating Challenges and Optimizing Learning During an Evaluation Internship Experience","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Internship; Autonomy; Psychology; Context (archaeology); Medical education; Quality (philosophy); Professional development; Best practice; Pedagogy; Knowledge management; Applied psychology; Computer science; Medicine; Management; Political science","score_opus":0.6665644262235942,"score_gpt":0.6224087149164251,"score_spread":0.04415571130716911,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2606229491","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99434316,0.0013646676,0.0003939591,0.0010037058,0.0009904205,0.0010810383,0.000001005596,0.000009144966,0.0008128818],"genre_scores_gemma":[0.9918654,0.00008594349,0.0073755,0.00001401586,0.00039796514,0.00019905786,0.0000047229214,0.00001290075,0.00004449122],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99567574,0.0008516183,0.00080587715,0.00032680389,0.0020300294,0.00030994628],"domain_scores_gemma":[0.99246997,0.00033161527,0.0032664263,0.00035661907,0.0031665384,0.0004088156],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.032381743,0.00013853285,0.00022076617,0.00027309256,0.0016424285,0.0021055865,0.00058262347,0.00007845411,0.00016869527],"category_scores_gemma":[0.024010178,0.00012172403,0.00007256873,0.000085164356,0.00010661362,0.0042371955,0.000038288304,0.0003476616,0.000002947896],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003441652,0.000015863057,0.018203216,0.000013584399,0.000020991334,0.0000016857035,0.022805987,0.0035088032,0.00054827036,0.00008213355,0.0000027029687,0.95476234],"study_design_scores_gemma":[0.003819191,0.0012630994,0.2635199,0.00057202537,0.00027430477,0.00011852478,0.0770184,0.64273137,0.0020711282,0.0035674665,0.0046303365,0.00041424824],"about_ca_topic_score_codex":0.00041897138,"about_ca_topic_score_gemma":0.007719832,"teacher_disagreement_score":0.9543481,"about_ca_system_score_codex":0.00032561907,"about_ca_system_score_gemma":0.0013688362,"threshold_uncertainty_score":0.9996573},"labels":[],"label_agreement":null},{"id":"W2606650297","doi":"10.3138/cjpe.386","title":"In Tribute to Lyn Shulha: The Authentic Evaluator","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"LYN; Honour; Tribute; Scholarship; Kindness; Fidelity; Sociology; Field (mathematics); Psychology; Environmental ethics; Psychoanalysis; History; Political science; Computer science; Art history; Law; Philosophy; Medicine; Telecommunications","score_opus":0.43053183270283146,"score_gpt":0.5840601491356326,"score_spread":0.15352831643280118,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2606650297","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8880172,0.00029857823,0.00062777847,0.101630285,0.003162472,0.0022990743,0.000009884513,0.000005132878,0.003949609],"genre_scores_gemma":[0.99697995,0.0000042265074,0.000816835,0.0006739964,0.00028170898,0.00010550046,0.0000018754521,0.000008099705,0.0011278337],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9950305,0.0006786468,0.000982164,0.0002115927,0.0027510638,0.0003459827],"domain_scores_gemma":[0.9951383,0.00025400368,0.0008959509,0.00080236356,0.0024060553,0.00050331035],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.037783016,0.000118605174,0.00024225126,0.00062361686,0.0006730651,0.0013911182,0.0015228671,0.000064856365,0.00275782],"category_scores_gemma":[0.0124409925,0.000073435396,0.00012829315,0.00047616535,0.00011877461,0.0009777821,0.0000350872,0.00024380561,0.00036650503],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029468132,0.00004252007,0.05750627,0.0000022414536,0.000023030056,0.000014303844,0.0028893396,0.0019498012,0.000033516906,0.00072230946,0.030751582,0.9060356],"study_design_scores_gemma":[0.001592516,0.0004995288,0.61413723,0.00007168888,0.000087179265,0.000038711,0.0012233796,0.05430193,0.00008404856,0.028888682,0.29889563,0.00017949706],"about_ca_topic_score_codex":0.0011081678,"about_ca_topic_score_gemma":0.080567405,"teacher_disagreement_score":0.90585613,"about_ca_system_score_codex":0.00049372436,"about_ca_system_score_gemma":0.0053571686,"threshold_uncertainty_score":0.99964553},"labels":[],"label_agreement":null},{"id":"W2606670574","doi":"10.3138/cjpe.327","title":"The Oral History of Evaluation: An Interview with Lyn Shulha","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Formative assessment; Scholarship; LYN; Oral history; Psychology; Evaluation methods; Pedagogy; Medical education; Sociology; Political science; Medicine; Engineering; Anthropology","score_opus":0.6363883769916328,"score_gpt":0.5707644898010387,"score_spread":0.06562388719059409,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2606670574","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9124907,0.009886858,0.00188707,0.021329576,0.007674767,0.0047476334,0.000012927525,0.000017725022,0.041952696],"genre_scores_gemma":[0.9974117,0.000026017007,0.0014923536,0.00014600401,0.00015600654,0.00007139397,0.000005821499,0.000009677075,0.0006809911],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99360275,0.0013528846,0.0009702855,0.00019283062,0.0036468394,0.00023441474],"domain_scores_gemma":[0.9887887,0.00019072289,0.002088967,0.00093274977,0.007617545,0.00038130677],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.05068516,0.00012273388,0.00025820546,0.00029442846,0.00055154104,0.00060013385,0.0011255959,0.000059345937,0.0024421879],"category_scores_gemma":[0.0038677317,0.00007018106,0.00011391179,0.00017729156,0.00042448915,0.0013618275,0.00001985237,0.00019202488,0.000027105372],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026638074,0.000029819485,0.010471033,0.000003279059,0.000032426895,0.000002256766,0.0011125536,0.00051329704,0.000008453749,0.0003907528,0.0058956407,0.98151386],"study_design_scores_gemma":[0.0021894048,0.0020746053,0.33506614,0.00015918573,0.00034359907,0.00007701368,0.0022348731,0.14517955,0.000043798223,0.009075994,0.5033405,0.00021533752],"about_ca_topic_score_codex":0.0006598737,"about_ca_topic_score_gemma":0.08782984,"teacher_disagreement_score":0.9812985,"about_ca_system_score_codex":0.0010599493,"about_ca_system_score_gemma":0.015386948,"threshold_uncertainty_score":0.9984697},"labels":[],"label_agreement":null},{"id":"W2606709931","doi":"10.3138/cjpe.349","title":"Developing the Program Evaluation Utility Standards: Scholarly Foundations and Collaborative Processes","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Scholarship; Task (project management); Task force; Political science; Engineering ethics; Program evaluation; Management science; Computer science; Process management; Knowledge management; Business; Public administration; Engineering; Management; Economics","score_opus":0.5392904759997819,"score_gpt":0.6027993397034421,"score_spread":0.06350886370366027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2606709931","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9153224,0.0040860237,0.006791781,0.042861804,0.0022846959,0.014553843,0.000114349736,0.00004252547,0.013942541],"genre_scores_gemma":[0.9899726,0.00006481805,0.008893352,0.0001399143,0.00018114183,0.0006607158,0.000018652874,0.000010310987,0.000058501555],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99230385,0.0011370424,0.0010200862,0.00032002514,0.0049047032,0.0003142668],"domain_scores_gemma":[0.9630292,0.00043310915,0.0016912267,0.00061475264,0.03388711,0.00034459212],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.051086746,0.00017383324,0.00026492466,0.00039631085,0.0028436428,0.008061376,0.0009255117,0.000098292905,0.0008040296],"category_scores_gemma":[0.051395074,0.00011301118,0.00006821852,0.0008337854,0.00047473825,0.0044970587,0.000043351978,0.0003216254,0.000015962087],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019892565,0.000028963597,0.03116664,0.0000100302705,0.000040788436,0.0000010310246,0.0020993366,0.00011738134,0.0000031406325,0.00080568535,0.00095814327,0.964749],"study_design_scores_gemma":[0.0019031978,0.0006878989,0.54367244,0.00018116776,0.0003069609,0.0000365892,0.007164702,0.060432673,0.00009799578,0.052078888,0.33315745,0.0002800353],"about_ca_topic_score_codex":0.00035162765,"about_ca_topic_score_gemma":0.06403078,"teacher_disagreement_score":0.96446896,"about_ca_system_score_codex":0.00081284577,"about_ca_system_score_gemma":0.04390121,"threshold_uncertainty_score":0.9984545},"labels":[],"label_agreement":null},{"id":"W2607080017","doi":"10.3138/cjpe.387","title":"Introduction — Setting the Evaluation Use Context","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Context (archaeology); Business; History; Archaeology","score_opus":0.542769667312793,"score_gpt":0.5681665235554011,"score_spread":0.025396856242608123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2607080017","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8910594,0.0005604245,0.0012239626,0.09429299,0.006397847,0.0030210153,0.000008851775,0.000012834583,0.0034226722],"genre_scores_gemma":[0.9968839,0.00000769302,0.00094092474,0.00028770557,0.0014009231,0.00008397217,0.00001196608,0.000009361688,0.00037354731],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9935149,0.0012531105,0.00097560557,0.00024358348,0.0037402653,0.00027256226],"domain_scores_gemma":[0.9882254,0.00033787417,0.001989384,0.000919414,0.008238472,0.00028943518],"candidate_categories":["metaresearch","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05391779,0.00012577699,0.00019542748,0.00038063477,0.0016205147,0.003203803,0.00095190655,0.00007699969,0.0037490628],"category_scores_gemma":[0.0321604,0.000079201156,0.00014331014,0.0002671174,0.00027159232,0.0025705604,0.00002383344,0.00028715175,0.00015486713],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001153426,0.00001363011,0.02201718,9.952984e-7,0.000023091543,0.0000010281663,0.00089745206,0.001912788,0.000028719582,0.00066004734,0.021439632,0.9529939],"study_design_scores_gemma":[0.0010934927,0.00024307618,0.5010826,0.0000318801,0.00020464777,0.000058237267,0.0023253844,0.18530788,0.00012895842,0.011581786,0.29780045,0.00014158688],"about_ca_topic_score_codex":0.0011129524,"about_ca_topic_score_gemma":0.03803256,"teacher_disagreement_score":0.9528523,"about_ca_system_score_codex":0.00053425005,"about_ca_system_score_gemma":0.0052626547,"threshold_uncertainty_score":0.99967927},"labels":[],"label_agreement":null},{"id":"W2607086309","doi":"10.3138/cjpe.335","title":"Reflections on the Meaning of Success in Collaborative Approaches to Evaluation: Results of an Empirical Study","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Queen's University; University of Ottawa; Carleton University","funders":"","keywords":"Meaning (existential); Set (abstract data type); Knowledge management; Core (optical fiber); Work (physics); Key (lock); Empirical research; Computer science; Conceptual framework; Psychology; Management science; Sociology; Epistemology; Engineering; Social science","score_opus":0.8398111028940528,"score_gpt":0.6344216308633112,"score_spread":0.20538947203074165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2607086309","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9773812,0.000027974209,0.000056611647,0.0065585165,0.00035963082,0.0026239478,0.000015439202,0.0000019797812,0.012974655],"genre_scores_gemma":[0.9982124,9.757964e-7,0.0014478213,0.000060466147,0.00008625419,0.00015271985,0.000004782412,0.0000062609365,0.0000283131],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99232435,0.0024458047,0.001369318,0.00025660754,0.0034191,0.00018484396],"domain_scores_gemma":[0.9918034,0.00054510584,0.00170024,0.0007544132,0.004947922,0.0002489194],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05158375,0.00011417402,0.00030823826,0.000827331,0.0004642102,0.00038455616,0.0009323044,0.000060032333,0.0002563511],"category_scores_gemma":[0.016011167,0.00007407186,0.00006748334,0.0011600712,0.0001422118,0.0007162368,0.000024405219,0.00021986732,0.0000065897466],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005548032,0.0009277689,0.17923789,0.0000053270564,0.00009828814,0.0000048829934,0.06965634,0.07971044,0.00007164557,0.0016190414,0.0010325597,0.667081],"study_design_scores_gemma":[0.0028276793,0.004373182,0.85937923,0.00010011043,0.00011958592,0.0000045935517,0.041031368,0.08270429,0.0005165667,0.0077411165,0.0010665316,0.00013571503],"about_ca_topic_score_codex":0.0010889642,"about_ca_topic_score_gemma":0.1882366,"teacher_disagreement_score":0.6801414,"about_ca_system_score_codex":0.00037213968,"about_ca_system_score_gemma":0.0058228215,"threshold_uncertainty_score":0.99981326},"labels":[],"label_agreement":null},{"id":"W2607364656","doi":"10.3138/cjpe.366","title":"Optimizing Use in the Field of Program Evaluation by Integrating Learning from the Knowledge Field","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Western University; Queen's University","funders":"","keywords":"Terminology; Field (mathematics); Knowledge translation; Body of knowledge; Health care; Engineering ethics; Psychology; Management science; Sociology; Knowledge management; Political science; Computer science; Engineering","score_opus":0.45805747849381845,"score_gpt":0.5653991971273034,"score_spread":0.1073417186334849,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2607364656","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97405136,0.0015096564,0.001942047,0.013813051,0.0009744423,0.0033799775,0.0000057017173,0.000008804912,0.004314944],"genre_scores_gemma":[0.9960682,0.000021116946,0.0031306914,0.00032080914,0.00017704467,0.00020445675,0.000016898279,0.000007661043,0.000053115516],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9944365,0.001912694,0.0010488128,0.000213799,0.0021303317,0.00025787088],"domain_scores_gemma":[0.9916392,0.0035820121,0.0015261513,0.00059035607,0.0025293422,0.00013296741],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.031399667,0.00013604583,0.00024133964,0.00023728298,0.00071852346,0.0015836356,0.0012687773,0.000111456815,0.0007946345],"category_scores_gemma":[0.03783556,0.0000770194,0.00013857176,0.00038589488,0.000105235515,0.0011186983,0.00003298311,0.0006096907,0.0000112324715],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015972222,0.0000491308,0.07677548,0.0000019030516,0.00001845429,9.84005e-7,0.005818509,0.0013600666,0.00003966841,0.00008788368,0.0051574986,0.91067445],"study_design_scores_gemma":[0.0018616763,0.001623004,0.18045038,0.00040000322,0.00023839428,0.000009894348,0.015933596,0.7172247,0.00046389952,0.004109736,0.07744071,0.0002439893],"about_ca_topic_score_codex":0.0050949897,"about_ca_topic_score_gemma":0.115409,"teacher_disagreement_score":0.9104305,"about_ca_system_score_codex":0.00018978871,"about_ca_system_score_gemma":0.0023636092,"threshold_uncertainty_score":0.9994528},"labels":[],"label_agreement":null},{"id":"W2608776241","doi":"","title":"An Exploratory Method for Practitioners Analyzing the Impact of Integrated Fare Structures in Decentralized Metropolitan Regions: A Toronto Region Case Study","year":2017,"lang":"en","type":"article","venue":"Transportation Research Board 96th Annual MeetingTransportation Research Board","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Metropolitan area; Regional science; Exploratory research; Exploratory analysis; Geography; Computer science; Sociology; Data science; Social science","score_opus":0.30831393271980234,"score_gpt":0.6029778324151642,"score_spread":0.2946638996953619,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2608776241","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9780845,0.00023949966,0.014665453,0.0013726234,0.00014380783,0.0046599326,0.0005271528,0.000058269972,0.00024876735],"genre_scores_gemma":[0.99314284,0.00026699508,0.004890793,0.000023182612,0.0000943393,0.0011228223,0.00025512,0.000061142535,0.00014276903],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98244935,0.0069807554,0.002438159,0.0014088339,0.00533942,0.0013834997],"domain_scores_gemma":[0.97984904,0.0046222163,0.0011447936,0.002198092,0.011581032,0.00060480874],"candidate_categories":["metaresearch","metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.04087245,0.00044831372,0.0008586542,0.0016352434,0.0028797924,0.00097293203,0.0021263782,0.00026818516,0.00045158333],"category_scores_gemma":[0.0056318557,0.0003060142,0.0004561023,0.0022037579,0.0008974872,0.0041097305,0.000026313051,0.001231772,0.0000063032207],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0044779023,0.0013410656,0.88100356,0.000100246936,0.00032292854,0.0005232599,0.074749954,0.009545066,0.00093236903,0.009323186,0.0025361858,0.015144264],"study_design_scores_gemma":[0.0028001056,0.0018151432,0.5678757,0.00007898091,0.000046400703,0.000004709901,0.41617125,0.004545797,0.00019513286,0.005608113,0.0005770263,0.00028164953],"about_ca_topic_score_codex":0.23930484,"about_ca_topic_score_gemma":0.54330534,"teacher_disagreement_score":0.34142128,"about_ca_system_score_codex":0.0012255202,"about_ca_system_score_gemma":0.0022182863,"threshold_uncertainty_score":0.9999392},"labels":[],"label_agreement":null},{"id":"W2610755599","doi":"","title":"An Exploration of Subject Curriculum and Policy Implementation in Ontario Schools: What Factors Support and Impede Effective Implementation?","year":2017,"lang":"en","type":"article","venue":"TSpace (University of Toronto)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Subject (documents); Curriculum; Political science; Mathematics education; Public relations; Pedagogy; Public administration; Computer science; Sociology; Psychology; Library science","score_opus":0.10424699865858691,"score_gpt":0.47475395680740584,"score_spread":0.37050695814881895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2610755599","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99740535,0.000023951938,0.0002888153,0.0006925895,0.00006708479,0.00041216126,0.0000119713,0.0000055356118,0.0010925309],"genre_scores_gemma":[0.99921596,0.00021583668,0.00040466094,0.0000131195375,0.000010069396,9.339459e-7,0.00002333058,0.0000032326395,0.00011285099],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9987577,0.00015144241,0.00020070796,0.00026016077,0.0004955019,0.00013449493],"domain_scores_gemma":[0.99880874,0.00007349752,0.00050502096,0.00031757817,0.00020711047,0.00008803207],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011504706,0.00009951164,0.0002179248,0.00014705694,0.00029158883,0.00019033396,0.00024934427,0.000042495503,0.005082835],"category_scores_gemma":[0.00004935745,0.000098491466,0.00003617796,0.000059394453,0.00008570682,0.012044757,0.00010935493,0.00006195058,0.0000023268979],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033987264,0.000032146178,0.84724677,0.0000050997505,0.00001407273,6.0811163e-7,0.05386609,0.000006616098,0.00063252053,0.00069276436,0.000039516923,0.097429805],"study_design_scores_gemma":[0.00086138106,0.00028592735,0.6866866,0.000008427403,0.000012678903,3.1244576e-7,0.31121734,0.00014148581,0.00037810227,0.00026958127,0.00007359526,0.00006460342],"about_ca_topic_score_codex":0.81045294,"about_ca_topic_score_gemma":0.97090656,"teacher_disagreement_score":0.25735125,"about_ca_system_score_codex":0.00034949087,"about_ca_system_score_gemma":0.0003161393,"threshold_uncertainty_score":0.99582666},"labels":[],"label_agreement":null},{"id":"W2611404306","doi":"10.56645/jmde.v13i28.456","title":"The World of Evaluation: Challenges Faced by Student Evaluators","year":2017,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Mathematics education; Psychology; Pedagogy; Sociology","score_opus":0.3297996531442704,"score_gpt":0.5830362193061646,"score_spread":0.25323656616189416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2611404306","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9595702,0.006640609,0.00021209354,0.020232763,0.0027079037,0.0011541661,0.000009270266,0.0000065474323,0.009466401],"genre_scores_gemma":[0.9972107,0.0008620375,0.00041926515,0.000019243602,0.00030162346,0.00005439047,0.0000046726004,0.000014788938,0.0011132691],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98054487,0.0024092172,0.0024525865,0.00038067717,0.0139220115,0.00029062148],"domain_scores_gemma":[0.98254776,0.0020867898,0.0056429873,0.0014828179,0.008081329,0.00015830969],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.09773402,0.0002310224,0.00050943816,0.00039844264,0.0015133062,0.000496556,0.0018485875,0.00008882129,0.0011270139],"category_scores_gemma":[0.008137129,0.0001334005,0.000321104,0.00029461103,0.00025034754,0.0014797699,0.00034718693,0.00031903078,0.00006917878],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005314693,0.0007191881,0.040327236,0.000017628035,0.0003071069,0.000002886709,0.008373955,0.019282859,0.0034758188,0.00094909006,0.01626585,0.9097469],"study_design_scores_gemma":[0.0045531644,0.0007230154,0.7414655,0.00013904682,0.00040823864,0.000018168495,0.010195237,0.21575132,0.0022514774,0.017216139,0.0070328224,0.0002458856],"about_ca_topic_score_codex":0.0000042579077,"about_ca_topic_score_gemma":0.00033917456,"teacher_disagreement_score":0.909501,"about_ca_system_score_codex":0.0003663333,"about_ca_system_score_gemma":0.0012422695,"threshold_uncertainty_score":0.9997866},"labels":[],"label_agreement":null},{"id":"W2611783036","doi":"","title":"Evaluation of Safety in Partnership: Phase Three Report - Moving Forward","year":2014,"lang":"en","type":"article","venue":"Research Portal (Queen's University Belfast)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Queen's University; Queen's University Belfast","keywords":"General partnership; Phase (matter); Business; Finance; Physics","score_opus":0.21774972623192876,"score_gpt":0.4943305294298912,"score_spread":0.2765808031979624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2611783036","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8469564,0.0000084830435,0.0034704423,0.0023679505,0.00010491445,0.0007036851,0.000013818528,0.000026310168,0.14634803],"genre_scores_gemma":[0.9952281,0.000019898385,0.0002861062,0.00001810838,0.000053693104,0.0000034353347,0.000037206835,0.000008799519,0.0043446464],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.986508,0.00226213,0.0008007501,0.000628817,0.009273838,0.00052645017],"domain_scores_gemma":[0.9936696,0.0012148424,0.00039794526,0.0009070903,0.0035648502,0.0002456391],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.06730021,0.00014235434,0.00035010156,0.001228685,0.00032081286,0.00007605395,0.0007791693,0.00012496018,0.003396079],"category_scores_gemma":[0.006969479,0.0001308545,0.00013779993,0.0020606932,0.0002661193,0.00092534634,0.0003279618,0.00043909662,0.0001270793],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013157313,0.0018570895,0.5007531,0.00007773901,0.00019461726,0.0005899743,0.0032458643,0.014223679,0.00071869,0.0804835,0.019717265,0.37682274],"study_design_scores_gemma":[0.013019387,0.0013688534,0.5455354,0.00021910101,0.00014609391,0.000027736936,0.016283913,0.23763481,0.0015006864,0.03762583,0.14590742,0.00073080056],"about_ca_topic_score_codex":0.0007477699,"about_ca_topic_score_gemma":0.0011943838,"teacher_disagreement_score":0.37609193,"about_ca_system_score_codex":0.0003739532,"about_ca_system_score_gemma":0.0015878883,"threshold_uncertainty_score":0.99751496},"labels":[],"label_agreement":null},{"id":"W2611988902","doi":"10.17483/2368-6669.1088","title":"Baccalaureate Program Evaluation, Preceptors, And Closing The Theory-Practice Gap: Is There A Connection?","year":2017,"lang":"en","type":"article","venue":"Quality Advancement in Nursing Education - Avancées en formation infirmière","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Trent University","funders":"","keywords":"Preceptor; Curriculum; Medical education; Objectivism; Cornerstone; Citizen journalism; Stakeholder; Nursing; Pedagogy; Nurse education; Medicine; Psychology; Engineering ethics; Political science; Engineering; Public relations","score_opus":0.20432993921469958,"score_gpt":0.5732179489078153,"score_spread":0.36888800969311575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2611988902","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60979706,0.0031649896,0.023373988,0.19004235,0.0081307,0.0100268405,0.00005123378,0.0002543265,0.15515849],"genre_scores_gemma":[0.9912729,0.00046129673,0.00431228,0.0013862845,0.00023107574,0.0008934431,0.000071587936,0.000017723616,0.0013533941],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99365216,0.002053664,0.0013810733,0.0005219284,0.0020653224,0.0003258698],"domain_scores_gemma":[0.99367326,0.0017326304,0.001690421,0.0012697099,0.0015296191,0.000104371466],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.018197358,0.00025490773,0.00028743496,0.0002740928,0.001704993,0.0015694724,0.0006873343,0.00011532054,0.0011599242],"category_scores_gemma":[0.006280148,0.00018696208,0.00007886665,0.00039015603,0.00030630617,0.005602649,0.000082015744,0.00030741844,0.00013275673],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000109294946,0.000576274,0.012009609,0.00002937549,0.000018318022,5.3898336e-8,0.016884755,0.0005468477,0.000024405574,0.06464914,0.0027555819,0.9023963],"study_design_scores_gemma":[0.0017331543,0.00021256911,0.16850905,0.0006215316,0.000104904495,0.000020861524,0.072191715,0.023964314,0.0005164884,0.20241746,0.5291922,0.0005157435],"about_ca_topic_score_codex":0.00006417451,"about_ca_topic_score_gemma":0.00010597449,"teacher_disagreement_score":0.9018806,"about_ca_system_score_codex":0.0005417223,"about_ca_system_score_gemma":0.00047015725,"threshold_uncertainty_score":0.9997532},"labels":[],"label_agreement":null},{"id":"W2612136089","doi":"10.1016/j.evalprogplan.2017.05.012","title":"The theory of change of the evaluation support program: Enhancing the role of community organizations in providing an ecology of care for neurological disorders","year":2017,"lang":"en","type":"article","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Ontario Brain Institute","funders":"","keywords":"Theory of change; Program evaluation; Capacity building; Field (mathematics); Business; Process management; Public relations; Knowledge management; Engineering; Political science; Computer science; Management; Public administration","score_opus":0.3067197470604154,"score_gpt":0.5514533322275317,"score_spread":0.2447335851671163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2612136089","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9943338,0.00028961926,0.00009961901,0.00075677654,0.00013438008,0.0038037784,0.000010417996,0.0000078517605,0.00056374486],"genre_scores_gemma":[0.9989187,0.000017138915,0.0003371204,0.000031673695,0.000017822766,0.0006372096,0.000028988681,0.000005872978,0.0000054850143],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9954653,0.002481503,0.0007129282,0.00014430212,0.0010512347,0.00014475617],"domain_scores_gemma":[0.9947876,0.0017329683,0.0011869046,0.0006420378,0.0016278806,0.000022661667],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024712777,0.00009054972,0.00021888263,0.00008597293,0.0010236786,0.000080164966,0.0007214946,0.000072425544,0.00004864006],"category_scores_gemma":[0.007627407,0.000045921624,0.000056850087,0.00032488772,0.00041281705,0.0002686385,0.00015332403,0.00016516424,2.1269217e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006697413,0.00012585276,0.31446168,0.000021183288,0.000009556661,5.353762e-9,0.0260304,0.00064966327,0.00022610792,0.0012281016,0.000003565885,0.6571769],"study_design_scores_gemma":[0.00065055175,0.0011279938,0.8426192,0.000040807718,0.000076676355,4.6497775e-7,0.044076,0.09414249,0.0013232812,0.015414734,0.00047305317,0.000054789365],"about_ca_topic_score_codex":0.0000462844,"about_ca_topic_score_gemma":0.0017010974,"teacher_disagreement_score":0.65712214,"about_ca_system_score_codex":0.000018595605,"about_ca_system_score_gemma":0.0003401846,"threshold_uncertainty_score":0.91312695},"labels":[],"label_agreement":null},{"id":"W2612308238","doi":"10.1016/j.evalprogplan.2017.05.013","title":"Putting evaluation capacity building in context: Reflections on the Ontario Brain Institute’s Evaluation Support Program","year":2017,"lang":"en","type":"article","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Framing (construction); Phenomenon; Theory of change; Context (archaeology); Engineering ethics; Public relations; Psychology; Sociology; Political science; Engineering; Epistemology","score_opus":0.6438070308226429,"score_gpt":0.6110897806645028,"score_spread":0.03271725015814009,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2612308238","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94494927,0.00008379597,0.00037331815,0.009806281,0.0011571653,0.0062688235,0.0000041637004,0.00010246112,0.037254743],"genre_scores_gemma":[0.9914548,0.0000039510332,0.004334268,0.0007830824,0.00018333222,0.002809977,0.00008381319,0.00001644538,0.00033032685],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9896468,0.0019959302,0.0011284641,0.00089029723,0.0058540665,0.0004844749],"domain_scores_gemma":[0.99478745,0.0009988833,0.0010474034,0.0010341124,0.001990291,0.00014185694],"candidate_categories":["metaresearch","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07483678,0.00030593982,0.00034056001,0.0004843903,0.0024433648,0.0023584429,0.00066335505,0.00017881485,0.0020468507],"category_scores_gemma":[0.015444839,0.00022158821,0.000110056346,0.0005221137,0.00026541617,0.0017589391,0.00013283658,0.0006188929,0.000082806524],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042340074,0.00017723354,0.064545624,0.000004471874,0.000024557654,9.770889e-7,0.00879097,0.005087309,0.00007030339,0.002018286,0.00081015856,0.91842777],"study_design_scores_gemma":[0.0021032896,0.0004857681,0.44474924,0.00018251008,0.000102327045,0.000011317804,0.0019482585,0.48730433,0.00009864777,0.019994784,0.042750213,0.0002693313],"about_ca_topic_score_codex":0.0020293884,"about_ca_topic_score_gemma":0.044385865,"teacher_disagreement_score":0.9181584,"about_ca_system_score_codex":0.00089542085,"about_ca_system_score_gemma":0.0015591828,"threshold_uncertainty_score":0.9988654},"labels":[],"label_agreement":null},{"id":"W2612615669","doi":"10.1016/j.evalprogplan.2017.05.001","title":"Valuing and embracing complexity: How an understanding of complex interventions needs to shape our evaluation capacities building initiatives","year":2017,"lang":"en","type":"article","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital; University of Toronto","funders":"","keywords":"Psychological intervention; Causality (physics); Intervention (counseling); Management science; Capacity building; Key (lock); Computer science; Process management; Engineering ethics; Public relations; Risk analysis (engineering); Psychology; Engineering; Political science; Business; Economic growth; Computer security; Economics","score_opus":0.796484179060009,"score_gpt":0.6287786959034635,"score_spread":0.16770548315654554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2612615669","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96862686,0.00025321537,0.02097211,0.0031288976,0.00030187273,0.0013677254,0.00001840473,0.000055698565,0.0052752397],"genre_scores_gemma":[0.98523355,0.000009652615,0.014329487,0.000107862455,0.00009328399,0.00012000483,0.00005019481,0.000013280423,0.000042702013],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99541473,0.00092112867,0.0006721146,0.00043550303,0.0022886605,0.00026788845],"domain_scores_gemma":[0.99711317,0.00035563103,0.00083477586,0.00045273188,0.0010622125,0.00018146036],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.018505536,0.00020116717,0.0003663705,0.00074377836,0.0015999242,0.001915623,0.00034488074,0.000073056864,0.0002562402],"category_scores_gemma":[0.0034146083,0.00017966534,0.00008249484,0.0003378248,0.00022910303,0.002301139,0.00019130207,0.00015975538,0.0000034571442],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010613216,0.00015664478,0.09997958,0.00014372836,0.00012542147,0.0000010312392,0.053815123,0.0043828865,0.0029025534,0.034789782,0.00027028008,0.80332685],"study_design_scores_gemma":[0.0008740122,0.00036941958,0.25332355,0.00043245018,0.00010015966,0.000006043665,0.094269045,0.6258152,0.00011022841,0.024356844,0.00014512429,0.00019786948],"about_ca_topic_score_codex":0.00002717278,"about_ca_topic_score_gemma":0.00008150215,"teacher_disagreement_score":0.80312896,"about_ca_system_score_codex":0.00013088794,"about_ca_system_score_gemma":0.00015691241,"threshold_uncertainty_score":0.99969983},"labels":[],"label_agreement":null},{"id":"W2612736585","doi":"10.3138/cjpe.0023.010","title":"Using Evaluation Capacity Building (ECB) to Interpret Evaluation Strategy and Practice in the United States National Tobacco Control Program (NTCP): A Preliminary Study","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Tobacco control; Control (management); Disease control; State (computer science); Tobacco use; Business; Program evaluation; Environmental health; Computer science; Medicine; Political science; Public administration; Public health; Nursing","score_opus":0.5351127052858893,"score_gpt":0.5825620174973914,"score_spread":0.04744931221150217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2612736585","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9818653,0.00038441864,0.0015152005,0.0050140573,0.00032138775,0.009986403,0.000012714637,0.000013336899,0.00088719715],"genre_scores_gemma":[0.9922042,0.000006439852,0.0059205596,0.0011539186,0.0001648924,0.0004921638,0.00004297733,0.000011531703,0.0000033473034],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98156536,0.007994354,0.0016957455,0.0004812572,0.007811853,0.00045144217],"domain_scores_gemma":[0.9841402,0.001749449,0.0009584496,0.0003445034,0.012429593,0.0003777744],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1077162,0.00025650449,0.00035092482,0.0018640122,0.00040924162,0.0013682245,0.00058945187,0.00011377118,0.00025676782],"category_scores_gemma":[0.029880203,0.00019060835,0.000089149886,0.0024907386,0.0000894835,0.0018999254,0.000016989234,0.00044038348,0.000007711529],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023236145,0.000511258,0.010192063,0.000002243069,0.000051005314,0.0000053230633,0.01416997,0.21551448,0.00004956286,0.0001869866,0.00036496113,0.7587198],"study_design_scores_gemma":[0.00294467,0.004626964,0.2102683,0.00008854987,0.00042317357,0.00011803628,0.021064766,0.7491639,0.000006989595,0.009413617,0.0016757438,0.00020526575],"about_ca_topic_score_codex":0.0015659845,"about_ca_topic_score_gemma":0.010001388,"teacher_disagreement_score":0.7585145,"about_ca_system_score_codex":0.0013522357,"about_ca_system_score_gemma":0.0060971477,"threshold_uncertainty_score":0.9996685},"labels":[],"label_agreement":null},{"id":"W2612922875","doi":"10.1016/j.evalprogplan.2017.05.003","title":"Experiments in evaluation capacity building: Enhancing brain disorders research impact in Ontario","year":2017,"lang":"en","type":"article","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"St. Michael's Hospital; Ontario Brain Institute; University of Toronto","funders":"","keywords":"Capacity building; Program evaluation; Psychological intervention; Research program; Evaluation methods; Business; Public relations; Knowledge management; Engineering; Political science; Computer science; Medicine; Nursing; Public administration","score_opus":0.668659228008001,"score_gpt":0.6638961236352161,"score_spread":0.004763104372784932,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2612922875","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98475254,0.00020618428,0.00013701574,0.0010610225,0.0002601112,0.0018560924,0.0000010770714,0.000018003857,0.011707936],"genre_scores_gemma":[0.9976893,0.000006614849,0.0014492257,0.00005284527,0.000039409348,0.0005160857,0.000020054615,0.000009596216,0.0002168538],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9913758,0.0018986529,0.0007982965,0.00066168065,0.0047589974,0.00050656893],"domain_scores_gemma":[0.9973257,0.0008469014,0.00035784126,0.00062803336,0.00071444974,0.0001270558],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0759088,0.00017541763,0.0002667576,0.00084108463,0.00073906436,0.0012332615,0.00048335234,0.0001232249,0.0016770973],"category_scores_gemma":[0.008361634,0.00014612896,0.00005621081,0.00047336306,0.00014104223,0.0013171788,0.00015022338,0.0005438316,0.00003385338],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049852388,0.000104988496,0.6914602,0.00000256525,0.000006185994,8.6746775e-7,0.010890872,0.0038048518,0.00041409928,0.000088537796,0.00019163315,0.29298538],"study_design_scores_gemma":[0.0016049163,0.00017832751,0.7572256,0.00011598491,0.000005248366,0.0000013382031,0.0017738139,0.22674282,0.00017352722,0.010536503,0.0015035059,0.00013845757],"about_ca_topic_score_codex":0.02063785,"about_ca_topic_score_gemma":0.20763355,"teacher_disagreement_score":0.29284692,"about_ca_system_score_codex":0.0009767746,"about_ca_system_score_gemma":0.0011151512,"threshold_uncertainty_score":0.99999136},"labels":[],"label_agreement":null},{"id":"W2613076730","doi":"10.1016/j.evalprogplan.2017.05.002","title":"Reflections on experiential learning in evaluation capacity building with a community organization, Dancing With Parkinson’s","year":2017,"lang":"en","type":"article","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital","funders":"","keywords":"Experiential learning; Capacity building; Process (computing); Work (physics); Knowledge management; Theory of change; Public relations; Process management; Business; Psychology; Engineering; Political science; Computer science; Sociology; Pedagogy","score_opus":0.4199949220885857,"score_gpt":0.5642586873955286,"score_spread":0.14426376530694296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2613076730","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9851391,0.00003125799,0.004515165,0.00046083686,0.00015519302,0.0010592462,0.0000012470657,0.00008504831,0.00855295],"genre_scores_gemma":[0.9936317,0.000004704584,0.0057763183,0.000105671046,0.00006857115,0.00027605827,0.000049147675,0.00001774721,0.00007006726],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.994604,0.0016600384,0.0004583109,0.00042977382,0.0025930945,0.0002547961],"domain_scores_gemma":[0.9967242,0.00041241152,0.00060647127,0.0005990343,0.0015616587,0.000096209],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.017212708,0.00019009727,0.00022842315,0.0003636777,0.0031410172,0.0013253493,0.0003251321,0.000082063045,0.0003023091],"category_scores_gemma":[0.0037505857,0.00013936001,0.000020286749,0.0006439447,0.00014522184,0.0010349401,0.000072223884,0.0005608833,0.000012035447],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001600464,0.00017236856,0.67796516,0.00000948067,0.000024131568,0.0000014515754,0.024131754,0.0714069,0.00029443513,0.00041189534,0.00004016925,0.22538216],"study_design_scores_gemma":[0.002483867,0.0008096066,0.7554376,0.00032976575,0.00005648537,0.00001677135,0.0113140335,0.22497329,0.00042188232,0.0008058529,0.003083935,0.00026692435],"about_ca_topic_score_codex":0.00019873703,"about_ca_topic_score_gemma":0.0012440444,"teacher_disagreement_score":0.22511524,"about_ca_system_score_codex":0.00021337382,"about_ca_system_score_gemma":0.0003935589,"threshold_uncertainty_score":0.9997114},"labels":[],"label_agreement":null},{"id":"W2613211359","doi":"10.58079/azj0","title":"Approches et pratiques en évaluation de programme","year":2009,"lang":"fr","type":"article","venue":"OpenEdition (OpenEdition)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Humanities; Political science; Art","score_opus":0.12366817072650632,"score_gpt":0.4360871768723677,"score_spread":0.3124190061458614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2613211359","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03857541,0.002209297,0.0766954,0.7376841,0.004576204,0.0031558904,0.0002613393,0.00034505906,0.13649733],"genre_scores_gemma":[0.7626198,0.0021936777,0.05990062,0.12758954,0.0022305616,0.00085021387,0.0018998947,0.00005823147,0.04265745],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99055034,0.0026217515,0.0016027855,0.001066204,0.0031881572,0.00097076205],"domain_scores_gemma":[0.99504066,0.0012447565,0.00083700166,0.00084052386,0.0015171963,0.000519868],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["scholarly_communication","insufficient_payload"],"category_scores_codex":[0.015441914,0.00055947556,0.0006073731,0.0004817724,0.0007264133,0.0020288518,0.0009774968,0.0005223939,0.018534305],"category_scores_gemma":[0.0025712836,0.00053298904,0.0002930471,0.0012971137,0.00028607273,0.027590247,0.00013927238,0.00066948525,0.005358558],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010944439,0.0010189665,0.00048677032,0.00004659106,0.00005070295,0.000019298808,0.0029205165,0.0016905746,0.0006555599,0.512776,0.0366511,0.44357446],"study_design_scores_gemma":[0.0024743204,0.0019951742,0.19245279,0.00058013503,0.00020168412,0.00015448571,0.004473105,0.027282061,0.005808439,0.13675429,0.6266948,0.0011286922],"about_ca_topic_score_codex":0.000079123674,"about_ca_topic_score_gemma":0.0011597115,"teacher_disagreement_score":0.7240444,"about_ca_system_score_codex":0.00064879743,"about_ca_system_score_gemma":0.0029174627,"threshold_uncertainty_score":0.99971217},"labels":[],"label_agreement":null},{"id":"W2614034809","doi":"","title":"Participation Trends In And Lessons Learned From Outreach","year":2007,"lang":"en","type":"article","venue":"Women in Engineering ProActive Network","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Outreach; Engineering ethics; Engineering; Engineering management; Political science; Computer science","score_opus":0.19836966444470258,"score_gpt":0.46001249182122617,"score_spread":0.26164282737652356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2614034809","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9902076,0.000068799476,0.0052540717,0.0003775935,0.00021430178,0.00009215129,0.0000021833318,0.000025108842,0.0037581616],"genre_scores_gemma":[0.99846,0.000015776337,0.0008755792,0.00003791197,0.00011924631,0.00005883296,0.0000069120424,0.000008643867,0.000417131],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9983713,0.00006966148,0.0003947132,0.0003004178,0.00043329495,0.00043060916],"domain_scores_gemma":[0.99899906,0.00061741704,0.00007373653,0.00018041719,0.000034945435,0.00009443924],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043827943,0.0001056296,0.00019873715,0.00037032962,0.00003294379,0.00006286392,0.000120646626,0.000062856445,0.00019642952],"category_scores_gemma":[0.00022133444,0.00009245153,0.000018121984,0.0011210361,0.000017112834,0.00024103317,0.000043707987,0.00019507235,0.000014188772],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008624755,0.00006845131,0.2264349,0.0000018467588,0.000015010384,0.0000042119973,0.009868177,0.33282253,0.00008904629,0.00075241015,0.00007958121,0.4297776],"study_design_scores_gemma":[0.00044107132,0.000034318662,0.8818777,0.000014452198,0.000001525931,1.7048097e-7,0.0007989133,0.11129953,0.000050248473,0.0028005028,0.0025761356,0.000105393694],"about_ca_topic_score_codex":0.00004024511,"about_ca_topic_score_gemma":0.0002933217,"teacher_disagreement_score":0.65544283,"about_ca_system_score_codex":0.00023653162,"about_ca_system_score_gemma":0.000022460245,"threshold_uncertainty_score":0.3770064},"labels":[],"label_agreement":null},{"id":"W261564656","doi":"10.3138/cjpe.23.008","title":"Moments of Truth: An Unexplored Dimension to Communicate Effectiveness","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Dimension (graph theory); Psychology; Mathematics; Computer science; Epistemology; Philosophy; Combinatorics","score_opus":0.6291875856848531,"score_gpt":0.5714788075621933,"score_spread":0.05770877812265984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W261564656","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9969319,0.00013502546,0.0005616374,0.00045170786,0.00059482385,0.00087215716,0.000008393598,0.0000055717605,0.0004387783],"genre_scores_gemma":[0.99678594,0.000011248179,0.002989018,0.00007481333,0.00004567781,0.000047186357,0.000017604032,0.000009277824,0.000019250134],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9951123,0.0014562093,0.0009174533,0.00017203281,0.0021243284,0.000217704],"domain_scores_gemma":[0.9946983,0.00042152134,0.0006279519,0.000497424,0.0031541656,0.0006006549],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014725799,0.00011066334,0.0003080802,0.00080852193,0.00024124622,0.000083638406,0.00063058734,0.000059234215,0.00043027633],"category_scores_gemma":[0.002363577,0.00008612325,0.00010323708,0.0009427145,0.00010727634,0.00070247817,0.000022989057,0.00014367653,0.000043947522],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024053075,0.00032037523,0.12953782,0.000012377579,0.00007552934,0.00001562613,0.007924815,0.01826162,0.0021265692,0.0005440908,0.0011546985,0.83978593],"study_design_scores_gemma":[0.002380152,0.0030950685,0.9360617,0.00015208252,0.000083987194,0.00007565042,0.0016786115,0.038870595,0.003587464,0.005433769,0.008351843,0.00022907942],"about_ca_topic_score_codex":0.0005378532,"about_ca_topic_score_gemma":0.0032763863,"teacher_disagreement_score":0.8395569,"about_ca_system_score_codex":0.0003034692,"about_ca_system_score_gemma":0.002510855,"threshold_uncertainty_score":0.5103697},"labels":[],"label_agreement":null},{"id":"W2616065796","doi":"","title":"Using Knowledge Brokering to Promote Evidence-Based Policy-Making: The Need for Support structures/Promotion De L'elaboration Des Politiques Sur la Base D'elements Factuels Grace a la Transmission Du Savoir: Necessite De Structures De soutien/Tecnicas De Mediacion De Conocimientos Para Promover la Formulacion De Politicas Basadas En la Evidencia: Necesidad De Estructuras De Apoyo","year":2006,"lang":"es","type":"article","venue":"Bulletin of the World Health Organization","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Public relations; Knowledge translation; Context (archaeology); Knowledge base; Promotion (chess); Process (computing); Foundation (evidence); Face (sociological concept); Health policy; Evidence-based policy; Sociology of scientific knowledge; Sociology; Knowledge management; Political science; Computer science; Medicine; Health care; Politics; Social science; World Wide Web","score_opus":0.09647297580064364,"score_gpt":0.44513964392420524,"score_spread":0.3486666681235616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2616065796","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7957863,0.00024747427,0.17564383,0.025920017,0.000076119664,0.0020398789,0.00008415241,0.00009973991,0.00010249423],"genre_scores_gemma":[0.9345757,0.0002221107,0.062015306,0.0023939097,0.00038904132,0.000092507405,0.000051260846,0.0001110828,0.00014908366],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98866266,0.0065033394,0.0015574372,0.0006747018,0.0010980404,0.0015038309],"domain_scores_gemma":[0.9920255,0.004295489,0.0013816201,0.0005836655,0.0011566931,0.00055700896],"candidate_categories":["metaresearch","metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.014791493,0.0005746955,0.00061751617,0.0006444779,0.0013595719,0.00084224413,0.00093557464,0.00048186583,0.00027039778],"category_scores_gemma":[0.009923035,0.0004475226,0.00020625112,0.0016108878,0.0002966387,0.00053854357,0.0001810947,0.00059792196,0.0000036893305],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.0012492923,0.00068579207,0.63577205,0.0036290695,0.000153012,0.000016874512,0.064352736,0.10145133,0.10048703,0.064651825,0.00610142,0.021449555],"study_design_scores_gemma":[0.0025503098,0.00052430894,0.6408136,0.0037599984,0.0004025044,0.00030294902,0.0017865461,0.121104635,0.17479965,0.037829757,0.015274298,0.0008514438],"about_ca_topic_score_codex":0.0033152408,"about_ca_topic_score_gemma":0.0009875511,"teacher_disagreement_score":0.1387894,"about_ca_system_score_codex":0.005400309,"about_ca_system_score_gemma":0.014930249,"threshold_uncertainty_score":0.9999405},"labels":[],"label_agreement":null},{"id":"W2616580122","doi":"10.4000/ries.5765","title":"Le Canada dans le PISA 2015 : une aventure renouvelée au sein d’épreuves internationales…","year":2017,"lang":"fr","type":"article","venue":"Revue internationale d éducation de Sèvres","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.17345554631066898,"score_gpt":0.45398665308900454,"score_spread":0.2805311067783356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2616580122","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34423593,0.0019368201,0.008597532,0.42005444,0.0149579095,0.00053341524,0.00045712382,0.00004465924,0.20918217],"genre_scores_gemma":[0.6605206,0.000356147,0.00072503707,0.0006891687,0.001175167,0.00006950601,0.00015364932,0.000027711414,0.33628303],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9953557,0.000441609,0.0011446654,0.00075884105,0.0017950764,0.00050410954],"domain_scores_gemma":[0.9945828,0.0008878665,0.0014004925,0.0012929426,0.0015233293,0.00031257264],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0026699004,0.00034837605,0.00037899608,0.00032237175,0.0014610187,0.0010576325,0.002577565,0.00021358997,0.0024253791],"category_scores_gemma":[0.003619155,0.00038323292,0.00020662934,0.00027183376,0.00039778868,0.0017248694,0.00032235263,0.00044073496,0.0004270999],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008056935,0.00089605205,0.11344019,0.00014881139,0.00037237836,0.00004006085,0.017219609,0.009573757,0.00046938067,0.5105731,0.26850906,0.078677036],"study_design_scores_gemma":[0.00086594577,0.000041898027,0.3023698,0.00039887906,0.000031158575,0.00008048692,0.0067010964,0.019873261,0.0009600404,0.017942568,0.6503481,0.00038676095],"about_ca_topic_score_codex":0.7649869,"about_ca_topic_score_gemma":0.95558774,"teacher_disagreement_score":0.4926305,"about_ca_system_score_codex":0.00301261,"about_ca_system_score_gemma":0.023757486,"threshold_uncertainty_score":0.9999794},"labels":[],"label_agreement":null},{"id":"W2616845762","doi":"10.3138/cjpe.328","title":"A Case Study of the Guiding Principles for Collaborative Approaches to Evaluation in a Developmental Evaluation Context","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Context (archaeology); Set (abstract data type); Reflection (computer programming); Engineering ethics; Sociology; Psychology; Knowledge management; Management science; Computer science; Engineering","score_opus":0.9106579329392426,"score_gpt":0.5628987801781327,"score_spread":0.3477591527611099,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2616845762","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98442066,0.00012051433,0.00023358618,0.0014125762,0.0006805535,0.012077159,0.000012598627,0.000002218585,0.0010401321],"genre_scores_gemma":[0.99528795,7.1408266e-7,0.0030441347,0.000046588633,0.00008135614,0.0014899422,0.000005189169,0.000010834903,0.000033263954],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9920684,0.0018031584,0.0016006816,0.00032885684,0.003932361,0.00026653492],"domain_scores_gemma":[0.98879313,0.00037740733,0.0020797548,0.0005437232,0.007962837,0.00024315504],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.064809516,0.000163367,0.00034562,0.00073820323,0.00086905586,0.0006243639,0.0008291595,0.00007674073,0.00023190225],"category_scores_gemma":[0.021869153,0.00011448229,0.000102367085,0.0007839989,0.000097840944,0.00086140016,0.000053429198,0.00011883363,0.000004689034],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006512539,0.00020470709,0.12024122,0.0000059622143,0.000057240646,0.0000069408584,0.03357006,0.02023438,0.000033513228,0.00021929716,0.00022471698,0.82513684],"study_design_scores_gemma":[0.007303105,0.0014681276,0.29415387,0.00016177403,0.00039006304,0.00019132238,0.20697147,0.48342752,0.00036446797,0.0030249713,0.0022904216,0.00025288848],"about_ca_topic_score_codex":0.0019691044,"about_ca_topic_score_gemma":0.3927177,"teacher_disagreement_score":0.82488394,"about_ca_system_score_codex":0.0016204901,"about_ca_system_score_gemma":0.015704846,"threshold_uncertainty_score":0.9898752},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":["metaresearch"],"domain":"methods","study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W2617611687","doi":"","title":"L'échange de connaissances en petite enfance: Comment mettre à profit les expertises des chercheurs et des praticiens","year":2011,"lang":"fr","type":"book","venue":"Project Muse (Johns Hopkins University)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Humanities; Political science; Art","score_opus":0.29784747056905814,"score_gpt":0.42751119483267636,"score_spread":0.12966372426361822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2617611687","genre_codex":"other","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05481192,0.00026619388,0.006190339,0.0030901297,0.0006691304,0.0024636548,0.00027467078,0.0002498941,0.93198407],"genre_scores_gemma":[0.21435204,0.7140307,0.027250588,0.0028380435,0.0006286703,0.00015015677,0.00024115726,0.00022148501,0.040287174],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9913316,0.003268225,0.00092140824,0.0014059102,0.00179163,0.0012812288],"domain_scores_gemma":[0.993382,0.0021069644,0.0009843461,0.001065339,0.0020166058,0.00044477603],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0045761126,0.0010163909,0.0011051336,0.0097800605,0.0013756913,0.0004682262,0.0022564514,0.00074714725,0.0029279552],"category_scores_gemma":[0.0017180317,0.0009393616,0.0005177076,0.006137134,0.0025983204,0.0020886841,0.0008404127,0.0010779478,0.00031945726],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000854641,0.001377052,0.060566258,0.0012712368,0.0010416971,0.0005730443,0.37660998,0.00029878956,0.000091219794,0.11823613,0.007586941,0.431493],"study_design_scores_gemma":[0.0013322615,0.0008014863,0.003459935,0.001327551,0.00039204143,0.000043302458,0.016151898,0.0010844689,0.0011078364,0.0001405866,0.9730925,0.001066158],"about_ca_topic_score_codex":0.038746186,"about_ca_topic_score_gemma":0.07877747,"teacher_disagreement_score":0.96550554,"about_ca_system_score_codex":0.0027596224,"about_ca_system_score_gemma":0.00700731,"threshold_uncertainty_score":0.99992436},"labels":[],"label_agreement":null},{"id":"W2617771608","doi":"","title":"Changes in Application, Admission, and Acceptance Rates of Underrepresented Groups in Ontario","year":2017,"lang":"en","type":"article","venue":"2017 Conference of the Canadian Society for the Study of Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Underrepresented Minority; Medicine; Medical education","score_opus":0.2619304662038329,"score_gpt":0.4688939690831858,"score_spread":0.2069635028793529,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2617771608","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9894312,0.000051515868,0.00004084771,0.007926383,0.00022461134,0.0010888294,0.00000821868,6.9417564e-7,0.0012276687],"genre_scores_gemma":[0.9987327,0.000025606676,0.00009196748,0.00006703004,0.000013052575,0.000112147536,0.0000022249783,0.000002669524,0.0009526145],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989541,0.000054930464,0.00034442169,0.00017981078,0.00035840823,0.00010832599],"domain_scores_gemma":[0.9977087,0.00025341933,0.00063872593,0.0008153824,0.0005328725,0.000050938088],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001864991,0.00006893142,0.00017638017,0.00006999487,0.00035922372,0.00007095546,0.0009794511,0.000043188258,0.00007894959],"category_scores_gemma":[0.0006492692,0.000042545817,0.000055661923,0.00014202886,0.0002036142,0.00017110888,0.00007052201,0.00009023281,4.755217e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011904035,0.00012361552,0.9578243,0.0000094935795,0.000016453641,5.121559e-9,0.023384012,0.000038124657,0.000123274,0.0013903984,0.0012733391,0.015805086],"study_design_scores_gemma":[0.00035422077,0.000043273085,0.95428693,0.00003763035,0.000012130507,1.2711033e-7,0.03609521,0.0016044605,0.00019162547,0.006485533,0.00084609014,0.0000427831],"about_ca_topic_score_codex":0.5739856,"about_ca_topic_score_gemma":0.9961009,"teacher_disagreement_score":0.4221153,"about_ca_system_score_codex":0.00014016917,"about_ca_system_score_gemma":0.0025604458,"threshold_uncertainty_score":0.4542121},"labels":[],"label_agreement":null},{"id":"W2618111936","doi":"","title":"Canadian Perspectives on a Few Stakes Relating to the Activity of Auditing, Counselling and Evaluation in Public Administration","year":2015,"lang":"en","type":"article","venue":"Revue française d’administration publique","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Audit; Normative; Relevance (law); Accountability; Task (project management); Administration (probate law); Control (management); Political science; Public relations; Process management; Computer science; Business; Accounting; Management; Artificial intelligence; Economics","score_opus":0.18049504173587053,"score_gpt":0.42125903187336966,"score_spread":0.24076399013749913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2618111936","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9232235,0.00014074183,0.0018986753,0.061605494,0.00021217429,0.0010087617,0.000032889893,0.000020168134,0.011857606],"genre_scores_gemma":[0.9986648,0.000034568744,0.00033393485,0.00031045265,0.00013586924,0.00013580709,0.000029240668,0.000011935339,0.00034338402],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99595416,0.00079930114,0.0007925584,0.0005366463,0.0016347448,0.0002825833],"domain_scores_gemma":[0.99606705,0.0007626677,0.00052373216,0.0005069069,0.0017692993,0.00037037188],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014091514,0.00017961401,0.00026469992,0.0006982462,0.00025050054,0.00055911124,0.00033513227,0.00013901586,0.00020373224],"category_scores_gemma":[0.005178677,0.00014311128,0.000054097934,0.0013117952,0.00006825253,0.0011335342,0.000013601878,0.0002967179,0.00003795916],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010412796,0.0011730836,0.12094201,0.00011617244,0.000101447455,0.000028140279,0.15286998,0.025281865,0.00098805,0.46005815,0.010600235,0.22679956],"study_design_scores_gemma":[0.003645319,0.0041650007,0.21829237,0.0004698811,0.00008510992,0.00009464844,0.0655595,0.4461928,0.002516057,0.019031186,0.23862365,0.0013244833],"about_ca_topic_score_codex":0.0041159084,"about_ca_topic_score_gemma":0.3517932,"teacher_disagreement_score":0.441027,"about_ca_system_score_codex":0.00036613975,"about_ca_system_score_gemma":0.0068347044,"threshold_uncertainty_score":0.9987956},"labels":[],"label_agreement":null},{"id":"W2618724611","doi":"","title":"Use of comparative performance indicators in rehabilitation","year":2017,"lang":"en","type":"preprint","venue":"RePEc: Research Papers in Economics","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Institut de Readaptation Gingras Lindsay de Montreal; Université de Montréal","funders":"","keywords":"Benchmarking; Performance indicator; Rehabilitation; Process management; Accountability; Business; Organizational performance; Set (abstract data type); Quality (philosophy); Knowledge management; Psychology; Marketing; Computer science; Political science","score_opus":0.3291881580341981,"score_gpt":0.5289024650894123,"score_spread":0.1997143070552142,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2618724611","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95133376,0.000026041536,0.0000020033533,0.0004520612,0.00032127797,0.00078858965,0.000034253186,0.000006684974,0.04703534],"genre_scores_gemma":[0.9951724,0.0017171525,0.0012332947,0.000022035983,0.00004151822,0.0001743751,0.000025159028,0.000013492958,0.0016006068],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9948844,0.00093135843,0.0015696017,0.0008684739,0.00130964,0.0004365407],"domain_scores_gemma":[0.9921782,0.0044933613,0.00092645234,0.0018382919,0.00044947697,0.00011423545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015072593,0.00021307927,0.0007444197,0.0030608692,0.00015735967,0.0003350273,0.0014491003,0.00030633586,0.00027681765],"category_scores_gemma":[0.004211111,0.000192339,0.00013601611,0.00046771512,0.00067138975,0.0006868851,0.001011517,0.0012935414,0.00004088203],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013250676,0.00015615635,0.6550771,0.000061014704,0.000017000511,0.0000013656498,0.0036614523,0.05705041,0.000018997105,0.00048041364,0.00012024802,0.28322333],"study_design_scores_gemma":[0.00047956762,0.0002004625,0.8612659,0.00029610633,0.0000024337803,6.249428e-7,0.0019319615,0.11372383,0.00016813891,0.0033943232,0.018300572,0.00023608908],"about_ca_topic_score_codex":0.00009393212,"about_ca_topic_score_gemma":0.0009934132,"teacher_disagreement_score":0.28298727,"about_ca_system_score_codex":0.00072754413,"about_ca_system_score_gemma":0.0014826894,"threshold_uncertainty_score":0.7843357},"labels":[],"label_agreement":null},{"id":"W2619698812","doi":"10.1055/s-2004-814549","title":"On the Value of Evaluation","year":2004,"lang":"de","type":"article","venue":"Aktuelle Dermatologie","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Value (mathematics); Medicine; Humanities; Philosophy; Computer science","score_opus":0.18413924728936398,"score_gpt":0.4602337598234607,"score_spread":0.2760945125340967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2619698812","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89755815,0.0042695967,0.0028504462,0.055875923,0.003778595,0.0014857324,0.000029451196,0.000050140185,0.034101944],"genre_scores_gemma":[0.9955912,0.00056195795,0.0003038615,0.0031974313,0.00007351799,0.000057399004,0.000013984722,0.000012767087,0.0001878534],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99328643,0.0010440722,0.0011064119,0.00047685878,0.0037031947,0.00038303767],"domain_scores_gemma":[0.9940612,0.0031090574,0.00065525476,0.0012242905,0.0008613529,0.00008886038],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008160918,0.00025382836,0.00040583432,0.00022967401,0.00038845307,0.00014299803,0.0008905625,0.00018751474,0.0043294774],"category_scores_gemma":[0.004876509,0.00014826994,0.00022407208,0.00092523964,0.00035328977,0.00026073772,0.00017143002,0.0003116013,0.007456996],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015972415,0.00091041176,0.007096169,0.000055422617,0.00025214578,0.000025513855,0.0030102713,0.13628177,0.00034788236,0.7435045,0.07197921,0.036376953],"study_design_scores_gemma":[0.0042138495,0.0006740714,0.027077712,0.00035961397,0.00041078363,0.000035085053,0.0052742395,0.15731782,0.03837328,0.72704715,0.038549386,0.0006669875],"about_ca_topic_score_codex":0.000034331813,"about_ca_topic_score_gemma":0.000016087668,"teacher_disagreement_score":0.098033056,"about_ca_system_score_codex":0.00018296704,"about_ca_system_score_gemma":0.0014900947,"threshold_uncertainty_score":0.9965807},"labels":[],"label_agreement":null},{"id":"W2620297369","doi":"10.1007/978-3-319-56129-5","title":"Understanding and Investigating Response Processes in Validation Research","year":2017,"lang":"en","type":"book","venue":"Social indicators research series","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":131,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Psychology; Test (biology); Data science; Computer science; Biology","score_opus":0.8421524619491882,"score_gpt":0.6459391458506124,"score_spread":0.19621331609857584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2620297369","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19701567,0.0007794315,0.000036904356,0.025178844,0.0004491682,0.00262036,0.00013375621,0.00009478271,0.77369106],"genre_scores_gemma":[0.5101663,0.0006919696,0.0001003471,0.000040781797,0.00055099383,0.00020289057,0.000058523554,0.000056850367,0.48813137],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98241276,0.0052147596,0.00094874,0.00096133986,0.009536144,0.0009262478],"domain_scores_gemma":[0.9875684,0.009066406,0.0005899268,0.0006854331,0.0018202224,0.00026962036],"candidate_categories":["metaresearch","sts","scholarly_communication","research_integrity"],"consensus_categories":["metaresearch","sts"],"category_scores_codex":[0.09630429,0.00025956647,0.00054154085,0.004855587,0.0045967945,0.0028714705,0.0015169017,0.00063123676,0.00045183627],"category_scores_gemma":[0.05306182,0.00022603646,0.00006114967,0.0023216344,0.0044099586,0.0015497344,0.0009750838,0.0025727353,0.00018508753],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021439726,0.00019975723,0.07754075,0.001403768,0.00017251623,0.00010278935,0.17705224,0.000015115906,0.00051987194,0.25020677,0.46807113,0.022571295],"study_design_scores_gemma":[0.00045951962,0.0003940171,0.013049088,0.00055825047,0.000006229721,0.000002954194,0.02553471,0.000024441608,0.00028905377,0.6822923,0.27700573,0.00038372842],"about_ca_topic_score_codex":0.00006141275,"about_ca_topic_score_gemma":0.00093258976,"teacher_disagreement_score":0.43208548,"about_ca_system_score_codex":0.0018938617,"about_ca_system_score_gemma":0.014279218,"threshold_uncertainty_score":0.9997284},"labels":[],"label_agreement":null},{"id":"W2621195220","doi":"","title":"The Cost of Failure in Ontario's Public Secondary Schools","year":2013,"lang":"en","type":"dissertation","venue":"Library and Archives Canada (Government of Canada)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Public administration; Business","score_opus":0.027282137893668068,"score_gpt":0.2551548744604858,"score_spread":0.22787273656681772,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2621195220","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44068363,0.0002996742,0.0000058337573,0.0081797475,0.0006782733,0.00055939535,0.00013316188,0.000003326592,0.54945695],"genre_scores_gemma":[0.8815364,0.00011480374,0.00017398605,0.00042952507,0.000021334414,0.000037623427,0.000063535845,0.000012509978,0.11761023],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9935381,0.00016056364,0.0008657601,0.00029891255,0.004858712,0.0002779462],"domain_scores_gemma":[0.99780923,0.0009154089,0.00067484775,0.00040233083,0.0000061632804,0.00019198969],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00013351698,0.00020502594,0.00037827753,0.00007883982,0.00020574486,0.00015347746,0.00073147565,0.000059760612,0.0012524425],"category_scores_gemma":[0.00004126859,0.0001407733,0.000047102858,0.00018991789,0.000056480643,0.00076911616,0.000092129245,0.0005235346,2.8159203e-8],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008803624,0.00009537254,0.4410616,0.00025399274,0.00022560285,0.000028500759,0.0013633026,0.00016245323,0.004187071,0.21842395,0.05464972,0.27866808],"study_design_scores_gemma":[0.0003745117,0.000048134618,0.6786278,0.00012973566,0.000009616028,0.0000011654353,0.024705492,0.0006107657,0.0055514863,0.004988339,0.28473568,0.00021726986],"about_ca_topic_score_codex":0.08012675,"about_ca_topic_score_gemma":0.99049705,"teacher_disagreement_score":0.91037035,"about_ca_system_score_codex":0.00002666838,"about_ca_system_score_gemma":0.018690431,"threshold_uncertainty_score":0.99966055},"labels":[],"label_agreement":null},{"id":"W2622490200","doi":"","title":"Évaluation des activités de développement des organismes humanitaires québécois en haïti depuis 2005.","year":2017,"lang":"fr","type":"dissertation","venue":"Depositum (Université du Québec en Abitibi-Témiscamingue)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Humanities; Political science; Art","score_opus":0.05018382279723848,"score_gpt":0.3550642215862402,"score_spread":0.3048803987890017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2622490200","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9373509,0.003057608,0.03236534,0.0031790459,0.0014350245,0.0011295903,0.00006957981,0.00021466336,0.021198224],"genre_scores_gemma":[0.91934097,0.0026030703,0.006751308,0.00025148984,0.0005972563,0.000058067904,0.0004966867,0.00016850459,0.06973266],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99037224,0.001770568,0.0014196584,0.0017591296,0.0031426765,0.0015357069],"domain_scores_gemma":[0.9919952,0.0022054887,0.0017752609,0.0015599476,0.00172161,0.0007424954],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["metaepi_narrow","insufficient_payload"],"category_scores_codex":[0.004969128,0.0012899725,0.0012686017,0.0012592452,0.0063527706,0.001539365,0.0028090312,0.00096002576,0.007573335],"category_scores_gemma":[0.0021625347,0.0013554053,0.0006983536,0.00068728806,0.00096512627,0.0027746232,0.00044687165,0.0010394469,0.0014079165],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00034926774,0.00067206606,0.15550874,0.0005173313,0.00070523715,0.00033600777,0.2670434,0.00078663806,0.08127603,0.001194093,0.0049659098,0.48664525],"study_design_scores_gemma":[0.0017063734,0.0004297847,0.89304644,0.0010239675,0.0010311219,0.00018067191,0.06917557,0.0064698993,0.012076439,0.0018133685,0.011566404,0.0014799562],"about_ca_topic_score_codex":0.5638737,"about_ca_topic_score_gemma":0.94902253,"teacher_disagreement_score":0.7375377,"about_ca_system_score_codex":0.006319867,"about_ca_system_score_gemma":0.011414303,"threshold_uncertainty_score":0.9999852},"labels":[],"label_agreement":null},{"id":"W2625272867","doi":"10.7202/1040214ar","title":"La conciliation des intérêts et enjeux entre chercheurs et professionnels lors de la phase initiale de recherches participatives en éducation","year":2017,"lang":"fr","type":"article","venue":"Phronesis","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.6989089805978838,"score_gpt":0.6670262019732578,"score_spread":0.03188277862462596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2625272867","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9295901,0.0005932054,0.0092585385,0.039555337,0.00057198334,0.0004224237,0.00003838337,0.000046968336,0.019923035],"genre_scores_gemma":[0.9841575,0.0020670083,0.0088644745,0.00082864764,0.0001840629,0.0002207867,0.00002272423,0.000027368713,0.0036274479],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98489743,0.012760006,0.00062215637,0.00046753447,0.0007676936,0.00048517837],"domain_scores_gemma":[0.9887921,0.009020856,0.00064187386,0.0006508053,0.00064022385,0.00025413287],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.031098824,0.00026389465,0.0003192806,0.0001565218,0.00070297346,0.000815111,0.00064841786,0.0004196861,0.0017912975],"category_scores_gemma":[0.029757954,0.0002363994,0.00011527515,0.00024150587,0.0009697782,0.0020062204,0.00017914697,0.0005443235,0.00029013964],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002294854,0.0016659333,0.0646701,0.00020579023,0.00009272399,0.000012265123,0.4194088,0.00041628807,0.0067942995,0.009066559,0.0032863552,0.4941514],"study_design_scores_gemma":[0.0035890266,0.00034624926,0.72732675,0.0012534228,0.00021261792,0.000024029461,0.07500584,0.02437927,0.03084077,0.116761625,0.019623887,0.0006365382],"about_ca_topic_score_codex":0.001149858,"about_ca_topic_score_gemma":0.0010482427,"teacher_disagreement_score":0.6626566,"about_ca_system_score_codex":0.0011831226,"about_ca_system_score_gemma":0.005536336,"threshold_uncertainty_score":0.9991212},"labels":[],"label_agreement":null},{"id":"W2625371932","doi":"10.1111/capa.12215","title":"Awareness and use of systematic literature reviews and meta‐analyses by ministerial policy analysts","year":2017,"lang":"en","type":"article","venue":"Canadian Public Administration","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Systematic review; Meta-analysis; Policy analysis; Evidence-based policy; Political science; Public relations; Business; MEDLINE; Public administration; Medicine; Alternative medicine","score_opus":0.5664630750604633,"score_gpt":0.5521975245560327,"score_spread":0.01426555050443068,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2625371932","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86766165,0.016828183,0.0013698908,0.105195984,0.00077084725,0.0033361956,0.0016602967,0.000032468073,0.0031444544],"genre_scores_gemma":[0.99706954,0.00031901064,0.00027150463,0.00040298136,0.0000621801,0.000050752104,0.00007381651,0.000005574558,0.0017446475],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99766123,0.00041352102,0.00085270626,0.0003360746,0.00054911786,0.00018732766],"domain_scores_gemma":[0.99710244,0.0002456183,0.000903133,0.00085160206,0.00045104633,0.00044613957],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0025955194,0.00016131964,0.0006686259,0.0004695504,0.0005419125,0.0034122104,0.0003704138,0.00010253899,0.00017205722],"category_scores_gemma":[0.0059724543,0.000108160726,0.00009639017,0.00033023927,0.00015058968,0.0017238283,0.000036554055,0.00006537741,0.0000068433656],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030918219,0.0005790556,0.32523257,0.038402293,0.00907071,0.00015039618,0.008447687,0.000009223352,0.00934349,0.3302414,0.23815298,0.04006102],"study_design_scores_gemma":[0.0033595779,0.0012895537,0.15555568,0.003320998,0.011805576,0.00040128973,0.0023566578,0.01905648,0.0032389143,0.006832148,0.7900018,0.0027813236],"about_ca_topic_score_codex":0.0020119494,"about_ca_topic_score_gemma":0.12344202,"teacher_disagreement_score":0.5518488,"about_ca_system_score_codex":0.00004976566,"about_ca_system_score_gemma":0.0014568446,"threshold_uncertainty_score":0.9976224},"labels":[],"label_agreement":null},{"id":"W2626053081","doi":"","title":"Evidence Based Policy Development","year":2015,"lang":"en","type":"article","venue":"oURspace (University of Regina)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Public policy; Political science; Public administration; Policy development; Management; Public relations; Economics; Law","score_opus":0.29959647066369066,"score_gpt":0.4143462645717577,"score_spread":0.11474979390806705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2626053081","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15024628,0.000085210195,0.024396753,0.8218983,0.000094004965,0.00008426216,0.0000010749046,0.000022996743,0.0031711366],"genre_scores_gemma":[0.7059992,0.00006066842,0.045039892,0.0005373029,0.000061256585,3.8227518e-7,0.0000028236154,0.0000074877717,0.24829097],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979746,0.00014315722,0.000021850432,0.00022599328,0.001477185,0.00015722576],"domain_scores_gemma":[0.9982612,0.00025097982,0.00021427426,0.0003911311,0.0006890701,0.00019335591],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027449855,0.00007541314,0.00015842095,0.00036984088,0.0001311445,0.00003693783,0.00060748635,0.000044752695,0.00008873331],"category_scores_gemma":[0.00086314976,0.00007323019,0.000054999342,0.0008257633,0.00010850817,0.00067306496,0.00011124417,0.0000656497,0.00060250476],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007127579,0.000025987998,0.023718461,0.000006929411,0.000010528,0.000009166206,0.0016490408,0.0016089978,0.000109912704,0.0037086057,0.906622,0.062459093],"study_design_scores_gemma":[0.00043108242,0.0000699045,0.013633509,0.000054941607,0.0000056284093,0.0000013484083,0.0068051443,0.0048594736,0.00017544889,0.0000657815,0.9738063,0.00009139268],"about_ca_topic_score_codex":0.00001653961,"about_ca_topic_score_gemma":0.00020210736,"teacher_disagreement_score":0.821361,"about_ca_system_score_codex":0.0001873086,"about_ca_system_score_gemma":0.002218999,"threshold_uncertainty_score":0.7744181},"labels":[],"label_agreement":null},{"id":"W262717460","doi":"10.3138/cjpe.018.010","title":"Reflections on the CES Case Competition: The Coaches’ Perspective","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Competition (biology); Enthusiasm; Perspective (graphical); Order (exchange); Curriculum; Psychology; Public relations; Mathematics education; Sociology; Pedagogy; Political science; Business; Computer science; Social psychology","score_opus":0.6127644386593305,"score_gpt":0.5922524016754245,"score_spread":0.020512036983906023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W262717460","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5286001,0.0012151854,0.0024878094,0.11729461,0.0036896556,0.0037414415,0.00002180182,0.000024675644,0.34292474],"genre_scores_gemma":[0.9981166,0.0000068538448,0.00046956426,0.0008984897,0.00016843466,0.00007974619,0.0000012882274,0.0000058509463,0.00025316357],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99574274,0.0017834615,0.00052154245,0.0001523529,0.0016029959,0.0001969161],"domain_scores_gemma":[0.9947631,0.00094383705,0.00046202887,0.00034382482,0.0032708314,0.00021639274],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.018129919,0.000098916986,0.00012425489,0.00029797002,0.0011085868,0.0005587806,0.00034286687,0.00004429487,0.0037123358],"category_scores_gemma":[0.005531213,0.00004856716,0.00012725536,0.0009366641,0.00019607444,0.00028528922,0.0000046469327,0.0003261657,0.00013033174],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002536927,0.00014285932,0.0034388138,0.0000018009523,0.00011810572,0.00010629598,0.015407433,0.008014999,0.000022311211,0.8113175,0.015307902,0.1460966],"study_design_scores_gemma":[0.0012203086,0.0015377138,0.0113380235,0.00006083179,0.00025286662,0.0046635484,0.25771245,0.016219238,0.00024826944,0.22175501,0.48469296,0.00029877934],"about_ca_topic_score_codex":0.00057869335,"about_ca_topic_score_gemma":0.045840163,"teacher_disagreement_score":0.5895625,"about_ca_system_score_codex":0.0005355977,"about_ca_system_score_gemma":0.0034574666,"threshold_uncertainty_score":0.9971984},"labels":[],"label_agreement":null},{"id":"W2634226797","doi":"10.22329/celt.v10i0.4728","title":"Engaging in Enhancement: Implications of Participatory Approaches in Higher Education Quality Assurance","year":2017,"lang":"en","type":"article","venue":"Collected Essays on Learning and Teaching","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Quality assurance; Scrutiny; Accountability; Higher education; Citizen journalism; Quality (philosophy); Public relations; Diversity (politics); Accreditation; Process (computing); Political science; Business; Process management; Engineering ethics; Engineering; Marketing; Computer science","score_opus":0.4660871418587771,"score_gpt":0.5247537382055542,"score_spread":0.05866659634677707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2634226797","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8821049,0.00007798321,0.00030740458,0.0019156092,0.00012436534,0.00014597534,8.5389127e-7,0.0000122239635,0.115310684],"genre_scores_gemma":[0.9956081,0.000015946003,0.00040102622,0.00005840149,0.000027404765,0.00007792444,0.0000037422444,0.000005953363,0.0038014934],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9974696,0.0010568234,0.0005595633,0.00032590385,0.00041607837,0.00017205332],"domain_scores_gemma":[0.99792576,0.0010652522,0.0004950011,0.0003849142,0.0000827889,0.000046298763],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0071539157,0.00009545521,0.00022986246,0.00030443523,0.00071461184,0.0001971836,0.0002694119,0.000053551477,0.0001514428],"category_scores_gemma":[0.0034774262,0.000083725725,0.00002737564,0.00018950502,0.00006604909,0.0003140225,0.00005805179,0.0005010875,0.000007823365],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021588958,0.00018234373,0.87670994,0.000014093463,0.0000041680196,1.1480145e-7,0.0024918874,0.0009839721,0.0007448071,0.022175837,0.00006764391,0.096603595],"study_design_scores_gemma":[0.0004386813,0.00003733102,0.98760366,0.00011458853,0.000003067252,2.1209347e-7,0.0013118649,0.0049035265,0.00018490825,0.0034007942,0.0019018692,0.000099520475],"about_ca_topic_score_codex":0.00015513391,"about_ca_topic_score_gemma":0.00026087096,"teacher_disagreement_score":0.11350321,"about_ca_system_score_codex":0.00007476795,"about_ca_system_score_gemma":0.00022419525,"threshold_uncertainty_score":0.54962885},"labels":[],"label_agreement":null},{"id":"W263836974","doi":"10.3138/cjpe.0014.003","title":"A Framework for Characterizing the Practice of Evaluation, with Application to Empowerment Evaluation","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Empowerment; Sanctions; Diversity (politics); Context (archaeology); Management science; Engineering ethics; Epistemology; Sociology; Psychology; Knowledge management; Computer science; Political science; Engineering; Law","score_opus":0.21391735746675264,"score_gpt":0.545183003893987,"score_spread":0.33126564642723433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W263836974","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8251722,0.0009274751,0.09099039,0.0509442,0.0011207025,0.024979768,0.00004322712,0.00002062019,0.0058014216],"genre_scores_gemma":[0.965483,0.000011194619,0.031179613,0.0010516983,0.00027215455,0.001892018,0.000041281204,0.000017608772,0.000051398376],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99084795,0.0013885824,0.0013917647,0.0003367239,0.005720144,0.00031483482],"domain_scores_gemma":[0.9810356,0.0011683265,0.0015007104,0.00061429146,0.015334818,0.00034627545],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.058795504,0.00017171436,0.0002899406,0.00049632153,0.0003751426,0.00037190024,0.0005322826,0.00009806873,0.0031448484],"category_scores_gemma":[0.010573389,0.00011062345,0.00012658806,0.0013744435,0.000091249225,0.00093182706,0.000008573213,0.00020663966,0.00006094207],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019894581,0.00008204333,0.0011490446,0.000005275692,0.000059160866,2.6363762e-7,0.0036567694,0.019545028,0.00010831574,0.00091129617,0.0009336216,0.9733502],"study_design_scores_gemma":[0.0035280813,0.0033573993,0.082911536,0.00030296436,0.0015548486,0.000098027296,0.006785382,0.48069587,0.0007722619,0.042713832,0.3768523,0.00042749586],"about_ca_topic_score_codex":0.00021291888,"about_ca_topic_score_gemma":0.0023405068,"teacher_disagreement_score":0.97292274,"about_ca_system_score_codex":0.00070641766,"about_ca_system_score_gemma":0.0070281876,"threshold_uncertainty_score":0.998601},"labels":[],"label_agreement":null},{"id":"W2647300701","doi":"","title":"Performance assessment: G8 foreign ministers meeting, Whistler, British Columbia","year":2002,"lang":"en","type":"article","venue":"TSpace (University of Toronto)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Whistler; Council of Ministers; Public administration; Operations research; Engineering; Business; International trade; Physics","score_opus":0.0882419083478615,"score_gpt":0.351160791393753,"score_spread":0.2629188830458915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2647300701","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4765294,0.00013737366,0.00018915554,0.00038483788,0.00014963138,0.00013362145,0.000010489428,0.00003176379,0.52243376],"genre_scores_gemma":[0.8919767,0.0005830366,0.003957808,0.00009118973,0.000029672288,5.8684407e-7,0.0000053731783,0.000008243888,0.10334736],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99744827,0.00012811835,0.00027074927,0.00041616298,0.0014417762,0.00029495152],"domain_scores_gemma":[0.9983654,0.00016600522,0.00040440782,0.0005291189,0.0003779899,0.00015708164],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013562691,0.00011173843,0.0003156084,0.00004360787,0.00054391084,0.0002555689,0.00081655715,0.00009257129,0.24418317],"category_scores_gemma":[0.00007556596,0.00017116313,0.00015234466,0.00020456228,0.00019834854,0.0013901634,0.00017277856,0.000110567584,0.00025447446],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027057049,0.0002582148,0.299117,0.00003879512,0.000066076085,0.000021549411,0.0066443635,0.00016182219,0.00019821334,0.00022793665,0.17624442,0.51699454],"study_design_scores_gemma":[0.0010790033,0.00027474458,0.85916215,0.00006384365,0.00003602009,0.000011264415,0.017609783,0.0626016,0.0000062984955,0.000048687212,0.058843736,0.0002628741],"about_ca_topic_score_codex":0.11116833,"about_ca_topic_score_gemma":0.33307412,"teacher_disagreement_score":0.5600451,"about_ca_system_score_codex":0.0002837674,"about_ca_system_score_gemma":0.00008812152,"threshold_uncertainty_score":0.8947505},"labels":[],"label_agreement":null},{"id":"W267994948","doi":"","title":"Leading From Within - Integral Leadership for Sustainable Development - One Sky: Canadian Institute of Sustainable Living","year":2009,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Sustainable development; Sky; Sustainable living; Sustainability; Political science; Geography; Meteorology; Ecology","score_opus":0.262731225042136,"score_gpt":0.4212126549143073,"score_spread":0.15848142987217134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W267994948","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85374165,0.00015543039,0.040974684,0.0085270675,0.0003571273,0.0013958628,0.000005001469,0.000076900076,0.09476628],"genre_scores_gemma":[0.88656515,0.0000014042229,0.020886399,0.0012175001,0.000049533013,0.000027441345,0.000015630008,0.0000076165547,0.09122934],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.997043,0.00007239455,0.0008159571,0.0003981573,0.0009674299,0.0007030488],"domain_scores_gemma":[0.997474,0.0004348694,0.00024344302,0.0003631834,0.0012098465,0.0002746683],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0053060683,0.00016837969,0.00034233136,0.00068842596,0.0004634168,0.00033467545,0.00059475214,0.00009835109,0.0011626938],"category_scores_gemma":[0.0026434762,0.0001357506,0.00007593046,0.0008004827,0.000068363835,0.001456209,0.000054180087,0.00014265144,0.00007411557],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010659929,0.00024736917,0.027311089,0.00008694542,0.00009024681,0.00003385702,0.033673402,0.0031517213,0.00039832635,0.8690655,0.023442732,0.04239222],"study_design_scores_gemma":[0.0015033846,0.00060178945,0.123030886,0.0002894746,0.000052060186,0.0000026725936,0.5318059,0.016282503,0.014679866,0.090675294,0.22009231,0.0009838864],"about_ca_topic_score_codex":0.041861787,"about_ca_topic_score_gemma":0.1352789,"teacher_disagreement_score":0.7783902,"about_ca_system_score_codex":0.00064693234,"about_ca_system_score_gemma":0.0037742185,"threshold_uncertainty_score":0.9997504},"labels":[],"label_agreement":null},{"id":"W268578929","doi":"10.3138/cjpe.018.012","title":"The CES Case Competition: A Valuable Resource for Community-Based Agencies","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Competition (biology); Resource (disambiguation); Public relations; Limited resources; Marketing; Business; Political science; Computer science","score_opus":0.5127025743481258,"score_gpt":0.5276762218078191,"score_spread":0.014973647459693318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W268578929","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91354156,0.0029485498,0.023121523,0.016334567,0.0030101037,0.0066307615,0.00006996794,0.000040767576,0.03430223],"genre_scores_gemma":[0.993355,0.0000037115863,0.005424759,0.0005541494,0.00009342108,0.00017579123,0.000015286607,0.0000096868325,0.00036823688],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.994419,0.002795329,0.00083482446,0.00011870395,0.0015316027,0.00030058768],"domain_scores_gemma":[0.9925592,0.0023485683,0.0006627161,0.00043221904,0.0036600397,0.0003372484],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.050125197,0.00011235072,0.0001817791,0.0003319853,0.0022589585,0.0008372051,0.00048987614,0.00005955789,0.0006915499],"category_scores_gemma":[0.0071553066,0.00007281335,0.00016324244,0.00063456985,0.00019794136,0.00032741588,0.000006216202,0.00027979558,0.000021906933],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000098794735,0.00017314966,0.0064299973,0.000034715504,0.00010980764,0.0000685287,0.0069178985,0.041680392,0.00005321389,0.028084928,0.047683828,0.86866474],"study_design_scores_gemma":[0.0012181201,0.00075138157,0.0007816802,0.000035292407,0.00009030308,0.00040226796,0.01590375,0.04990901,0.00020145981,0.023820799,0.90675944,0.00012651214],"about_ca_topic_score_codex":0.00035356433,"about_ca_topic_score_gemma":0.040430177,"teacher_disagreement_score":0.86853826,"about_ca_system_score_codex":0.00038575497,"about_ca_system_score_gemma":0.0065175095,"threshold_uncertainty_score":0.99911463},"labels":[],"label_agreement":null},{"id":"W268891095","doi":"10.3138/cjpe.0015.009","title":"A Performance Measurement and Evaluation Framework for Continuing Education","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Continuing education; Performance measurement; Data collection; Evaluation methods; Computer science; Process management; Business; Medical education; Engineering; Statistics; Reliability engineering; Mathematics; Medicine; Marketing","score_opus":0.44393524640381515,"score_gpt":0.5410512913199274,"score_spread":0.0971160449161122,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W268891095","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9803695,0.0018298466,0.009521586,0.0023344774,0.0014949843,0.0027592771,0.0000022229399,0.000007981344,0.0016800998],"genre_scores_gemma":[0.9827579,0.000057079655,0.016188208,0.00016942718,0.00036618678,0.00038196967,0.000008888714,0.00001049157,0.000059844046],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99482846,0.00043623138,0.0009123235,0.00023409846,0.003322633,0.0002662792],"domain_scores_gemma":[0.9872529,0.0002450633,0.00081334595,0.00024467774,0.01106791,0.00037613354],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03751922,0.00012849465,0.00021743268,0.00063726894,0.00026263102,0.0004617994,0.00026671038,0.00009497721,0.00066309166],"category_scores_gemma":[0.008429529,0.00010576938,0.000088686014,0.0005812864,0.00006285819,0.0008269981,0.000007421845,0.00015645428,0.00001412521],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002704436,0.00003353739,0.037130494,0.000006142117,0.000013739291,1.655958e-7,0.0009971255,0.0007442045,0.000028425064,0.00053812837,0.00075333926,0.95972764],"study_design_scores_gemma":[0.002131611,0.0011757503,0.3358462,0.0005142589,0.00038750554,0.00009914981,0.004850159,0.49216226,0.00012663726,0.06531086,0.09708182,0.0003137914],"about_ca_topic_score_codex":0.0000808625,"about_ca_topic_score_gemma":0.0027450162,"teacher_disagreement_score":0.9594139,"about_ca_system_score_codex":0.00068691495,"about_ca_system_score_gemma":0.006253464,"threshold_uncertainty_score":0.9999229},"labels":[],"label_agreement":null},{"id":"W269339287","doi":"","title":"STRESSFUL, HECTIC, DAUNTING: A CRITICAL POLICY STUDY OF THE ONTARIO TEACHER PERFORMANCE APPRAISAL SYSTEM","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Educational Administration and Policy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Accountability; Performance appraisal; Perspective (graphical); Critical appraisal; Policy analysis; Teacher education; Pedagogy; Education policy; Political science; Sociology; Psychology; Public administration; Higher education; Management; Economics; Medicine; Computer science","score_opus":0.09902617439614883,"score_gpt":0.4796405919107734,"score_spread":0.38061441751462455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W269339287","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95497394,0.000036936664,0.0000071423015,0.030759752,0.00044434925,0.0001309586,0.0000072089674,0.0000013684761,0.013638346],"genre_scores_gemma":[0.9969016,0.0000016806589,0.000076894714,0.00048401853,0.00079149107,0.0000029672046,0.0000015302263,0.0000037507075,0.001736077],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9978362,0.0002004087,0.0008273702,0.0001446119,0.00079945714,0.00019196738],"domain_scores_gemma":[0.9976648,0.000449645,0.0004676856,0.00023978196,0.00075710437,0.00042099194],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012698562,0.00011149209,0.00019938628,0.00054411247,0.00035186313,0.00023863686,0.00039115784,0.00005066937,0.0006805298],"category_scores_gemma":[0.0029236567,0.000075318414,0.0000684859,0.0005929466,0.000119006385,0.00039293818,0.000009992021,0.00022991266,0.000009511406],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004981138,0.00041828206,0.8580458,0.000015581169,0.000028292447,0.0000019318527,0.015071514,0.00016975509,0.000023781522,0.115924746,0.0039744712,0.006276028],"study_design_scores_gemma":[0.00033991114,0.0006506682,0.98398393,0.000041564737,0.00001911252,0.00015321777,0.0062341713,0.00016371463,0.000029298279,0.0012437596,0.0070623956,0.00007826396],"about_ca_topic_score_codex":0.019766718,"about_ca_topic_score_gemma":0.16124761,"teacher_disagreement_score":0.1414809,"about_ca_system_score_codex":0.0003261338,"about_ca_system_score_gemma":0.022399122,"threshold_uncertainty_score":0.98676074},"labels":[],"label_agreement":null},{"id":"W2701826080","doi":"10.1332/174426417x14945838375124","title":"Development of a framework for knowledge mobilisation and impact competencies","year":2017,"lang":"en","type":"article","venue":"Evidence & Policy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; York University","funders":"","keywords":"Competence (human resources); Knowledge management; Process (computing); Set (abstract data type); Psychology; Computer science; Social psychology","score_opus":0.5018446917631735,"score_gpt":0.6137119546868033,"score_spread":0.1118672629236298,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2701826080","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9791625,0.00034296385,0.016966663,0.0020180019,0.00014086266,0.00032061874,0.0000055820606,0.000010221292,0.0010325703],"genre_scores_gemma":[0.9574797,0.000053865726,0.04184625,0.00007866196,0.00013701433,0.000042912838,7.5545853e-7,0.000004349342,0.00035650286],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9985227,0.00006124225,0.00046648737,0.00022247204,0.00055915694,0.00016792408],"domain_scores_gemma":[0.9965501,0.001836358,0.00046515357,0.0005887156,0.00047323824,0.000086426604],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0037106504,0.00009564739,0.00020495654,0.00019122468,0.0005163743,0.00028811613,0.00055169046,0.00005143954,0.00016010362],"category_scores_gemma":[0.016471727,0.00006503354,0.000066265566,0.00015372876,0.0001718154,0.0008377563,0.00014577946,0.000056854897,0.00005731951],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008602874,0.00008367184,0.14249973,0.000061879065,0.000030499068,1.416867e-7,0.04761236,0.00007618585,0.0032581938,0.06902393,0.0010742764,0.7361931],"study_design_scores_gemma":[0.00023766466,0.00013124802,0.91393495,0.00028024247,0.000008173852,0.0000015245297,0.0018177651,0.0047816634,0.002737403,0.06675416,0.009175153,0.00014007265],"about_ca_topic_score_codex":0.000077401666,"about_ca_topic_score_gemma":0.00015719025,"teacher_disagreement_score":0.7714352,"about_ca_system_score_codex":0.00008047594,"about_ca_system_score_gemma":0.001098325,"threshold_uncertainty_score":0.99181294},"labels":[],"label_agreement":null},{"id":"W2721840214","doi":"","title":"L'évaluation des enseignants permanents au Québec: une question actuelle et litigieuse","year":2017,"lang":"fr","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Humanities; Philosophy; Political science","score_opus":0.7008908610215171,"score_gpt":0.6810978034072567,"score_spread":0.019793057614260423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2721840214","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9219449,0.021087473,0.0015536014,0.0065368963,0.004015392,0.0008582292,0.0000990559,0.00003166225,0.043872755],"genre_scores_gemma":[0.9353683,0.03957359,0.0009722659,0.00065050443,0.0003964797,0.000056327437,0.000025628979,0.00005918853,0.022897724],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99034494,0.0019763224,0.00210521,0.0008969976,0.0039117434,0.00076480414],"domain_scores_gemma":[0.9907202,0.0012416389,0.003424873,0.0018276367,0.00220264,0.00058299775],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.017602049,0.00056423433,0.0010656881,0.0010301762,0.002988797,0.009589158,0.0065276204,0.00028526396,0.031614095],"category_scores_gemma":[0.0047759768,0.0004931382,0.0003692334,0.0009042245,0.000899486,0.018937511,0.0018327396,0.00065478164,0.00062130357],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018573327,0.0004712077,0.48131672,0.00008276416,0.00013146982,0.0000309213,0.004637021,0.0014203544,0.0031561276,0.00052311644,0.01963058,0.488414],"study_design_scores_gemma":[0.0011126056,0.00004191691,0.8984518,0.0015794534,0.00016288797,0.000034136887,0.000684911,0.0058020568,0.0039823395,0.050649833,0.03695546,0.0005425982],"about_ca_topic_score_codex":0.15942894,"about_ca_topic_score_gemma":0.0523211,"teacher_disagreement_score":0.48787138,"about_ca_system_score_codex":0.0008645541,"about_ca_system_score_gemma":0.004898976,"threshold_uncertainty_score":0.99975204},"labels":[],"label_agreement":null},{"id":"W2725327667","doi":"10.3138/cjpe.31124","title":"Finding Balance: An Evaluation Governance Model to Ease Tension between Independence and Inclusion","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Canadian Institutes of Health Research; Alberta Innovates","funders":"","keywords":"Independence (probability theory); Balance (ability); Inclusion (mineral); Corporate governance; Business; Psychology; Social psychology; Mathematics; Statistics; Neuroscience","score_opus":0.4753921117862232,"score_gpt":0.5589934326762455,"score_spread":0.08360132089002226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2725327667","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9881238,0.00022524985,0.0045976695,0.0041557867,0.00051554583,0.0013714407,0.000019880645,0.0000062532067,0.0009843743],"genre_scores_gemma":[0.9931535,0.000015934207,0.0061656474,0.00025760676,0.00025396745,0.000051380764,0.000014097754,0.000012145264,0.00007571142],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9924226,0.0005273378,0.0008826979,0.00039309022,0.005449278,0.00032502672],"domain_scores_gemma":[0.9920589,0.00014591907,0.0013831161,0.00070859067,0.0047691544,0.00093432923],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.035944693,0.00016748648,0.00030061285,0.00042932178,0.002705105,0.0010113158,0.0010582507,0.00013918913,0.00036061084],"category_scores_gemma":[0.0099268695,0.00013703282,0.00006860624,0.0002879108,0.00010216281,0.0025979776,0.00032876845,0.00028780507,0.00002579897],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022041486,0.000019170428,0.11894907,0.0000031370337,0.000008536799,0.000003005214,0.0020672851,0.013592883,0.00033972407,0.00014008333,0.00042841455,0.8644267],"study_design_scores_gemma":[0.00078610994,0.00032000893,0.37520728,0.000089635156,0.00007323924,0.0000106877715,0.00019252585,0.6054202,0.00013744434,0.016461622,0.0011643138,0.00013700176],"about_ca_topic_score_codex":0.00076657557,"about_ca_topic_score_gemma":0.013397373,"teacher_disagreement_score":0.86428964,"about_ca_system_score_codex":0.0006418607,"about_ca_system_score_gemma":0.0050816415,"threshold_uncertainty_score":0.9985932},"labels":[],"label_agreement":null},{"id":"W2725495193","doi":"","title":"Recherche-intervention et méthodes mixtes des pistes d’observation des pratiques collaboratives pluri-adressées.","year":2016,"lang":"fr","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"L'Alliance Boviteq","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.2590626863967925,"score_gpt":0.4534259084557086,"score_spread":0.19436322205891615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2725495193","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36270687,0.0067091566,0.54266137,0.03449567,0.0005819648,0.0011880308,0.00024092998,0.0002918126,0.051124223],"genre_scores_gemma":[0.4907412,0.00990711,0.39916065,0.00033919388,0.00008301301,0.00040644172,0.00045550437,0.000095480085,0.09881141],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9123707,0.08077557,0.0023021433,0.0017548031,0.0020111413,0.00078565243],"domain_scores_gemma":[0.9537383,0.023198431,0.0024830967,0.002866297,0.01729021,0.00042367374],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09239158,0.0008382198,0.00092459,0.0005426386,0.0013537301,0.002683732,0.0024837207,0.0008730047,0.0028774666],"category_scores_gemma":[0.04352677,0.00071167195,0.0005484066,0.0017615836,0.001960197,0.0024274692,0.0014661413,0.0011149998,0.00043785636],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008774562,0.0014507611,0.032871563,0.00048660891,0.00021721386,0.0000035670696,0.06402879,0.00012989387,0.01196185,0.48408422,0.0014026441,0.40327513],"study_design_scores_gemma":[0.0021155032,0.000011207497,0.10746306,0.019079646,0.00017671635,0.000019111068,0.0074051777,0.02449363,0.25079912,0.5417745,0.04515201,0.0015102858],"about_ca_topic_score_codex":0.0018893731,"about_ca_topic_score_gemma":0.0179273,"teacher_disagreement_score":0.40176487,"about_ca_system_score_codex":0.0011040099,"about_ca_system_score_gemma":0.002376468,"threshold_uncertainty_score":0.99999297},"labels":[],"label_agreement":null},{"id":"W2725947572","doi":"10.3138/cjpe.31142","title":"La fidélité d’implantation d’un programme probant au-delà de son implantation initiale : l’exemple de Ces années incroyables en protection de l’enfance de 2003 à 2013","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Fidelity; Sustainability; Computer science; Humanities; Philosophy; Telecommunications","score_opus":0.21206354201125907,"score_gpt":0.48399008829918905,"score_spread":0.27192654628793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2725947572","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97911566,0.00019226645,0.014637342,0.002108095,0.0004105414,0.001969649,0.000030464798,0.00002906211,0.0015069024],"genre_scores_gemma":[0.98161596,0.00010778188,0.017091338,0.00012444163,0.0004023495,0.0005381055,0.00004119517,0.000023103601,0.00005570256],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99458426,0.0018568834,0.0009687118,0.000318917,0.001456078,0.0008151754],"domain_scores_gemma":[0.9945914,0.00030407758,0.0016121654,0.00040726826,0.0024195304,0.00066555047],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.026995739,0.00022626367,0.00030222273,0.00057646004,0.0013159093,0.0016211974,0.00074672425,0.0002573352,0.0003130032],"category_scores_gemma":[0.0066975523,0.00019867158,0.00011574305,0.00045454566,0.00019247667,0.0016895252,0.000025988369,0.00043058651,0.000030504954],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000113405586,0.000093704846,0.1101594,0.000042120788,0.000048621303,0.000033170527,0.014698196,0.0035951224,0.00084573997,0.00041086992,0.00079867424,0.86916095],"study_design_scores_gemma":[0.002129861,0.0009493543,0.81231374,0.00025918268,0.00022301101,0.0013895795,0.00633672,0.12762384,0.003984281,0.020786652,0.023592709,0.00041105403],"about_ca_topic_score_codex":0.018780673,"about_ca_topic_score_gemma":0.081707306,"teacher_disagreement_score":0.8687499,"about_ca_system_score_codex":0.0018060259,"about_ca_system_score_gemma":0.015971802,"threshold_uncertainty_score":0.99998426},"labels":[],"label_agreement":null},{"id":"W2726639547","doi":"10.7202/1040806ar","title":"La co-construction de la gestion axée sur les résultats : les logiques de médiation des commissions scolaires","year":2017,"lang":"fr","type":"article","venue":"McGill Journal of Education / Revue des sciences de l éducation de McGill","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Political science; Humanities; Philosophy","score_opus":0.6007852846976613,"score_gpt":0.5619358360005106,"score_spread":0.03884944869715079,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2726639547","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9402908,0.0020170975,0.010121776,0.015762674,0.0029736285,0.00032983368,0.000082553335,0.00004362942,0.028377986],"genre_scores_gemma":[0.92279786,0.0056204665,0.06736636,0.00043276142,0.0005283658,0.000040294828,0.000009482409,0.000027724267,0.0031766715],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9918613,0.0043140342,0.0014715662,0.0005217377,0.001136249,0.00069511955],"domain_scores_gemma":[0.989737,0.003290334,0.0029396946,0.0005915307,0.0028300027,0.000611478],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["sts"],"category_scores_codex":[0.02440845,0.00036489256,0.0004559059,0.00094975426,0.008051668,0.0015120641,0.0015643855,0.00053249125,0.0009267933],"category_scores_gemma":[0.020826211,0.0003431918,0.00027906534,0.0008069484,0.0038096688,0.0039634327,0.00009991795,0.00084461813,0.000046009194],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00008837164,0.0010004047,0.17048518,0.00023091881,0.000052718227,0.000009200456,0.011823966,0.010842527,0.0027632727,0.04374113,0.0057643964,0.7531979],"study_design_scores_gemma":[0.00073472667,0.0005654981,0.65617675,0.0023903686,0.00021686844,0.0037642324,0.030432217,0.01999955,0.0052944506,0.10728632,0.17255804,0.0005809615],"about_ca_topic_score_codex":0.0025496196,"about_ca_topic_score_gemma":0.0013818159,"teacher_disagreement_score":0.75261694,"about_ca_system_score_codex":0.004368546,"about_ca_system_score_gemma":0.006799797,"threshold_uncertainty_score":0.99998647},"labels":[],"label_agreement":null},{"id":"W2727038118","doi":"10.3138/cjpe.31039","title":"“Advocates Change the World; Evaluation Can Help”: A Literature Review and Key Insights from the Practice of Advocacy Evaluation","year":2017,"lang":"en","type":"review","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Public relations; Work (physics); Theory of change; Resource (disambiguation); Value (mathematics); Public administration; Sociology; Computer science","score_opus":0.5690707156508308,"score_gpt":0.5993917126532878,"score_spread":0.03032099700245705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2727038118","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000061306855,0.9724339,0.000008450843,0.012914937,0.0012393304,0.011843903,0.00007788868,0.0000056346307,0.0014146438],"genre_scores_gemma":[0.0023616438,0.9926481,0.00040910498,0.001182943,0.0010108835,0.0017925188,0.0004442251,0.00003678213,0.000113763774],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9774043,0.011379148,0.0029359057,0.0006154536,0.00728634,0.0003788274],"domain_scores_gemma":[0.96919787,0.0039438736,0.008475054,0.0016219937,0.016402269,0.00035893766],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07291153,0.00051892555,0.0016248536,0.00093456573,0.00088806363,0.0015804203,0.0019270699,0.00027854033,0.0009794922],"category_scores_gemma":[0.041236766,0.00026016549,0.0005465642,0.0019677165,0.00034266914,0.001713788,0.000079622136,0.0010254161,0.000034517503],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000067116202,0.000031758973,0.000042130483,0.0006453435,0.00021229191,0.000002699908,0.0029606111,0.000010902661,7.416629e-8,0.000092189024,0.006089825,0.9899055],"study_design_scores_gemma":[0.0005992185,0.00021150189,0.0010808572,0.027334658,0.011349582,0.000101802514,0.00061449176,0.0033841284,4.3789782e-7,0.0026308363,0.95241934,0.00027311817],"about_ca_topic_score_codex":0.0014018117,"about_ca_topic_score_gemma":0.04540981,"teacher_disagreement_score":0.98963237,"about_ca_system_score_codex":0.0009126953,"about_ca_system_score_gemma":0.020629065,"threshold_uncertainty_score":0.99998504},"labels":[],"label_agreement":null},{"id":"W2727167739","doi":"10.3138/cjpe.32.1.146","title":"Thomas A. Schwandt. (2015). <i>Evaluation Foundations Revisited: Cultivating a Life of Mind for Practice</i> .","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Philosophy; Epistemology; Sociology","score_opus":0.5163532067272812,"score_gpt":0.6042933576740629,"score_spread":0.08794015094678165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2727167739","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79167676,0.0047652544,0.047028646,0.06858322,0.006627358,0.019851228,0.00023921367,0.000030252724,0.061198052],"genre_scores_gemma":[0.95665854,0.000018205,0.04222947,0.00020444395,0.00041519527,0.00019025823,0.000053478238,0.000015222778,0.00021518725],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99346375,0.0008390518,0.0016722727,0.00029014243,0.0034296121,0.0003051728],"domain_scores_gemma":[0.9752511,0.001072118,0.0045607514,0.0007351005,0.017897617,0.0004833445],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.050257515,0.00015915334,0.00037724894,0.0006146824,0.0010527811,0.0012349264,0.0008063904,0.00011479884,0.0013694151],"category_scores_gemma":[0.09772682,0.00013027938,0.00022079403,0.0004009839,0.0001853805,0.0027768346,0.000024834186,0.00020293202,0.00003212024],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007282833,0.00008912434,0.0156752,0.000016674032,0.00009813658,0.0000010908376,0.0016093518,0.0015794375,0.00023685605,0.0010932292,0.012971222,0.96655685],"study_design_scores_gemma":[0.0066972333,0.0015941561,0.08155417,0.0004572119,0.0012740826,0.00006776866,0.0066477736,0.29632238,0.0008054233,0.020859387,0.5832479,0.00047250246],"about_ca_topic_score_codex":0.0003339741,"about_ca_topic_score_gemma":0.004332546,"teacher_disagreement_score":0.96608436,"about_ca_system_score_codex":0.00038884542,"about_ca_system_score_gemma":0.01218033,"threshold_uncertainty_score":0.9998019},"labels":[],"label_agreement":null},{"id":"W2727296767","doi":"10.3138/cjpe.30975","title":"Building Evaluation Culture and Capacity in a Community-Level Program: Lessons Learned from Evaluating Youth Futures","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Futures contract; General partnership; Context (archaeology); Political science; Humanities; Sociology; Library science; Business; Computer science; Geography","score_opus":0.8259677997461102,"score_gpt":0.605372997880777,"score_spread":0.2205948018653332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2727296767","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9918023,0.00063019426,0.00033806538,0.0031080977,0.0007284758,0.0020921335,0.0000578772,0.00001424614,0.0012286131],"genre_scores_gemma":[0.97430265,0.00002853809,0.025029054,0.00010272322,0.00026620345,0.00016962242,0.000049788985,0.000016956332,0.000034455043],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99026656,0.003785133,0.0012921749,0.00038526973,0.0038185092,0.0004523503],"domain_scores_gemma":[0.9918488,0.0004225737,0.0019212583,0.000889472,0.00440033,0.0005175504],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05743654,0.00025196388,0.00046298225,0.00071901904,0.0020670467,0.002353604,0.0011535832,0.00021916637,0.00043287585],"category_scores_gemma":[0.020869743,0.00020331745,0.00013925099,0.00044412242,0.0002927609,0.0016451012,0.000075991455,0.0010142889,0.000011465422],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003027457,0.00008435847,0.034706958,0.000005991459,0.00003512235,0.000001925575,0.016085299,0.001241716,0.00022102185,0.00022590937,0.000118175885,0.9472433],"study_design_scores_gemma":[0.0035671259,0.0008472436,0.6877733,0.00032776978,0.0003237689,0.000017013137,0.01916118,0.20970999,0.00014337458,0.07583732,0.0019694238,0.0003225288],"about_ca_topic_score_codex":0.015488176,"about_ca_topic_score_gemma":0.20538081,"teacher_disagreement_score":0.9469207,"about_ca_system_score_codex":0.0007153561,"about_ca_system_score_gemma":0.0040806853,"threshold_uncertainty_score":0.9992321},"labels":[],"label_agreement":null},{"id":"W2727808690","doi":"10.3138/cjpe.018.008","title":"Students’ Perspective of the CES Case Competition","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Competition (biology); Presentation (obstetrics); Perspective (graphical); Task (project management); Relevance (law); Argument (complex analysis); Psychology; Medical education; Work (physics); Time limit; Management; Computer science; Medicine; Political science; Engineering; Law","score_opus":0.3255601195178861,"score_gpt":0.550185675195576,"score_spread":0.22462555567768994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2727808690","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98810875,0.000361183,0.00033489146,0.0013533976,0.0009130803,0.00077095337,0.000005712027,0.0000023498574,0.008149685],"genre_scores_gemma":[0.99896103,0.0000039752,0.0007535993,0.000087035354,0.00005016103,0.000015617863,7.2377804e-7,0.0000041055764,0.00012375168],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99579173,0.0010197745,0.00065614306,0.00011888596,0.0022701365,0.00014335397],"domain_scores_gemma":[0.99426824,0.00018151857,0.0007543783,0.00024581255,0.0043585766,0.00019149376],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.012928829,0.00007444649,0.0001551493,0.00032117194,0.00022977193,0.00019810846,0.00039213622,0.000041766372,0.0019839052],"category_scores_gemma":[0.0036637841,0.000046046967,0.00012995547,0.0007275511,0.00012587484,0.00033703592,0.0000083798905,0.00014583144,0.000017767628],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033236396,0.00037908848,0.5408571,0.000012317627,0.00017530183,0.00009887618,0.01761708,0.008520252,0.00016553413,0.0912168,0.0035285968,0.33739585],"study_design_scores_gemma":[0.004966115,0.0019128931,0.6008514,0.0002371217,0.00055633974,0.0037860307,0.11017147,0.01519459,0.0022224644,0.1756864,0.08393037,0.00048478803],"about_ca_topic_score_codex":0.0007318702,"about_ca_topic_score_gemma":0.029348806,"teacher_disagreement_score":0.33691105,"about_ca_system_score_codex":0.00040022124,"about_ca_system_score_gemma":0.0034395633,"threshold_uncertainty_score":0.9989284},"labels":[],"label_agreement":null},{"id":"W2728160106","doi":"10.3917/dbu.ceon.2015.02.0197","title":"Évaluation et autoévaluation","year":2015,"lang":"fr","type":"book-chapter","venue":"Pédagogies en développement. Problématiques et recherches","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Valuation (finance); Economics; Actuarial science; Business; Accounting","score_opus":0.7830736468671708,"score_gpt":0.5865493914727481,"score_spread":0.19652425539442275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2728160106","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006165237,0.0024346684,0.0404473,0.13836212,0.0022110627,0.0044332976,0.00016519536,0.0007271111,0.805054],"genre_scores_gemma":[0.00927646,0.016719034,0.32205996,0.0031166642,0.00042243002,0.0007463165,0.0012852924,0.00027167826,0.64610213],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9772453,0.008362795,0.003917514,0.0020344704,0.0074033616,0.0010366008],"domain_scores_gemma":[0.9837843,0.007020625,0.0024780077,0.0018311896,0.0044393563,0.00044652575],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"category_scores_codex":[0.08843752,0.0015389953,0.0016518485,0.0012295166,0.00043315341,0.0014424918,0.0019593586,0.0018073396,0.011977626],"category_scores_gemma":[0.01200465,0.0013634124,0.00055917684,0.0005902571,0.0005684701,0.0027931067,0.0010627109,0.0022729824,0.0048506493],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00011328166,0.00021799478,0.0010969487,0.0002966644,0.0003661882,0.0000074221457,0.05017303,0.0053485767,0.0005054624,0.4026395,0.014152675,0.52508223],"study_design_scores_gemma":[0.0012095567,0.0006681798,0.004537809,0.0012180238,0.00031065778,0.000023734341,0.00340935,0.01863288,0.0013866049,0.62609786,0.34101266,0.0014927213],"about_ca_topic_score_codex":0.00018415072,"about_ca_topic_score_gemma":0.0010021642,"teacher_disagreement_score":0.52358955,"about_ca_system_score_codex":0.0039133225,"about_ca_system_score_gemma":0.009175931,"threshold_uncertainty_score":0.9999105},"labels":[],"label_agreement":null},{"id":"W2728340321","doi":"10.3138/cjpe.31121","title":"Contribution Analysis: Theoretical and Practical Challenges and Prospects for Evaluators","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Victoria; University of Toronto","funders":"","keywords":"Rigour; Management science; Causality (physics); Attribution; Engineering ethics; Psychological intervention; Epistemology; Psychology; Computer science; Sociology; Risk analysis (engineering); Medicine; Economics; Social psychology; Engineering; Philosophy","score_opus":0.35549175255489224,"score_gpt":0.5707339832883228,"score_spread":0.21524223073343057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2728340321","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94927293,0.004151816,0.005194082,0.03644398,0.0006063743,0.0027080171,0.000015726248,0.000008719662,0.001598384],"genre_scores_gemma":[0.99621207,0.00015872982,0.0033090017,0.000065275744,0.00014305081,0.0000891916,0.000005224018,0.000005298758,0.000012134546],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9971632,0.00040375965,0.00059334317,0.00024611957,0.0013601014,0.00023348672],"domain_scores_gemma":[0.9942558,0.00055270316,0.0006302605,0.00032593976,0.003740685,0.00049465185],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02515919,0.000106476524,0.0003099456,0.00046328467,0.00057531934,0.00094762,0.00019288098,0.000095247255,0.00020514925],"category_scores_gemma":[0.021706032,0.00007683884,0.00010625939,0.00014483731,0.00040575356,0.0008098275,0.000019078789,0.00013756774,0.0000033866665],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006130395,0.000034732824,0.029322706,0.000006737375,0.000200528,0.000004189936,0.0007376529,0.000041589792,0.000012603744,0.12084187,0.0002034688,0.8485326],"study_design_scores_gemma":[0.001525595,0.00093599904,0.6283925,0.00003111747,0.0012894806,0.00006453919,0.0008333989,0.17872797,0.00006197354,0.18098138,0.007005973,0.00015007252],"about_ca_topic_score_codex":0.000027417384,"about_ca_topic_score_gemma":0.005266195,"teacher_disagreement_score":0.84838253,"about_ca_system_score_codex":0.00012719336,"about_ca_system_score_gemma":0.0016668714,"threshold_uncertainty_score":0.98653454},"labels":[],"label_agreement":null},{"id":"W2729149433","doi":"10.3917/dbu.ceon.2015.02.0099","title":"Évaluation et autoévaluation","year":2015,"lang":"fr","type":"book-chapter","venue":"Pédagogies en développement. Problématiques et recherches","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Valuation (finance); Economics; Business; Finance","score_opus":0.7830736468671708,"score_gpt":0.5865493914727481,"score_spread":0.19652425539442275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2729149433","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006165237,0.0024346684,0.0404473,0.13836212,0.0022110627,0.0044332976,0.00016519536,0.0007271111,0.805054],"genre_scores_gemma":[0.00927646,0.016719034,0.32205996,0.0031166642,0.00042243002,0.0007463165,0.0012852924,0.00027167826,0.64610213],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9772453,0.008362795,0.003917514,0.0020344704,0.0074033616,0.0010366008],"domain_scores_gemma":[0.9837843,0.007020625,0.0024780077,0.0018311896,0.0044393563,0.00044652575],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"category_scores_codex":[0.08843752,0.0015389953,0.0016518485,0.0012295166,0.00043315341,0.0014424918,0.0019593586,0.0018073396,0.011977626],"category_scores_gemma":[0.01200465,0.0013634124,0.00055917684,0.0005902571,0.0005684701,0.0027931067,0.0010627109,0.0022729824,0.0048506493],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00011328166,0.00021799478,0.0010969487,0.0002966644,0.0003661882,0.0000074221457,0.05017303,0.0053485767,0.0005054624,0.4026395,0.014152675,0.52508223],"study_design_scores_gemma":[0.0012095567,0.0006681798,0.004537809,0.0012180238,0.00031065778,0.000023734341,0.00340935,0.01863288,0.0013866049,0.62609786,0.34101266,0.0014927213],"about_ca_topic_score_codex":0.00018415072,"about_ca_topic_score_gemma":0.0010021642,"teacher_disagreement_score":0.52358955,"about_ca_system_score_codex":0.0039133225,"about_ca_system_score_gemma":0.009175931,"threshold_uncertainty_score":0.9999105},"labels":[],"label_agreement":null},{"id":"W27308458","doi":"10.46743/2160-3715/2007.1645","title":"On Becoming a Qualitative Researcher: The Value of Reflexivity","year":2015,"lang":"en","type":"article","venue":"The Qualitative Report","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":600,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Reflexivity; Qualitative research; Value (mathematics); Phenomenon; Epistemology; Narrative; Process (computing); Field (mathematics); Task (project management); Sociology; Engineering ethics; Psychology; Computer science; Social science; Management","score_opus":0.8577058564611163,"score_gpt":0.7533929997569319,"score_spread":0.10431285670418444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W27308458","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88327265,0.000073230316,0.0040302984,0.022793652,0.00025872365,0.0004821563,0.000024724863,0.000021057096,0.08904348],"genre_scores_gemma":[0.98174226,0.0000032965463,0.0008657159,0.00057225476,0.0000570078,0.00005293678,0.0000049674645,0.000009749294,0.016691782],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98002976,0.013208376,0.00128175,0.0003956799,0.004813217,0.00027121505],"domain_scores_gemma":[0.9688401,0.026550045,0.00112723,0.0013414258,0.0020123017,0.00012884609],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.15837185,0.00014539192,0.00034109337,0.00014060723,0.00028586882,0.00009284744,0.000867712,0.000048471098,0.0004256122],"category_scores_gemma":[0.041140173,0.00006280229,0.00014908992,0.0009077045,0.0007221018,0.00026496113,0.00018650205,0.000349973,0.00029997143],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029836706,0.000107978216,0.00016736354,0.000005303441,0.00006343748,0.000012696117,0.71634156,0.00026829747,0.00016221401,0.25966194,0.020507155,0.0024036537],"study_design_scores_gemma":[0.00031156678,0.00041693912,0.0019057981,0.000021077443,0.000009306118,0.000018440567,0.45728233,0.0008735577,0.0009206796,0.5290682,0.009077872,0.00009427477],"about_ca_topic_score_codex":0.00028269633,"about_ca_topic_score_gemma":0.00013032678,"teacher_disagreement_score":0.2694062,"about_ca_system_score_codex":0.00014030491,"about_ca_system_score_gemma":0.000818942,"threshold_uncertainty_score":0.9669367},"labels":[],"label_agreement":null},{"id":"W2731520452","doi":"10.3138/cjpe.32.1.143","title":"Patricia Burch and Carolyn J. Heinrich. (2015). <i>Mixed Methods for Policy Research and Program Evaluation</i> .","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sociology; Psychology; Psychoanalysis","score_opus":0.6318859600826949,"score_gpt":0.6992112929537181,"score_spread":0.06732533287102316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2731520452","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80369335,0.01880951,0.0131175285,0.12233289,0.0038860955,0.03026198,0.00007531469,0.000059298298,0.007764022],"genre_scores_gemma":[0.93178535,0.0001572233,0.06578954,0.0001336831,0.00065055804,0.0012166618,0.000014627119,0.000022446611,0.00022993276],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99189764,0.0024772235,0.001106126,0.00046817906,0.003388331,0.0006625167],"domain_scores_gemma":[0.98192334,0.0016700502,0.001085364,0.0007358346,0.013615108,0.0009703225],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10920446,0.00019559269,0.00040749906,0.0015140739,0.0019409007,0.0027247446,0.0008382624,0.00017506708,0.0001895421],"category_scores_gemma":[0.040108003,0.00015437852,0.00011172614,0.00075361907,0.0006045282,0.0011453605,0.00007995249,0.0003824219,0.000010870337],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027420967,0.000058195747,0.011492266,0.000010777912,0.000037613503,0.0000011489485,0.00059999904,0.000063261665,0.000040514595,0.0010915007,0.0042150384,0.9823623],"study_design_scores_gemma":[0.0041319616,0.003181826,0.1840824,0.000086947126,0.00024091276,0.000088407876,0.0018918394,0.2831626,0.00015791,0.13397364,0.38864943,0.00035211843],"about_ca_topic_score_codex":0.0015057649,"about_ca_topic_score_gemma":0.016240811,"teacher_disagreement_score":0.9820101,"about_ca_system_score_codex":0.00060706155,"about_ca_system_score_gemma":0.011684499,"threshold_uncertainty_score":0.9993584},"labels":[],"label_agreement":null},{"id":"W2732819684","doi":"10.3138/cjpe.20.006","title":"Evaluator Competencies in University-Based Evaluation Training Programs","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Credentialing; Accreditation; Licensure; Certificate; Taxonomy (biology); Competence (human resources); Computer science; Medical education; Psychology; Medicine","score_opus":0.4101080033795569,"score_gpt":0.5034090358417598,"score_spread":0.09330103246220289,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2732819684","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9816959,0.00062371936,0.002328594,0.006192556,0.0008146368,0.0030898442,0.0000071885825,0.000023894792,0.0052236696],"genre_scores_gemma":[0.98323494,0.0000041461976,0.016183592,0.00020108884,0.00019793892,0.00004278359,0.00003061808,0.000011946847,0.00009296449],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9917924,0.0017565354,0.001146272,0.00031102216,0.0045495047,0.00044428452],"domain_scores_gemma":[0.99293274,0.00030854112,0.0008512482,0.00033177555,0.005067927,0.000507794],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.042099725,0.00017668224,0.0003380694,0.0017718719,0.00023997194,0.00036515866,0.00064361264,0.00011902698,0.00300078],"category_scores_gemma":[0.00302336,0.00015640634,0.00017624156,0.0018003136,0.0001472594,0.0011349069,0.0000111835725,0.0003088309,0.000102892554],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026108299,0.00007310702,0.023866137,0.0000026718121,0.000013397807,0.0000049270193,0.0025372135,0.052246507,0.000022200884,0.00036533788,0.00031678015,0.9205256],"study_design_scores_gemma":[0.0031356057,0.00052789313,0.05854617,0.000102561964,0.00012596555,0.000019128143,0.007297549,0.8207593,0.000028460357,0.0025597215,0.106688336,0.00020933995],"about_ca_topic_score_codex":0.0004243129,"about_ca_topic_score_gemma":0.08864555,"teacher_disagreement_score":0.9203163,"about_ca_system_score_codex":0.0018353434,"about_ca_system_score_gemma":0.018273171,"threshold_uncertainty_score":0.9979106},"labels":[],"label_agreement":null},{"id":"W2733727893","doi":"","title":"Ontario Education Governance 1995 to the Present: More Accountability, More Regulation, and More Centralization?","year":2015,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Corporate governance; Accountability; Government (linguistics); Context (archaeology); Public administration; Political science; Section (typography); Higher education; Sociology; Law; Economics; Management; Business; Geography","score_opus":0.14949051454693515,"score_gpt":0.4721207598118616,"score_spread":0.32263024526492645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2733727893","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82077396,0.00021818932,0.003997327,0.14546044,0.001045672,0.0011303728,0.000016098826,0.00004408727,0.027313828],"genre_scores_gemma":[0.9478068,0.000014379267,0.0012166479,0.0037286582,0.00019681717,0.000060660383,0.000030637962,0.000007609733,0.046937793],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9967154,0.00010374814,0.00049480767,0.00041986548,0.0020734447,0.00019273529],"domain_scores_gemma":[0.9976329,0.00016433302,0.0001893633,0.0007598503,0.0010431296,0.00021041748],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0021449842,0.0001348571,0.00014733648,0.00006511802,0.00020802033,0.0004289325,0.0004954455,0.000052422827,0.0022709002],"category_scores_gemma":[0.0005990906,0.00007993238,0.000036648948,0.00063058676,0.0000894881,0.0008536983,0.00016792979,0.00009082359,0.00024382361],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032499433,0.00011234157,0.5866326,0.0000037770994,0.000008351514,1.0657397e-7,0.02383914,0.0071683135,0.0000061238497,0.009345813,0.33424488,0.038606033],"study_design_scores_gemma":[0.0001624565,0.000017773642,0.59002626,0.0000068888194,0.000006137796,0.0000026939192,0.004272614,0.008228867,0.000035442063,0.0035853346,0.39357078,0.00008473363],"about_ca_topic_score_codex":0.009709911,"about_ca_topic_score_gemma":0.04332158,"teacher_disagreement_score":0.14173178,"about_ca_system_score_codex":0.00032496682,"about_ca_system_score_gemma":0.0011600222,"threshold_uncertainty_score":0.99864113},"labels":[],"label_agreement":null},{"id":"W273644060","doi":"10.3138/cjpe.17.007","title":"Evaluating Organizational Capacity Development","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Danish International Development Agency; International Fund for Agricultural Development; Australian Centre for International Agricultural Research; Ministerie van Buitenlandse Zaken; Concordia University; Direktion für Entwicklung und Zusammenarbeit; International Development Research Centre","keywords":"Capacity development; Agricultural development; Capacity building; Process management; Business; Latin Americans; Organization development; Agriculture; Management science; Environmental resource management; Knowledge management; Political science; Computer science; Economic growth; Engineering; Economics","score_opus":0.6856435831176912,"score_gpt":0.546893715148618,"score_spread":0.1387498679690733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W273644060","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98220676,0.00048290618,0.003045828,0.002563382,0.0013521977,0.0010264877,0.000005451642,0.000017571754,0.0092994245],"genre_scores_gemma":[0.96302533,0.0000033173826,0.036003113,0.0002350955,0.00021933143,0.00003495821,0.000010680516,0.0000109729435,0.00045721958],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99383044,0.00060989126,0.0012215291,0.00021127643,0.0038391,0.00028773563],"domain_scores_gemma":[0.99202603,0.00025733607,0.0008016487,0.00024176344,0.006172373,0.0005008579],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01948341,0.00012787351,0.0002104844,0.00069530774,0.00041550063,0.0004378934,0.00048786725,0.00007570252,0.026113644],"category_scores_gemma":[0.007731335,0.000102119375,0.000081227976,0.0011190163,0.00007589227,0.0006515527,0.000013223206,0.00020196545,0.0005803004],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000030298504,0.00005327824,0.032548126,0.0000026396553,0.000026895757,0.0000023160053,0.0029181002,0.0037544828,0.00007221778,0.0004466684,0.0037937858,0.95637846],"study_design_scores_gemma":[0.0024939468,0.00081933825,0.1784929,0.00009324187,0.00013269702,0.00018540748,0.0013071537,0.5798509,0.0007311821,0.016401123,0.21900049,0.0004915818],"about_ca_topic_score_codex":0.00007124245,"about_ca_topic_score_gemma":0.0059288144,"teacher_disagreement_score":0.9558869,"about_ca_system_score_codex":0.00063846743,"about_ca_system_score_gemma":0.0039606327,"threshold_uncertainty_score":0.9747766},"labels":[],"label_agreement":null},{"id":"W2740976090","doi":"","title":"Experience on collaborative research: A successful case of international and multidisciplinary knowledge exchange between researchers from Paraguay and Canada","year":2012,"lang":"en","type":"article","venue":"Investigación agraria","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Multidisciplinary approach; Political science; Knowledge management; Public relations; Sociology; Social science; Computer science","score_opus":0.5038004400464232,"score_gpt":0.5618780699602622,"score_spread":0.058077629913839024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2740976090","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99112725,0.00081753964,0.000015294505,0.0019494037,0.00031706877,0.00028424693,0.00022145653,0.0000075877556,0.0052601337],"genre_scores_gemma":[0.9984581,0.00007702851,0.0005867359,0.00006376057,0.00018855455,0.00005541459,0.000018886774,0.000007717674,0.0005438061],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99621767,0.0010246506,0.00047229332,0.00040344143,0.0015350593,0.00034691274],"domain_scores_gemma":[0.9941782,0.0040313555,0.00016837174,0.00036550712,0.0007565582,0.000500011],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0054660076,0.00013900467,0.00024382409,0.00033991245,0.00031134917,0.00015709769,0.00040113486,0.00007862776,0.00036445397],"category_scores_gemma":[0.0030576666,0.0001039934,0.000018300121,0.00075528974,0.00075547484,0.0006935955,0.0003561227,0.00028746863,0.000019857067],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006354214,0.00006217034,0.9343412,0.000008858256,0.000031659874,0.000041033207,0.047107562,0.000005247012,0.00038641985,0.0015738736,0.00652332,0.009855139],"study_design_scores_gemma":[0.00095175847,0.00020532263,0.91582817,0.00008961775,0.000010616707,0.000022850758,0.04966767,0.0021301904,0.004582728,0.005202819,0.021053731,0.00025454204],"about_ca_topic_score_codex":0.22848265,"about_ca_topic_score_gemma":0.31032357,"teacher_disagreement_score":0.08184093,"about_ca_system_score_codex":0.000154037,"about_ca_system_score_gemma":0.0010108917,"threshold_uncertainty_score":0.77665496},"labels":[],"label_agreement":null},{"id":"W274204648","doi":"10.3138/cjpe.16.008","title":"Do Evaluator and Program Practitioner Perspectives Converge in Collaborative Evaluation?","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Stakeholder; Participatory evaluation; Program evaluation; Citizen journalism; Collaborative model; Medical education; Psychology; Computer science; Knowledge management; Management science; Sociology; Public relations; Medicine; Political science; Engineering; World Wide Web","score_opus":0.21392616880582213,"score_gpt":0.5507446156045417,"score_spread":0.33681844679871953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W274204648","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9724502,0.0053493935,0.00014951696,0.006474746,0.0009641022,0.00519776,0.000011170163,0.000018771134,0.009384329],"genre_scores_gemma":[0.9950497,0.00020051214,0.0036027452,0.0001272762,0.00024014036,0.0006078901,0.000017095323,0.000015112417,0.00013953935],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99165,0.002134522,0.0012575639,0.00043518055,0.004127073,0.0003956541],"domain_scores_gemma":[0.9861191,0.00044310628,0.0010227911,0.00033585323,0.011524617,0.0005545664],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.035171587,0.00021007496,0.00037459,0.0014101504,0.0002839864,0.00085604854,0.000345369,0.00013414028,0.0059668273],"category_scores_gemma":[0.009294563,0.00017043049,0.00009702894,0.0023503243,0.0002370804,0.0017486694,0.000018090606,0.00034002122,0.000072658375],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009695263,0.00023796545,0.08687122,0.000003773943,0.000051175073,0.000015334119,0.008455431,0.001615013,0.000020185436,0.0009387365,0.0025505575,0.89914364],"study_design_scores_gemma":[0.006864706,0.0027707107,0.5433184,0.00018747101,0.00034352855,0.00024144712,0.057153072,0.23429844,0.00004025505,0.029191665,0.12505315,0.00053718966],"about_ca_topic_score_codex":0.0003277641,"about_ca_topic_score_gemma":0.018702539,"teacher_disagreement_score":0.8986065,"about_ca_system_score_codex":0.0011007432,"about_ca_system_score_gemma":0.011161479,"threshold_uncertainty_score":0.99920356},"labels":[],"label_agreement":null},{"id":"W2742989314","doi":"10.7728/0102201002","title":"Knowledge Transfer in Community-Based Organizations: A Needs Assessment Study","year":2017,"lang":"en","type":"article","venue":"Global Journal of Community Psychology Practice","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Knowledge management; Knowledge transfer; Sociology; Computer science","score_opus":0.31493270844537463,"score_gpt":0.6152913321588346,"score_spread":0.30035862371345995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2742989314","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88989156,0.00006906138,0.0128052635,0.018971436,0.0010101824,0.00030483297,0.000009430865,0.000012158913,0.07692605],"genre_scores_gemma":[0.99366444,0.000048467617,0.0017454408,0.0044142525,0.00005401166,0.000006266442,0.0000037335503,0.000009377033,0.000054029348],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9757998,0.02103978,0.001502716,0.0001073154,0.0012881848,0.0002621935],"domain_scores_gemma":[0.98764884,0.0050532473,0.0012656697,0.0024999233,0.0033730115,0.00015928195],"candidate_categories":["metaresearch","sts","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.044731494,0.00019971421,0.00053086557,0.0005393967,0.002166227,0.00066045165,0.004312361,0.00014344833,0.00037950056],"category_scores_gemma":[0.0114712855,0.00016181282,0.000109469074,0.0013813039,0.00028673693,0.002227367,0.00028844827,0.0029229152,0.00011787055],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010540735,0.025897706,0.89232284,0.000014052869,0.00025739326,0.00005742675,0.02500796,0.00084661733,0.00010017187,0.002771377,0.007603075,0.044067286],"study_design_scores_gemma":[0.006037709,0.0020128952,0.88411367,0.000041341318,0.00010993601,0.00022651031,0.050134465,0.00017231604,0.0000066715456,0.0036309352,0.053344432,0.00016909135],"about_ca_topic_score_codex":0.0003757819,"about_ca_topic_score_gemma":0.0019641754,"teacher_disagreement_score":0.10377284,"about_ca_system_score_codex":0.00025061803,"about_ca_system_score_gemma":0.0010036208,"threshold_uncertainty_score":0.99937737},"labels":[],"label_agreement":null},{"id":"W2743660306","doi":"10.3138/9781442685529-004","title":"2. The Policy Analysis Profession in Canada","year":2007,"lang":"en","type":"book-chapter","venue":"University of Toronto Press eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.1228467241691305,"score_gpt":0.386569506770558,"score_spread":0.2637227826014275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2743660306","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020589824,0.00042484998,0.000094225106,0.00014394269,0.0001434236,0.00020541962,0.0000338634,0.0000052406567,0.9987431],"genre_scores_gemma":[0.020028317,0.00029888027,0.00007424681,0.000055534525,0.000034824036,1.5659218e-7,0.000006477142,0.00000578576,0.97949576],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974653,0.00008463653,0.00039330055,0.00028171143,0.0015882858,0.00018674532],"domain_scores_gemma":[0.99791145,0.0004878401,0.0005273413,0.0006363745,0.00034948284,0.00008749788],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013862529,0.00014578878,0.00035414664,0.00013066942,0.0002031718,0.000027918566,0.0009374578,0.00012347123,0.0009793281],"category_scores_gemma":[0.000052173873,0.000108574095,0.00016310264,0.000011262109,0.000102255435,0.00010305209,0.00024482858,0.00017250123,0.000005561693],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046975186,0.000025102428,0.0035005875,0.000028868126,0.0009477461,0.00006225511,0.009650729,0.0009619203,0.000007699937,0.36208686,0.030998414,0.5912601],"study_design_scores_gemma":[0.00021122866,0.000015475202,0.0049891965,0.00002891084,0.00010204354,1.9662446e-7,0.00068482937,0.0010154127,0.0000076692995,0.00083979324,0.9919772,0.00012804993],"about_ca_topic_score_codex":0.9937945,"about_ca_topic_score_gemma":0.9997402,"teacher_disagreement_score":0.9609788,"about_ca_system_score_codex":0.0015310112,"about_ca_system_score_gemma":0.0026762176,"threshold_uncertainty_score":0.9999339},"labels":[],"label_agreement":null},{"id":"W2745386225","doi":"10.1177/0008417417723121","title":"Book Review: The evidence-based practitioner: Applying research to meet client needs","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Occupational Therapy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Nursing; Medicine","score_opus":0.7570177012649955,"score_gpt":0.6365381178705904,"score_spread":0.12047958339440501,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2745386225","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035954677,0.20060588,0.0034170414,0.7472535,0.0025345162,0.0022805543,0.00005387177,0.000007785106,0.007892192],"genre_scores_gemma":[0.7968311,0.014574758,0.00072383677,0.18284182,0.0010617938,0.00014835033,0.0000045690335,0.000019220166,0.0037945611],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99518484,0.0006991224,0.0007369252,0.00016006856,0.002938707,0.00028031596],"domain_scores_gemma":[0.9923802,0.0018492879,0.00076816307,0.00079114106,0.0036816339,0.000529595],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.021724623,0.00010069524,0.00020961175,0.00073693896,0.0018320845,0.00091894355,0.0016965701,0.000040909687,0.006241199],"category_scores_gemma":[0.007918836,0.000058425107,0.00014295407,0.00056744524,0.00019437741,0.0012555983,0.000023425788,0.000259672,0.00021745221],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010846699,0.000011950819,0.013300301,0.000004098493,0.000014531708,0.000006164182,0.0002537675,0.00079228816,0.000029225863,0.0010561609,0.95362073,0.030802311],"study_design_scores_gemma":[0.00025324454,0.00017664168,0.07952074,0.000523976,0.000004538783,0.000013004115,0.00015872845,0.00025807135,0.000081755934,0.00085059344,0.9180871,0.00007159076],"about_ca_topic_score_codex":0.0006691707,"about_ca_topic_score_gemma":0.0028336793,"teacher_disagreement_score":0.7608764,"about_ca_system_score_codex":0.00026981957,"about_ca_system_score_gemma":0.0065134964,"threshold_uncertainty_score":0.9994674},"labels":[],"label_agreement":null},{"id":"W2747878032","doi":"10.3917/rsi.129.0060","title":"Les pratiques évaluatives d’enseignants en soins infirmiers lors des stages : une étude descriptive qualitative","year":2017,"lang":"fr","type":"article","venue":"Recherche en soins infirmiers","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université du Québec à Chicoutimi; Cégep de Chicoutimi","funders":"","keywords":"Humanities; Sociology; Art","score_opus":0.76731433810934,"score_gpt":0.62346737298251,"score_spread":0.14384696512683004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2747878032","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87586737,0.0029604994,0.013741059,0.01817508,0.0022542966,0.0017464417,0.00032861583,0.00020659207,0.08472006],"genre_scores_gemma":[0.88930815,0.0059385784,0.056102287,0.0005549995,0.00047712962,0.00021400844,0.00004129122,0.0001290229,0.047234517],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9691631,0.02183774,0.0022376513,0.0017075032,0.003430856,0.0016231395],"domain_scores_gemma":[0.9771818,0.015411506,0.0022353786,0.0023438518,0.0020284269,0.00079906615],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"category_scores_codex":[0.04894568,0.0011794424,0.0015003663,0.00078735047,0.003202239,0.0019946347,0.0030758798,0.0018165609,0.003130104],"category_scores_gemma":[0.04023529,0.0010298693,0.00063986,0.0013689194,0.004796203,0.0051461374,0.0008894859,0.003122234,0.0012041972],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019876564,0.00033949767,0.014921841,0.00012211656,0.00053879805,0.000032219705,0.6085202,0.0006507322,0.00062899897,0.017303748,0.0026808858,0.35406217],"study_design_scores_gemma":[0.002409588,0.0012819823,0.12164428,0.0012695137,0.00033458852,0.000024876028,0.7063295,0.00659386,0.006902041,0.07618871,0.07531357,0.0017074838],"about_ca_topic_score_codex":0.01196195,"about_ca_topic_score_gemma":0.020069256,"teacher_disagreement_score":0.35235468,"about_ca_system_score_codex":0.003652471,"about_ca_system_score_gemma":0.0078548845,"threshold_uncertainty_score":0.99957347},"labels":[],"label_agreement":null},{"id":"W2748186553","doi":"","title":"Influence of Pedagogical Supervisors’ Practices and Perceptions on the Use of Results-Based Management","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Educational Administration and Policy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université Laval","funders":"","keywords":"Obligation; Pedagogy; Perception; Sociology; Political science; Psychology; Humanities; Public relations; Law","score_opus":0.5238539425264882,"score_gpt":0.5675586609891903,"score_spread":0.043704718462702075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2748186553","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8784257,0.00001555328,0.000007402593,0.11914495,0.000048927013,0.000076187775,0.00005211135,2.768868e-7,0.002228855],"genre_scores_gemma":[0.997354,0.000056930814,0.00045987728,0.0009277549,0.00009420049,0.000002589665,0.0000036771096,0.0000018970696,0.001099119],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9987145,0.00012093811,0.00053074857,0.00009759391,0.0004576721,0.0000785334],"domain_scores_gemma":[0.996472,0.0012136531,0.0012171911,0.0002641479,0.0006162163,0.00021677623],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013377165,0.00006097342,0.00010745608,0.00029213514,0.00036541448,0.0002860357,0.00027190792,0.00002924038,0.00036549623],"category_scores_gemma":[0.007133224,0.000038763537,0.000036270394,0.00011237208,0.00029914186,0.00047912478,0.000009854131,0.00008866399,0.000004986314],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033453523,0.00026692986,0.3980871,0.000041927873,0.00007374497,0.000004246988,0.0096101295,0.0033509019,0.00026200828,0.5617577,0.014563631,0.011647143],"study_design_scores_gemma":[0.00023966574,0.00024110278,0.97185755,0.000050640003,0.000014022823,0.000016062999,0.001736404,0.00021859597,0.000057435005,0.0033570868,0.02216764,0.00004381066],"about_ca_topic_score_codex":0.0012736107,"about_ca_topic_score_gemma":0.0064543462,"teacher_disagreement_score":0.5737704,"about_ca_system_score_codex":0.000027705317,"about_ca_system_score_gemma":0.0033800444,"threshold_uncertainty_score":0.85396504},"labels":[],"label_agreement":null},{"id":"W2749550125","doi":"","title":"Een dynamische kennis-/leeragenda voor TransForum, verslag van interne brainstorm sessie","year":2007,"lang":"nl","type":"article","venue":"VU Research Portal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athena Sustainable Materials Institute","funders":"","keywords":"Art","score_opus":0.2721454229194646,"score_gpt":0.5569446691373249,"score_spread":0.2847992462178603,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2749550125","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49495506,0.00068924634,0.006549105,0.005526605,0.0021673304,0.0012805403,0.00023589238,0.000100832214,0.48849538],"genre_scores_gemma":[0.91604286,0.0003827312,0.00049570296,0.00044720698,0.0005433601,0.00003592234,0.00013514988,0.000062497325,0.08185459],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9826522,0.0009513627,0.0019774777,0.00145756,0.01043234,0.0025290917],"domain_scores_gemma":[0.99284023,0.002361561,0.0003474798,0.0014609606,0.0017230839,0.0012667055],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.044087593,0.0005281008,0.0006826847,0.0016872927,0.0010974448,0.0010729906,0.0022935895,0.00047173077,0.083781384],"category_scores_gemma":[0.0020266904,0.00043518888,0.00046683324,0.0029454876,0.001187682,0.0014789583,0.00048094845,0.002141647,0.010510446],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016501348,0.0015833899,0.07963482,0.0002301009,0.0006036522,0.0024340507,0.014993814,0.00030895983,0.0056474283,0.019543791,0.2974917,0.57587814],"study_design_scores_gemma":[0.0034776637,0.001760853,0.069631316,0.0002646092,0.000050879247,0.00009026882,0.020142538,0.021844303,0.0030395105,0.0016147039,0.8770929,0.0009904393],"about_ca_topic_score_codex":0.00037993293,"about_ca_topic_score_gemma":0.0035281244,"teacher_disagreement_score":0.5796012,"about_ca_system_score_codex":0.00042025922,"about_ca_system_score_gemma":0.0025749085,"threshold_uncertainty_score":0.999964},"labels":[],"label_agreement":null},{"id":"W2750272493","doi":"10.56105/cjsae.v16i2.1883","title":"The Art of Evaluation: A Handbook for Educators and Trainers. Tara Fenwick and Jim Parsons. (2000). Toronto: Thompson Educational Publishing, Inc., 244 pages.","year":2002,"lang":"en","type":"article","venue":"Canadian Journal for the Study of Adult Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Publishing; Media studies; Sociology; Art; Project commissioning; Management; Library science; Gerontology; Medicine; Computer science; Literature","score_opus":0.1427637102844234,"score_gpt":0.42329631775616516,"score_spread":0.2805326074717418,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2750272493","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79146916,0.029133145,0.00035960952,0.15904085,0.00802509,0.006075811,0.00012524023,0.000006396462,0.005764697],"genre_scores_gemma":[0.99010825,0.0005143476,0.00044837556,0.00045823623,0.00055203546,0.00035773448,0.000016106584,0.000012346282,0.0075325845],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975968,0.00024276182,0.0007427139,0.00024848024,0.0009106049,0.00025864338],"domain_scores_gemma":[0.99402165,0.0017660587,0.0006544763,0.00034472413,0.0028870637,0.00032600857],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0056185224,0.00014177775,0.0002093267,0.00018461123,0.0014490599,0.00079859595,0.00043515916,0.000054011416,0.0009091888],"category_scores_gemma":[0.004579152,0.00008596508,0.00007379449,0.0002434949,0.00020461928,0.0009330747,0.000014586145,0.00014299173,0.0000030068009],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036257305,0.00022463854,0.015456514,0.000014352141,0.00008949205,3.5604547e-8,0.03651221,0.000054278862,0.000004903588,0.001697472,0.61920553,0.3267043],"study_design_scores_gemma":[0.0029769463,0.0011897709,0.22587779,0.00012871002,0.0003446953,0.00007102987,0.28519017,0.013231682,0.000029849429,0.017578045,0.45305303,0.00032827698],"about_ca_topic_score_codex":0.0019805015,"about_ca_topic_score_gemma":0.11114437,"teacher_disagreement_score":0.32637602,"about_ca_system_score_codex":0.00029574754,"about_ca_system_score_gemma":0.0045769466,"threshold_uncertainty_score":0.9998509},"labels":[],"label_agreement":null},{"id":"W2750400467","doi":"10.1016/j.evalprogplan.2017.08.010","title":"On the evaluation of social innovations and social enterprises: Recognizing and integrating two solitudes in the empirical knowledge base","year":2017,"lang":"en","type":"article","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":36,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"University of Ottawa","keywords":"Scholarship; Knowledge management; Empirical research; Field (mathematics); Sociology; Knowledge base; Public relations; Computer science; Political science; Epistemology","score_opus":0.6846078680975961,"score_gpt":0.6471283739198773,"score_spread":0.037479494177718786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2750400467","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9818749,0.00017681789,0.00016051088,0.0073985765,0.00010239786,0.00093383004,0.000004495779,0.000009603843,0.009338871],"genre_scores_gemma":[0.99891055,0.00000534311,0.0003463363,0.00038224095,0.00009373339,0.0002202619,0.0000162635,0.0000049335317,0.000020342555],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99573594,0.0016168902,0.00054983335,0.00029654425,0.0016342887,0.00016647618],"domain_scores_gemma":[0.99672985,0.001671499,0.00048720482,0.00020701931,0.000880816,0.000023598674],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.039005596,0.00012329081,0.00018027626,0.0001963483,0.0015933986,0.00085613783,0.000254827,0.000060229937,0.00014432272],"category_scores_gemma":[0.0056045465,0.00006998098,0.00003240067,0.00027935553,0.00024206363,0.0003854732,0.00009431857,0.00024067026,0.000003937937],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035903442,0.000098793025,0.082101226,0.000009012349,0.000015568485,1.8027113e-7,0.06834025,0.000037932346,0.000051678177,0.00621044,0.0007345802,0.84236443],"study_design_scores_gemma":[0.0014025053,0.0001307908,0.6369286,0.000089329376,0.00006845092,0.0000028166016,0.026665386,0.31371048,0.000022941756,0.01989461,0.00096819387,0.00011588529],"about_ca_topic_score_codex":0.000015121209,"about_ca_topic_score_gemma":0.0001495005,"teacher_disagreement_score":0.84224856,"about_ca_system_score_codex":0.000043285334,"about_ca_system_score_gemma":0.00025093564,"threshold_uncertainty_score":0.9997064},"labels":[],"label_agreement":null},{"id":"W2752092069","doi":"10.1016/j.evalprogplan.2017.08.014","title":"Building a community-based culture of evaluation","year":2017,"lang":"en","type":"article","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":34,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alzheimer Society of Canada; Centre for Community Based Research","funders":"","keywords":"Alliance; Capacity building; Argument (complex analysis); Program evaluation; Sociology; Theory of change; Action research; Conceptual framework; Research program; Public relations; Engineering ethics; Political science; Pedagogy; Engineering; Public administration; Social science; Medicine","score_opus":0.4616641335208906,"score_gpt":0.6253219780203569,"score_spread":0.16365784449946635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2752092069","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97033393,0.00043863532,0.003809411,0.0008660518,0.0003418446,0.0013395856,0.0000074259183,0.000048745427,0.022814352],"genre_scores_gemma":[0.9852898,0.0000047513636,0.014182191,0.00018589506,0.000051494146,0.00015352928,0.00004750109,0.0000065905215,0.0000782188],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9945277,0.0014400859,0.0005525577,0.0002444643,0.0030711184,0.00016405663],"domain_scores_gemma":[0.996054,0.00046573367,0.00081531197,0.00079267856,0.0017925644,0.00007971888],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.03550531,0.000127329,0.00021958015,0.0002014692,0.0013361741,0.0006747977,0.00043788413,0.00008870551,0.00049054244],"category_scores_gemma":[0.004687742,0.00009700596,0.000064956235,0.00019454227,0.00014780877,0.000596909,0.0000933128,0.00025021448,0.000015812173],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004179732,0.00010841232,0.0647881,0.000019232424,0.000018017236,2.9228866e-7,0.003859647,0.005766472,0.0005247075,0.00059583614,0.000748875,0.9235286],"study_design_scores_gemma":[0.001728658,0.00029765395,0.25101766,0.00014526906,0.000086551314,0.0000025602528,0.0016617947,0.7192286,0.0007979378,0.013897266,0.010986032,0.00014995462],"about_ca_topic_score_codex":0.000038633705,"about_ca_topic_score_gemma":0.000019289806,"teacher_disagreement_score":0.92337865,"about_ca_system_score_codex":0.000046993744,"about_ca_system_score_gemma":0.00032342455,"threshold_uncertainty_score":0.99996394},"labels":[],"label_agreement":null},{"id":"W2752246894","doi":"","title":"Doing participatory evaluation in Indigenous contexts - methodological issues and questions","year":2013,"lang":"en","type":"article","venue":"ALAR","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Indigenous; Mainstream; Participatory action research; Citizen journalism; Participatory evaluation; Sociology; Action research; Political science; Public relations; Engineering ethics; Public administration; Engineering; Pedagogy; Ecology","score_opus":0.5338162209381445,"score_gpt":0.5972862119027038,"score_spread":0.0634699909645593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2752246894","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9927529,0.0011091065,0.0014695404,0.002611375,0.00013149658,0.0004385304,8.6974916e-7,0.00001763088,0.0014685303],"genre_scores_gemma":[0.9941263,0.00006263114,0.004933004,0.00039728632,0.000033058397,0.00014941007,0.0000022698541,0.000003145939,0.0002928959],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99705034,0.0012989,0.00039777366,0.00020545871,0.0008777768,0.00016976599],"domain_scores_gemma":[0.99820065,0.001108556,0.000098084514,0.00021871066,0.00030335214,0.00007061438],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009969319,0.00007130871,0.00016408267,0.00015037875,0.00011487192,0.00014954025,0.00013655529,0.000059332797,0.0029923515],"category_scores_gemma":[0.0023190768,0.00004978755,0.000022727801,0.00025587206,0.00006265834,0.0004677711,0.000043873846,0.0000972892,0.0006118268],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006012186,0.00007317029,0.3517359,0.0000026744583,0.000008305913,0.0000017001958,0.0073106107,0.00062549114,0.0010224883,0.0019032237,0.0016105613,0.63569987],"study_design_scores_gemma":[0.000345136,0.00007576446,0.9397216,0.000013142045,0.000010129237,0.0000036865954,0.0009654888,0.012830858,0.00027558583,0.03383543,0.01182677,0.00009640766],"about_ca_topic_score_codex":0.00029202455,"about_ca_topic_score_gemma":0.0002244319,"teacher_disagreement_score":0.6356035,"about_ca_system_score_codex":0.00003866318,"about_ca_system_score_gemma":0.00009737126,"threshold_uncertainty_score":0.997919},"labels":[],"label_agreement":null},{"id":"W2752376276","doi":"10.4000/dse.973","title":"Conséquences des conceptions curriculaires actuelles sur les modes évaluatifs","year":2011,"lang":"fr","type":"article","venue":"Les dossiers des sciences de l éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Humanities; Philosophy; Sociology; Political science","score_opus":0.7784961794011411,"score_gpt":0.553268324582771,"score_spread":0.22522785481837015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2752376276","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9061771,0.015666842,0.020860014,0.002579002,0.002279401,0.0005002546,0.000045278943,0.00011200906,0.051780075],"genre_scores_gemma":[0.94202614,0.002579751,0.047748633,0.00032318424,0.00021418251,0.00010918054,0.000013082489,0.000021409274,0.006964443],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99276733,0.0017186922,0.0011738478,0.0010816272,0.0021311273,0.0011273654],"domain_scores_gemma":[0.9950537,0.001584219,0.0007422349,0.000623359,0.0015334521,0.0004630374],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["sts"],"category_scores_codex":[0.009285034,0.00048829935,0.00046239467,0.0006462982,0.005108749,0.0012537992,0.0016891975,0.00032274597,0.016336666],"category_scores_gemma":[0.003210328,0.0004011322,0.0002796947,0.0027579248,0.01920815,0.0037555003,0.00017028333,0.0003778897,0.0007595761],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032572225,0.0006301329,0.2561099,0.000125129,0.00006449722,0.0000056755584,0.12287859,0.004785542,0.0009279222,0.08940836,0.0045779445,0.52045375],"study_design_scores_gemma":[0.00066044333,0.0008198332,0.26968506,0.0008622311,0.00021203989,0.00012288128,0.18947417,0.1337233,0.003531674,0.39067236,0.009198565,0.001037436],"about_ca_topic_score_codex":0.011495198,"about_ca_topic_score_gemma":0.009438528,"teacher_disagreement_score":0.5194163,"about_ca_system_score_codex":0.0015170693,"about_ca_system_score_gemma":0.0043006176,"threshold_uncertainty_score":0.9998441},"labels":[],"label_agreement":null},{"id":"W2753183045","doi":"10.47678/cjhe.v47i2.186704","title":"The Online Evaluation of Courses: Impact on Participation Rates and Evaluation Scores","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Higher Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"Simon Fraser University; University of Saskatchewan; University of Ottawa","keywords":"Online course; Medical education; Course evaluation; Class (philosophy); Psychology; Higher education; Evaluation methods; Mathematics education; Computer science; Medicine; Engineering; Political science","score_opus":0.3395601152054726,"score_gpt":0.6097107975871295,"score_spread":0.27015068238165696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2753183045","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9885131,0.0017982991,0.000007070426,0.0060935137,0.0018651522,0.00026551355,0.0000100736925,8.905191e-7,0.0014463622],"genre_scores_gemma":[0.99884164,0.00004143315,0.000048893457,0.00013146813,0.00029793402,0.000012286092,0.000009871951,0.000005388815,0.0006110981],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9967253,0.0005360949,0.00063176046,0.00012627574,0.0018316854,0.00014887666],"domain_scores_gemma":[0.9928333,0.0004290562,0.0014394935,0.00046422853,0.0045960797,0.00023782186],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.012009926,0.0000914886,0.00015359781,0.00030356555,0.0006324624,0.00052167143,0.0004037235,0.000045222794,0.0010087399],"category_scores_gemma":[0.0033068114,0.00005267936,0.0000649555,0.00014135943,0.00016181426,0.00068823656,0.00000806417,0.000108973014,0.000012825407],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006131195,0.00009609447,0.54447484,0.0000036297138,0.000049435315,2.0861857e-7,0.0011009485,0.004945849,0.000114359245,0.0016563459,0.023357889,0.42413908],"study_design_scores_gemma":[0.00044404477,0.00018420554,0.97044796,0.00005934047,0.000104602914,0.0000031239663,0.0005319879,0.009107505,0.00015205286,0.013978333,0.004930199,0.00005664798],"about_ca_topic_score_codex":0.0010836256,"about_ca_topic_score_gemma":0.010049124,"teacher_disagreement_score":0.42597312,"about_ca_system_score_codex":0.00033474187,"about_ca_system_score_gemma":0.008138046,"threshold_uncertainty_score":0.99990445},"labels":[],"label_agreement":null},{"id":"W2754383811","doi":"10.1111/capa.12225","title":"Use of systematic literature reviews in Canadian government departments: Where do we need to go?","year":2017,"lang":"en","type":"article","venue":"Canadian Public Administration","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Systematic review; Process (computing); Public relations; Point (geometry); Political science; Business; Computer science","score_opus":0.22936838704720292,"score_gpt":0.440118211327871,"score_spread":0.21074982428066807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2754383811","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37842214,0.009882783,0.00040568606,0.55144286,0.003472139,0.012675986,0.0021660463,0.000038821032,0.041493572],"genre_scores_gemma":[0.9936915,0.00027860218,0.00036396692,0.00073370297,0.000046976427,0.00016059665,0.000025759842,0.0000089919695,0.004689887],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99670565,0.00029051458,0.0010619591,0.00036599298,0.0011283208,0.000447537],"domain_scores_gemma":[0.99627686,0.00013448614,0.00058950833,0.0013160002,0.00037856,0.0013046054],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0036770478,0.00017120685,0.00041181297,0.0004903787,0.000339529,0.0024640814,0.00082417665,0.00012543787,0.0007802501],"category_scores_gemma":[0.005726914,0.00013863038,0.000077785,0.00055615214,0.00003751918,0.0016479044,0.000028750446,0.00012547662,0.00032712505],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048057125,0.00015952933,0.510256,0.0035851263,0.0000770217,0.00015616689,0.0033592249,0.00003914347,0.00010050206,0.13119335,0.30492637,0.046099517],"study_design_scores_gemma":[0.00021530197,0.00010838378,0.03499856,0.0023329796,0.000012279395,0.000009510148,0.000481238,0.001053076,0.000025339228,0.00028886768,0.9602587,0.00021575051],"about_ca_topic_score_codex":0.058021754,"about_ca_topic_score_gemma":0.9966883,"teacher_disagreement_score":0.9386665,"about_ca_system_score_codex":0.0013033461,"about_ca_system_score_gemma":0.0042993384,"threshold_uncertainty_score":0.99857146},"labels":[],"label_agreement":null},{"id":"W2755020612","doi":"10.1332/174426417x15034894876108","title":"Building the concept of research impact literacy","year":2017,"lang":"en","type":"article","venue":"Evidence & Policy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":58,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"York University","funders":"","keywords":"Literacy; Impact assessment; Scale (ratio); Impact evaluation; Knowledge management; Management science; Political science; Computer science; Sociology; Engineering; Pedagogy; Public administration; Geography","score_opus":0.6282059592432973,"score_gpt":0.7316061843853462,"score_spread":0.10340022514204894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2755020612","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94758064,0.0006746318,0.00042363626,0.04064203,0.00024117107,0.00028602965,0.000007733993,0.000012394902,0.010131722],"genre_scores_gemma":[0.9957442,0.00009553909,0.0003893625,0.0003121205,0.0005391454,0.000013347623,2.0192917e-7,0.000005340697,0.0029006903],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9954261,0.00061815477,0.00050090835,0.00027968045,0.002819932,0.00035521088],"domain_scores_gemma":[0.9918032,0.0042899507,0.00044607508,0.0020133376,0.0013356479,0.0001117612],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016610442,0.000091651076,0.00018843937,0.00033005708,0.001065025,0.0012074495,0.0027711878,0.000042217587,0.0013953984],"category_scores_gemma":[0.039189033,0.000046560366,0.0001325211,0.0006502398,0.00070498715,0.0020007296,0.00047403752,0.00026351179,0.00040969095],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008066326,0.000059178554,0.18300204,0.000010621267,0.000027681066,0.0000043749824,0.01748854,0.0006351065,0.004317065,0.14396994,0.03894781,0.611457],"study_design_scores_gemma":[0.0002443329,0.00023042726,0.8665061,0.00032524316,0.0000053770964,0.000008207509,0.0006967037,0.004585908,0.005858788,0.079931445,0.04147984,0.00012761836],"about_ca_topic_score_codex":0.0024281985,"about_ca_topic_score_gemma":0.00003516191,"teacher_disagreement_score":0.68350405,"about_ca_system_score_codex":0.00010327546,"about_ca_system_score_gemma":0.0010654632,"threshold_uncertainty_score":0.9998294},"labels":[],"label_agreement":null},{"id":"W2756789610","doi":"","title":"Guest Editorial: Copied it RIGHT OUT of the Solution Manual!","year":2017,"lang":"en","type":"editorial","venue":"Chemical Engineering Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Science education; Engineering ethics; Engineering; Engineering management; Mathematics education; Computer science; Psychology","score_opus":0.04923768687240831,"score_gpt":0.43452908148987585,"score_spread":0.38529139461746753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2756789610","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00040631925,0.000067559,0.000193616,0.000779971,0.9956375,0.00023347622,0.000037789407,0.000030622115,0.0026131535],"genre_scores_gemma":[0.0053342404,0.000024938636,0.00022405271,0.000017809733,0.98675036,0.00006578471,0.00019962827,0.000024799945,0.0073583703],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957074,0.00004915169,0.0007346597,0.00041166332,0.002887846,0.00020928413],"domain_scores_gemma":[0.99556834,0.0010615916,0.0007590991,0.0012558847,0.0012642147,0.00009086116],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0019222819,0.00023489051,0.00036727084,0.0001312273,0.00012138889,0.00019445125,0.0014640457,0.00059320807,0.00012826099],"category_scores_gemma":[0.013238489,0.00016146374,0.00017863167,0.000162254,0.00008025691,0.0002578032,0.00016924691,0.0006672141,0.00016220927],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005618817,0.00005350011,0.000010412307,0.000056969446,0.000011578434,4.0504e-8,0.00012994594,0.000044478445,0.0021968419,0.000029263776,0.99667263,0.0007887456],"study_design_scores_gemma":[0.00015739877,0.0000102665745,0.00010671299,0.00021941707,0.000034826942,3.2596952e-7,0.000011215191,0.00048184278,0.007201319,0.00022756154,0.9913703,0.00017880404],"about_ca_topic_score_codex":0.000021402502,"about_ca_topic_score_gemma":0.0000075337575,"teacher_disagreement_score":0.011316206,"about_ca_system_score_codex":0.00029010847,"about_ca_system_score_gemma":0.001902328,"threshold_uncertainty_score":0.99507344},"labels":[],"label_agreement":null},{"id":"W2758565161","doi":"10.55016/ojs/ajer.v63i2.56421","title":"An Introduction to Program Evaluation: Basic Concepts and Example Cases (2016), by Richard M. Jones","year":2017,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Mathematics education; Psychology","score_opus":0.48309057357250834,"score_gpt":0.6454334808679035,"score_spread":0.1623429072953952,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2758565161","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87575763,0.00038558006,0.000017243277,0.11811826,0.00080469577,0.000572908,0.0000046852424,7.2549744e-7,0.0043382486],"genre_scores_gemma":[0.9819599,0.0000894203,0.0008374273,0.00015517726,0.0018981979,0.00011626373,0.000015578393,0.000009065122,0.014918996],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9941599,0.00085841544,0.000653246,0.00038016512,0.0036640672,0.00028421165],"domain_scores_gemma":[0.9837216,0.00918595,0.00048173772,0.0007478631,0.005445879,0.00041693464],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016116552,0.0001065053,0.00020766909,0.00045163615,0.0010411366,0.0012576638,0.00094578374,0.000051652845,0.025018496],"category_scores_gemma":[0.048139893,0.000077625686,0.00004974523,0.00035030372,0.0002755355,0.0017247781,0.000102905375,0.00026416383,0.00040106656],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001855217,0.0006645254,0.09675705,0.0000074314,0.00004235316,4.8989904e-7,0.0018847261,0.00011310367,0.0015564294,0.004578242,0.65900683,0.23520328],"study_design_scores_gemma":[0.000707284,0.0014900566,0.29779527,0.000032165044,0.000026197273,0.0001379331,0.0020983974,0.0013369713,0.0005845914,0.004326403,0.69130176,0.0001629805],"about_ca_topic_score_codex":0.00071948825,"about_ca_topic_score_gemma":0.001148322,"teacher_disagreement_score":0.2350403,"about_ca_system_score_codex":0.0001495566,"about_ca_system_score_gemma":0.00196904,"threshold_uncertainty_score":0.9997791},"labels":[],"label_agreement":null},{"id":"W2758849335","doi":"10.1086/693355","title":"Evidence-Based Beliefs?","year":2017,"lang":"en","type":"article","venue":"KNOW A Journal on the Formation of Knowledge","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Download; Library science; Discipline; Sociology; Media studies; Political science; Computer science; World Wide Web; Social science","score_opus":0.4045764426865554,"score_gpt":0.4994157288962871,"score_spread":0.0948392862097317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2758849335","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5889432,0.0029411037,0.030489806,0.08745309,0.0045992443,0.00086226984,0.000017634182,0.000046207715,0.28464743],"genre_scores_gemma":[0.99566454,0.00021592155,0.00022287386,0.00041982016,0.00023316265,0.000007933343,5.7538574e-7,0.0000057133143,0.003229456],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.996876,0.00043025074,0.0008848123,0.00012089004,0.0015144068,0.00017361091],"domain_scores_gemma":[0.99416834,0.0017121177,0.0016261924,0.00094067096,0.0014429659,0.00010968377],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.011952995,0.00011807914,0.0002134227,0.0002896448,0.0014016557,0.00072351034,0.0017353769,0.000050823743,0.0026637085],"category_scores_gemma":[0.0073823454,0.000059872997,0.00020204806,0.00019749781,0.00014496951,0.0021100002,0.00008930903,0.0002822626,0.0023649368],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032341533,0.000444782,0.0054377518,0.00004007884,0.0000410266,0.0000029907073,0.006657067,0.0018985472,0.0011965025,0.051470928,0.14792392,0.784563],"study_design_scores_gemma":[0.0027420986,0.0014588478,0.08039466,0.0026752627,0.000056049244,0.00006991868,0.0016577421,0.20086774,0.040981304,0.04070082,0.62790674,0.00048880326],"about_ca_topic_score_codex":0.0000012350996,"about_ca_topic_score_gemma":0.000015949276,"teacher_disagreement_score":0.7840742,"about_ca_system_score_codex":0.00008520883,"about_ca_system_score_gemma":0.00039658856,"threshold_uncertainty_score":0.9998984},"labels":[],"label_agreement":null},{"id":"W2759101306","doi":"10.1002/jid.3328","title":"An Evaluation Toolkit for Small NGOs in Water‐based Development","year":2017,"lang":"en","type":"article","venue":"Journal of International Development","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Regional Municipality of Waterloo; University of Waterloo","funders":"Mitacs","keywords":"Disadvantaged; Accountability; Face (sociological concept); International development; Political science; Business; Public relations; Public administration; Economic growth; Economics; Sociology; Social science; Law","score_opus":0.37996231950821485,"score_gpt":0.5406847779891295,"score_spread":0.16072245848091465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2759101306","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9622473,0.000016196256,0.029916072,0.0033729358,0.0019237944,0.00035010595,0.0000019215881,0.0000045014303,0.0021671453],"genre_scores_gemma":[0.934726,0.0000038026233,0.064098366,0.00033958073,0.00016840037,0.00005827526,0.000024475989,0.000008250402,0.00057282817],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9950898,0.00011700529,0.0015478939,0.00024048872,0.0027997326,0.00020502099],"domain_scores_gemma":[0.9953227,0.00020551604,0.0010272766,0.0003196329,0.0030111591,0.00011373157],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016299855,0.00013758692,0.00024141597,0.00062593946,0.00031028234,0.0006456092,0.0015442999,0.000060034068,0.0010534907],"category_scores_gemma":[0.0015220044,0.00008943908,0.000084242674,0.000059851573,0.00002897523,0.00095194747,0.00007951199,0.000126176,0.00007908579],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004905181,0.0006042066,0.21221076,0.000011142837,0.00011337539,0.000011404094,0.0045374054,0.013953404,0.0032976442,0.00039130574,0.0010187796,0.76336],"study_design_scores_gemma":[0.0030759005,0.00012354097,0.7655667,0.000099732315,0.000009460756,0.000010631445,0.0003411385,0.04463043,0.037493262,0.0018599599,0.14658347,0.0002057986],"about_ca_topic_score_codex":0.0000046982505,"about_ca_topic_score_gemma":0.00026898403,"teacher_disagreement_score":0.76315427,"about_ca_system_score_codex":0.0006440462,"about_ca_system_score_gemma":0.0018837595,"threshold_uncertainty_score":0.9998597},"labels":[],"label_agreement":null},{"id":"W2759512360","doi":"10.1186/s13012-017-0646-0","title":"Advancing the literature on designing audit and feedback interventions: identifying theory-informed hypotheses","year":2017,"lang":"en","type":"article","venue":"Implementation Science","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":160,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; University of British Columbia; Ottawa Hospital; Women's College Hospital; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Psychological intervention; Medicine; Health services research; Audit; Health administration; Health informatics; Health care; Health economics; Public health; Nursing; Applied psychology; Psychology; Accounting","score_opus":0.39725757600893574,"score_gpt":0.6178921478400988,"score_spread":0.22063457183116308,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2759512360","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9385494,0.0002448399,0.03983736,0.008320465,0.0014722202,0.0010012641,0.000026790805,0.000051560273,0.0104961125],"genre_scores_gemma":[0.99572307,0.00007705073,0.0024470363,0.00078303897,0.00006158539,0.000043573804,0.0000023591576,0.000004907555,0.0008573758],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9966256,0.0001844763,0.00057792803,0.00041718714,0.0018800807,0.00031473007],"domain_scores_gemma":[0.99631804,0.0015978889,0.00070474384,0.0007913002,0.0004902575,0.000097761564],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.014886214,0.00012021909,0.0001255742,0.00033114135,0.0037170877,0.0056007705,0.001360085,0.000020574174,0.00095273287],"category_scores_gemma":[0.0067097945,0.00007028599,0.00007424974,0.0005491129,0.0005222167,0.0040391623,0.0003055912,0.00012564055,0.00013969986],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055191285,0.000033957847,0.047177527,0.00003161447,0.000017693474,0.0000027061685,0.016926061,0.00017003491,0.0058110687,0.0467508,0.0033600666,0.8796633],"study_design_scores_gemma":[0.001173443,0.00020760753,0.8374136,0.0005200054,0.000023392653,0.000018229232,0.049162205,0.0017458571,0.015446756,0.08728727,0.006711119,0.0002905116],"about_ca_topic_score_codex":0.000014312402,"about_ca_topic_score_gemma":0.00020119849,"teacher_disagreement_score":0.8793728,"about_ca_system_score_codex":0.00009410956,"about_ca_system_score_gemma":0.0002996968,"threshold_uncertainty_score":0.99996054},"labels":[],"label_agreement":null},{"id":"W2759592504","doi":"","title":"The Canadian M&E System","year":2010,"lang":"en","type":"article","venue":"World Bank Publications","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Business; Economics","score_opus":0.1326465923699032,"score_gpt":0.45201368111878076,"score_spread":0.31936708874887754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2759592504","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008881543,0.000020794627,0.00017275417,0.15087748,0.001473571,0.00025399664,0.00001614307,0.00008797829,0.83821577],"genre_scores_gemma":[0.912294,9.759991e-7,0.0004113088,0.00062100333,0.00015107739,0.00011191094,0.000010311955,0.0000047311546,0.0863947],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981861,0.00008085266,0.0003694704,0.00021036938,0.000909896,0.00024328647],"domain_scores_gemma":[0.9970395,0.0006748079,0.0001286184,0.0010941834,0.0008192766,0.00024363704],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.004387674,0.000064668326,0.00006932491,0.0004544725,0.0019256551,0.0015151202,0.0010515889,0.00003385746,0.0027715145],"category_scores_gemma":[0.0011016278,0.00003768046,0.000049795326,0.0018615446,0.000105536754,0.0003433942,0.000039327446,0.00024245633,0.0036008642],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.3060707e-7,0.000005023055,0.011158005,2.716586e-7,0.0000029617017,5.7303467e-8,0.00006790007,0.0000073341866,0.00003394088,0.81348103,0.16022742,0.015015714],"study_design_scores_gemma":[0.000043233635,0.0000019826798,0.12080166,9.045814e-7,0.0000023034281,0.0000025676106,0.00018229344,0.0034531727,0.00001857069,0.0021552313,0.8732905,0.00004757662],"about_ca_topic_score_codex":0.008502612,"about_ca_topic_score_gemma":0.95154536,"teacher_disagreement_score":0.94304276,"about_ca_system_score_codex":0.00011247131,"about_ca_system_score_gemma":0.0013055108,"threshold_uncertainty_score":0.9995214},"labels":[],"label_agreement":null},{"id":"W2762648200","doi":"","title":"International perspectives on positive action measures: a comparative analysis in the European Union, Canada, the United [...]","year":2017,"lang":"en","type":"article","venue":"Books | European Encyclopedia of Law","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"European union; Action (physics); Political science; International trade; Economics","score_opus":0.17748416552263757,"score_gpt":0.42951981174237497,"score_spread":0.2520356462197374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2762648200","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14885889,0.000011819647,0.00020432698,0.0031221146,0.00020242365,0.00018224496,0.00003349814,0.0000073595256,0.8473773],"genre_scores_gemma":[0.9950398,0.0000806206,0.000038987233,0.0006416449,0.00015513225,0.000003648531,0.00002342251,0.000007805548,0.0040089316],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9917662,0.00550071,0.000523102,0.0003394728,0.001716993,0.00015351441],"domain_scores_gemma":[0.9969034,0.0009443765,0.0006029238,0.0009367333,0.00056425505,0.000048300306],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010304108,0.00015217539,0.00021351135,0.00025721983,0.00071466825,0.00032043082,0.0018625732,0.000014078937,0.00014625161],"category_scores_gemma":[0.00068602426,0.000081549486,0.00011247671,0.00034070227,0.00027663453,0.00024136863,0.00014093496,0.0002925935,0.000055982367],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005522703,0.0012335888,0.18365721,0.000010092803,0.002439012,0.00024930984,0.2964079,0.025943546,0.00016727907,0.33899757,0.07444989,0.07589232],"study_design_scores_gemma":[0.0002792747,0.000050155595,0.7578572,0.000014332263,0.000056568064,0.0000016607701,0.015226036,0.0005131896,0.000011050608,0.00018697507,0.22570553,0.0000980403],"about_ca_topic_score_codex":0.07282416,"about_ca_topic_score_gemma":0.45037448,"teacher_disagreement_score":0.8461809,"about_ca_system_score_codex":0.00011635979,"about_ca_system_score_gemma":0.00012961663,"threshold_uncertainty_score":0.93334997},"labels":[],"label_agreement":null},{"id":"W2763322498","doi":"10.12688/f1000research.12496.3","title":"The peer review process for awarding funds to international science research consortia: a qualitative developmental evaluation","year":2018,"lang":"en","type":"preprint","venue":"F1000Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Royal Society; Department for International Development; Department for International Development, UK Government","keywords":"Peer review; Political science; CLARITY; Process (computing); Psychology; Computer science; Biology","score_opus":0.897925971119104,"score_gpt":0.791179746983318,"score_spread":0.10674622413578594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2763322498","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1967904,0.0053569446,0.014615315,0.4714038,0.010135021,0.038842417,0.00083006837,0.00018117392,0.26184487],"genre_scores_gemma":[0.92753816,0.0014781641,0.007456796,0.0014972636,0.0012393972,0.014759634,0.00029468694,0.0000699543,0.045665964],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9418961,0.0035883612,0.0016938365,0.0018202834,0.049773064,0.0012283644],"domain_scores_gemma":[0.89899164,0.009780183,0.00044096552,0.0012491891,0.08910974,0.00042824884],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.41548574,0.00026521497,0.00042505085,0.0015333827,0.0027866373,0.0027406448,0.0065096645,0.00014662146,0.0027383878],"category_scores_gemma":[0.20035195,0.00017002199,0.00016101287,0.0035562126,0.0017388496,0.0005575212,0.0037832686,0.0011363323,0.0016935789],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037481298,0.00014785936,0.001726074,0.0004311625,0.00013848444,0.0000014119595,0.03142442,0.00044419646,0.00033635774,0.0052057686,0.7554136,0.20435587],"study_design_scores_gemma":[0.0008580961,0.00038524426,0.0053895563,0.0023797783,0.00003648161,0.00000811246,0.058123086,0.08216264,0.0017420581,0.12947735,0.718829,0.0006086168],"about_ca_topic_score_codex":0.000045791952,"about_ca_topic_score_gemma":0.00015811132,"teacher_disagreement_score":0.73074776,"about_ca_system_score_codex":0.0021634623,"about_ca_system_score_gemma":0.02031184,"threshold_uncertainty_score":0.9990837},"labels":[],"label_agreement":null},{"id":"W2765146448","doi":"10.5465/ambpp.2016.18348abstract","title":"Modeling the Evaluation Process in a Controversy","year":2016,"lang":"en","type":"article","venue":"Academy of Management Proceedings","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"HEC Montréal","funders":"","keywords":"Process (computing); Perspective (graphical); Political science; Budget process; Management science; Economics; Computer science; Law","score_opus":0.23031673308266856,"score_gpt":0.4966744928186267,"score_spread":0.2663577597359581,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2765146448","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9394479,0.00006758114,0.001515857,0.025936097,0.000059593272,0.0009576565,0.0000010799843,0.000019716872,0.031994566],"genre_scores_gemma":[0.99798054,0.000099990255,0.00014630663,0.00074234203,0.000038613176,0.00015084782,2.029435e-7,0.0000059631348,0.0008352285],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99602383,0.000042142063,0.0006884412,0.00034937146,0.002683592,0.00021261214],"domain_scores_gemma":[0.9990944,0.00018469615,0.00026600342,0.00009588524,0.00032549383,0.000033505246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0120632155,0.00010560532,0.00016889867,0.00031539015,0.000076599936,0.000070377966,0.0007654551,0.000055097167,0.00041495374],"category_scores_gemma":[0.0006497524,0.000050527688,0.000050507984,0.0007292482,0.000059768692,0.0009996801,0.000116494106,0.00009917932,0.000077837896],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021724684,0.00013070485,0.04137021,0.00008450059,0.00007426071,2.6636326e-7,0.0033709123,0.009580913,0.0010400022,0.15258832,0.0065615554,0.78498113],"study_design_scores_gemma":[0.0035221854,0.000065762324,0.05801969,0.00025500642,0.00007372114,0.0000012227893,0.007979367,0.68347967,0.0012054245,0.23626922,0.008886258,0.00024248785],"about_ca_topic_score_codex":0.0000024331996,"about_ca_topic_score_gemma":0.000001619712,"teacher_disagreement_score":0.7847386,"about_ca_system_score_codex":0.000076099735,"about_ca_system_score_gemma":0.00003067083,"threshold_uncertainty_score":0.45434526},"labels":[],"label_agreement":null},{"id":"W2765317239","doi":"10.5070/bp326115800","title":"Finding Your Fit: A Proposal for Emerging Planning Scholars","year":2013,"lang":"en","type":"article","venue":"Berkeley Planning Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Waterloo","keywords":"Scholarship; Sociology; Engineering ethics; Range (aeronautics); Management science; Political science; Engineering; Law","score_opus":0.33471734241241974,"score_gpt":0.5273009678173074,"score_spread":0.19258362540488766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2765317239","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94406754,0.0004806071,0.04217597,0.0057605365,0.0016445409,0.0005781568,0.000008602434,0.000070840826,0.005213231],"genre_scores_gemma":[0.9520478,0.0000090309495,0.042513616,0.00058548653,0.0011762242,0.00006643746,0.000008249103,0.000033023676,0.0035601351],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9958664,0.00021098179,0.0010399972,0.00038582133,0.0018592128,0.0006375616],"domain_scores_gemma":[0.9971077,0.00080694776,0.000703324,0.0002884166,0.000783525,0.00031012134],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0072696377,0.00022527273,0.00033116428,0.0006174809,0.0012738253,0.0021398235,0.000768503,0.00011027045,0.0020562292],"category_scores_gemma":[0.0023403931,0.00016532607,0.00019684494,0.00049193064,0.00004054259,0.0020854543,0.000095728305,0.00066291715,0.00043654998],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001498564,0.0000910008,0.54869395,0.000026270734,0.00015171398,0.000056555502,0.011059428,0.045543715,0.004320382,0.0010850091,0.20123537,0.18758677],"study_design_scores_gemma":[0.0047709695,0.00083192653,0.40743294,0.0010378514,0.000098888224,0.0012350784,0.0246794,0.28727886,0.0011330165,0.055299778,0.2148675,0.0013337723],"about_ca_topic_score_codex":0.0000067462533,"about_ca_topic_score_gemma":0.000001175346,"teacher_disagreement_score":0.24173516,"about_ca_system_score_codex":0.0001073989,"about_ca_system_score_gemma":0.00057368155,"threshold_uncertainty_score":0.99889606},"labels":[],"label_agreement":null},{"id":"W2766824975","doi":"10.33524/cjar.v18i2.331","title":"ACTIVE RESEARCH IN THE AGE OF RECONCILIATION: A RELATIONSHIP-BASED APPROACH FOR NON-INDIGENOUS RESEARCHERS","year":2018,"lang":"en","type":"article","venue":"The Canadian Journal of Action Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Indigenous; Nova scotia; Action research; Commission; Sociology; TRACE (psycholinguistics); Natural (archaeology); Qualitative research; Pedagogy; Political science; Law; Social science; History; Archaeology; Ethnology; Ecology","score_opus":0.863243550385139,"score_gpt":0.6463898467525075,"score_spread":0.21685370363263146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766824975","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92391634,0.00010238224,0.004973062,0.036851015,0.00045773,0.0025324381,0.000035008627,0.000002958487,0.031129094],"genre_scores_gemma":[0.99750495,0.000008536391,0.00078116846,0.00013749769,0.0003467285,0.00006768726,0.0000060334246,0.000009073651,0.0011382987],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9889502,0.004819075,0.00075616466,0.00021474231,0.0046442607,0.0006155609],"domain_scores_gemma":[0.9800814,0.010615087,0.00030014917,0.00064144994,0.008117473,0.00024446408],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12629737,0.00007855686,0.00019347171,0.0025046587,0.0019079999,0.0004359498,0.0017283832,0.00011875788,0.00035120884],"category_scores_gemma":[0.011156788,0.000043797296,0.00011063357,0.004196131,0.0012198891,0.00042455675,0.000027341885,0.0015347592,0.00005399001],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0066754995,0.0008786685,0.16104202,0.00021596391,0.00026708134,0.000117363394,0.30569398,0.014918953,0.0029411986,0.014592638,0.1883003,0.30435634],"study_design_scores_gemma":[0.0037021176,0.005058449,0.5430354,0.00019462763,0.000023103541,0.00009164647,0.17691375,0.03441129,0.0044488474,0.06959255,0.1622292,0.00029904558],"about_ca_topic_score_codex":0.008948644,"about_ca_topic_score_gemma":0.153844,"teacher_disagreement_score":0.38199335,"about_ca_system_score_codex":0.0010005339,"about_ca_system_score_gemma":0.012559192,"threshold_uncertainty_score":0.9993914},"labels":[],"label_agreement":null},{"id":"W2766861252","doi":"10.1093/reseval/rvx037","title":"Using contribution analysis to evaluate the impacts of research on policy: Getting to ‘good enough’","year":2017,"lang":"en","type":"article","venue":"Research Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Impact; University of Waterloo","funders":"University of Waterloo; Canadian Cancer Society","keywords":"Management science; Regional science; Operations research; Public economics; Political science; Psychology; Sociology; Economics; Mathematics","score_opus":0.8233162217039798,"score_gpt":0.7626251681297992,"score_spread":0.06069105357418059,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766861252","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94695306,0.00004612406,0.002495474,0.038954534,0.00014717094,0.0025154166,0.000025963536,0.000011940491,0.008850327],"genre_scores_gemma":[0.99828464,0.0000172436,0.00049045234,0.00022238758,0.00039495993,0.00017924466,0.000013902824,0.000013531965,0.00038363325],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9600894,0.009900765,0.0011042964,0.0008738126,0.026899844,0.0011318797],"domain_scores_gemma":[0.9701758,0.005652245,0.00036345527,0.0028389194,0.020552509,0.00041706982],"candidate_categories":["metaresearch","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.296196,0.00016049661,0.00039747552,0.004401063,0.0034368122,0.0015060768,0.0021138107,0.0001109212,0.0009325754],"category_scores_gemma":[0.14534761,0.00010222519,0.00018396747,0.0077941343,0.00029634102,0.0006425466,0.0007466074,0.0005805732,0.0009983936],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015592136,0.00059958344,0.083287455,0.000032056712,0.000878086,0.0000041898766,0.013846855,0.33368924,0.10515947,0.06176222,0.0075446707,0.39163697],"study_design_scores_gemma":[0.0008857088,0.00076719833,0.47774345,0.00010041211,0.00012172131,9.040789e-7,0.0021804743,0.4768889,0.017996687,0.020776868,0.0023692178,0.00016846877],"about_ca_topic_score_codex":0.0021473593,"about_ca_topic_score_gemma":0.0012826022,"teacher_disagreement_score":0.394456,"about_ca_system_score_codex":0.0013851862,"about_ca_system_score_gemma":0.002949105,"threshold_uncertainty_score":0.9999807},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"evaluation","study_design":"theoretical_or_conceptual","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"evaluation","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W2767708843","doi":"10.2147/amep.s141886","title":"Understanding of evaluation capacity building in practice: a case study of a national medical education organization","year":2017,"lang":"en","type":"article","venue":"Advances in Medical Education and Practice","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Royal College of Physicians and Surgeons of Canada; Royal Ottawa Mental Health Centre; Ottawa Hospital","funders":"","keywords":"Context (archaeology); Foundation (evidence); Accountability; Qualitative research; Face (sociological concept); Medical education; Public relations; Psychology; Exploratory research; Political science; Medicine; Sociology; Social science","score_opus":0.3888434078001919,"score_gpt":0.6264228859226412,"score_spread":0.23757947812244928,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2767708843","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9568656,0.00062282855,0.0040527005,0.017913949,0.0013909871,0.0007624378,0.0000014300257,0.0000070922856,0.018382946],"genre_scores_gemma":[0.99509746,0.0007001294,0.0030261762,0.0010006098,0.00009257725,0.000051352217,0.000005600775,0.0000064609085,0.000019637191],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99157834,0.0016937694,0.0011049643,0.00036907312,0.0051280125,0.00012585189],"domain_scores_gemma":[0.9892803,0.005677002,0.0016476286,0.00039410926,0.0028249274,0.00017604142],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.029634448,0.00010891166,0.00024544724,0.000488262,0.00025709445,0.00012340005,0.00033834708,0.00013089644,0.0009463085],"category_scores_gemma":[0.37848282,0.000095260664,0.000017111895,0.0008382796,0.00020272071,0.0043520546,0.00009562149,0.00033225797,0.0000032927023],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026654443,0.012418305,0.30246663,0.000097144,0.000042888412,0.000039724895,0.041073624,0.00064772024,0.000027678143,0.074166104,0.00067321985,0.5680804],"study_design_scores_gemma":[0.0075337933,0.0006846414,0.09636512,0.0010349536,0.00019384884,0.004010917,0.7177497,0.08296182,0.00006112375,0.07167351,0.017164357,0.00056619087],"about_ca_topic_score_codex":0.00096249476,"about_ca_topic_score_gemma":0.0025844974,"teacher_disagreement_score":0.6766761,"about_ca_system_score_codex":0.0003294545,"about_ca_system_score_gemma":0.007981908,"threshold_uncertainty_score":0.999967},"labels":[],"label_agreement":null},{"id":"W2769074550","doi":"","title":"Implementation of the Alberta Accountability Framework","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Educational Administration and Policy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Accountability; Legislation; Government (linguistics); Jurisdiction; Public administration; Public relations; Political science; Christian ministry","score_opus":0.09160122295192488,"score_gpt":0.5123396007272927,"score_spread":0.4207383777753678,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2769074550","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9098959,0.000046449797,0.000012840441,0.07938707,0.00025405554,0.00008176024,0.000023920433,2.8775915e-7,0.010297715],"genre_scores_gemma":[0.9956163,0.000012892037,0.00020522402,0.0013832535,0.00030860803,0.0000021354726,0.000003181196,0.00000231466,0.0024660807],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986369,0.000114423245,0.0006067576,0.00008415416,0.00045817904,0.00009960822],"domain_scores_gemma":[0.99822253,0.00059189147,0.00034535985,0.00017247055,0.00043670795,0.0002310566],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00095296645,0.000058421254,0.000100803816,0.00017624877,0.00017207181,0.00011785354,0.00025779984,0.000037840247,0.03326477],"category_scores_gemma":[0.0009679156,0.00003856023,0.000063377505,0.00043559627,0.000116806,0.00029567195,0.000003896547,0.00009635748,0.000028129616],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019285419,0.00004059405,0.70393175,0.0000054906955,0.000018061583,1.2112864e-7,0.004710292,0.000064212996,0.000020736867,0.20445108,0.0073633706,0.07937501],"study_design_scores_gemma":[0.00012049397,0.00006631892,0.87191683,0.000012039518,0.000007530779,0.000033905613,0.0012935788,0.00001801358,0.0001330616,0.054947607,0.07140738,0.00004323317],"about_ca_topic_score_codex":0.009746926,"about_ca_topic_score_gemma":0.12452336,"teacher_disagreement_score":0.1679851,"about_ca_system_score_codex":0.00008069702,"about_ca_system_score_gemma":0.011798499,"threshold_uncertainty_score":0.9968473},"labels":[],"label_agreement":null},{"id":"W2769555506","doi":"10.7870/cjcmh-2017-015","title":"Les effets d’une formation dans le domaine de la violence sexuelle sur les connaissances, les attitudes, l’autoefficacité et le transfert des apprentissages","year":2017,"lang":"fr","type":"article","venue":"Canadian Journal of Community Mental Health","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Humanities; Political science; Art","score_opus":0.1856557777139592,"score_gpt":0.45510009266615525,"score_spread":0.26944431495219606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2769555506","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9335298,0.015696319,0.015416732,0.029854806,0.0005977993,0.0003388705,0.00026266175,0.000010812784,0.0042921887],"genre_scores_gemma":[0.9924502,0.0051982906,0.0011042207,0.00044990476,0.000055171142,0.000005758678,0.000048760816,0.000022278085,0.00066544546],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9924036,0.004909256,0.0011424485,0.0001432121,0.0007723116,0.00062914944],"domain_scores_gemma":[0.9959072,0.00093656057,0.0009598657,0.0006616768,0.0004856438,0.0010490703],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.014331515,0.0002818806,0.00056938507,0.00030985955,0.010681932,0.00082901097,0.0017989974,0.00018675502,0.00031931323],"category_scores_gemma":[0.0004682424,0.00026847192,0.00017257956,0.00021161498,0.0019313705,0.0019580263,0.00007797653,0.0013289782,0.000010998671],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009416159,0.00061429525,0.08040596,0.000521161,0.00007668285,0.000026595297,0.032353617,0.0011090888,0.00037374615,0.014126459,0.0035358649,0.86676234],"study_design_scores_gemma":[0.0041270135,0.0010573986,0.8464337,0.0040050107,0.000037046506,0.0007341526,0.047822576,0.0033409882,0.0011897241,0.0050342833,0.085786484,0.00043160122],"about_ca_topic_score_codex":0.3931635,"about_ca_topic_score_gemma":0.712024,"teacher_disagreement_score":0.86633074,"about_ca_system_score_codex":0.00087744836,"about_ca_system_score_gemma":0.006124645,"threshold_uncertainty_score":0.99997675},"labels":[],"label_agreement":null},{"id":"W2769686994","doi":"","title":"Analyse des outils d'accompagnement et d'évaluation : point de vue des formateurs de terrain","year":2016,"lang":"fr","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Commission Scolaire des Hautes Rivières; Université du Québec à Trois-Rivières","funders":"","keywords":"Confusion; Valuation (finance); Practicum; Computer science; Focus group; Psychology; Pedagogy; Sociology; Business","score_opus":0.2156167144206303,"score_gpt":0.4822309899115136,"score_spread":0.2666142754908833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2769686994","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.65776104,0.00050162047,0.28017208,0.020843744,0.00042302278,0.00033160206,0.000022029748,0.000058766298,0.039886124],"genre_scores_gemma":[0.9131804,0.0012770235,0.05010258,0.0029796527,0.00010541206,0.000060995433,0.0000074069544,0.00001858738,0.032267906],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9944044,0.0015259165,0.0011450456,0.00047921558,0.0015584155,0.00088701095],"domain_scores_gemma":[0.99702156,0.0010279878,0.00032111886,0.0005993512,0.0006344814,0.0003955228],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.021351652,0.0003047896,0.00035006387,0.00042515187,0.00044211972,0.00052208506,0.0005928891,0.00014849786,0.050197314],"category_scores_gemma":[0.0013647074,0.00018969498,0.00023297047,0.0006886572,0.00046352265,0.0022563084,0.00017925346,0.00013895438,0.001922242],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049449787,0.0002270517,0.108124204,0.000028982351,0.00005860912,0.000003804746,0.02754136,0.0011738301,0.0041378997,0.00472322,0.013504031,0.8404276],"study_design_scores_gemma":[0.0024846445,0.00060295395,0.59143233,0.0004954676,0.00017156012,0.00006610569,0.03834068,0.09569169,0.015929213,0.21952325,0.034618635,0.00064346945],"about_ca_topic_score_codex":0.0008038912,"about_ca_topic_score_gemma":0.0058369627,"teacher_disagreement_score":0.8397841,"about_ca_system_score_codex":0.001162848,"about_ca_system_score_gemma":0.0015306398,"threshold_uncertainty_score":0.9988549},"labels":[],"label_agreement":null},{"id":"W2771643987","doi":"10.3138/cjpe.31144","title":"Théories du changement : comment élaborer des modèles utiles","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Causality (physics); Epistemology; Intervention (counseling); Psychological intervention; Theory of change; Computer science; Sociology; Psychology; Philosophy; Physics","score_opus":0.5023497063004002,"score_gpt":0.5392922766264496,"score_spread":0.03694257032604942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2771643987","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9457531,0.0011182101,0.0018797952,0.031730004,0.00250622,0.001514196,0.000025180945,0.00001449938,0.015458795],"genre_scores_gemma":[0.9955312,0.00006271767,0.003418754,0.0003973605,0.0003222578,0.00007439488,0.0000069990247,0.000008398184,0.00017789114],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99635345,0.00033438954,0.000722031,0.00017839977,0.0021174382,0.00029430192],"domain_scores_gemma":[0.99418896,0.00012475636,0.0010554761,0.0005542157,0.003631063,0.0004455329],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.013941428,0.00013069781,0.00022805222,0.00038549403,0.001242567,0.0015686755,0.0009060487,0.000057363868,0.0027138742],"category_scores_gemma":[0.0034697014,0.0000941544,0.000116445015,0.00018176807,0.00030862156,0.001108568,0.000038445043,0.00013570733,0.000069006164],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012789222,0.0000434855,0.14187501,0.0000041700055,0.000033954122,0.0000054841335,0.0018314279,0.00045666896,0.000011004939,0.0015928565,0.013874839,0.8402583],"study_design_scores_gemma":[0.0009865595,0.00045517817,0.61870253,0.000074422984,0.00008793435,0.000019006102,0.0026416583,0.028825117,0.00017587084,0.028913075,0.31895617,0.00016248513],"about_ca_topic_score_codex":0.00089079636,"about_ca_topic_score_gemma":0.03625453,"teacher_disagreement_score":0.8400958,"about_ca_system_score_codex":0.0004118313,"about_ca_system_score_gemma":0.0025069483,"threshold_uncertainty_score":0.9994678},"labels":[],"label_agreement":null},{"id":"W2771770473","doi":"10.3138/cjpe.31128","title":"Using Rubrics for an Evaluation: A National Research Council Pilot","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Rubric; Excellence; Relevance (law); Context (archaeology); Psychology; Political science; Computer science; Medical education; Pedagogy; Medicine; Geography","score_opus":0.9730025773537614,"score_gpt":0.7170565067688764,"score_spread":0.25594607058488494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2771770473","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8876423,0.0012111469,0.010642959,0.00967995,0.0060327095,0.010795872,0.00010425991,0.000023342023,0.07386744],"genre_scores_gemma":[0.98470426,0.000004604855,0.013873204,0.00012343349,0.00088528066,0.00021522916,0.000012827835,0.000015305353,0.00016587308],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9746389,0.001330455,0.0010430451,0.00033734995,0.022208577,0.00044170397],"domain_scores_gemma":[0.8787238,0.0005346013,0.0010955519,0.0005820711,0.118514165,0.0005498141],"candidate_categories":["metaresearch","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.26418558,0.00013146864,0.00024189812,0.00078465923,0.0022827906,0.002524644,0.0012490937,0.00009464572,0.0013717236],"category_scores_gemma":[0.08519602,0.00011039406,0.00011926915,0.00047096855,0.00027900952,0.0022541007,0.000026344198,0.00029091508,0.000042766234],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00012303914,0.00018348102,0.009522122,0.000009612614,0.000055562068,0.0000022962213,0.0016183474,0.018156866,0.00024167066,0.0039800135,0.027361965,0.938745],"study_design_scores_gemma":[0.0020936097,0.0015512388,0.028511992,0.000046503636,0.00008726859,0.000036370737,0.0008288218,0.76247776,0.00004408643,0.09416685,0.110001944,0.00015357237],"about_ca_topic_score_codex":0.0013355825,"about_ca_topic_score_gemma":0.07478361,"teacher_disagreement_score":0.9385915,"about_ca_system_score_codex":0.006140058,"about_ca_system_score_gemma":0.09513073,"threshold_uncertainty_score":0.99954116},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":["metaresearch"],"domain":"evaluation","study_design":"not_applicable","genre":"commentary","about_ca_system":true,"about_ca_topic":true,"confidence":"low"}],"label_agreement":"split"},{"id":"W2771999481","doi":"10.1016/j.evalprogplan.2017.12.001","title":"Uncovering the mysteries of inclusion: Empirical and methodological possibilities in participatory evaluation in an international context","year":2017,"lang":"en","type":"review","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":45,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Inclusion (mineral); Citizen journalism; Privilege (computing); Context (archaeology); Participatory evaluation; Participatory action research; Empirical evidence; Public relations; Sociology; Empirical research; Power (physics); Engineering ethics; Political science; Psychology; Social science; Engineering; Epistemology; Geography","score_opus":0.8922807118038334,"score_gpt":0.7301766260124527,"score_spread":0.1621040857913807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2771999481","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2031894,0.79265434,0.00003871861,0.00027697752,0.0004607272,0.0023527513,0.000012334928,0.000015538446,0.0009992184],"genre_scores_gemma":[0.5856336,0.41132444,0.001079873,0.00013931388,0.00015685969,0.0014267305,0.00014788705,0.000018791783,0.00007252415],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9891104,0.006051161,0.0015544415,0.00052238326,0.0025545808,0.00020704896],"domain_scores_gemma":[0.9949964,0.0029425567,0.00096544815,0.00047851208,0.0005500864,0.00006696907],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.06150194,0.00023452792,0.00091579324,0.00044160653,0.0002964109,0.00045177454,0.00053534406,0.00021303787,0.0003130883],"category_scores_gemma":[0.008204847,0.00013848957,0.00009085654,0.00028445214,0.00027503807,0.00074658415,0.0005445777,0.00034132032,0.0000031839986],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030421768,0.00004753995,0.030068679,0.0001551073,0.000013882648,9.290169e-7,0.010932707,0.00021323265,1.7915974e-7,0.00006988383,0.000009524905,0.9584579],"study_design_scores_gemma":[0.0022500688,0.0007437077,0.19429666,0.008178119,0.00041707145,0.000033064687,0.014865057,0.17391302,0.0000018564864,0.02117863,0.583485,0.0006377682],"about_ca_topic_score_codex":0.000029339708,"about_ca_topic_score_gemma":0.00026579972,"teacher_disagreement_score":0.9578201,"about_ca_system_score_codex":0.0001533829,"about_ca_system_score_gemma":0.0007090001,"threshold_uncertainty_score":0.98225605},"labels":[],"label_agreement":null},{"id":"W2772792681","doi":"10.1177/1558689817743581","title":"Distinct Yet Synergetic Contributors to Mixed Methods Research: Intersections for MMIRA and <i>JMMR</i>","year":2017,"lang":"en","type":"article","venue":"Journal of Mixed Methods Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Multimethodology; Sociology; Management science; Computer science; Psychology; Social science; Engineering","score_opus":0.7320044775351187,"score_gpt":0.7489588481319771,"score_spread":0.016954370596858448,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2772792681","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22744957,0.0005739001,0.740204,0.021120898,0.0043804315,0.001149723,0.00004694772,0.000011953645,0.0050625782],"genre_scores_gemma":[0.41389817,0.00017958232,0.58013225,0.000088453795,0.0005161506,0.00010992205,0.0000015022629,0.000030611795,0.00504334],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9736955,0.018427629,0.0016513446,0.00061089726,0.0046184123,0.0009962197],"domain_scores_gemma":[0.94135976,0.045968376,0.00079569645,0.0013444179,0.009638664,0.00089307147],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.31856078,0.00020268094,0.0007839562,0.002093499,0.002525887,0.0017666738,0.0023551488,0.00017715723,0.00037493202],"category_scores_gemma":[0.22767426,0.00013826971,0.0003058504,0.0011799259,0.0007427539,0.0008057137,0.0009939679,0.0015022982,0.000056949462],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00070624676,0.00016293295,0.0024520622,0.000032982585,0.00011337034,0.00001435487,0.0012967649,0.000033331537,0.032893896,0.0027147473,0.11062738,0.84895194],"study_design_scores_gemma":[0.0026794623,0.003094089,0.0992916,0.00026396048,0.000059506594,0.000112986316,0.012069317,0.0051237848,0.041078433,0.14656925,0.6892934,0.00036423255],"about_ca_topic_score_codex":0.00007981876,"about_ca_topic_score_gemma":0.00022070673,"teacher_disagreement_score":0.8485877,"about_ca_system_score_codex":0.00031787084,"about_ca_system_score_gemma":0.0009457547,"threshold_uncertainty_score":0.9992696},"labels":[],"label_agreement":null},{"id":"W2773019329","doi":"10.4000/ethiquepublique.3061","title":"Intégrer la culture au jugement sur la performance : l’impossible position de l’évaluateur sensible","year":2017,"lang":"fr","type":"article","venue":"Éthique Publique","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.06233124697919556,"score_gpt":0.4121215141281255,"score_spread":0.3497902671489299,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2773019329","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5988805,0.00088999566,0.0022877925,0.084976986,0.0027040087,0.0008003936,0.00005433079,0.000117566735,0.30928838],"genre_scores_gemma":[0.8757436,0.0036308346,0.002855904,0.007085259,0.0007290064,0.00013336858,0.000042370044,0.00004759462,0.10973203],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99358857,0.0016497581,0.0009988255,0.00087199925,0.0018796992,0.0010111665],"domain_scores_gemma":[0.9946548,0.00059059844,0.0009179221,0.0016085159,0.0017446073,0.00048360776],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.019389598,0.00045888821,0.0005333844,0.00030039417,0.0016969342,0.0050786613,0.0015377179,0.00089763815,0.002393977],"category_scores_gemma":[0.0023274703,0.00042247956,0.00026159326,0.0004180082,0.000564507,0.0050722174,0.0005806096,0.0012894556,0.00091811747],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032546703,0.0011913782,0.21258523,0.0005144064,0.00026131832,0.00023266004,0.009807142,0.0043611936,0.0019470837,0.21960817,0.20580333,0.34336263],"study_design_scores_gemma":[0.0012486312,0.00032227245,0.2071525,0.0005809365,0.00007668699,0.00043013858,0.00042705418,0.053946834,0.003618789,0.014001387,0.7175805,0.00061427476],"about_ca_topic_score_codex":0.0024277056,"about_ca_topic_score_gemma":0.0023111328,"teacher_disagreement_score":0.51177716,"about_ca_system_score_codex":0.0008424935,"about_ca_system_score_gemma":0.006045349,"threshold_uncertainty_score":0.9998598},"labels":[],"label_agreement":null},{"id":"W2773387923","doi":"10.4000/sdt.1353","title":"La nouvelle gestion publique de l’école au Québec : vers une gestion de la pédagogie","year":2017,"lang":"fr","type":"article","venue":"Sociologie du Travail","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Cégep Marie-Victorin","funders":"","keywords":"Political science; Humanities; Philosophy","score_opus":0.155042220096391,"score_gpt":0.4494768585674255,"score_spread":0.29443463847103446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2773387923","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8311882,0.0013816942,0.0046603265,0.12943538,0.0015261378,0.00029042325,0.000034121364,0.00011689422,0.031366844],"genre_scores_gemma":[0.9533541,0.0037950478,0.0013557118,0.0011382262,0.0004347281,0.00006921717,0.000014100504,0.000023008117,0.039815824],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99432343,0.0030153997,0.00058536546,0.00058409985,0.0007440543,0.00074765994],"domain_scores_gemma":[0.9923237,0.0056128837,0.0005445459,0.00088564726,0.00036103226,0.00027216834],"candidate_categories":["metaresearch","metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.01760703,0.00030280443,0.00037126458,0.00013192224,0.0016888754,0.0007839028,0.0012514441,0.0012336124,0.0013151141],"category_scores_gemma":[0.0150669515,0.00026834954,0.00022929371,0.00017983648,0.0023260152,0.0009648411,0.0002011096,0.0010930302,0.0008579202],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008812485,0.00026238186,0.4341728,0.00003416867,0.000056882753,0.000034775912,0.014255606,0.0031346995,0.00053162617,0.0049238103,0.033443592,0.5090615],"study_design_scores_gemma":[0.0009557045,0.00021797432,0.8336003,0.00008086278,0.000056650068,0.000028631552,0.00881207,0.011988758,0.00017563169,0.0065561975,0.1372341,0.00029310214],"about_ca_topic_score_codex":0.085087255,"about_ca_topic_score_gemma":0.033540033,"teacher_disagreement_score":0.50876844,"about_ca_system_score_codex":0.0026305153,"about_ca_system_score_gemma":0.012408871,"threshold_uncertainty_score":0.9999769},"labels":[],"label_agreement":null},{"id":"W2773692454","doi":"10.3138/cjpe.31130","title":"The Impact of Practice on Pedagogy: Reflections of Novice Evaluation Teachers","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Practicum; Syllabus; Pedagogy; Psychology; Mathematics education; Medical education; Sociology; Medicine","score_opus":0.5343895073017358,"score_gpt":0.6801314847072718,"score_spread":0.14574197740553596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2773692454","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9520902,0.00050610554,0.00034177385,0.007993322,0.0011751173,0.0017852497,0.000014226627,0.000004700592,0.036089294],"genre_scores_gemma":[0.99853766,0.000029121014,0.0010566171,0.000037779984,0.00014995027,0.0000442757,0.0000046324053,0.000008634332,0.00013134872],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.993353,0.0014508878,0.001183095,0.00017816042,0.0035984744,0.00023640052],"domain_scores_gemma":[0.9832164,0.0011141977,0.0037852006,0.00082920224,0.010785506,0.00026946442],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.048882425,0.00012394822,0.00025198382,0.00050618075,0.0008988548,0.0004976697,0.0008841729,0.00008739465,0.00074493675],"category_scores_gemma":[0.041408867,0.00007575478,0.0002563493,0.00041935293,0.000260255,0.0011610065,0.000016102898,0.00029124675,0.000025880512],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000088944216,0.00009633283,0.014360751,0.0000017555718,0.00011505143,7.512901e-7,0.0031738717,0.013428288,0.00019867564,0.00043828067,0.0023242123,0.9657731],"study_design_scores_gemma":[0.002477278,0.0037999447,0.8471397,0.00012497339,0.00055330724,0.000056686997,0.008631938,0.09125762,0.000488908,0.011792368,0.033472527,0.00020475779],"about_ca_topic_score_codex":0.004715839,"about_ca_topic_score_gemma":0.03071858,"teacher_disagreement_score":0.9655683,"about_ca_system_score_codex":0.0007365628,"about_ca_system_score_gemma":0.01378103,"threshold_uncertainty_score":0.9918099},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"qualitative","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W2773791117","doi":"10.3138/cjpe.0020.006","title":"Randomized and Quasi-Experimental Evaluations of Program Impact in Child Welfare in Canada: A Review","year":2006,"lang":"en","type":"review","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Psychological intervention; Welfare; Randomized controlled trial; Context (archaeology); Psychology; Impact evaluation; Applied psychology; Medicine; Political science; Psychiatry; Geography","score_opus":0.3183477250621403,"score_gpt":0.5792820356604422,"score_spread":0.2609343105983019,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2773791117","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010244915,0.9863102,0.0000060486623,0.00067585707,0.00032633988,0.010644915,0.00005538783,0.0000037053046,0.0009530772],"genre_scores_gemma":[0.052458085,0.94479847,0.0006321942,0.0000510965,0.00008916393,0.0017140523,0.00020267206,0.00003407319,0.000020188507],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9863227,0.004552088,0.004797248,0.00043314043,0.0034166765,0.0004781319],"domain_scores_gemma":[0.9931383,0.0007085223,0.0034762903,0.0004475085,0.0017615785,0.0004677819],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03402999,0.00043484275,0.0034271735,0.0019991822,0.00013691971,0.00018506889,0.00063421496,0.00018279263,0.0013417087],"category_scores_gemma":[0.0047979313,0.00029883784,0.00067226175,0.0020192987,0.00016837062,0.0004341735,0.00002698498,0.0006299109,0.000004894221],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000090292844,0.00018202502,0.00051224494,0.0010629671,0.00006535382,0.00001277916,0.00012317984,0.0001623635,9.909797e-9,0.00004412255,0.00050575484,0.99723893],"study_design_scores_gemma":[0.051870394,0.0014901083,0.0054449043,0.062169127,0.0023714018,0.00046218483,0.0007283357,0.0142270485,7.1604904e-7,0.0004482992,0.85985214,0.00093536224],"about_ca_topic_score_codex":0.5622053,"about_ca_topic_score_gemma":0.97487724,"teacher_disagreement_score":0.99630356,"about_ca_system_score_codex":0.00415267,"about_ca_system_score_gemma":0.043822292,"threshold_uncertainty_score":0.99994636},"labels":[],"label_agreement":null},{"id":"W2774864855","doi":"10.3138/10.3138/cjpe.31132","title":"Moving Beyond the Buzzword: A Framework for Teaching Culturally Responsive Approaches to Evaluation","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Valuation (finance); Sociology; Competence (human resources); Conceptual framework; Epistemology; Humanities; Psychology; Social science; Philosophy; Social psychology; Business","score_opus":0.6407724104552023,"score_gpt":0.5597165071488638,"score_spread":0.0810559033063385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2774864855","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7964171,0.0006996965,0.06172205,0.11679335,0.0039230823,0.010497101,0.000029389254,0.00001937502,0.009898834],"genre_scores_gemma":[0.9442305,0.0000020867046,0.053669736,0.0006807805,0.00062992965,0.0005111801,0.000010829728,0.000014514366,0.00025042123],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99375,0.0012998708,0.0009640276,0.00032071312,0.0032831854,0.00038220125],"domain_scores_gemma":[0.9916731,0.001200062,0.0015481611,0.00085052446,0.0042589023,0.0004692256],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06413532,0.00017211442,0.00027153068,0.00047589108,0.0025056505,0.002436947,0.0014618158,0.000120825745,0.00044665832],"category_scores_gemma":[0.05975384,0.00010669613,0.00021011101,0.00027187346,0.00015377066,0.0012010831,0.000033656175,0.00042033644,0.000043056185],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000063470805,0.000021310096,0.0030200302,0.0000031741024,0.00004120647,8.601991e-7,0.0076990915,0.0064308494,0.000034300905,0.012181978,0.0043913624,0.9661124],"study_design_scores_gemma":[0.0017336969,0.001117979,0.1500711,0.0002102308,0.0004454044,0.000045278404,0.01645248,0.3153688,0.00016640026,0.42197177,0.092011586,0.00040529348],"about_ca_topic_score_codex":0.00029378763,"about_ca_topic_score_gemma":0.012848757,"teacher_disagreement_score":0.96570706,"about_ca_system_score_codex":0.00061139866,"about_ca_system_score_gemma":0.005132222,"threshold_uncertainty_score":0.99879295},"labels":[],"label_agreement":null},{"id":"W2775174218","doi":"10.3138/cjpe.31122","title":"Theory of Change Analysis: Building Robust Theories of Change","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":145,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Theory of change; Computer science; Management science; Risk analysis (engineering); Positive economics; Econometrics; Economics; Business; Management","score_opus":0.7318312016170765,"score_gpt":0.5642255157815168,"score_spread":0.16760568583555968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2775174218","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9858212,0.001821543,0.004568031,0.002264469,0.0010388135,0.0012550073,0.000034085555,0.000005312036,0.0031915265],"genre_scores_gemma":[0.9968542,0.000026881331,0.0026687658,0.00006407727,0.00024572315,0.000061056875,0.000005214231,0.0000067769884,0.000067304754],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9960204,0.00062979443,0.0010030975,0.0001674196,0.001959151,0.00022013996],"domain_scores_gemma":[0.9925872,0.00026836395,0.0026439263,0.00062085094,0.0036190725,0.00026060364],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.026955493,0.00011363576,0.0004325363,0.0012458136,0.00031206998,0.0002771632,0.0009126268,0.0000778667,0.0020791108],"category_scores_gemma":[0.0041024433,0.000083899016,0.00027305138,0.00072359474,0.00028276595,0.0012250163,0.000028463764,0.0001323784,0.000008144712],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030530093,0.000036060126,0.17731944,0.0000094595325,0.00021964867,0.0000020951818,0.004115089,0.0006708325,0.000042895455,0.010831987,0.00009081062,0.80663115],"study_design_scores_gemma":[0.0008044912,0.0005412624,0.9022572,0.00013624241,0.0010517199,0.0000071640447,0.003570409,0.03193347,0.00056329387,0.05624328,0.0027309563,0.00016050326],"about_ca_topic_score_codex":0.0013118197,"about_ca_topic_score_gemma":0.019375427,"teacher_disagreement_score":0.80647063,"about_ca_system_score_codex":0.00013321328,"about_ca_system_score_gemma":0.0014140626,"threshold_uncertainty_score":0.9988331},"labels":[],"label_agreement":null},{"id":"W2775558257","doi":"10.36510/learnland.v8i2.693","title":"Commentary: The Importance of Generating Middle Leading Through Action Research for Collaborative Learning","year":2015,"lang":"en","type":"article","venue":"LEARNing Landscapes","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Action research; Action (physics); Key (lock); Action learning; Collaborative learning; Pedagogy; Sociology; Psychology; Cooperative learning; Computer science; Teaching method","score_opus":0.5094442936318268,"score_gpt":0.5428956122052506,"score_spread":0.03345131857342387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2775558257","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97453994,0.0005055731,0.0060070227,0.010378232,0.000318133,0.00046483558,0.0000042760366,0.000041872132,0.007740114],"genre_scores_gemma":[0.9927563,0.00004059108,0.0035473127,0.0004100036,0.00029326775,0.00007314484,0.000026236345,0.000013846199,0.002839285],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9959828,0.0013337531,0.00051687204,0.00030522209,0.0015678416,0.00029348792],"domain_scores_gemma":[0.99461955,0.0031753057,0.00042972947,0.00023823703,0.0014786449,0.00005853335],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015105474,0.00010854832,0.00023861739,0.00012824264,0.0008913986,0.00025309017,0.00037010325,0.00005887667,0.0001640495],"category_scores_gemma":[0.0052177,0.00006726959,0.00006123359,0.0009897971,0.00008832772,0.0004960746,0.000101416124,0.0004811468,0.00005005173],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022830488,0.00006363702,0.6168822,0.00002667714,0.000060639217,0.0000010339868,0.049620993,0.23531838,0.0025729188,0.002922046,0.07423304,0.01807015],"study_design_scores_gemma":[0.001190807,0.0007730935,0.0025434368,0.00006178263,0.000017167748,0.000003149173,0.15623885,0.23695703,0.0034062057,0.0035797546,0.5950434,0.00018528652],"about_ca_topic_score_codex":0.00003944459,"about_ca_topic_score_gemma":0.0003676805,"teacher_disagreement_score":0.61433876,"about_ca_system_score_codex":0.000077508084,"about_ca_system_score_gemma":0.00021299312,"threshold_uncertainty_score":0.68560076},"labels":[],"label_agreement":null},{"id":"W2775784773","doi":"10.3138/cjpe.31119","title":"Making Evaluation More Responsive to Policy Needs: The Case of the Labour Market Development Agreements","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Statistics Canada; Employment and Social Development Canada","funders":"","keywords":"Process (computing); Business; Key (lock); Market development; Policy development; Process management; Public economics; Economics; Computer science; Economic policy","score_opus":0.4694491553349992,"score_gpt":0.586143825088606,"score_spread":0.11669466975360676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2775784773","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96954966,0.00012834888,0.00019388364,0.023378411,0.0009323553,0.0022909506,0.000012613222,0.0000025735808,0.0035111967],"genre_scores_gemma":[0.9963447,0.0000021674725,0.0017408866,0.00072858913,0.00020429313,0.0001185566,0.000001620592,0.000009228237,0.0008499662],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.993852,0.0013944159,0.0010876873,0.00018301174,0.0031801278,0.000302742],"domain_scores_gemma":[0.9900824,0.00029165242,0.0019094081,0.00093838596,0.0064996555,0.0002785183],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.038803276,0.00014301541,0.00021354477,0.0012935508,0.0014616142,0.0007565008,0.0013913765,0.0000661596,0.0012851319],"category_scores_gemma":[0.020733798,0.000080100035,0.00012775812,0.0013392285,0.00016800381,0.00055311027,0.000091567745,0.00020208489,0.000027734412],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043336182,0.000022632594,0.02187172,0.000004446487,0.000049331422,0.000012434197,0.009437569,0.00201106,0.000025168205,0.0006912184,0.003750853,0.96208024],"study_design_scores_gemma":[0.001236979,0.00022518623,0.8503207,0.00020340901,0.00015637348,0.00030119502,0.01356567,0.04068647,0.00022086466,0.0054435194,0.08745911,0.00018050328],"about_ca_topic_score_codex":0.0011872062,"about_ca_topic_score_gemma":0.03437901,"teacher_disagreement_score":0.9618997,"about_ca_system_score_codex":0.0008860046,"about_ca_system_score_gemma":0.01505088,"threshold_uncertainty_score":0.99983835},"labels":[],"label_agreement":null},{"id":"W2776186257","doi":"10.3917/nras.073.0125","title":"Les composantes d’une intégration de qualité en services de garde éducatifs","year":2016,"lang":"fr","type":"article","venue":"La nouvelle revue - Éducation et société inclusives","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.10005523826412317,"score_gpt":0.4831452912523388,"score_spread":0.38309005298821563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2776186257","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68993485,0.0023409913,0.013752804,0.23768358,0.0027312487,0.0006442355,0.0001249683,0.00012053404,0.052666765],"genre_scores_gemma":[0.9301295,0.0051984373,0.006143937,0.0026044813,0.00091774313,0.00014393055,0.00007608273,0.000050728224,0.05473515],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.99238986,0.00389453,0.0012735956,0.00077013037,0.0010268973,0.0006450068],"domain_scores_gemma":[0.9897338,0.0073706787,0.00096301537,0.0007944384,0.00083177513,0.00030625946],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008812237,0.00043359364,0.00054590777,0.0003225085,0.000865081,0.00043877587,0.0010326372,0.00047198773,0.007886791],"category_scores_gemma":[0.0016420381,0.0003461289,0.0002764688,0.00060145336,0.00037980868,0.001358367,0.00039050775,0.00037446248,0.0008378079],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054282005,0.0007142503,0.011670812,0.00034881983,0.000109091474,0.000003033338,0.48664662,0.00029309574,0.008402773,0.043976787,0.005157104,0.44262332],"study_design_scores_gemma":[0.0016810219,0.00023070094,0.16985874,0.001704067,0.00017608731,0.00009877257,0.2567312,0.007345916,0.004165897,0.052954588,0.5040642,0.0009887813],"about_ca_topic_score_codex":0.0024171283,"about_ca_topic_score_gemma":0.004141566,"teacher_disagreement_score":0.49890712,"about_ca_system_score_codex":0.001663149,"about_ca_system_score_gemma":0.0034176207,"threshold_uncertainty_score":0.99994016},"labels":[],"label_agreement":null},{"id":"W2778556126","doi":"10.15171/ijhpm.2017.142","title":"The Qualitative Descriptive Approach in International Comparative Studies: Using Online Qualitative Surveys","year":2017,"lang":"en","type":"article","venue":"International Journal of Health Policy and Management","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":136,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vancouver Coastal Health; Vancouver Coastal Health Research Institute; University of British Columbia","funders":"","keywords":"Depiction; Context (archaeology); Realm; Data science; Qualitative research; Data collection; Computer science; Proposition; Qualitative property; Descriptive statistics; Sociology; Management science; Political science; Epistemology; Social science","score_opus":0.8202046577575901,"score_gpt":0.737857736916085,"score_spread":0.08234692084150508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2778556126","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6359779,0.0034006685,0.07016329,0.26407084,0.0071679535,0.0013439612,0.00019943996,0.000013569226,0.017662348],"genre_scores_gemma":[0.9879096,0.0031350167,0.0067419573,0.0011509361,0.00031748723,0.000010046856,0.000005334474,0.000005189926,0.00072442193],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99317384,0.0028122365,0.0015594031,0.00023005294,0.001997855,0.00022661853],"domain_scores_gemma":[0.9938699,0.0016950082,0.0024131513,0.00023800935,0.0016988835,0.00008503793],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03256046,0.00013883405,0.00038692117,0.00060813315,0.00057261885,0.00048230175,0.0013144328,0.000025493602,0.000013625693],"category_scores_gemma":[0.0022573937,0.00008523451,0.000084201565,0.00015765395,0.00034094407,0.00084890286,0.00038398523,0.00021667931,0.000004892475],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043331087,0.00049971073,0.0014300528,0.000030551517,0.0014318593,0.000024586005,0.65378225,0.0024463814,0.0000042574793,0.20197234,0.0039115404,0.13403319],"study_design_scores_gemma":[0.0021668745,0.00023222694,0.046592187,0.00021511823,0.000011759444,0.000026343154,0.84269065,0.010069991,0.000003963226,0.071747154,0.026096674,0.0001470634],"about_ca_topic_score_codex":0.0007375666,"about_ca_topic_score_gemma":0.000686954,"teacher_disagreement_score":0.3519317,"about_ca_system_score_codex":0.00067405106,"about_ca_system_score_gemma":0.00036162286,"threshold_uncertainty_score":0.9961826},"labels":[],"label_agreement":null},{"id":"W2778673878","doi":"","title":"The OECD and Educational Policy Reform: International Surveys, Governance, and Policy Evidence.","year":2017,"lang":"en","type":"article","venue":"Research Publications (Maastricht University)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Scope (computer science); Corporate governance; Normative; Political science; International education; Education policy; Economic growth; Higher education; Public administration; Economics","score_opus":0.39928669892739754,"score_gpt":0.566551750219364,"score_spread":0.16726505129196645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2778673878","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04303945,0.0003008646,0.00040975225,0.59192735,0.0001928512,0.00039899434,0.00007883312,0.000027372858,0.36362454],"genre_scores_gemma":[0.81504315,0.004988385,0.00022650458,0.0000696395,0.00037655229,0.000009413062,0.000010998882,0.000005668291,0.17926967],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99613523,0.0007092156,0.00027308727,0.000435322,0.0020783122,0.00036882758],"domain_scores_gemma":[0.99328655,0.0027706411,0.0003161837,0.0011420253,0.002200662,0.00028396622],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.010809006,0.00009972998,0.00011045799,0.0013768985,0.004048372,0.002644738,0.0023733142,0.00006384016,0.00030860727],"category_scores_gemma":[0.01700574,0.00007253381,0.000040910985,0.0015167579,0.00092545204,0.0023967323,0.0011285918,0.0003075017,0.00017217555],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000137008265,0.000037348123,0.0873064,0.0000017914634,0.000021450425,4.4700016e-7,0.00009519473,0.0000027538506,0.000019369541,0.7275295,0.012349753,0.17262226],"study_design_scores_gemma":[0.00017547478,0.000021406022,0.59552777,0.000007700808,0.0000019423476,0.0000039963784,0.0004025268,0.0005846391,0.00000477152,0.007382879,0.39583534,0.00005153627],"about_ca_topic_score_codex":0.0020560995,"about_ca_topic_score_gemma":0.0011391207,"teacher_disagreement_score":0.7720037,"about_ca_system_score_codex":0.0007294235,"about_ca_system_score_gemma":0.0033119458,"threshold_uncertainty_score":0.9983906},"labels":[],"label_agreement":null},{"id":"W2779494915","doi":"10.3138/cjpe.19.002","title":"Using Multi-Site Core Evaluation to Provide “Scientific” Evidence","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Fidelity; Excellence; Core (optical fiber); Computer science; Program evaluation; Order (exchange); Management science; Service (business); Knowledge management; Process management; Engineering ethics; Engineering management; Business; Engineering; Political science","score_opus":0.8288838258260318,"score_gpt":0.6324526320169,"score_spread":0.19643119380913177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2779494915","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9627763,0.0006880113,0.028316455,0.002516814,0.0023098576,0.0031719252,0.000008975952,0.000013137646,0.00019852127],"genre_scores_gemma":[0.946097,0.0000025031554,0.053163752,0.00029203363,0.0002055688,0.00009692521,0.000011515213,0.000014121919,0.00011657657],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9912465,0.00063695485,0.0013656901,0.00045379452,0.0058032055,0.00049382343],"domain_scores_gemma":[0.9861012,0.0002062887,0.0009676562,0.00054829364,0.011265336,0.00091120123],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.049381033,0.00018357889,0.0002823768,0.0014633965,0.00063336827,0.0013689016,0.0006930419,0.00009786842,0.0014065749],"category_scores_gemma":[0.01606486,0.00014968491,0.00016263843,0.0021513659,0.00013657988,0.002308617,0.000031370582,0.00023525872,0.00032449877],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029950843,0.000074271156,0.024392884,0.000006682376,0.000020262569,0.000007240859,0.004559657,0.20429613,0.0027180852,0.00019297081,0.00062220986,0.76307964],"study_design_scores_gemma":[0.0036402987,0.0011653336,0.17266774,0.00076240837,0.00043241284,0.00015432021,0.0025512222,0.7761448,0.0013505644,0.014276601,0.026309935,0.0005443512],"about_ca_topic_score_codex":0.001478979,"about_ca_topic_score_gemma":0.06279187,"teacher_disagreement_score":0.7625353,"about_ca_system_score_codex":0.0022106834,"about_ca_system_score_gemma":0.020473465,"threshold_uncertainty_score":0.99966776},"labels":[],"label_agreement":null},{"id":"W2779787372","doi":"","title":"Canadian Corporate Social Responsibility Reports: Practitioner Responses to (Selected) Academic Ideas","year":2007,"lang":"en","type":"article","venue":"Proceedings of the International Association for Business and Society","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Social responsibility; Public relations; Corporate social responsibility; Political science; Sociology","score_opus":0.09069500983009288,"score_gpt":0.41375905054213663,"score_spread":0.32306404071204375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2779787372","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94846356,0.000009994751,0.00026005149,0.04729057,0.0006884285,0.00039821983,0.000078027915,0.000016697895,0.0027944609],"genre_scores_gemma":[0.986217,0.000010655246,0.0008705509,0.00161402,0.00024734947,0.000023377428,0.0000107791475,0.000008348303,0.010997885],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99709857,0.00001916792,0.0007604235,0.00031268856,0.0015832968,0.00022587233],"domain_scores_gemma":[0.98900235,0.0007257832,0.0015211137,0.00007468291,0.008579479,0.0000965775],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013866848,0.00010513049,0.00017778795,0.00016470956,0.00045972734,0.0002091385,0.00037268363,0.00016305342,0.00006139769],"category_scores_gemma":[0.015793437,0.00007768081,0.00012775887,0.0011636727,0.000041996755,0.00058347237,0.00009993343,0.00017356638,0.000005079246],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023406696,0.000035833084,0.86087155,0.000012285345,0.00007813869,1.4007217e-7,0.0022599162,0.000016575648,0.007196106,0.011914671,0.11625501,0.0011257195],"study_design_scores_gemma":[0.00023669802,0.000014850799,0.9182992,0.000016260865,0.00001796889,0.000003977691,0.0012860843,0.00028390766,0.0013196201,0.028890578,0.04952789,0.000102977945],"about_ca_topic_score_codex":0.0015015115,"about_ca_topic_score_gemma":0.003056219,"teacher_disagreement_score":0.06672712,"about_ca_system_score_codex":0.0009785716,"about_ca_system_score_gemma":0.0006679078,"threshold_uncertainty_score":0.99249697},"labels":[],"label_agreement":null},{"id":"W2781564089","doi":"10.18438/b85q29","title":"Gathering Evidence for Routine Decision-making","year":2017,"lang":"en","type":"article","venue":"Evidence Based Library and Information Practice","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Data science; Information retrieval","score_opus":0.194519781953016,"score_gpt":0.5002989919418588,"score_spread":0.3057792099888428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2781564089","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05538854,0.0016507949,0.6235514,0.293574,0.0018107622,0.0017862564,0.000033987082,0.00022696759,0.021977238],"genre_scores_gemma":[0.90540975,0.0008136522,0.061042164,0.032165647,0.00015887647,0.000070292335,0.00000460779,0.000008434117,0.0003265535],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.997173,0.00020632375,0.0009039611,0.00028703889,0.0012053391,0.00022432323],"domain_scores_gemma":[0.9722771,0.024756238,0.0014474046,0.0010229492,0.00037223328,0.00012405828],"candidate_categories":["metaresearch","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.007361177,0.00015658513,0.00020048492,0.0002428845,0.0013063696,0.004846107,0.0010351324,0.00007784263,0.0012040889],"category_scores_gemma":[0.089512564,0.00011969697,0.00008179659,0.00024925792,0.00009485959,0.42635536,0.0002913844,0.00016800602,0.0002539072],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019472262,0.000036154936,0.018186133,0.00007749928,0.000016241354,0.0000022283862,0.000545078,0.0022376925,0.000046026405,0.11030349,0.0073550483,0.8592472],"study_design_scores_gemma":[0.0007042743,0.00025476786,0.116484486,0.0016915846,0.000035374083,0.000016497923,0.001041146,0.20124565,0.00053347676,0.0051867976,0.67250943,0.00029649693],"about_ca_topic_score_codex":0.000002735631,"about_ca_topic_score_gemma":1.7627816e-7,"teacher_disagreement_score":0.8589507,"about_ca_system_score_codex":0.000017108334,"about_ca_system_score_gemma":0.0004101672,"threshold_uncertainty_score":0.9999938},"labels":[],"label_agreement":null},{"id":"W2782394023","doi":"10.1016/j.evalprogplan.2018.01.002","title":"Validation of the evaluation capacity in organizations questionnaire","year":2018,"lang":"en","type":"article","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University; University of Ottawa","funders":"Social Sciences and Humanities Research Council of Canada; University of Ottawa","keywords":"Construct (python library); Exploratory factor analysis; Confirmatory factor analysis; Organizational learning; Organization development; Construct validity; Organizational effectiveness; Organizational commitment; Psychology; Business; Knowledge management; Sample (material); Government (linguistics); Public relations; Political science; Social psychology; Marketing; Computer science","score_opus":0.3933076051605602,"score_gpt":0.5428849468054116,"score_spread":0.14957734164485137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2782394023","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99204326,0.00012523583,0.0010452685,0.0011866608,0.00042211436,0.0011663759,0.0000026184077,0.000026410764,0.0039820615],"genre_scores_gemma":[0.9986806,0.0000035084452,0.0009267935,0.00010867109,0.00008426972,0.00010833846,0.000019884084,0.0000057560846,0.00006221129],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9953531,0.0011593685,0.00061515754,0.00027771387,0.0024622465,0.00013240371],"domain_scores_gemma":[0.9959444,0.00020155076,0.00037618735,0.00032685275,0.0031103007,0.00004072914],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016030077,0.00009546114,0.00013398795,0.00024097269,0.00028085837,0.00012974736,0.00021550138,0.00007075038,0.00093862816],"category_scores_gemma":[0.006462545,0.00006509756,0.000028436833,0.0018570909,0.00016107567,0.00043930294,0.00005392494,0.00010663563,0.000031979092],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013675388,0.00008696563,0.6290045,0.0000059922527,0.000007703827,3.6587643e-8,0.0066686813,0.005988754,0.0005941769,0.001109526,0.0003568732,0.35616314],"study_design_scores_gemma":[0.00053407287,0.00008259195,0.67192674,0.00008353089,0.000029367746,0.0000020522505,0.00058516493,0.31442413,0.0024768978,0.009157857,0.0006249509,0.0000726807],"about_ca_topic_score_codex":0.000035142515,"about_ca_topic_score_gemma":0.00010878291,"teacher_disagreement_score":0.3560905,"about_ca_system_score_codex":0.00009337147,"about_ca_system_score_gemma":0.00042810838,"threshold_uncertainty_score":0.99997467},"labels":[],"label_agreement":null},{"id":"W2784550741","doi":"10.17269/cjph.108.5813","title":"Soutenir le changement de pratiques d’enseignement chez les professionnels de la santé: le cas des rencontres prénatales dans un CSSS de Montréal","year":2017,"lang":"fr","type":"article","venue":"Canadian Journal of Public Health","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Francophone University Association; Université de Montréal; Sante Montreal","funders":"","keywords":"Political science; Humanities; Art","score_opus":0.1657397965872037,"score_gpt":0.4643965058273592,"score_spread":0.2986567092401555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2784550741","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7818897,0.016609188,0.021548118,0.17405508,0.0008102059,0.0004499006,0.00010315513,0.000010774171,0.0045239176],"genre_scores_gemma":[0.97979534,0.0030397591,0.011466293,0.0016807745,0.0005607295,0.000029201945,0.00000538024,0.00002574085,0.003396787],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9925114,0.0035359883,0.0012577834,0.0003066236,0.0009309095,0.0014573281],"domain_scores_gemma":[0.9931467,0.0005949043,0.0016537746,0.0005782272,0.00088050356,0.0031458973],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.031718407,0.0002715872,0.00051747076,0.0006510543,0.0042501055,0.001610653,0.001291806,0.00024063024,0.00083068653],"category_scores_gemma":[0.0048249005,0.0002303091,0.00017572084,0.00026177804,0.00097311655,0.0013888505,0.00008898469,0.000627446,0.000014369149],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000017692064,0.00024143235,0.21761255,0.00015239656,0.00013411898,0.00032002898,0.2663182,0.0001740926,0.000100849174,0.012209165,0.039825924,0.46289355],"study_design_scores_gemma":[0.0017064562,0.0006320306,0.5852349,0.0008202912,0.000032281052,0.00064589974,0.25469542,0.0031268918,0.00046580978,0.011620381,0.14068364,0.00033604898],"about_ca_topic_score_codex":0.31336644,"about_ca_topic_score_gemma":0.8996478,"teacher_disagreement_score":0.58628136,"about_ca_system_score_codex":0.0039727804,"about_ca_system_score_gemma":0.08803939,"threshold_uncertainty_score":0.9998508},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W2784838195","doi":"10.1037/xge0000414","title":"Living near the edge: How extreme outcomes and their neighbors drive risky choice.","year":2018,"lang":"en","type":"article","venue":"Journal of Experimental Psychology General","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Alberta Gambling Research Institute, University of Calgary; Natural Sciences and Engineering Research Council of Canada","keywords":"Psychology; Social psychology; Cognitive psychology; Developmental psychology","score_opus":0.20156180933121742,"score_gpt":0.4984954185257945,"score_spread":0.29693360919457706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2784838195","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98428524,0.0010688897,0.00073240616,0.008184621,0.0025497864,0.000105205596,0.0000023433684,0.0000069369694,0.0030645793],"genre_scores_gemma":[0.99148065,0.0000444806,0.001522742,0.0047319587,0.0009855932,0.0000043721343,3.341036e-7,0.0000111343925,0.0012187243],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9975873,0.0005316979,0.00066711305,0.0002686939,0.0006928961,0.00025226048],"domain_scores_gemma":[0.99777526,0.0006696257,0.0006954873,0.00040277568,0.00031808802,0.00013877476],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003361482,0.00018330268,0.00033090793,0.00015526607,0.00058002904,0.00043428811,0.00067933905,0.000086406515,0.0016177265],"category_scores_gemma":[0.000388889,0.0000888286,0.00017089302,0.00023638352,0.0007016235,0.00050709,0.00013897484,0.0003107489,0.000063974905],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017317875,0.00047553336,0.7343921,0.0000011296302,0.00024053693,0.000009648337,0.026648859,0.000028228298,0.10477726,0.00066799804,0.09245074,0.04013481],"study_design_scores_gemma":[0.0015800351,0.001381481,0.8926474,0.000017902894,0.000018132721,0.0002559463,0.008894842,0.0028459786,0.0067159454,0.0013147277,0.084093936,0.00023368975],"about_ca_topic_score_codex":0.0000073573415,"about_ca_topic_score_gemma":0.000028900628,"teacher_disagreement_score":0.15825531,"about_ca_system_score_codex":0.00004056444,"about_ca_system_score_gemma":0.00009787941,"threshold_uncertainty_score":0.99929494},"labels":[],"label_agreement":null},{"id":"W2785353273","doi":"10.21810/sfuer.v10i2.317","title":"Is This Business or Education? When Education Becomes a Commodity","year":2018,"lang":"en","type":"article","venue":"SFU Educational Review","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Christian ministry; Business ethics; Convergence (economics); Commodity; Process (computing); Business education; Political science; Engineering ethics; Point (geometry); Philosophy of business; Public relations; Business; Sociology; Knowledge management; Higher education; Computer science; Engineering; Marketing; Economics; Business model; Law; Economic growth; Mathematics; Finance","score_opus":0.3228753251928207,"score_gpt":0.5858153835932299,"score_spread":0.26294005840040924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2785353273","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013494572,0.054873567,0.00047717604,0.67491114,0.0116829425,0.0023255341,0.00008345468,0.00007802495,0.24207361],"genre_scores_gemma":[0.121493585,0.04019633,0.025388693,0.24872313,0.007033733,0.0018860175,0.0007086381,0.00007029824,0.55449957],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960623,0.00033388828,0.0010288367,0.0005709881,0.0017631903,0.00024080598],"domain_scores_gemma":[0.99220145,0.00083098764,0.00057542196,0.001113676,0.0050642467,0.00021419916],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0033429484,0.0002240386,0.00039717107,0.0002773979,0.00042890178,0.00026277627,0.0009718529,0.000066554334,0.18493965],"category_scores_gemma":[0.004569884,0.00015188832,0.00013130256,0.0017024236,0.00017961721,0.0008401749,0.00010329881,0.00014117303,0.014950283],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000059117133,0.00039168488,0.0067548337,0.00015724137,0.000009410039,1.6739856e-8,0.00041997494,1.1959507e-7,0.0000018869405,0.007876892,0.7659376,0.21844442],"study_design_scores_gemma":[0.00008162141,0.000033539447,0.07956043,0.00092897465,0.000039259397,0.00001679698,0.00021858128,0.000029923005,0.000013820621,0.0386094,0.8802752,0.00019248668],"about_ca_topic_score_codex":0.00013580151,"about_ca_topic_score_gemma":0.00015151582,"teacher_disagreement_score":0.426188,"about_ca_system_score_codex":0.00022594107,"about_ca_system_score_gemma":0.017262936,"threshold_uncertainty_score":0.98830825},"labels":[],"label_agreement":null},{"id":"W2785498366","doi":"10.4000/books.pum.5976","title":"5. La construction du modèle logique d’un programme","year":2012,"lang":"fr","type":"book-chapter","venue":"Presses de l’Université de Montréal eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Agency of Canada","funders":"","keywords":"Mod; Philosophy; Humanities; Mathematics; Discrete mathematics","score_opus":0.059717839985286715,"score_gpt":0.278348835813316,"score_spread":0.21863099582802928,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2785498366","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01622422,0.003926635,0.013790805,0.0018307206,0.00060712994,0.00081642094,0.0000975578,0.00017126842,0.96253526],"genre_scores_gemma":[0.64460915,0.0063113244,0.028973917,0.0006611524,0.00071078487,0.00006600949,0.00008372005,0.00013849286,0.31844544],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957151,0.00060832885,0.00071293104,0.00072291656,0.0013256427,0.0009151163],"domain_scores_gemma":[0.99616355,0.0011114031,0.00075713824,0.0007647785,0.0005533119,0.00064981787],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0025877138,0.0006124917,0.0006324251,0.00036293693,0.00084933883,0.00030243475,0.00094822905,0.0010108835,0.032533854],"category_scores_gemma":[0.0001901051,0.00059757574,0.0004222568,0.00007261327,0.00078855274,0.00044971466,0.0007810957,0.00087762414,0.0011845559],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025468264,0.00007523173,0.009844066,0.00006163551,0.0002133184,0.00018304275,0.0038591248,0.00052981474,0.00031974292,0.3333382,0.0016839115,0.6496372],"study_design_scores_gemma":[0.0013936863,0.00022069797,0.008052715,0.00017872456,0.000511158,0.0010908397,0.0019354064,0.008605286,0.00147924,0.060867105,0.9148725,0.0007926398],"about_ca_topic_score_codex":0.0009296314,"about_ca_topic_score_gemma":0.0011515544,"teacher_disagreement_score":0.9131886,"about_ca_system_score_codex":0.0012535827,"about_ca_system_score_gemma":0.00051822356,"threshold_uncertainty_score":0.99964756},"labels":[],"label_agreement":null},{"id":"W2789492532","doi":"10.1177/1035719x0700700103","title":"The fate of recommendations","year":2007,"lang":"en","type":"article","venue":"Evaluation Journal of Australasia","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"General Dynamics (Canada)","funders":"","keywords":"Audit; Performance audit; Identification (biology); Business; Government (linguistics); Audit plan; Auditor independence; Parliament; Accounting; Chief audit executive; Joint audit; Public relations; Internal audit; Political science; Law; Politics","score_opus":0.26287728300665364,"score_gpt":0.5593003095300301,"score_spread":0.29642302652337643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2789492532","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9394496,0.00023775964,0.019151086,0.02098752,0.0025746278,0.00033379617,0.0000040604355,0.0000058891715,0.017255671],"genre_scores_gemma":[0.9964011,0.00005805738,0.0021770445,0.00007149699,0.00014908184,0.000001332166,0.0000013480427,0.0000036946071,0.0011368867],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99426514,0.0004458823,0.0017066842,0.00009588423,0.003323097,0.00016328832],"domain_scores_gemma":[0.99276984,0.001757742,0.0015379757,0.00026949152,0.0035730905,0.0000918402],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.05582915,0.00007056839,0.0001619728,0.00028151018,0.00019578522,0.00010414078,0.00049185735,0.00003939964,0.0027300534],"category_scores_gemma":[0.003732657,0.000039411076,0.00013422444,0.00063194113,0.0000826511,0.00048533877,0.000022245495,0.00017605584,0.00007279115],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012456987,0.0000885012,0.02319669,0.0000018653271,0.0000601689,0.000001170297,0.0014053069,0.0029749584,0.0019508477,0.0040457835,0.04344601,0.9227041],"study_design_scores_gemma":[0.0024683517,0.00062306266,0.6841198,0.000067442495,0.00013557273,0.000094280964,0.010261884,0.010483724,0.012785486,0.052629706,0.22615927,0.00017138009],"about_ca_topic_score_codex":0.0000014283061,"about_ca_topic_score_gemma":0.000028517457,"teacher_disagreement_score":0.92253274,"about_ca_system_score_codex":0.00007786153,"about_ca_system_score_gemma":0.0004706749,"threshold_uncertainty_score":0.9981816},"labels":[],"label_agreement":null},{"id":"W2789725530","doi":"10.71781/5398","title":"Étude de la prise en compte de la compétence 5 du référentiel en enseignement lors de son adaptation et de son adoption dans le programme de BEPEP de l’Université de Montréal","year":2017,"lang":"fr","type":"dissertation","venue":"Papyrus : Institutional Repository (Université de Montréal)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Université de Montréal","keywords":"Humanities; Political science; Philosophy","score_opus":0.018382892868234864,"score_gpt":0.2734800547413439,"score_spread":0.25509716187310905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2789725530","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88093036,0.002682789,0.09515597,0.0010564821,0.0004182289,0.00077246415,0.00007295241,0.00014187036,0.018768879],"genre_scores_gemma":[0.9565411,0.0029020347,0.028811626,0.00024980327,0.00020943866,0.000094536415,0.0004011102,0.000054012897,0.010736325],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.991771,0.0032349322,0.00080729177,0.00097004796,0.0018761728,0.0013405563],"domain_scores_gemma":[0.9951861,0.0013103832,0.0012614457,0.00068276556,0.0006232909,0.00093602174],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.006913176,0.00070629263,0.00062321825,0.0005778704,0.009482847,0.00062664726,0.0014079841,0.00101905,0.00014180323],"category_scores_gemma":[0.00066685176,0.000835678,0.0004766188,0.00040993805,0.0006848903,0.0012172712,0.00033383106,0.0010244225,0.00004906431],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.0024101746,0.001344104,0.24615157,0.0002649922,0.00052533473,0.0022125242,0.35275435,0.28436044,0.04784225,0.031869337,0.001271002,0.028993906],"study_design_scores_gemma":[0.0027270014,0.00028060144,0.6229174,0.00044755812,0.00054817455,0.0012666609,0.102204494,0.24292988,0.0056075933,0.0018917175,0.018439619,0.00073931593],"about_ca_topic_score_codex":0.12990074,"about_ca_topic_score_gemma":0.06423116,"teacher_disagreement_score":0.37676582,"about_ca_system_score_codex":0.02971836,"about_ca_system_score_gemma":0.015447085,"threshold_uncertainty_score":0.9994094},"labels":[],"label_agreement":null},{"id":"W2789757110","doi":"10.1126/science.aat3904","title":"Half of Canada’s government scientists still feel muzzled","year":2018,"lang":"en","type":"article","venue":"Science","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Business; Political science; Internet privacy; Computer science; Philosophy","score_opus":0.11142100812925557,"score_gpt":0.45046402636697175,"score_spread":0.3390430182377162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2789757110","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85861784,0.000021727988,0.0016894481,0.0030061498,0.002379574,0.00016872071,0.000016786184,0.000011304488,0.13408844],"genre_scores_gemma":[0.9893175,0.0000011938029,0.0013461915,0.0004182909,0.000052826523,0.0000028213055,1.5418776e-7,0.0000022290312,0.008858846],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9895615,0.000048888458,0.0004258082,0.00044182397,0.009182819,0.00033917767],"domain_scores_gemma":[0.9977691,0.000171868,0.00025167657,0.0006331534,0.000987816,0.00018636923],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008179025,0.00007916705,0.00013554958,0.0001125331,0.000391206,0.00017214642,0.0013702341,0.000016110014,0.0019583644],"category_scores_gemma":[0.0023569507,0.00005492398,0.000027637816,0.0017717642,0.0011759031,0.0005197623,0.0002384132,0.00004850618,0.000116732204],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016052248,0.0004937803,0.20898682,0.00002679407,0.000025870522,0.000016495258,0.009641446,0.0011363666,0.25976393,0.09982435,0.12770182,0.2922218],"study_design_scores_gemma":[0.00044993818,0.00020891831,0.5197641,0.00002545644,0.0000050607327,0.000006673165,0.0016687481,0.039518774,0.10437178,0.0035524678,0.3301904,0.00023763881],"about_ca_topic_score_codex":0.006631911,"about_ca_topic_score_gemma":0.1963951,"teacher_disagreement_score":0.31077734,"about_ca_system_score_codex":0.00030170503,"about_ca_system_score_gemma":0.005070841,"threshold_uncertainty_score":0.999983},"labels":[],"label_agreement":null},{"id":"W2789761522","doi":"","title":"Le développement des politiques d'accountability et leur instrumentation dans le domaine de l'éducation : une perspective franco-canadienne","year":2013,"lang":"fr","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Humanities; Art","score_opus":0.09686327686596116,"score_gpt":0.3911112338349639,"score_spread":0.29424795696900274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2789761522","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6249342,0.00028952435,0.19082713,0.1213768,0.000552004,0.00096091424,0.00009985663,0.000114732095,0.06084485],"genre_scores_gemma":[0.91801316,0.0011041473,0.06674058,0.0006662101,0.000058515707,0.00041686554,0.0005453688,0.000059106416,0.0123960255],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.97951883,0.014846619,0.0016274938,0.0016041999,0.0014420126,0.0009608622],"domain_scores_gemma":[0.9829521,0.0026281397,0.0013421867,0.0025963376,0.009892838,0.0005883609],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.027878523,0.0006456469,0.0006854166,0.00048097054,0.0017689735,0.0014501542,0.0019581132,0.00041134754,0.0014711032],"category_scores_gemma":[0.0041619446,0.0006895328,0.00035054667,0.0013566096,0.0012934644,0.0015249257,0.0009852208,0.00088080723,0.000284185],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000022919465,0.0012037704,0.027248235,0.000086283784,0.00009737584,0.0000011554023,0.19928698,0.0004365663,0.002624487,0.7329599,0.00072915346,0.035303153],"study_design_scores_gemma":[0.0016462682,0.000005905625,0.4989339,0.0011322432,0.00008474808,0.000024265524,0.08148414,0.023536256,0.025387935,0.35298705,0.013855896,0.00092136895],"about_ca_topic_score_codex":0.3622196,"about_ca_topic_score_gemma":0.4164463,"teacher_disagreement_score":0.47168568,"about_ca_system_score_codex":0.0040179137,"about_ca_system_score_gemma":0.008205718,"threshold_uncertainty_score":0.9998055},"labels":[],"label_agreement":null},{"id":"W2789990818","doi":"10.18432/ari29370","title":"Review of the Sixth International Symposium on Poetic Inquiry: Breaking Through the Abstract: Poetry as/in/for Social Justice","year":2018,"lang":"en","type":"article","venue":"Art/Research International A Transdisciplinary Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Poetry; Theme (computing); Social justice; Economic Justice; Nova scotia; State (computer science); Sociology; Literature; Law; Social science; Political science; Art; Computer science","score_opus":0.3981289487120754,"score_gpt":0.6047868530804608,"score_spread":0.20665790436838538,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2789990818","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14412633,0.00074896036,0.0022193163,0.6468442,0.010816163,0.0013896086,0.00013316153,0.000018732977,0.19370352],"genre_scores_gemma":[0.98844105,0.0015136696,0.0001741125,0.004036069,0.0033183272,0.000060012477,0.0000124864355,0.000018126704,0.0024261198],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9923845,0.0005725821,0.0012228462,0.00039101185,0.0049993754,0.0004296818],"domain_scores_gemma":[0.99415034,0.002186404,0.00048668252,0.00038315033,0.0027075328,0.00008587363],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.013573807,0.00017630149,0.000257841,0.00028941376,0.0011952773,0.00036652363,0.0030266112,0.00007898962,0.004153398],"category_scores_gemma":[0.001594396,0.00009530786,0.00033591184,0.00081230496,0.0007391574,0.00078135676,0.00028815246,0.0009486567,0.00032903493],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003677516,0.0023621516,0.0032654246,0.0007945149,0.00067179784,0.00005786459,0.16452731,0.0023989035,0.0036492844,0.12409932,0.6289719,0.06552405],"study_design_scores_gemma":[0.0034771136,0.0012569923,0.06628932,0.0063284514,0.00009892404,0.00048557698,0.027109215,0.008286885,0.00089453417,0.14614636,0.73916024,0.00046640655],"about_ca_topic_score_codex":0.000006946114,"about_ca_topic_score_gemma":0.000065974105,"teacher_disagreement_score":0.84431475,"about_ca_system_score_codex":0.00027768465,"about_ca_system_score_gemma":0.00056604977,"threshold_uncertainty_score":0.9967569},"labels":[],"label_agreement":null},{"id":"W2790025778","doi":"10.1522/rhe.v1i1.6","title":"Le développement d’une culture de recherche participative par le Consortium régional de recherche en éducation","year":2017,"lang":"fr","type":"article","venue":"Revue hybride de l éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.8181601580569172,"score_gpt":0.6147609870152431,"score_spread":0.20339917104167415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2790025778","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5215099,0.0010197451,0.047033597,0.38980728,0.0027386763,0.000923659,0.00004899548,0.000065660344,0.036852494],"genre_scores_gemma":[0.8851887,0.002501172,0.068826176,0.0025968926,0.00092347467,0.00042999757,0.0001242975,0.000041071664,0.039368205],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9873548,0.009061835,0.0011018033,0.0008091287,0.0008375427,0.0008348571],"domain_scores_gemma":[0.992724,0.0032068312,0.0011960078,0.0013044063,0.0011560867,0.0004126659],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.041348245,0.0003482724,0.00043284125,0.00017637019,0.0012970773,0.000828347,0.0011012844,0.00074354996,0.0009278414],"category_scores_gemma":[0.025491113,0.00036802702,0.00021214852,0.00048856786,0.00031028237,0.0013294322,0.00015006281,0.0013906108,0.0009288183],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00023015284,0.0024547284,0.088743985,0.00039875202,0.00030872808,0.000025795647,0.33432055,0.0030365377,0.015130009,0.096315466,0.21974996,0.23928535],"study_design_scores_gemma":[0.0015961668,0.00024127003,0.34730813,0.000731056,0.0002570743,0.00018966886,0.047745977,0.036169898,0.04238326,0.3201603,0.20231313,0.00090406666],"about_ca_topic_score_codex":0.0025587773,"about_ca_topic_score_gemma":0.0025240402,"teacher_disagreement_score":0.3872104,"about_ca_system_score_codex":0.007609683,"about_ca_system_score_gemma":0.023977159,"threshold_uncertainty_score":0.99998546},"labels":[],"label_agreement":null},{"id":"W2790752207","doi":"10.1177/1035719x1701700204","title":"Interactive Logic Models: Using Design and Technology to Explore the Effects of Dynamic Situations on Program Logic","year":2017,"lang":"en","type":"article","venue":"Evaluation Journal of Australasia","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Ontario College of Art and Design; Centre for Advancing Health Outcomes","funders":"","keywords":"Logic model; Computer science; Interactivity; Software engineering; Software; Process (computing); Logic programming; Human–computer interaction; Programming language; World Wide Web","score_opus":0.4434407751028504,"score_gpt":0.5792202090185361,"score_spread":0.1357794339156857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2790752207","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89579386,0.000072534174,0.09252,0.009646002,0.00048102488,0.001234435,9.448086e-7,0.000008979317,0.00024222981],"genre_scores_gemma":[0.9770121,0.000030579966,0.022735666,0.000083739775,0.0000342233,0.00003759086,4.9952786e-7,0.000006035834,0.000059595295],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967277,0.0005618194,0.0007045566,0.00019957397,0.0016522991,0.000154064],"domain_scores_gemma":[0.99499124,0.0009985052,0.0013728607,0.00048341235,0.002074495,0.00007946606],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0070545785,0.00012700603,0.00026594536,0.00054434425,0.00038647107,0.0002558834,0.00066119403,0.00007832239,0.000104781175],"category_scores_gemma":[0.0062539964,0.00007329917,0.00007174731,0.00035793605,0.00017204652,0.0007863135,0.00007797802,0.00025318368,0.0000136247645],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025916207,0.00041356354,0.0016905107,0.000016965849,0.00013310352,0.000008249871,0.005204042,0.25239727,0.011040946,0.002811854,0.00076350797,0.72526085],"study_design_scores_gemma":[0.0010619723,0.0024296073,0.022475405,0.0002225181,0.000141694,0.000056414203,0.0030589742,0.765372,0.0027335281,0.20228429,0.000047931433,0.00011568746],"about_ca_topic_score_codex":0.000001551459,"about_ca_topic_score_gemma":0.000004237009,"teacher_disagreement_score":0.72514516,"about_ca_system_score_codex":0.00012891418,"about_ca_system_score_gemma":0.00036136448,"threshold_uncertainty_score":0.74870694},"labels":[],"label_agreement":null},{"id":"W2791138626","doi":"10.1177/1035719x0500500104","title":"The Development of a Logic Model for the Protection against Family Violence Act: An Incremental Approach","year":2005,"lang":"en","type":"article","venue":"Evaluation Journal of Australasia","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Government of Northwest Territories","funders":"","keywords":"Legislation; Jurisdiction; Economic Justice; Process (computing); Domestic violence; Political science; Law; Computer science; Poison control; Medicine; Human factors and ergonomics; Environmental health; Programming language","score_opus":0.37940263289098225,"score_gpt":0.4914204480204588,"score_spread":0.11201781512947656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2791138626","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73522466,0.00009898156,0.261471,0.0014758765,0.00020114114,0.0009832239,0.0000018886543,0.0000046118635,0.0005385911],"genre_scores_gemma":[0.9649699,0.000038196547,0.03448948,0.00011985717,0.00014923543,0.000085947824,0.0000029969513,0.000005991021,0.00013842454],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9948038,0.0003661676,0.0013841132,0.00017182938,0.003092328,0.00018176751],"domain_scores_gemma":[0.9959968,0.00034883482,0.001241942,0.0002869418,0.0020511195,0.00007437767],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027956976,0.00011887703,0.00017480475,0.00014712285,0.00053727545,0.00017136043,0.00069782994,0.000054198026,0.000077148215],"category_scores_gemma":[0.00083465345,0.00005769844,0.0001188613,0.00030576627,0.0000860327,0.0007649029,0.00003276292,0.0001941498,0.000013154309],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000115065624,0.000100750956,0.00030047836,0.0000028003844,0.000028255743,2.0644038e-8,0.0021587186,0.30002734,0.0041022743,0.00019126249,0.0002686378,0.6927044],"study_design_scores_gemma":[0.0008197395,0.00017169586,0.023117507,0.00002628605,0.000038576396,0.0000060217358,0.0044096154,0.96493363,0.0026385842,0.002652424,0.0011120109,0.000073909774],"about_ca_topic_score_codex":7.5628856e-7,"about_ca_topic_score_gemma":0.00002784377,"teacher_disagreement_score":0.69263047,"about_ca_system_score_codex":0.00020520821,"about_ca_system_score_gemma":0.0012530881,"threshold_uncertainty_score":0.9689385},"labels":[],"label_agreement":null},{"id":"W2792364707","doi":"","title":"The Politics of Scale","year":2005,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Scale (ratio); Politics; Political science; Geography; Cartography; Law","score_opus":0.20982787495727742,"score_gpt":0.53236490785292,"score_spread":0.3225370328956426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2792364707","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4506903,0.00007520843,0.0021052395,0.021012735,0.00015746104,0.00006173055,0.000001387897,0.000010249715,0.5258857],"genre_scores_gemma":[0.926546,0.00001220771,0.0014456346,0.0005228958,0.000054384127,0.0000011803636,1.3077398e-7,8.8751085e-7,0.07141671],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99884754,0.000037216014,0.0002449017,0.00005646819,0.0007396196,0.00007426006],"domain_scores_gemma":[0.99901456,0.00047325218,0.00005677895,0.00024230142,0.00018754417,0.000025595877],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0019112932,0.000022007767,0.000043471202,0.000026503634,0.00011304783,0.00004652944,0.0002482926,0.000010357712,0.0022827848],"category_scores_gemma":[0.0001943262,0.000009648619,0.000027506889,0.00014145878,0.00005144672,0.00009688569,0.000027926139,0.000022519285,0.0006684748],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000042104302,0.000043364715,0.03945326,5.935541e-7,0.00000452271,3.320778e-8,0.0006941338,0.0004926703,0.00027364556,0.23708048,0.106847994,0.6151051],"study_design_scores_gemma":[0.000103968094,0.000021105268,0.049403153,9.2397863e-7,0.0000014084309,6.235866e-7,0.0011327016,0.018562995,0.005107426,0.016765967,0.9088707,0.000029018942],"about_ca_topic_score_codex":0.0000055866217,"about_ca_topic_score_gemma":0.000119383236,"teacher_disagreement_score":0.8020227,"about_ca_system_score_codex":0.000008539699,"about_ca_system_score_gemma":0.000059656188,"threshold_uncertainty_score":0.9986293},"labels":[],"label_agreement":null},{"id":"W2792650082","doi":"10.7202/1043469ar","title":"L’avis des groupes dans l’analyse des politiques éducatives, une voie prometteuse : le cas de la Société des professeurs d’histoire du Québec","year":2018,"lang":"fr","type":"article","venue":"Recherches sociographiques","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université Laval","funders":"","keywords":"Humanities; Philosophy; Political science","score_opus":0.3758475774534781,"score_gpt":0.5275928898998368,"score_spread":0.1517453124463587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2792650082","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91190904,0.027091049,0.004545126,0.023624884,0.00038424597,0.00063869177,0.000053497697,0.00035593665,0.0313975],"genre_scores_gemma":[0.9237583,0.019306615,0.03703986,0.0008479059,0.0007857315,0.00028312101,0.000021234882,0.00011036936,0.017846849],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9863358,0.008853971,0.0012622311,0.0010642951,0.0011373966,0.0013463029],"domain_scores_gemma":[0.989799,0.00548461,0.0006798331,0.000904008,0.0025267745,0.00060572475],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":["sts"],"category_scores_codex":[0.015819982,0.0007531562,0.00088675314,0.0010108192,0.0030382257,0.00077889644,0.0013606423,0.0009201307,0.0007474262],"category_scores_gemma":[0.005409083,0.00066817267,0.0008424153,0.0037807527,0.020643538,0.0022383034,0.0002795539,0.0010752472,0.00013754058],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00005331107,0.00083117356,0.5547968,0.0002123729,0.00037919232,0.000011190174,0.3109255,0.000002631919,0.0012524396,0.005971355,0.005820752,0.11974328],"study_design_scores_gemma":[0.0004917097,0.00060915307,0.5867267,0.0005113812,0.00030516688,0.00005685458,0.09075509,0.0003319811,0.008429042,0.29681394,0.014237268,0.0007317232],"about_ca_topic_score_codex":0.5569009,"about_ca_topic_score_gemma":0.54164815,"teacher_disagreement_score":0.29084256,"about_ca_system_score_codex":0.008894272,"about_ca_system_score_gemma":0.007349142,"threshold_uncertainty_score":0.9995769},"labels":[],"label_agreement":null},{"id":"W2793638346","doi":"10.1177/1035719x0300300205","title":"Reflections on a decade in the life of the Australasian Evaluation Society: 1990-1999","year":2003,"lang":"en","type":"article","venue":"Evaluation Journal of Australasia","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Rigour; Professional association; Consolidation (business); Political science; Sociology; Psychology; Public relations; Epistemology","score_opus":0.3166674843876108,"score_gpt":0.5439863815010553,"score_spread":0.2273188971134445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2793638346","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96114254,0.00016862033,0.00041516774,0.01621635,0.001386323,0.001120911,0.000004963602,0.00000520164,0.019539941],"genre_scores_gemma":[0.9980512,0.00002997059,0.0006854401,0.00077824114,0.00015132796,0.00003290743,0.0000018271037,0.00000907029,0.00026001624],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.985623,0.0040258043,0.0018071062,0.00026136165,0.008015937,0.0002667616],"domain_scores_gemma":[0.9944098,0.001050083,0.001600194,0.0006389757,0.0021943734,0.000106565436],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.052213907,0.00018044015,0.00030929624,0.00036807155,0.00027927515,0.00016875261,0.00089052675,0.00013069811,0.0027191648],"category_scores_gemma":[0.008996985,0.0000951842,0.00041749244,0.0021131758,0.00014121438,0.0005697297,0.000020449368,0.0006323112,0.00005246361],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003688242,0.0022087446,0.13704538,0.000037012614,0.0004818566,0.0000042142483,0.053645268,0.48059088,0.007215796,0.032879252,0.17706536,0.10845741],"study_design_scores_gemma":[0.0045153066,0.00082638394,0.8715647,0.00018190563,0.00049075333,0.00013392301,0.026139261,0.022303298,0.0031654933,0.041474797,0.028932681,0.00027153682],"about_ca_topic_score_codex":0.000008911642,"about_ca_topic_score_gemma":0.00008877196,"teacher_disagreement_score":0.7345193,"about_ca_system_score_codex":0.00028063444,"about_ca_system_score_gemma":0.0024138507,"threshold_uncertainty_score":0.99935067},"labels":[],"label_agreement":null},{"id":"W2794043366","doi":"10.7202/1043569ar","title":"Modération statistique et modération sociale des résultats scolaires : approches opposées ou complémentaires ?","year":2018,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Political science; Humanities; Art","score_opus":0.27048728715022835,"score_gpt":0.5320097625098449,"score_spread":0.26152247535961654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2794043366","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39194882,0.0011235654,0.5061428,0.08266071,0.0048666727,0.0020819237,0.00016854254,0.00017918505,0.010827815],"genre_scores_gemma":[0.9552202,0.000677917,0.028691093,0.0024685333,0.0008939166,0.00032759516,0.0012540494,0.000058582667,0.010408117],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9829369,0.010512433,0.0017415904,0.0010526815,0.0031734381,0.0005829681],"domain_scores_gemma":[0.9919538,0.0022362312,0.001167475,0.0006807915,0.0037479508,0.0002137346],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.03954118,0.00052074686,0.00051036256,0.00057526416,0.0010493883,0.0013120266,0.00054443494,0.00039267555,0.003632803],"category_scores_gemma":[0.005057762,0.0005184172,0.0001657065,0.001247691,0.0006740954,0.004663076,0.000115699615,0.00040192448,0.0017970218],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017515142,0.0010209185,0.01221595,0.0001836206,0.0001771327,0.0000010447885,0.31078017,0.012167618,0.0052821543,0.09736164,0.03489627,0.52573836],"study_design_scores_gemma":[0.0013034581,0.00062923576,0.51331496,0.00033031713,0.00020361677,0.000009718318,0.0102138715,0.28518704,0.005289153,0.16355391,0.019274727,0.0006899891],"about_ca_topic_score_codex":0.00097633194,"about_ca_topic_score_gemma":0.015861515,"teacher_disagreement_score":0.5632714,"about_ca_system_score_codex":0.0011946622,"about_ca_system_score_gemma":0.005938378,"threshold_uncertainty_score":0.9997267},"labels":[],"label_agreement":null},{"id":"W2794312167","doi":"10.1016/j.evalprogplan.2018.02.008","title":"The influence of evaluation recommendations on instrumental and conceptual uses: A preliminary analysis","year":2018,"lang":"en","type":"article","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; École Nationale d'Administration Publique","funders":"","keywords":"Timeline; Context (archaeology); Relevance (law); Government (linguistics); Process (computing); Process management; Program evaluation; Management science; Computer science; Business; Engineering; Political science; Public administration","score_opus":0.251468143086531,"score_gpt":0.5619848745859857,"score_spread":0.3105167314994547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2794312167","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99501896,0.0002949445,0.00017400579,0.0013080183,0.00012416164,0.0009009512,0.000008508604,0.000020693033,0.0021497787],"genre_scores_gemma":[0.998348,0.00004168234,0.0010469665,0.00020609006,0.000043691514,0.00018735086,0.000051049556,0.0000040487957,0.00007112868],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99600106,0.0008695995,0.00059714465,0.0003324407,0.002047953,0.00015177077],"domain_scores_gemma":[0.9967238,0.0012304208,0.000419672,0.00029521892,0.0012602488,0.000070651935],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013527491,0.00011323261,0.00017060204,0.00029827535,0.00064732373,0.000276234,0.00015037757,0.000052096442,0.00048042828],"category_scores_gemma":[0.002057956,0.00007420896,0.00004621206,0.0010018821,0.00041982593,0.00041531379,0.00006793599,0.00009942165,0.000018956032],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001377365,0.00006446979,0.113695934,0.0000019804522,0.000121113415,9.570874e-8,0.0068797064,0.005167861,0.000044524386,0.0010846944,0.0007457313,0.8720561],"study_design_scores_gemma":[0.0006852024,0.0009810133,0.5697394,0.00003822215,0.00026996632,0.0000022266674,0.0064376392,0.41430956,0.00008256934,0.001839832,0.005520203,0.0000941297],"about_ca_topic_score_codex":0.000014461601,"about_ca_topic_score_gemma":0.000039704286,"teacher_disagreement_score":0.871962,"about_ca_system_score_codex":0.000044515404,"about_ca_system_score_gemma":0.00018718613,"threshold_uncertainty_score":0.52603525},"labels":[],"label_agreement":null},{"id":"W2794762349","doi":"10.1332/174426418x15212871808802","title":"Rethinking knowledge translation for public health policy","year":2018,"lang":"en","type":"article","venue":"Evidence & Policy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; University of Ottawa","funders":"","keywords":"Public policy; Public relations; Knowledge translation; Political science; Context (archaeology); Hierarchy; Policy studies; Politics; Public health policy; Evidence-based policy; Health policy; Process (computing); Policy analysis; Sociology; Public administration; Computer science; Knowledge management; Health care; Medicine; Geography","score_opus":0.7758085422292174,"score_gpt":0.6380480485743207,"score_spread":0.13776049365489662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2794762349","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05309833,0.0020603766,0.10735201,0.7971973,0.0012900801,0.0017313049,0.000030020708,0.00025752204,0.036983065],"genre_scores_gemma":[0.97932875,0.00017330894,0.004706685,0.008789448,0.0035887614,0.00006817594,0.000005788732,0.000017004655,0.0033220926],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99626684,0.00049415225,0.000869583,0.00050657516,0.001237547,0.0006253123],"domain_scores_gemma":[0.99521387,0.0022215068,0.00041715513,0.0007104369,0.0011241717,0.00031287668],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01283744,0.00016710395,0.0002834582,0.0010216226,0.0007149593,0.00051560305,0.0008248339,0.0000904499,0.0005515295],"category_scores_gemma":[0.013019977,0.00013153483,0.00014764653,0.0024761828,0.00019913692,0.0017072652,0.00007287098,0.0001328671,0.0011600388],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022900642,0.00004548421,0.0016856865,0.000019694155,0.000007943073,7.551837e-8,0.036382627,0.000009737165,0.00018482214,0.10080358,0.015573075,0.8452644],"study_design_scores_gemma":[0.00057005335,0.0006613401,0.0172309,0.00016338138,0.000005186592,0.000006414147,0.00073723664,0.017804919,0.00032269902,0.17685932,0.78536564,0.00027288948],"about_ca_topic_score_codex":0.00061850355,"about_ca_topic_score_gemma":0.0012996121,"teacher_disagreement_score":0.92623043,"about_ca_system_score_codex":0.00039916424,"about_ca_system_score_gemma":0.0057695834,"threshold_uncertainty_score":0.9998668},"labels":[],"label_agreement":null},{"id":"W2795216215","doi":"10.1016/j.puhe.2018.01.031","title":"Building evaluation capacity in Ontario's public health units: promising practices and strategies","year":2018,"lang":"en","type":"article","venue":"Public Health","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa; École Nationale d'Administration Publique","funders":"","keywords":"Capacity building; Context (archaeology); Unit (ring theory); Set (abstract data type); Process management; Knowledge management; Business; Public health; Public relations; Medicine; Medical education; Nursing; Psychology; Computer science; Political science","score_opus":0.8565810250614335,"score_gpt":0.5770020493415039,"score_spread":0.2795789757199296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2795216215","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8867375,0.00020389043,0.004434367,0.09992861,0.00042059118,0.0008032313,0.00000441108,0.000045546254,0.007421841],"genre_scores_gemma":[0.98966604,0.000055012086,0.006278206,0.0036792003,0.00013014024,0.000051817064,0.00001382769,0.000009840935,0.00011593008],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9914226,0.002826183,0.0013185751,0.0007144725,0.0028279587,0.0008902337],"domain_scores_gemma":[0.99496806,0.0006895996,0.0015767143,0.0004923971,0.0017309346,0.0005422982],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07517434,0.00017236684,0.00037059767,0.0007663014,0.00071189733,0.001977792,0.00039541684,0.000077324454,0.0011491005],"category_scores_gemma":[0.008530377,0.00013917607,0.00002227003,0.0019363154,0.00017439331,0.0046455488,0.00010631698,0.00041012498,0.000038790135],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014227487,0.00021459283,0.20724465,0.000045488996,0.000016233102,3.6842692e-7,0.041427873,0.000033836634,0.000028245524,0.045566507,0.002119989,0.703288],"study_design_scores_gemma":[0.0009522839,0.0005204583,0.684625,0.00005463295,0.0000024087972,0.000013971273,0.014845248,0.022782126,0.0000064534966,0.0132525265,0.26273504,0.00020981621],"about_ca_topic_score_codex":0.07473179,"about_ca_topic_score_gemma":0.57070506,"teacher_disagreement_score":0.7030782,"about_ca_system_score_codex":0.0016438313,"about_ca_system_score_gemma":0.029242752,"threshold_uncertainty_score":0.9998212},"labels":[],"label_agreement":null},{"id":"W2795502110","doi":"","title":"Northern expressions : understanding collaboration in northern Canadian nurses' practice","year":2004,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Geography","score_opus":0.20278089029455715,"score_gpt":0.500796541623375,"score_spread":0.2980156513288178,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2795502110","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60980606,0.000039835675,0.011654968,0.054930706,0.00087568,0.0005566281,0.000012385506,0.000047974296,0.32207575],"genre_scores_gemma":[0.9962065,0.000008018498,0.001213637,0.0012288295,0.000038091872,0.00001746286,0.000007975012,0.000007662171,0.0012718228],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9977431,0.00015527947,0.00044498502,0.00028642756,0.0011174339,0.00025274084],"domain_scores_gemma":[0.9983403,0.00041673044,0.00014800741,0.0003416488,0.0005434464,0.00020985129],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0020363838,0.00009755153,0.00012247151,0.00044424683,0.00027039138,0.00030984147,0.00027527421,0.00006673761,0.0009827162],"category_scores_gemma":[0.0019016009,0.00007319394,0.00002859393,0.0014134772,0.00003365103,0.0011946112,0.000020886093,0.00012676248,0.0008451388],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001004172,0.00038695015,0.62065625,0.0000041205467,0.000028859027,0.000069368536,0.039625093,0.16273409,0.0007580388,0.1568047,0.0031153923,0.015716756],"study_design_scores_gemma":[0.004223934,0.00026774942,0.08515595,0.00011869763,0.000029346533,0.000027632901,0.5049437,0.0077414857,0.0006627701,0.14810194,0.24785703,0.00086975173],"about_ca_topic_score_codex":0.05347279,"about_ca_topic_score_gemma":0.99034965,"teacher_disagreement_score":0.9368769,"about_ca_system_score_codex":0.0016967197,"about_ca_system_score_gemma":0.003101902,"threshold_uncertainty_score":0.9999328},"labels":[],"label_agreement":null},{"id":"W2796946910","doi":"10.17483/2368-6669.1129","title":"Valuing Curriculum Evaluation as Scholarship: A Process of Developing a Community of Scholars","year":2018,"lang":"en","type":"article","venue":"Quality Advancement in Nursing Education - Avancées en formation infirmière","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Vancouver Island University; University of British Columbia, Okanagan Campus; Thompson Rivers University; University of British Columbia","funders":"","keywords":"Scholarship; Curriculum; Accreditation; Sociology; Pedagogy; Curriculum development; Political science; Medical education; Medicine","score_opus":0.20751831975398952,"score_gpt":0.5859287900782192,"score_spread":0.3784104703242297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2796946910","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9766458,0.0001472028,0.011094641,0.0013994465,0.0010541126,0.0009535002,0.000008494353,0.000029694385,0.008667052],"genre_scores_gemma":[0.9911894,0.000039300197,0.008118354,0.00025081416,0.00007666166,0.00013655164,0.00009976358,0.000012191817,0.00007697137],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99119985,0.002581621,0.0025304088,0.00032261765,0.0030769526,0.0002885576],"domain_scores_gemma":[0.9914948,0.0006879068,0.001966782,0.00075746985,0.0050099804,0.00008308528],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022256846,0.00021502632,0.00042436132,0.00095248636,0.00041028313,0.00013168307,0.0006908039,0.000120649915,0.0004841033],"category_scores_gemma":[0.0071212356,0.00020536815,0.00008655342,0.0019873432,0.00024402248,0.004348841,0.000060804345,0.00040079094,0.000082754974],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020048523,0.0027822817,0.11743857,0.00055467925,0.000031438332,4.761408e-8,0.10018894,0.0052976217,0.0032364083,0.06327663,0.00025245704,0.70674044],"study_design_scores_gemma":[0.0031107503,0.0007857301,0.34585977,0.005799558,0.00008438401,0.000013393293,0.20842962,0.023529902,0.054458402,0.34941712,0.0076324968,0.00087888126],"about_ca_topic_score_codex":0.00011636595,"about_ca_topic_score_gemma":0.00014671194,"teacher_disagreement_score":0.70586157,"about_ca_system_score_codex":0.00084886997,"about_ca_system_score_gemma":0.0015548117,"threshold_uncertainty_score":0.8525298},"labels":[],"label_agreement":null},{"id":"W2797491711","doi":"10.3138/cjpe.43180","title":"Expenditure Reviews and the Federal Experience: Program Evaluation and Its Contribution to Assurance Provision","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Accountability; Function (biology); Business; Accounting; Public administration; Administration (probate law); Focus (optics); Public relations; Finance; Political science; Law","score_opus":0.2778351949623966,"score_gpt":0.5486718860554921,"score_spread":0.2708366910930955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2797491711","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.963474,0.0079164,0.0011068695,0.009961411,0.0014121142,0.015356447,0.000006611026,0.000017093593,0.00074906833],"genre_scores_gemma":[0.99546856,0.0001309349,0.0018563187,0.0005386712,0.00046573524,0.0014400651,0.00001168716,0.000008680671,0.00007934491],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9936644,0.001841773,0.0011515532,0.00035983755,0.0026424094,0.0003400538],"domain_scores_gemma":[0.99212295,0.00029600444,0.0008908103,0.0002944941,0.005869351,0.00052640314],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.036498778,0.00018565216,0.0003792477,0.00037259576,0.00076191954,0.001068776,0.00036651018,0.00010553317,0.0007422859],"category_scores_gemma":[0.012842332,0.00010921902,0.00008890064,0.0007231594,0.0002756966,0.0010186115,0.000029845274,0.00021200208,0.00005719603],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000102972655,0.000025597783,0.0036186562,0.0000055809433,0.0000117947875,7.061192e-7,0.0045437636,0.000053702064,0.00008176782,0.000510277,0.0026106075,0.98843455],"study_design_scores_gemma":[0.0073798196,0.0028977194,0.14882688,0.00038596528,0.00023501922,0.00016120079,0.003049907,0.31502858,0.0005540017,0.008502748,0.5125342,0.00044397902],"about_ca_topic_score_codex":0.00010977349,"about_ca_topic_score_gemma":0.0071976576,"teacher_disagreement_score":0.9879906,"about_ca_system_score_codex":0.00029401804,"about_ca_system_score_gemma":0.001968665,"threshold_uncertainty_score":0.99996823},"labels":[],"label_agreement":null},{"id":"W2797550683","doi":"10.3138/cjpe.43179","title":"Strategic Evaluation Utilization in the Canadian Federal Government","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa; École Nationale d'Administration Publique","funders":"","keywords":"Government (linguistics); Focus group; Program evaluation; Function (biology); Business; Public relations; Public policy; Content analysis; Key (lock); Qualitative research; Psychology; Marketing; Public administration; Political science; Sociology; Computer science","score_opus":0.6515255366463052,"score_gpt":0.5637168640848468,"score_spread":0.08780867256145841,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2797550683","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91871685,0.00038755045,0.0002614475,0.009375454,0.0018030719,0.0029878246,0.000014139971,0.000006041015,0.066447645],"genre_scores_gemma":[0.998169,0.000004466714,0.00046074478,0.0007203966,0.0004412351,0.00010479941,0.00002210994,0.000008203179,0.00006903651],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.990897,0.0016413016,0.00100835,0.00023338037,0.0058206157,0.00039936256],"domain_scores_gemma":[0.994249,0.00017290992,0.00060809916,0.00035802968,0.0041712136,0.0004407681],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.044159926,0.00013885184,0.0001792468,0.00060438324,0.00061701436,0.0011590645,0.0006729854,0.00010938925,0.0045465464],"category_scores_gemma":[0.0025493717,0.00009433388,0.000086693195,0.0013224176,0.00014919092,0.00069425703,0.0000067752353,0.0002468108,0.00013660223],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001898322,0.00005286507,0.050530616,0.000002223284,0.000017890485,0.000006681161,0.0041386806,0.002318686,0.000012724437,0.003154253,0.0053432933,0.9344031],"study_design_scores_gemma":[0.0017248044,0.0010806263,0.45951247,0.000054734617,0.00010096508,0.000056658584,0.0099863,0.42540658,0.00005872124,0.047508426,0.054271072,0.00023863462],"about_ca_topic_score_codex":0.049120218,"about_ca_topic_score_gemma":0.98032767,"teacher_disagreement_score":0.93416446,"about_ca_system_score_codex":0.0025127514,"about_ca_system_score_gemma":0.017308533,"threshold_uncertainty_score":0.9998778},"labels":[],"label_agreement":null},{"id":"W2797660137","doi":"10.14507/epaa.26.3810","title":"Introduction to the special issue: Historical and contemporary perspectives on educational evaluation","year":2018,"lang":"en","type":"article","venue":"Education Policy Analysis Archives","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Institut écologie et environnement","keywords":"Perspective (graphical); Educational evaluation; Educational assessment; Evaluation methods; Sociology; Educational research; Political science; Engineering ethics; Pedagogy; Computer science; Engineering","score_opus":0.1170286283268526,"score_gpt":0.5017547438808525,"score_spread":0.38472611555399994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2797660137","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08335906,0.00022175754,0.0013176702,0.7926385,0.0018734487,0.0005154364,0.0000097079555,0.000016419697,0.12004802],"genre_scores_gemma":[0.90923923,0.000027216784,0.00064928556,0.0022779892,0.058006447,0.00011068826,0.00003801426,0.0000064899828,0.029644622],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965124,0.0007694114,0.00051095453,0.00061416824,0.0014363695,0.00015666122],"domain_scores_gemma":[0.99745417,0.0007757186,0.0002693824,0.0006719191,0.0006721495,0.0001566697],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0028600474,0.00013976516,0.00021288091,0.0017453169,0.0005787137,0.00026517277,0.00036122676,0.000030240702,0.006936904],"category_scores_gemma":[0.0043979455,0.00009291505,0.00012865194,0.0027248142,0.0001800732,0.00029468248,0.000057850924,0.000117716176,0.00087536743],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000070908245,0.0003444068,0.006793351,0.0000010171175,0.00012580695,1.1711249e-8,0.036985222,0.0003388329,0.00004354827,0.04100064,0.7660748,0.14822145],"study_design_scores_gemma":[0.00012083025,0.00012183455,0.29317257,0.0000029991245,0.00009634404,0.0000011088047,0.008099413,0.0034645845,0.000037006706,0.018090133,0.6766824,0.00011079019],"about_ca_topic_score_codex":0.00023519578,"about_ca_topic_score_gemma":0.00022482267,"teacher_disagreement_score":0.82588017,"about_ca_system_score_codex":0.0003571006,"about_ca_system_score_gemma":0.0017548553,"threshold_uncertainty_score":0.99990255},"labels":[],"label_agreement":null},{"id":"W2797709357","doi":"10.56645/jmde.v14i30.501","title":"Customizing the Standard to the Purpose of the Assessment","year":2018,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Psychology","score_opus":0.2134546959921358,"score_gpt":0.5487707242592667,"score_spread":0.33531602826713086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2797709357","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9189567,0.000109771456,0.014647754,0.05967933,0.002606291,0.0010075292,0.00000879224,0.000003888149,0.0029799698],"genre_scores_gemma":[0.9966023,0.000015550657,0.0021195777,0.0003085457,0.00059685874,0.000018712284,5.7027614e-7,0.000007635706,0.0003302536],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9903857,0.0017687633,0.0013150823,0.0001806289,0.006173948,0.00017588625],"domain_scores_gemma":[0.9920549,0.0012046146,0.0015685844,0.0008012665,0.004298581,0.00007205031],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04721186,0.00012319227,0.00024838938,0.00017927476,0.0008100446,0.00017099433,0.0014531803,0.00004486865,0.00079548114],"category_scores_gemma":[0.0027026485,0.000044179975,0.00023113309,0.0009896084,0.00020511294,0.0004481355,0.00035631965,0.0002939054,0.00006713737],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011251178,0.0004226338,0.113124005,0.000014136906,0.00020359295,0.0000018583394,0.046912905,0.14468713,0.01312502,0.0027388025,0.07555421,0.6020906],"study_design_scores_gemma":[0.0015504512,0.0011071519,0.73840845,0.0001236672,0.00018517379,0.00003637719,0.012461375,0.201395,0.0033782145,0.010010527,0.031210853,0.00013274865],"about_ca_topic_score_codex":0.00000399215,"about_ca_topic_score_gemma":0.00012763738,"teacher_disagreement_score":0.62528443,"about_ca_system_score_codex":0.00025682923,"about_ca_system_score_gemma":0.0012600537,"threshold_uncertainty_score":0.9810959},"labels":[],"label_agreement":null},{"id":"W2798137084","doi":"10.3138/cjpe.43184","title":"Sunshine, Scrutiny, and Spending Review in Canada, Trudeau to Trudeau: From Program Evaluation and Policy to Commitment and Results","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa; University of Victoria","funders":"","keywords":"Scrutiny; Cabinet (room); Government (linguistics); Public administration; Public relations; Political science; Adaptation (eye); Public policy; Psychology; Law","score_opus":0.3498588876004434,"score_gpt":0.5499745996534898,"score_spread":0.2001157120530464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2798137084","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.954098,0.006808052,0.000072986564,0.030617349,0.0004389597,0.006806308,0.000071833165,0.000007583,0.0010789542],"genre_scores_gemma":[0.9905923,0.00029702342,0.0066248532,0.0018214693,0.00025608373,0.0003338271,0.000029577339,0.000012141395,0.000032751268],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.994385,0.00090254896,0.0014427624,0.0004395051,0.0024426868,0.00038749244],"domain_scores_gemma":[0.9956627,0.0003400702,0.00061452907,0.00032405864,0.0019621584,0.0010965199],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01985883,0.00020551888,0.00048860017,0.0008552792,0.00023300853,0.00046772332,0.00029031714,0.000058468668,0.00047213212],"category_scores_gemma":[0.0072314753,0.00016198198,0.00004441044,0.0012630792,0.00008882903,0.0004522527,0.000048082384,0.00017790117,0.000010908838],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045518424,0.0000194658,0.03002815,0.000014102676,0.000042101674,0.0000033471078,0.0011365082,0.00011176697,0.000008516773,0.00007984013,0.004807351,0.96370333],"study_design_scores_gemma":[0.0021680577,0.0014199454,0.85272217,0.00071825396,0.00044017512,0.000038186772,0.0011336348,0.028520094,0.000033288823,0.002998393,0.109511614,0.0002961926],"about_ca_topic_score_codex":0.5291579,"about_ca_topic_score_gemma":0.98953867,"teacher_disagreement_score":0.96340716,"about_ca_system_score_codex":0.0014900164,"about_ca_system_score_gemma":0.008792443,"threshold_uncertainty_score":0.99682677},"labels":[],"label_agreement":null},{"id":"W2798849220","doi":"10.4135/9781412950558.n399","title":"Participatory Monitoring And Evaluation","year":2005,"lang":"en","type":"reference-entry","venue":"Encyclopedia of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":64,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Department for International Development; International Development Research Centre","keywords":"Participatory evaluation; Citizen journalism; Environmental resource management; Geography; Environmental planning; Computer science; Environmental science; Political science; World Wide Web; Public administration","score_opus":0.3061055399075754,"score_gpt":0.5210402523813807,"score_spread":0.21493471247380536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2798849220","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22163284,0.017409764,0.00012433698,0.00053696026,0.005107075,0.0019207551,0.000057489466,0.000037248454,0.75317353],"genre_scores_gemma":[0.8113917,0.116336286,0.0023556345,0.000092349226,0.0058598625,0.0011839671,0.00059464586,0.00008862801,0.062096942],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9842775,0.001845762,0.001851199,0.0008593561,0.010813926,0.0003522963],"domain_scores_gemma":[0.99267006,0.0012680151,0.0015102286,0.00088722084,0.0034941472,0.00017034968],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02872859,0.00036677,0.0006695485,0.0007203261,0.00017888028,0.00015313334,0.00040818084,0.00041012833,0.0075207697],"category_scores_gemma":[0.0062413923,0.00030335103,0.00015074109,0.00062710827,0.00011341296,0.00075446727,0.00015180396,0.0004129493,0.00031405422],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017288377,0.00006556257,0.0101509895,0.000038126036,0.0000380924,2.4484618e-7,0.0011229385,0.0009770801,0.000003644094,0.00006788881,0.042438444,0.9450797],"study_design_scores_gemma":[0.002308472,0.0002723328,0.22526102,0.0006880607,0.0012918704,0.0000052648597,0.0014654766,0.110418476,0.00015214115,0.013204348,0.6441315,0.0008010747],"about_ca_topic_score_codex":0.000025733705,"about_ca_topic_score_gemma":0.00005592192,"teacher_disagreement_score":0.94427866,"about_ca_system_score_codex":0.00042209204,"about_ca_system_score_gemma":0.0026656357,"threshold_uncertainty_score":0.9999419},"labels":[],"label_agreement":null},{"id":"W2799580554","doi":"10.7939/r3bd9h","title":"Adoption of the Alberta Nutrition Guidelines for Children and Youth: Assessing Organizational Behaviour Change in Childcare Organizations","year":2012,"lang":"en","type":"article","venue":"University of Alberta Library","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Public relations; Organizational change; Business; Psychology; Political science","score_opus":0.10255961661631124,"score_gpt":0.35365832764552585,"score_spread":0.2510987110292146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2799580554","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99434835,0.00009466289,0.00028619575,0.0041637644,0.000103837025,0.00037791685,0.00005655158,0.0000053488393,0.0005633565],"genre_scores_gemma":[0.9962823,0.000055889963,0.0024004008,0.00018038168,0.00007429047,4.5758196e-7,0.00041343062,0.000007800567,0.0005850674],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99909633,0.0000818332,0.00026004767,0.00013915841,0.00032370232,0.00009891471],"domain_scores_gemma":[0.9988954,0.0002695759,0.00024059993,0.00017637438,0.0003740509,0.000044009896],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002682315,0.00007105863,0.00013080217,0.00017696933,0.00014832414,0.00003162082,0.00026530965,0.00006428866,0.00054306124],"category_scores_gemma":[0.00045999786,0.000058472462,0.000038934668,0.00081816333,0.00006258667,0.0020237311,0.00013962414,0.000046083554,0.000004436683],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007742633,0.000099087876,0.98676276,0.0000054513453,0.00000570359,9.348836e-9,0.008662392,0.000020455685,0.0000236025,0.0030423566,0.0008789723,0.0004914598],"study_design_scores_gemma":[0.00053459604,0.000016750653,0.9931548,0.00006061737,0.000028453567,0.0000014589397,0.004783793,0.0005755457,0.00024148819,0.00020425355,0.0003282481,0.00006994762],"about_ca_topic_score_codex":0.0010241218,"about_ca_topic_score_gemma":0.00084478525,"teacher_disagreement_score":0.0063920813,"about_ca_system_score_codex":0.000013306372,"about_ca_system_score_gemma":0.000102217404,"threshold_uncertainty_score":0.59461397},"labels":[],"label_agreement":null},{"id":"W2800395496","doi":"10.1177/1356389018763242","title":"The evaluation of social innovation: A review and integration of the current empirical knowledge base","year":2018,"lang":"en","type":"review","venue":"Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":75,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Empirical research; Knowledge management; Knowledge base; Social innovation; Scale (ratio); Social learning; Perspective (graphical); Public relations; Computer science; Political science","score_opus":0.735361020503894,"score_gpt":0.6846952553233857,"score_spread":0.05066576518050825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2800395496","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014783848,0.99107516,0.00016549493,0.0010946924,0.0011065527,0.0037372555,0.00002689948,0.000006465999,0.0026396567],"genre_scores_gemma":[0.0020497027,0.9965651,0.000041487958,0.00006971597,0.00030366136,0.00061240286,0.00011480591,0.000015048337,0.00022808951],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9819608,0.008051935,0.0030800223,0.0005149441,0.0062072347,0.00018508136],"domain_scores_gemma":[0.98232067,0.0015576759,0.0034916,0.0008422759,0.011757849,0.000029923061],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08993141,0.0002714268,0.00095171126,0.00033570552,0.0004428288,0.0001018824,0.0007263231,0.00012299456,0.0008066486],"category_scores_gemma":[0.018286293,0.00012663752,0.00028981417,0.0036579224,0.0003287219,0.00026726292,0.00019542979,0.00033856486,0.00007970074],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000033094568,0.000052527623,0.000010198817,0.001352405,0.000027472895,2.1335878e-9,0.00034433434,0.0000012537071,5.2038274e-7,0.0009825772,0.018810531,0.9784149],"study_design_scores_gemma":[0.00038427,0.0000958495,0.0017016963,0.0071949116,0.0032132156,0.0000019288075,0.00007722396,0.010307582,0.000005541917,0.006293852,0.9705553,0.00016864366],"about_ca_topic_score_codex":0.0000014479458,"about_ca_topic_score_gemma":0.000060101356,"teacher_disagreement_score":0.9782462,"about_ca_system_score_codex":0.0003575836,"about_ca_system_score_gemma":0.004849209,"threshold_uncertainty_score":0.9899831},"labels":[],"label_agreement":null},{"id":"W2800401326","doi":"10.1177/1098214018765698","title":"Outcomes and Impacts of Development Interventions","year":2018,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":120,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Roads University","funders":"International Fund for Agricultural Development; Consortium of International Agricultural Research Centers; Centre for International Forestry Research; Canada Research Chairs; United Nations Development Programme","keywords":"CLARITY; Psychological intervention; Consistency (knowledge bases); Outcome (game theory); Accountability; Confusion; Management science; Psychology; Computer science; Sociology; Political science; Economics","score_opus":0.2737634216383244,"score_gpt":0.5787112819025034,"score_spread":0.304947860264179,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2800401326","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99097604,0.0000636114,0.006919491,0.0010627599,0.00022952331,0.0000828946,8.281481e-7,0.0000017187499,0.00066312455],"genre_scores_gemma":[0.99255407,0.000013506447,0.0071610655,0.00015662558,0.00004617428,0.0000017148126,6.7665894e-7,0.0000028493553,0.00006332814],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99667937,0.00032731696,0.0010154138,0.00009055112,0.0018050603,0.00008226833],"domain_scores_gemma":[0.9954387,0.00035768538,0.0015249758,0.00014170352,0.0024612339,0.00007569888],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011818907,0.00006126443,0.00024832212,0.00034753414,0.000067655004,0.000043317494,0.00014963512,0.00001190632,0.0010169207],"category_scores_gemma":[0.00220232,0.000039332393,0.000090562506,0.00042057206,0.0002053173,0.00046221333,0.000033248245,0.000054540607,0.00003021261],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042912277,0.00006814596,0.25180614,0.0000027702313,0.000056657536,2.2020177e-7,0.002524343,0.00004020466,0.00048378002,0.00023233889,0.0004708661,0.74427164],"study_design_scores_gemma":[0.00054136215,0.0009014718,0.99006087,0.00006337133,0.00004447654,0.000014693979,0.002282281,0.002044455,0.0012246512,0.001731304,0.0010384527,0.000052634045],"about_ca_topic_score_codex":0.000007969195,"about_ca_topic_score_gemma":0.00003772479,"teacher_disagreement_score":0.744219,"about_ca_system_score_codex":0.000056297216,"about_ca_system_score_gemma":0.0005211114,"threshold_uncertainty_score":0.9998963},"labels":[],"label_agreement":null},{"id":"W2800498576","doi":"10.1186/s13012-018-0715-z","title":"Proceedings of the 4th Biennial Conference of the Society for Implementation Research Collaboration (SIRC) 2017: implementation mechanisms: what makes implementation work and why? part 2","year":2018,"lang":"en","type":"article","venue":"Implementation Science","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Mental Health; University of North Carolina at Chapel Hill; College of Pharmacy, University of Michigan; York University; University of Michigan; University of Denver; University of Washington; Drexel University; Washington State University; Harvard University; U.S. Department of Veterans Affairs; Washington University in St. Louis; Center for Healthcare Organization and Implementation Research; Portland State University; Ohio State University","keywords":"Medicine; Health services research; Health informatics; Health administration; Work (physics); Public health; Nursing","score_opus":0.4554942824456179,"score_gpt":0.625355280973748,"score_spread":0.16986099852813014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2800498576","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98135966,0.00002890064,0.0034185448,0.009483513,0.0012349964,0.004036239,0.0002267302,0.000018141522,0.00019329977],"genre_scores_gemma":[0.9955066,0.00007009627,0.0030519199,0.0006570671,0.00013900157,0.00042349944,0.00003678679,0.000014183764,0.00010084943],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9918035,0.0002628944,0.0017061738,0.00081484724,0.0047802376,0.00063232874],"domain_scores_gemma":[0.9887733,0.00051447155,0.0017472696,0.0005093611,0.008339245,0.0001163898],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017261598,0.00023045063,0.00028241414,0.0003933281,0.0020085108,0.0014805748,0.0012986569,0.00006640789,0.0013693307],"category_scores_gemma":[0.00035325348,0.00015117842,0.00018715802,0.0051082405,0.0014027316,0.004745319,0.00047246352,0.00014028436,0.000006582672],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029102803,0.00013438365,0.14764746,0.00010774656,0.00011580071,6.048489e-8,0.08519035,0.00001792793,0.22918318,0.16757469,0.08705934,0.28267804],"study_design_scores_gemma":[0.0025374936,0.0006218577,0.1572106,0.000057305937,0.000072523195,0.0000021222672,0.4076845,0.00048700557,0.393943,0.02505733,0.012081821,0.00024443195],"about_ca_topic_score_codex":0.00021573562,"about_ca_topic_score_gemma":0.0034968785,"teacher_disagreement_score":0.32249415,"about_ca_system_score_codex":0.00029690255,"about_ca_system_score_gemma":0.0016650399,"threshold_uncertainty_score":0.999556},"labels":[],"label_agreement":null},{"id":"W2801790340","doi":"10.1177/1356389018765487","title":"Theory-based evaluations: Framing the existence of a new theory in evaluation and the rise of the 5th generation","year":2018,"lang":"en","type":"article","venue":"Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Intégré Universitaire de Santé et de Services Sociaux du Saguenay–Lac-Saint-Jean; Université de Sherbrooke; University of Victoria","funders":"","keywords":"Epistemology; Framing (construction); Complementarity (molecular biology); Realism; Sociology; Computer science; Philosophy","score_opus":0.28830792381595954,"score_gpt":0.5359311604701663,"score_spread":0.24762323665420677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2801790340","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96020854,0.0012979815,0.026404109,0.004957583,0.00064242544,0.0030336266,0.000005543953,0.000008794125,0.0034413922],"genre_scores_gemma":[0.9981953,0.000018662413,0.0006308205,0.0004261561,0.00017538865,0.00020625164,0.0000071777968,0.00000878782,0.0003314902],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98093605,0.011423248,0.0013131201,0.00038277914,0.005752627,0.00019215721],"domain_scores_gemma":[0.9910332,0.0038688737,0.0010831376,0.0011110315,0.0028686158,0.000035146444],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12298959,0.00015409176,0.00024806117,0.00022443909,0.00043036835,0.00012472861,0.0006983181,0.00008327469,0.0017113321],"category_scores_gemma":[0.021416653,0.000069813956,0.00011409014,0.0013736546,0.00085816195,0.0004040151,0.00009762762,0.00016725733,0.00002819772],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00050857814,0.00012141381,0.0123663675,0.000012434962,0.000047216385,2.7144022e-8,0.03323808,0.039657474,0.0041656904,0.1441031,0.000825192,0.76495445],"study_design_scores_gemma":[0.0021884877,0.0000692762,0.10523258,0.000044547756,0.00014188897,5.495108e-7,0.0021916716,0.6534495,0.003167833,0.23328385,0.00016444045,0.00006540613],"about_ca_topic_score_codex":0.000078720295,"about_ca_topic_score_gemma":0.000550226,"teacher_disagreement_score":0.764889,"about_ca_system_score_codex":0.00013061018,"about_ca_system_score_gemma":0.00177896,"threshold_uncertainty_score":0.99920124},"labels":[],"label_agreement":null},{"id":"W2802150666","doi":"","title":"Total Quality Management and local government in Canada : practice, problems and prospects","year":2000,"lang":"en","type":"dissertation","venue":"OpenGrey (Institut de l'Information Scientifique et Technique)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Local government; Public administration; Government (linguistics); Quality (philosophy); Political science; Environmental planning; Business; Environmental science; Philosophy; Epistemology","score_opus":0.0445803647035329,"score_gpt":0.3750468840496053,"score_spread":0.3304665193460724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2802150666","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25624585,0.00032583647,0.027546661,0.0028330882,0.0016136247,0.024360357,0.00030039766,0.00014836185,0.68662584],"genre_scores_gemma":[0.9637545,0.0010242871,0.010616023,0.0018113425,0.000027419661,0.0032520574,0.00056545855,0.000028234936,0.018920675],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99274296,0.0004117987,0.0017773851,0.00067417254,0.003948885,0.0004448158],"domain_scores_gemma":[0.9973164,0.00029423513,0.0009965104,0.0006398111,0.0005220388,0.00023100455],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.012490703,0.00038088355,0.0004849699,0.00046192235,0.000313098,0.0014884837,0.00054981664,0.00022015705,0.00043807525],"category_scores_gemma":[0.00077312806,0.0003348537,0.000054835917,0.00093835685,0.000107209395,0.004915885,0.00017963651,0.00056453276,0.00005069397],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044315463,0.00015037911,0.003883832,0.0011536351,0.000053196545,0.00003586824,0.008451362,0.0033649488,0.00009132478,0.020931534,0.01110207,0.9503387],"study_design_scores_gemma":[0.0018303384,0.000098813216,0.17856643,0.0015742683,0.00006336754,0.0000782394,0.018157724,0.011565384,0.0026356115,0.003941535,0.7801664,0.0013219392],"about_ca_topic_score_codex":0.08713621,"about_ca_topic_score_gemma":0.66443056,"teacher_disagreement_score":0.94901675,"about_ca_system_score_codex":0.0018761598,"about_ca_system_score_gemma":0.0028835323,"threshold_uncertainty_score":0.99991035},"labels":[],"label_agreement":null},{"id":"W2802703442","doi":"10.1016/j.socscimed.2018.04.035","title":"A combined theoretical and empirical approach to evidence quality evaluation: A commentary on Deaton and Cartwright","year":2018,"lang":"en","type":"letter","venue":"Social Science & Medicine","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Habitus; Socioeconomic status; Social class; Social stratification; Social status; Sociology; Social position; Social mobility; Social inequality; Social psychology; Embodied cognition; Social capital; Gender studies; Psychology; Cultural capital; Inequality; Demography; Population; Social science; Social relation; Political science","score_opus":0.38564589058277254,"score_gpt":0.5843031532739283,"score_spread":0.1986572626911558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2802703442","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10430638,0.00008874249,0.0002643751,0.8742282,0.0006659477,0.00096596143,0.000010825507,0.000024541265,0.01944503],"genre_scores_gemma":[0.38649723,0.000015664906,0.00009815301,0.6100475,0.003068959,0.00007326643,0.000018943098,0.000008864655,0.00017138301],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.985691,0.0015796835,0.00089956744,0.001344023,0.009936272,0.00054947095],"domain_scores_gemma":[0.99480367,0.0026396213,0.00033849772,0.0006201743,0.0012556451,0.0003423983],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03687319,0.000329197,0.0007191798,0.0004741731,0.0011255374,0.00032682728,0.0010701217,0.00030484423,0.0013126092],"category_scores_gemma":[0.006814762,0.00019946514,0.00006209769,0.0016484375,0.0068461257,0.00039410108,0.0003081139,0.00080193987,0.000054052914],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006580751,0.00003783697,0.0064822547,0.000015978972,0.0000072435355,0.0000023774148,0.010819881,4.3797317e-7,0.000021823078,0.0032502771,0.9680456,0.011250479],"study_design_scores_gemma":[0.0037071055,0.0038825565,0.12899724,0.00078269787,0.00035524624,0.000024377803,0.005575059,0.010532521,0.000062798616,0.10837054,0.7363243,0.001385552],"about_ca_topic_score_codex":0.00007019459,"about_ca_topic_score_gemma":0.000011575716,"teacher_disagreement_score":0.28219086,"about_ca_system_score_codex":0.000352174,"about_ca_system_score_gemma":0.000703619,"threshold_uncertainty_score":0.99960035},"labels":[],"label_agreement":null},{"id":"W2802781340","doi":"10.1177/1098214018763553","title":"Evaluating Social Innovations","year":2018,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Variety (cybernetics); Psychological intervention; Management science; Conceptual framework; Computer science; Knowledge management; Sociology; Engineering ethics; Psychology; Social science; Economics; Engineering","score_opus":0.4567176324915049,"score_gpt":0.6367359267377268,"score_spread":0.18001829424622195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2802781340","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9731865,0.000018389845,0.0129062645,0.0048571792,0.00072452927,0.00014329681,0.0000017995858,0.0000075781595,0.008154453],"genre_scores_gemma":[0.9889687,0.0000024358178,0.008880067,0.0008206981,0.0011505797,0.000005978549,0.0000026032603,0.000007642472,0.00016131654],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.992362,0.0010343203,0.001291858,0.0001798744,0.004962357,0.0001695766],"domain_scores_gemma":[0.9859452,0.0005964832,0.0022153198,0.00022726557,0.010950129,0.000065588356],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.032424934,0.00009744492,0.00027721564,0.00058837526,0.00034786362,0.00016175439,0.00035065945,0.000026425563,0.003952151],"category_scores_gemma":[0.0066091036,0.00007178003,0.000111762034,0.0022922105,0.00033091032,0.0006909236,0.000039206978,0.00015895585,0.0003063791],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000063171734,0.00004459918,0.004868916,4.280241e-7,0.000026935952,3.2161535e-7,0.0025068521,0.0004301437,0.0023995347,0.0011696892,0.0044741505,0.9840153],"study_design_scores_gemma":[0.0033168541,0.0072653242,0.5896171,0.00005132813,0.00028828564,0.00012563792,0.016700009,0.2807485,0.00214496,0.07520051,0.024069246,0.0004722529],"about_ca_topic_score_codex":0.000007162983,"about_ca_topic_score_gemma":0.000013964075,"teacher_disagreement_score":0.983543,"about_ca_system_score_codex":0.00016530743,"about_ca_system_score_gemma":0.0011202603,"threshold_uncertainty_score":0.9969584},"labels":[],"label_agreement":null},{"id":"W2803262589","doi":"","title":"What Language Does a “Plangineer” Speaks? Cross-Disciplinary Expertise and Environmental Governance in Canadian Cities","year":2018,"lang":"en","type":"article","venue":"XIX ISA World Congress of Sociology (July 15-21, 2018)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Corporate governance; Discipline; Political science; Cross disciplinary; Environmental governance; Sociology; Social science; Management; Economics; Data science; Computer science","score_opus":0.04507539961071806,"score_gpt":0.40269436326207375,"score_spread":0.3576189636513557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2803262589","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98802686,0.0033224334,0.0000042448614,0.0023658169,0.002238731,0.00023353827,0.00021491668,0.000017842993,0.0035756226],"genre_scores_gemma":[0.9800901,0.0005339805,0.00014694668,0.00081677374,0.00025730106,0.000033453398,0.0000391472,0.000015601305,0.018066736],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9974982,0.00018509403,0.000655709,0.0005180653,0.00059088477,0.000552035],"domain_scores_gemma":[0.9984795,0.00039645535,0.00031605872,0.00051335373,0.00007559211,0.00021902798],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014308096,0.0002365987,0.00042879416,0.00031769893,0.00023102765,0.00017128176,0.0005848049,0.0001673981,0.0057574334],"category_scores_gemma":[0.00017786882,0.00017310586,0.00007847192,0.0001981141,0.0019901772,0.0009869215,0.00021570445,0.00022648077,0.00033067417],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014993756,0.00009429989,0.918114,0.000026883747,0.00006169429,0.00005978393,0.03982847,0.000041248186,0.0011857619,0.0017953372,0.029525703,0.009116864],"study_design_scores_gemma":[0.0014559467,0.00021376381,0.93282115,0.0001553999,0.000015535023,0.000012872508,0.021283716,0.0023107056,0.0017542425,0.002711798,0.03679035,0.0004745199],"about_ca_topic_score_codex":0.004961144,"about_ca_topic_score_gemma":0.20438024,"teacher_disagreement_score":0.1994191,"about_ca_system_score_codex":0.0002178056,"about_ca_system_score_gemma":0.00020985346,"threshold_uncertainty_score":0.99515146},"labels":[],"label_agreement":null},{"id":"W2803278848","doi":"10.4212/cjhp.v52i3.1816","title":"Are You a Member of CSHP","year":2018,"lang":"en","type":"article","venue":"The Canadian Journal of Hospital Pharmacy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Business; Biology; Business administration","score_opus":0.2237177174749129,"score_gpt":0.48676654599771185,"score_spread":0.263048828522799,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2803278848","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9652385,0.00026008522,0.000040073734,0.019315548,0.0018328273,0.000092149035,0.000014476303,0.0000018640123,0.013204491],"genre_scores_gemma":[0.997283,0.00000984448,0.000078742276,0.0011010881,0.0005060273,7.809811e-7,2.1251807e-7,0.0000061380206,0.0010141749],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.997959,0.00013619654,0.0006127354,0.000091620954,0.0009989402,0.00020151117],"domain_scores_gemma":[0.99674314,0.00015794349,0.00094890106,0.00025795557,0.0015339991,0.0003580361],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0034238158,0.00008255556,0.000192011,0.00024035115,0.00023489045,0.00013663509,0.0008795028,0.000018277877,0.006862625],"category_scores_gemma":[0.00079465937,0.00004600215,0.00012749902,0.00043738887,0.00031422652,0.00040660243,0.000022913951,0.00018165413,0.0002786131],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010427414,0.00009695574,0.4704791,0.0000076000656,0.00018220667,0.0000941249,0.011312982,0.00026081572,0.00033787228,0.0021370484,0.458554,0.05643301],"study_design_scores_gemma":[0.0017275581,0.00069870043,0.22434236,0.00007002254,0.000080182406,0.000091910595,0.0036505263,0.0015575049,0.005991746,0.014946683,0.74659413,0.00024866703],"about_ca_topic_score_codex":0.0017290325,"about_ca_topic_score_gemma":0.019039357,"teacher_disagreement_score":0.28804013,"about_ca_system_score_codex":0.00007740324,"about_ca_system_score_gemma":0.0014045794,"threshold_uncertainty_score":0.9988606},"labels":[],"label_agreement":null},{"id":"W2804858062","doi":"10.18848/1447-9494/cgp/v17i04/46990","title":"Ontario Principal Preparation Programs: How are Aspiring School Administrators Trained?","year":2010,"lang":"en","type":"article","venue":"The International Journal of Learning Annual Review","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Principal (computer security); Medical education; Mathematics education; Psychology; Pedagogy; Political science; Computer science; Medicine; Computer security","score_opus":0.13223598463215827,"score_gpt":0.48303113093327715,"score_spread":0.35079514630111885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2804858062","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9516814,0.0016264274,0.00065763184,0.037677407,0.0020886958,0.00036279464,0.0000032368616,0.00002060821,0.0058818352],"genre_scores_gemma":[0.99033225,0.00067271903,0.0006077506,0.00080792385,0.0005538739,0.000010150331,0.000003639018,0.000007440983,0.00700426],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99555516,0.000304336,0.00090512296,0.00017380982,0.0029158455,0.00014572995],"domain_scores_gemma":[0.9949955,0.00036267514,0.0017506938,0.00023182033,0.0025167894,0.00014251977],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01043613,0.00012953854,0.00028881663,0.00013712318,0.00014561698,0.0005205574,0.0013085013,0.00004696935,0.0022288163],"category_scores_gemma":[0.0062037907,0.000072595045,0.00023626629,0.0002233782,0.000063387124,0.00081854075,0.00008656493,0.0010423161,0.00016636858],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003085161,0.00035127398,0.32797238,0.00009469583,0.00037639285,0.000071241906,0.008443976,0.0010937382,0.00047756804,0.002005982,0.021244492,0.6375597],"study_design_scores_gemma":[0.00031371007,0.0003211817,0.033415403,0.00091284135,0.000042312226,0.00025417798,0.0018725146,0.00029735846,0.000060006485,0.00032565588,0.9620695,0.00011531192],"about_ca_topic_score_codex":0.000042542473,"about_ca_topic_score_gemma":0.002471524,"teacher_disagreement_score":0.94082505,"about_ca_system_score_codex":0.00012487372,"about_ca_system_score_gemma":0.0010014174,"threshold_uncertainty_score":0.9986833},"labels":[],"label_agreement":null},{"id":"W2805310559","doi":"10.11575/prism/38768","title":"Initial Teacher Education in Ontario: The First Year of Four-Semester Teacher Education Programs","year":2017,"lang":"en","type":"article","venue":"PRISM (University of Calgary)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada; Ministère de l’Éducation, Gouvernement de l’Ontario; Office of International Science and Engineering; Brock University; Government of Ontario; University of Windsor; American Educational Research Association","keywords":"Mathematics education; Pedagogy; Teacher education; Medical education; Psychology; Political science; Medicine","score_opus":0.10285964955849525,"score_gpt":0.37510539373086565,"score_spread":0.2722457441723704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2805310559","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9024859,0.000014752056,0.0017984051,0.0022606016,0.00028691697,0.00029696667,7.835486e-8,0.0000052280766,0.09285112],"genre_scores_gemma":[0.96301347,0.000005819958,0.003249444,0.000051584557,0.00002166297,0.0000019233455,0.00000558155,0.0000038491394,0.033646654],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9987869,0.00009267291,0.00020942437,0.00018666075,0.0006193848,0.00010496037],"domain_scores_gemma":[0.99868214,0.000044061115,0.0004102715,0.0006062336,0.00021469781,0.000042608626],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001265152,0.0000723476,0.00014649991,0.00014322744,0.00024514535,0.00006806514,0.0007703433,0.000072835704,0.0013821619],"category_scores_gemma":[0.000121320976,0.000058931008,0.000074413874,0.00009267666,0.00018319815,0.00058932713,0.00014074246,0.00017878486,0.00006293275],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026735868,0.00028214196,0.6186407,0.0000034935924,0.000004317884,2.3221769e-7,0.0032616416,4.1786896e-7,0.0000053725325,0.00039858092,0.002658322,0.374718],"study_design_scores_gemma":[0.00034756085,0.00004845574,0.9293019,0.000033430275,0.000014819794,6.972735e-7,0.0016012283,0.001585091,0.000010663263,0.0018840259,0.06510492,0.00006718708],"about_ca_topic_score_codex":0.04114206,"about_ca_topic_score_gemma":0.074805215,"teacher_disagreement_score":0.3746508,"about_ca_system_score_codex":0.000111010486,"about_ca_system_score_gemma":0.0014986871,"threshold_uncertainty_score":0.99953073},"labels":[],"label_agreement":null},{"id":"W2806047900","doi":"10.1057/s41599-018-0098-4","title":"Navigating the politics of evidence-informed policymaking: strategies of influential policy actors in Ontario","year":2018,"lang":"en","type":"article","venue":"Palgrave Communications","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Framing (construction); Persuasion; Elite; Politics; Public relations; Context (archaeology); Political science; Sociology; Social psychology; Psychology; Law","score_opus":0.5283007954504657,"score_gpt":0.590458830676522,"score_spread":0.06215803522605634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2806047900","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9602684,0.0000932826,0.00028579644,0.0062135,0.00008058138,0.0002809007,0.000010378099,0.000010831589,0.032756373],"genre_scores_gemma":[0.9977552,0.000073692216,0.0018248154,0.00017147038,0.000045387424,0.000019552752,0.0000060399366,0.0000049791483,0.000098807024],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9973338,0.00036042152,0.0010911594,0.00012744022,0.0008715239,0.00021562181],"domain_scores_gemma":[0.9934231,0.002862424,0.0006847967,0.0020431732,0.00093581213,0.000050712853],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024253328,0.00010380203,0.00022189798,0.00020607756,0.00031522644,0.00011502419,0.0021803847,0.000057856134,0.00027234378],"category_scores_gemma":[0.0032271412,0.000063122134,0.00009103663,0.0012051652,0.00090574933,0.00026231987,0.0005091916,0.00037177576,0.00002970478],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014301488,0.00006185935,0.39540398,0.000011193476,0.000028786357,5.9418635e-8,0.06972567,0.00020576674,0.0007435828,0.51743084,0.0000689427,0.016304988],"study_design_scores_gemma":[0.00029385343,0.00013578834,0.86983657,0.00030274852,0.000016149219,0.0000018318981,0.024379391,0.0030133422,0.0013943381,0.09577611,0.004734516,0.00011533556],"about_ca_topic_score_codex":0.10545979,"about_ca_topic_score_gemma":0.43543363,"teacher_disagreement_score":0.4744326,"about_ca_system_score_codex":0.0001811602,"about_ca_system_score_gemma":0.0030246826,"threshold_uncertainty_score":0.900497},"labels":[],"label_agreement":null},{"id":"W2807339672","doi":"10.7939/r38w3876s","title":"Decision Making and the Superintendency","year":2014,"lang":"en","type":"article","venue":"University of Alberta Library","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Accountability; Jurisdiction; Public relations; Corporate governance; Political science; Government (linguistics); Sample (material); Public administration; Sociology; Business; Law","score_opus":0.03864387725000259,"score_gpt":0.32025719113294665,"score_spread":0.2816133138829441,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2807339672","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79022634,0.00003668268,0.004847188,0.006352131,0.00012152264,0.000080950565,5.4544563e-7,0.00000963804,0.19832501],"genre_scores_gemma":[0.98890907,0.000043686978,0.0024189008,0.00036979516,0.000014782247,3.916413e-8,7.906638e-7,0.00000229851,0.008240668],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99910605,0.00014614106,0.0001325344,0.00014485247,0.00040229934,0.000068152774],"domain_scores_gemma":[0.99681044,0.0027686092,0.00008328369,0.00026571224,0.000039181356,0.00003278634],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00074128085,0.000046724435,0.00011855989,0.00008966097,0.0001462924,0.00005615218,0.0004387991,0.000026883277,0.003891461],"category_scores_gemma":[0.00036012786,0.000029364039,0.000051662133,0.00018661446,0.00019942386,0.00073505734,0.00023506688,0.00005341994,0.00010509929],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00084345834,0.00004494343,0.22613947,0.000008544241,0.000028113616,0.0000017688104,0.017508065,0.0002087484,0.000016695043,0.39616677,0.03195046,0.32708296],"study_design_scores_gemma":[0.0028656533,0.00011036495,0.26860437,0.00007390541,0.000024882484,0.000008767049,0.008545793,0.087119326,0.000054446326,0.1401776,0.49223176,0.00018312002],"about_ca_topic_score_codex":0.000068679066,"about_ca_topic_score_gemma":0.000109688175,"teacher_disagreement_score":0.4602813,"about_ca_system_score_codex":0.0000028206064,"about_ca_system_score_gemma":0.000037405294,"threshold_uncertainty_score":0.9970191},"labels":[],"label_agreement":null},{"id":"W2809604660","doi":"10.7202/1047141ar","title":"La conciliation des pressions internes et externes dans la mise en oeuvre de la gestion axée sur les résultats par des directions d’établissement d’enseignement","year":2018,"lang":"fr","type":"article","venue":"Éducation et francophonie","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.08552784719839832,"score_gpt":0.4305855913622313,"score_spread":0.34505774416383295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2809604660","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9066819,0.0025881035,0.043697722,0.0068391045,0.0038526,0.00063999573,0.000099147685,0.00014711465,0.035454296],"genre_scores_gemma":[0.9707807,0.0041528926,0.0060876026,0.0005002278,0.00039956448,0.0003749816,0.00007895408,0.00004519528,0.017579932],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99109733,0.0054544457,0.0010180493,0.00073166064,0.0012026991,0.00049580703],"domain_scores_gemma":[0.99225736,0.004824955,0.00053920236,0.00060377974,0.0014966157,0.000278102],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010026141,0.0004166427,0.00035269628,0.00039059724,0.0010387043,0.0008444389,0.00050067797,0.00043862913,0.004346398],"category_scores_gemma":[0.004073281,0.00037865312,0.00017204536,0.0009558777,0.0013514224,0.0015276681,0.00014469876,0.0004971991,0.0005268765],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014446182,0.0023157536,0.07137762,0.00022942542,0.00014759893,0.0000089127925,0.45753947,0.0027054588,0.013475618,0.008451231,0.03391908,0.40968537],"study_design_scores_gemma":[0.0011032948,0.000262985,0.61295336,0.0010868078,0.00010466342,0.00005629761,0.03113263,0.0100117745,0.006798946,0.008084354,0.32797408,0.0004308036],"about_ca_topic_score_codex":0.0052734395,"about_ca_topic_score_gemma":0.018761316,"teacher_disagreement_score":0.54157573,"about_ca_system_score_codex":0.00111804,"about_ca_system_score_gemma":0.0020857938,"threshold_uncertainty_score":0.99986655},"labels":[],"label_agreement":null},{"id":"W2809729443","doi":"10.1080/15236803.2018.1473024","title":"Critical gaps in public policy programs in Canada: Identifying subject areas for graduate training in rural policy","year":2018,"lang":"en","type":"article","venue":"Journal of Public Affairs Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Brandon University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Coursework; Public policy; Public administration; Policy analysis; Political science; Policy studies; Subject (documents); Politics; Rural area; Education policy; Rural management; Economic growth; Public relations; Rural development; Higher education; Sociology; Pedagogy; Economics; Library science; Geography","score_opus":0.36770038066511457,"score_gpt":0.5067593930706427,"score_spread":0.1390590124055281,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2809729443","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90516144,0.00008060398,0.0007842548,0.08871723,0.0013157439,0.00035489854,0.000002854584,0.000005658458,0.0035773],"genre_scores_gemma":[0.99700826,0.000021134483,0.0011542009,0.00038209703,0.0012330349,0.00006043886,0.00000844675,0.000013049987,0.00011934815],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99540603,0.0004816381,0.0016012312,0.00023800242,0.0016342325,0.00063883874],"domain_scores_gemma":[0.99625087,0.0007257404,0.0006325269,0.00024035416,0.001840068,0.00031045746],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010855763,0.00015482273,0.00037276975,0.0034233606,0.00011483808,0.0006869963,0.00063097844,0.00007250169,0.00013127588],"category_scores_gemma":[0.017229404,0.00012895132,0.00009599195,0.003626568,0.000111998525,0.0024644819,0.00004646594,0.0003414523,0.000007768909],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044444576,0.0003978669,0.34489825,0.000021387626,0.0000115034745,0.000003406601,0.012393746,0.000023564888,0.00008268596,0.04236057,0.0025313727,0.5972312],"study_design_scores_gemma":[0.0013686912,0.00026527172,0.7091378,0.00024089022,0.0000063624775,0.00009224747,0.19956584,0.0036668505,0.0000493292,0.08013068,0.005220125,0.00025591743],"about_ca_topic_score_codex":0.14580281,"about_ca_topic_score_gemma":0.8219751,"teacher_disagreement_score":0.67617226,"about_ca_system_score_codex":0.0030497643,"about_ca_system_score_gemma":0.058162175,"threshold_uncertainty_score":0.9910489},"labels":[],"label_agreement":null},{"id":"W2810073460","doi":"10.1007/978-3-319-77407-7_29","title":"Performance of the Ontario (Canada) Higher-education System: Measuring Only What Matters","year":2018,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mandate; Government (linguistics); Equity (law); Higher education; Ranking (information retrieval); Quality (philosophy); Performance measurement; Sustainability; Performance indicator; Business; Political science; Public economics; Public relations; Public administration; Accounting; Actuarial science; Economic growth; Economics; Marketing; Computer science","score_opus":0.15276911903972729,"score_gpt":0.34969285757743285,"score_spread":0.19692373853770556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2810073460","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054599106,0.00011099966,0.00000620577,0.00278127,0.007115471,0.0004058936,0.0000049934433,0.000018731589,0.9349573],"genre_scores_gemma":[0.24438968,0.000022812226,0.00008836895,0.0015880566,0.00016690792,0.0000070097276,0.00000513536,0.000016169044,0.7537159],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9945392,0.000055123393,0.00094908004,0.00041857886,0.0038558377,0.00018215578],"domain_scores_gemma":[0.99674875,0.00014903051,0.00090272934,0.0011437025,0.0009715417,0.00008425182],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017326677,0.0002583807,0.0003844998,0.00016268759,0.00022246613,0.00026714324,0.0010907723,0.00014485553,0.028668825],"category_scores_gemma":[0.000016060028,0.00015176214,0.00014534441,0.00009241162,0.00011295713,0.000633325,0.00016450745,0.00025144898,0.00045329306],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012356514,0.00008031103,0.044670288,0.0005665599,0.00028253163,0.0000014854667,0.0028512902,0.0003573967,0.000048475267,0.11758664,0.72087926,0.11255218],"study_design_scores_gemma":[0.00013582107,0.0000558281,0.042826433,0.0011901015,0.00005359162,0.000010126607,0.00060613645,0.00028670224,0.00013762122,0.0007455303,0.9536694,0.0002826531],"about_ca_topic_score_codex":0.11473898,"about_ca_topic_score_gemma":0.84413576,"teacher_disagreement_score":0.7293968,"about_ca_system_score_codex":0.0012786866,"about_ca_system_score_gemma":0.008556295,"threshold_uncertainty_score":0.9970643},"labels":[],"label_agreement":null},{"id":"W2810492838","doi":"10.1057/978-1-137-35230-9_9","title":"The Integrated Capabilities Framework: Exploring Multiculturalism and Human Well-Being in Participatory Settings","year":2019,"lang":"en","type":"book-chapter","venue":"Palgrave Macmillan UK eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Multiculturalism; Citizen journalism; Sociology; Engineering ethics; Political science; Engineering; Pedagogy","score_opus":0.16016281494334178,"score_gpt":0.391543364852403,"score_spread":0.2313805499090612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2810492838","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19001873,0.0004503494,0.000017212005,0.00047802628,0.0009364678,0.0010110033,0.000020285186,0.000074853124,0.80699307],"genre_scores_gemma":[0.98141855,0.00012163101,0.00015195877,0.00033997756,0.00015415926,0.00009839017,0.000014654845,0.00004451372,0.017656172],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99576896,0.00022422073,0.0012718035,0.00076591055,0.0014491372,0.0005199817],"domain_scores_gemma":[0.9956154,0.0023773687,0.00052886986,0.00094274007,0.00038600218,0.00014961517],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0037355865,0.0004948634,0.00063226774,0.0003178713,0.00049505424,0.00054335094,0.00066584727,0.00031326278,0.0007298429],"category_scores_gemma":[0.000572304,0.00029637502,0.00017666155,0.00005642901,0.000426892,0.000007526557,0.00030589593,0.00085306284,0.0003188036],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019213692,4.0765045e-7,0.004556637,0.00002849475,0.000039293303,0.00000791092,0.012630129,0.000016491755,0.00007769756,0.97281617,0.000037519432,0.009770012],"study_design_scores_gemma":[0.0003667547,0.00007655804,0.0073778294,0.0005455406,0.000034128185,0.0000056427098,0.0064687924,0.0006320235,0.00016589336,0.9659942,0.017799007,0.0005336242],"about_ca_topic_score_codex":0.0001287914,"about_ca_topic_score_gemma":0.0010902617,"teacher_disagreement_score":0.79139984,"about_ca_system_score_codex":0.00015774107,"about_ca_system_score_gemma":0.00014586294,"threshold_uncertainty_score":0.99994886},"labels":[],"label_agreement":null},{"id":"W2810537707","doi":"","title":"Contribution à une observation critique des pratiques collaboratives","year":2019,"lang":"fr","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"L'Alliance Boviteq","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.07135766949411573,"score_gpt":0.3847160045655593,"score_spread":0.3133583350714436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2810537707","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44950035,0.0031412418,0.3930392,0.096156895,0.0011450973,0.001928155,0.00028908686,0.00024702988,0.054552943],"genre_scores_gemma":[0.87046754,0.0037945486,0.05622657,0.0006506942,0.00007975912,0.00025851384,0.0011546342,0.00006136087,0.067306355],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9700099,0.02328814,0.002059133,0.0016330539,0.0022586288,0.0007511237],"domain_scores_gemma":[0.9591142,0.0072017065,0.0019263228,0.0029885138,0.02839455,0.00037468344],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.033031803,0.00072740903,0.0009709386,0.00042471272,0.0012207141,0.0021820501,0.0021447747,0.0007822422,0.0018766096],"category_scores_gemma":[0.018352693,0.0007196719,0.00037998162,0.0024462696,0.0010417604,0.0017105215,0.0011072892,0.0010825945,0.000936691],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000064520835,0.0010299202,0.033015355,0.00024624032,0.00015109168,0.000003953599,0.034764748,0.0012971963,0.008121282,0.8453137,0.0036703206,0.07232166],"study_design_scores_gemma":[0.0028325228,0.000008934145,0.21468464,0.008590999,0.0002186628,0.000022764792,0.006140234,0.21484132,0.17387807,0.1234338,0.2534166,0.0019314749],"about_ca_topic_score_codex":0.0027869768,"about_ca_topic_score_gemma":0.014183671,"teacher_disagreement_score":0.7218799,"about_ca_system_score_codex":0.00074130984,"about_ca_system_score_gemma":0.0034834114,"threshold_uncertainty_score":0.9998412},"labels":[],"label_agreement":null},{"id":"W2810759134","doi":"10.3138/cjpe.33.1.171","title":"Hallie Preskill and Darlene Russ-Eft. (2016). <i>Building Evaluation Capacity: Activities for Teaching and Training</i> . 2nd ed.","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Training (meteorology); Sociology; Physics","score_opus":0.41552976865334557,"score_gpt":0.5066036827221413,"score_spread":0.09107391406879572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2810759134","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98489696,0.0010985237,0.0068154344,0.0021315473,0.0009715791,0.0018865152,0.000022173928,0.000012312132,0.002164947],"genre_scores_gemma":[0.9724831,0.00002903265,0.026318451,0.0002464341,0.0006517839,0.00013648655,0.000010207149,0.000017011329,0.00010750128],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99547756,0.00092143903,0.0008644582,0.00034764508,0.0020064295,0.0003824472],"domain_scores_gemma":[0.99514854,0.00078928634,0.0008246227,0.00024324161,0.0025093406,0.00048498382],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04072903,0.00018424231,0.00032070107,0.00063409784,0.0008565719,0.00083603046,0.00026620584,0.00011634035,0.00048473064],"category_scores_gemma":[0.007307568,0.00015075042,0.00008303573,0.00022504399,0.00035899755,0.0014889393,0.000020020185,0.00028285556,0.0000041013786],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030283485,0.000019617597,0.0021137912,0.000009356621,0.000040239975,4.4495678e-7,0.0077104876,0.00016593415,0.0003830463,0.0007895817,0.0029318137,0.9858054],"study_design_scores_gemma":[0.0063037467,0.003913138,0.049012747,0.0004926115,0.0008389927,0.00025892406,0.018221028,0.55820525,0.0010381668,0.08966454,0.27127668,0.00077416043],"about_ca_topic_score_codex":0.00039047835,"about_ca_topic_score_gemma":0.009109433,"teacher_disagreement_score":0.98503125,"about_ca_system_score_codex":0.00032574695,"about_ca_system_score_gemma":0.0034114087,"threshold_uncertainty_score":0.98777133},"labels":[],"label_agreement":null},{"id":"W2810879288","doi":"10.3138/cjpe.42116","title":"Using Logic Models and the Action Model/Change Model Schema in Planning the Learning Community Program: A Comparative Case Study","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Schema (genetic algorithms); Logic model; Computer science; Strengths and weaknesses; Logic program; Management science; Action (physics); Theory of change; Artificial intelligence; Process management; Knowledge management; Data science; Machine learning; Psychology; Logic programming; Sociology; Engineering; Social psychology","score_opus":0.9477306850220157,"score_gpt":0.6849694826574051,"score_spread":0.26276120236461065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2810879288","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9817613,0.00019929184,0.014129663,0.00060431194,0.00010896921,0.0028175893,0.000001086136,0.0000086177715,0.00036920587],"genre_scores_gemma":[0.9954032,0.000002377586,0.004129612,0.00013336804,0.00008724578,0.00022249369,0.0000016990567,0.00000727399,0.000012731555],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9943299,0.0032848977,0.0007350776,0.00016159206,0.0012321825,0.00025634965],"domain_scores_gemma":[0.9965197,0.00044875074,0.00069037464,0.00028154455,0.0018853834,0.00017427639],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.029921554,0.00014074324,0.00027798425,0.0004101466,0.0014334745,0.00058870995,0.0003645508,0.00006162608,0.00002844396],"category_scores_gemma":[0.0006666227,0.000077723606,0.00006168794,0.0007302986,0.00038942217,0.0010652675,0.000042600357,0.0007604981,0.0000020735101],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007665419,0.00010682781,0.007909619,0.0000023815285,0.000025416728,0.000011292352,0.1150244,0.7675112,0.0000040564146,0.00021341098,0.000030480685,0.109084286],"study_design_scores_gemma":[0.0014612635,0.00054872857,0.0013274628,0.00003576399,0.00007681399,0.0002449971,0.09261434,0.891412,0.0000027021988,0.012160245,0.000035452143,0.00008021186],"about_ca_topic_score_codex":0.007919003,"about_ca_topic_score_gemma":0.11437771,"teacher_disagreement_score":0.12390085,"about_ca_system_score_codex":0.00030883652,"about_ca_system_score_gemma":0.0014232375,"threshold_uncertainty_score":0.99986655},"labels":[],"label_agreement":null},{"id":"W2810908922","doi":"10.1080/15236803.2006.12001449","title":"Canadian Public Policy Analysis and Public Policy Programs: A Comparative Perspective","year":2006,"lang":"en","type":"article","venue":"Journal of Public Affairs Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Carleton University; Simon Fraser University","funders":"","keywords":"Policy analysis; Public policy; Policy studies; Public administration; Political science; Context (archaeology); Curriculum; Perspective (graphical); Education policy; Public relations; Higher education; Geography; Law","score_opus":0.13789251001622943,"score_gpt":0.4787830098492154,"score_spread":0.34089049983298597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2810908922","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48894235,0.00079788914,0.0030621625,0.40784714,0.00046979214,0.00042728003,0.000016985588,0.000026077645,0.09841033],"genre_scores_gemma":[0.99461204,0.000044507942,0.0014567189,0.0004276941,0.0012887568,0.000025193904,0.000033473876,0.000010503924,0.0021011347],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.995356,0.0006425946,0.00116341,0.00037079176,0.0018786952,0.0005884889],"domain_scores_gemma":[0.9905029,0.00031392288,0.001349492,0.00041982875,0.0064545358,0.0009593488],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0050825067,0.0002208036,0.00052204146,0.0094572585,0.00047624102,0.0024607931,0.0007070734,0.000116522795,0.000716329],"category_scores_gemma":[0.003214323,0.00016874456,0.0002728378,0.009979284,0.00020827392,0.003035967,0.000055782926,0.000309427,0.000051998755],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009777151,0.0008271083,0.4374822,0.0000039139068,0.00045466013,0.0000016860031,0.005284816,0.000048029135,0.000028277762,0.4353434,0.021264669,0.09925143],"study_design_scores_gemma":[0.000792427,0.00034305046,0.5433039,0.000016347265,0.00019455215,0.0001190912,0.19035977,0.0023652515,0.000016814649,0.0868845,0.17518646,0.00041781203],"about_ca_topic_score_codex":0.09977248,"about_ca_topic_score_gemma":0.39138314,"teacher_disagreement_score":0.50566965,"about_ca_system_score_codex":0.0028861617,"about_ca_system_score_gemma":0.034983587,"threshold_uncertainty_score":0.99857473},"labels":[],"label_agreement":null},{"id":"W2811284056","doi":"10.3138/cjpe.33.1.168","title":"Colin Robson. (2017). <i>Small-Scale Evaluation: Principles and Practice</i> . 2nd ed.","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University; University of Waterloo","funders":"","keywords":"Scale (ratio); Psychology; Sociology; Applied psychology; Psychoanalysis; Geography; Cartography","score_opus":0.4912241652614992,"score_gpt":0.5469421384034869,"score_spread":0.05571797314198773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2811284056","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8887343,0.006920687,0.0043371245,0.02406544,0.0044455905,0.0053121136,0.000027681492,0.000037229474,0.06611983],"genre_scores_gemma":[0.9730451,0.00009546449,0.024455061,0.000849152,0.00097576855,0.0001239315,0.000016662972,0.000017334138,0.00042153415],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99289495,0.001621646,0.001250312,0.0003604044,0.0034917619,0.00038089894],"domain_scores_gemma":[0.98466134,0.00079579995,0.001312239,0.0004539389,0.012053107,0.00072356354],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05080273,0.00018134424,0.00029737764,0.0005497739,0.0005145842,0.00089528423,0.00050370954,0.00013185332,0.0045615905],"category_scores_gemma":[0.015495425,0.00014539731,0.00009852074,0.00074165856,0.00033387155,0.0016240836,0.000032317217,0.00024833623,0.00019116346],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008033689,0.00007703857,0.010419814,0.0000056854033,0.00005331878,0.0000063074544,0.0026323427,0.0009693421,0.000080880134,0.00051009667,0.018974837,0.96619],"study_design_scores_gemma":[0.0022843245,0.0015562455,0.08029883,0.00009794321,0.0004285792,0.0004768852,0.0039356346,0.15209009,0.00019604294,0.0066832486,0.7516378,0.000314348],"about_ca_topic_score_codex":0.000401122,"about_ca_topic_score_gemma":0.03967019,"teacher_disagreement_score":0.9658756,"about_ca_system_score_codex":0.0004675948,"about_ca_system_score_gemma":0.008665908,"threshold_uncertainty_score":0.996954},"labels":[],"label_agreement":null},{"id":"W281362470","doi":"10.3138/cjpe.23.004","title":"Challenges in Applying Indigenous Evaluation Practices in Mainstream Grant Programs to Indigenous Communities","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Indigenous; Mainstream; Government (linguistics); Substance abuse prevention; Competence (human resources); Cultural competence; Traditional knowledge; Political science; Culturally appropriate; Public relations; Substance use; Sociology; Psychology; Medicine; Pedagogy; Gerontology; Social psychology","score_opus":0.6836246640574786,"score_gpt":0.5359148392352847,"score_spread":0.14770982482219386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W281362470","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9874831,0.003014898,0.000053148,0.0011996025,0.000467846,0.0053914245,0.000003227307,0.000012009694,0.0023747478],"genre_scores_gemma":[0.99566954,0.00039184786,0.002439309,0.00012468305,0.000116357514,0.0011869711,0.00003243436,0.000018866305,0.00001998828],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.990861,0.0023435503,0.0016722241,0.00031553773,0.004174825,0.0006328358],"domain_scores_gemma":[0.993859,0.00045303363,0.0016524073,0.0005076333,0.0030332222,0.00049469015],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.041886877,0.00022860302,0.00045645054,0.0028721574,0.00042561057,0.00036328787,0.00085173553,0.00015545532,0.00030928114],"category_scores_gemma":[0.0034687035,0.00019820184,0.000105307365,0.0018952156,0.00012316594,0.0013000737,0.000029974368,0.0005348659,0.000062017585],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029644563,0.00018659937,0.20170644,0.0000075378057,0.0000137263505,0.000026981354,0.06978314,0.006109251,0.0000058644982,0.000025210951,0.000023555047,0.722082],"study_design_scores_gemma":[0.0028897785,0.0019354913,0.86680204,0.00034294525,0.0000798074,0.00040500044,0.08073063,0.029028755,0.000037726026,0.004880816,0.01242668,0.000440351],"about_ca_topic_score_codex":0.0118608,"about_ca_topic_score_gemma":0.63693124,"teacher_disagreement_score":0.7216417,"about_ca_system_score_codex":0.0015564553,"about_ca_system_score_gemma":0.010329314,"threshold_uncertainty_score":0.9952812},"labels":[],"label_agreement":null},{"id":"W2847723360","doi":"","title":"Assessment Policy/Administration Trends in the US & Canada","year":2018,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Administration (probate law); Political science; Public administration; Law","score_opus":0.19524768186011776,"score_gpt":0.5557593032862372,"score_spread":0.3605116214261195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2847723360","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4128862,0.0000018694628,0.00041263297,0.030453283,0.0002340697,0.00006362227,0.0000034107773,0.000006400701,0.55593854],"genre_scores_gemma":[0.98314536,0.0000011344257,0.00033574924,0.0064998805,0.00021715541,0.000011976247,0.0000064769956,0.0000019435959,0.0097803045],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.997356,0.00020095779,0.00036854332,0.00018487754,0.0017308631,0.00015878295],"domain_scores_gemma":[0.9990713,0.0002426365,0.00008784656,0.00038837464,0.00016787281,0.000041988857],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003100023,0.00006685468,0.00008456426,0.00020429546,0.00013668528,0.00020255924,0.00045203502,0.000022499606,0.0063375654],"category_scores_gemma":[0.0001363173,0.000034551493,0.000023930244,0.0012035153,0.00004517727,0.00018753693,0.000025496396,0.00007322126,0.000083983556],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018887273,0.000142174,0.26188,9.719746e-7,0.000008245435,0.000007948921,0.0010592599,0.00013898301,0.00011036712,0.12585962,0.30712965,0.30364388],"study_design_scores_gemma":[0.00014231437,0.00010227986,0.7966557,9.266075e-7,0.0000011906355,0.00000359085,0.00084870297,0.0062759924,0.00009563118,0.0014718855,0.19435062,0.000051125153],"about_ca_topic_score_codex":0.22051787,"about_ca_topic_score_gemma":0.9652125,"teacher_disagreement_score":0.74469465,"about_ca_system_score_codex":0.00015917947,"about_ca_system_score_gemma":0.0020924932,"threshold_uncertainty_score":0.9945708},"labels":[],"label_agreement":null},{"id":"W285038260","doi":"","title":"Reflections on the \"Policy-Relevant Turn\" in Research","year":2003,"lang":"en","type":"article","venue":"Social Justice A Journal of Crime Conflict & World Order","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Relevance (law); Policy Sciences; Sociology; Public policy; Social policy; Discipline; Politics; Political science; Public relations; Social science; Public administration; Law","score_opus":0.6153319296370796,"score_gpt":0.6448795132282173,"score_spread":0.029547583591137738,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W285038260","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.104047894,0.0005839837,0.00072838407,0.12026155,0.0020441546,0.00050543656,0.000005624703,0.000015462347,0.7718075],"genre_scores_gemma":[0.9792999,0.00013719183,0.00032613287,0.0051187077,0.00096870563,0.000011186784,2.8203365e-7,0.000014867295,0.01412303],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9931555,0.002081876,0.0010545084,0.00020921315,0.0030618021,0.00043713042],"domain_scores_gemma":[0.99136573,0.004822996,0.00047623512,0.00030683112,0.0029052524,0.0001229458],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.019664641,0.00013919907,0.00031344578,0.001448747,0.00078705576,0.00033756712,0.0007086596,0.000071367904,0.00304909],"category_scores_gemma":[0.017626844,0.000082853534,0.00015215139,0.004778817,0.00024601835,0.0002998804,0.0000516734,0.0012517525,0.00035971813],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025361672,0.00038699448,0.00056926167,0.000012505211,0.00006386329,0.000024956817,0.019127058,0.0007737275,0.0012297133,0.84135985,0.12687515,0.009323328],"study_design_scores_gemma":[0.0008409378,0.00020253556,0.009721973,0.000052034105,0.00005176591,0.000018025157,0.017684821,0.00014015437,0.0003846812,0.02780794,0.9429624,0.00013271451],"about_ca_topic_score_codex":0.00004767025,"about_ca_topic_score_gemma":0.00048337295,"teacher_disagreement_score":0.875252,"about_ca_system_score_codex":0.00025762932,"about_ca_system_score_gemma":0.0019032774,"threshold_uncertainty_score":0.9978623},"labels":[],"label_agreement":null},{"id":"W285975702","doi":"10.3138/cjpe.23.005","title":"Using Technology to Enhance Aboriginal Evaluations","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Focus (optics); Sociology; Data collection; Knowledge management; Engineering ethics; Computer science; Social science; Engineering; History; Archaeology","score_opus":0.4108376583250716,"score_gpt":0.6419507109411706,"score_spread":0.23111305261609905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W285975702","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97145474,0.00036759186,0.019411402,0.0047402983,0.0010171836,0.0010814486,0.0000054993443,0.000015170038,0.001906652],"genre_scores_gemma":[0.9571604,0.000009700276,0.04210057,0.00025043444,0.0002100486,0.00006191687,0.0000031189327,0.000009944887,0.00019387783],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99532825,0.00037170865,0.0010133714,0.00024929104,0.0026911928,0.00034618884],"domain_scores_gemma":[0.991846,0.0001318697,0.0006001761,0.00038039987,0.006469931,0.0005716277],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010592289,0.00012916709,0.0002538125,0.002035391,0.0004956335,0.00016683611,0.0005983008,0.00009900635,0.002402062],"category_scores_gemma":[0.0034544477,0.00010809454,0.00010209737,0.0026721566,0.0001445196,0.0006140793,0.000010768164,0.00023183001,0.00027697138],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000175076,0.000060667746,0.06388902,0.0000019500783,0.000030090925,0.00002109441,0.0018842606,0.025485653,0.00096392183,0.0009238864,0.004424878,0.9022971],"study_design_scores_gemma":[0.0018077698,0.0023494011,0.18278107,0.00018318782,0.00029851694,0.0013976241,0.0030588023,0.23724146,0.005465108,0.036098067,0.5285443,0.0007746545],"about_ca_topic_score_codex":0.00040374586,"about_ca_topic_score_gemma":0.009029506,"teacher_disagreement_score":0.9015224,"about_ca_system_score_codex":0.00066717196,"about_ca_system_score_gemma":0.01418327,"threshold_uncertainty_score":0.9985099},"labels":[{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W286621326","doi":"10.3138/cjpe.017.002","title":"A Peer Support Approach to Evaluation: Assessing Supported Employment Programs for People with Developmental Disabilities","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Centre for Addiction and Mental Health","funders":"","keywords":"Agency (philosophy); Peer support; Psychology; Peer review; Medical education; Applied psychology; Knowledge management; Computer science; Sociology; Political science; Medicine","score_opus":0.4885163999449404,"score_gpt":0.4936480799662604,"score_spread":0.005131680021320029,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W286621326","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9295927,0.0001825192,0.016632583,0.00954464,0.0010729538,0.012963536,0.000031365355,0.00004561225,0.029934071],"genre_scores_gemma":[0.9410963,0.0000010206213,0.054942477,0.00022250577,0.0001885235,0.0017841096,0.00013630878,0.000026608577,0.001602159],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99060816,0.00049618806,0.0013423471,0.00045408128,0.0065270094,0.00057220605],"domain_scores_gemma":[0.9871219,0.00027811623,0.0006515754,0.0003337563,0.010770808,0.0008438645],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.023960588,0.00025285684,0.00043172072,0.0007340269,0.00045825244,0.0014151711,0.00054644747,0.00009470644,0.0054486683],"category_scores_gemma":[0.0048733843,0.00018508629,0.00016334365,0.0013047126,0.00012026534,0.0012767116,0.000019114634,0.00017873428,0.000096883516],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033046912,0.00031466727,0.0714994,0.00001370759,0.00007680376,0.000001178943,0.0146707045,0.0025432997,0.000009170708,0.00012183259,0.021994794,0.8887214],"study_design_scores_gemma":[0.0076958532,0.0050624446,0.15464248,0.00018998851,0.000826647,0.00062587013,0.087198496,0.41407746,0.00015301928,0.003992982,0.3243736,0.0011611521],"about_ca_topic_score_codex":0.0001876257,"about_ca_topic_score_gemma":0.011842891,"teacher_disagreement_score":0.88756025,"about_ca_system_score_codex":0.0013247981,"about_ca_system_score_gemma":0.006248266,"threshold_uncertainty_score":0.99962145},"labels":[],"label_agreement":null},{"id":"W2883975331","doi":"10.1177/1049732318786703","title":"A Guide to Multisite Qualitative Analysis","year":2018,"lang":"en","type":"article","venue":"Qualitative Health Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":88,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; University of British Columbia","funders":"Canadian Institutes of Health Research","keywords":"Qualitative research; Psychology; Qualitative analysis; Sociology; Medicine; Social science","score_opus":0.8898421656892707,"score_gpt":0.8366267141935086,"score_spread":0.05321545149576201,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2883975331","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4301543,0.0003370616,0.28289634,0.18403956,0.00058194186,0.0030403347,0.0003467957,0.00013138312,0.09847229],"genre_scores_gemma":[0.88520384,0.000033732762,0.045072384,0.007199335,0.0003127099,0.00027754772,0.000033318396,0.000022381579,0.06184476],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9584223,0.029163055,0.0018115746,0.0010890892,0.008338606,0.0011753934],"domain_scores_gemma":[0.966253,0.02161266,0.0003785414,0.0011814593,0.009617476,0.0009568898],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.19504447,0.00018937113,0.00066777907,0.0032709122,0.0012550337,0.00035799664,0.0010497408,0.00007670122,0.0061235214],"category_scores_gemma":[0.027914966,0.00014000812,0.0001910244,0.014305018,0.0006551352,0.00044452606,0.0003264735,0.00047469386,0.014879388],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014431101,0.00010077331,0.00081140175,0.000011861143,0.00013549197,0.0000010988238,0.7654091,0.000036689045,0.000059965605,0.020367024,0.16630487,0.046617396],"study_design_scores_gemma":[0.0004995747,0.0017761608,0.013898354,0.000028445598,0.0000106630905,4.106291e-7,0.59988546,0.004523112,0.00016543175,0.019676039,0.3593238,0.00021252374],"about_ca_topic_score_codex":0.004024553,"about_ca_topic_score_gemma":0.008921681,"teacher_disagreement_score":0.45504954,"about_ca_system_score_codex":0.00059548847,"about_ca_system_score_gemma":0.0013625846,"threshold_uncertainty_score":0.994785},"labels":[],"label_agreement":null},{"id":"W2884210948","doi":"10.31265/jcsw.v11i2.140","title":"Making sense, discovering what works…","year":2016,"lang":"en","type":"article","venue":"Journal of Comparative Social Work","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Montréal","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Scope (computer science); Agency (philosophy); Set (abstract data type); Public relations; Subject (documents); Core (optical fiber); Knowledge management; Business; Sociology; Political science; Process management; Law and economics; Engineering ethics; Computer science; Engineering; Social science","score_opus":0.43744549694464446,"score_gpt":0.560291544606063,"score_spread":0.12284604766141854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2884210948","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9487591,0.0007556662,0.030191375,0.012256368,0.001925286,0.00008511146,8.7395244e-7,0.000007787957,0.006018462],"genre_scores_gemma":[0.99721587,0.0000981737,0.000752914,0.00026385486,0.00074911246,0.0000012050149,9.240938e-8,0.0000047566255,0.00091401703],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9969496,0.00036356796,0.00079211785,0.00012747911,0.0015852337,0.00018196153],"domain_scores_gemma":[0.9970203,0.0011677453,0.000960743,0.00012063517,0.00066524185,0.000065323475],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002888419,0.00010791151,0.00038377827,0.0001636411,0.00032462887,0.0008190192,0.00030526784,0.000046702007,0.0014278213],"category_scores_gemma":[0.00020661639,0.00005619973,0.00020791985,0.00082762534,0.00010411083,0.0030626426,0.00006090532,0.00017222294,0.00025892106],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009925135,0.0001873003,0.051318835,0.0000036835931,0.00024139084,0.000040243234,0.037764095,0.0012676646,0.0014059516,0.0115974415,0.05124961,0.84393126],"study_design_scores_gemma":[0.0040416885,0.00047676882,0.52263474,0.0035322423,0.000084929794,0.00006375017,0.0852962,0.00029840824,0.0016307163,0.08956672,0.29160464,0.0007692022],"about_ca_topic_score_codex":1.4223367e-7,"about_ca_topic_score_gemma":0.0000065230465,"teacher_disagreement_score":0.84316206,"about_ca_system_score_codex":0.000090610905,"about_ca_system_score_gemma":0.00015227008,"threshold_uncertainty_score":0.999485},"labels":[],"label_agreement":null},{"id":"W2884500380","doi":"10.1177/1098214018778809","title":"The Need for Analysts in Social Impact Measurement","year":2018,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":40,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Psychology; Program evaluation; Management science; Actuarial science; Applied psychology; Business; Political science; Economics; Public administration","score_opus":0.3492754177554118,"score_gpt":0.5984297125613699,"score_spread":0.24915429480595808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2884500380","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9825596,0.0000785483,0.009103552,0.0063927914,0.00042405372,0.00030053587,0.0000015806925,0.000002129564,0.0011371803],"genre_scores_gemma":[0.9987721,0.000008117022,0.00046643423,0.00019099044,0.0005188208,0.0000116195115,6.2582535e-7,0.0000042044526,0.000027121496],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9942046,0.0007885481,0.0008783338,0.000112105656,0.0038493369,0.00016707985],"domain_scores_gemma":[0.9922832,0.00063762075,0.0012663141,0.00015721563,0.00560306,0.000052554948],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.047754526,0.000073518335,0.00022041409,0.00030005377,0.00028536434,0.00015123816,0.00029292883,0.000016201937,0.0002514507],"category_scores_gemma":[0.004443418,0.00003869888,0.00017157225,0.00097531825,0.00017239495,0.00028773514,0.000014413486,0.00008366511,0.000023197994],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043145442,0.00004743732,0.020313036,4.2812712e-7,0.000059421127,1.7618686e-7,0.0018366065,0.0010424188,0.0009110133,0.00017119928,0.009870947,0.9653159],"study_design_scores_gemma":[0.0021561254,0.0027265467,0.82544327,0.000020247358,0.00010150379,0.00000992085,0.007832703,0.13037603,0.00036275308,0.022662073,0.00817663,0.00013217433],"about_ca_topic_score_codex":0.000020014191,"about_ca_topic_score_gemma":0.00023436811,"teacher_disagreement_score":0.9651837,"about_ca_system_score_codex":0.00042002788,"about_ca_system_score_gemma":0.0009987229,"threshold_uncertainty_score":0.9805371},"labels":[],"label_agreement":null},{"id":"W2884511286","doi":"10.1177/1098214018781506","title":"Making Space for Adaptive Learning","year":2018,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"University of Ottawa","keywords":"Interrogation; Space (punctuation); Mediation; Psychology; Social learning; Process (computing); Social psychology; Computer science; Sociology; Pedagogy; Political science; Social science","score_opus":0.3892532860461554,"score_gpt":0.5842406175819069,"score_spread":0.19498733153575154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2884511286","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6728446,0.000060985865,0.31558532,0.0027838687,0.0007353945,0.00027406475,0.0000012162302,0.000007709418,0.0077068293],"genre_scores_gemma":[0.9772994,0.0000054157163,0.021568973,0.00028941,0.00056692166,0.000006874215,7.289678e-7,0.0000069746748,0.00025530256],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99622047,0.00060048053,0.00063758745,0.00014947429,0.0022483296,0.00014364207],"domain_scores_gemma":[0.9922931,0.0010215396,0.0016316983,0.00014638147,0.0048502604,0.00005701714],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017975984,0.00007641927,0.00022485429,0.00030752667,0.00019062601,0.000105700485,0.00021513333,0.00001770097,0.000992467],"category_scores_gemma":[0.0051589063,0.00005486158,0.000111979025,0.00061109714,0.00016542766,0.00046495566,0.000021593487,0.00011867804,0.00009168536],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029874736,0.000025989464,0.00678361,6.5574176e-7,0.000033264285,3.5590148e-7,0.0026591653,0.006485262,0.0006516275,0.0010979362,0.0024663252,0.9794971],"study_design_scores_gemma":[0.0019537557,0.010361776,0.07185193,0.00009561897,0.00017347884,0.00006289627,0.025596743,0.79883415,0.0013004179,0.028900327,0.060602874,0.00026603736],"about_ca_topic_score_codex":0.0000031952209,"about_ca_topic_score_gemma":0.000012210108,"teacher_disagreement_score":0.979231,"about_ca_system_score_codex":0.0001222234,"about_ca_system_score_gemma":0.0004932402,"threshold_uncertainty_score":0.9999208},"labels":[],"label_agreement":null},{"id":"W2885304761","doi":"10.20533/licej.2040.2589.2016.0309","title":"Evaluating the Power of CORE","year":2016,"lang":"en","type":"article","venue":"Literacy Information and Computer Education Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Core (optical fiber); Power (physics); Computer science; Telecommunications; Physics","score_opus":0.1373607850641019,"score_gpt":0.5151783790474126,"score_spread":0.3778175939833107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2885304761","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9025174,0.00007842051,0.08129423,0.01162848,0.0019669181,0.0001468164,0.0000040761815,0.000009111571,0.0023545565],"genre_scores_gemma":[0.9893122,0.000034909976,0.0066018933,0.0032040563,0.00023905162,0.0000058778114,0.000002298706,0.0000018875143,0.00059783936],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978842,0.00013918563,0.0008927392,0.00006803099,0.0009222232,0.000093604256],"domain_scores_gemma":[0.9969808,0.00050913874,0.0007342101,0.0002277429,0.0014504457,0.0000976955],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0035307505,0.00006944458,0.000097719945,0.00022603005,0.00021851121,0.0005212797,0.00029014066,0.00002321133,0.0017176999],"category_scores_gemma":[0.0004863314,0.000030047026,0.000050539886,0.00025083293,0.00004906203,0.0030317504,0.000047997997,0.00008639194,0.00012500717],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013034969,0.000013278161,0.0064898967,0.0000019758083,0.00000489116,1.6437035e-8,0.007945273,0.000033886918,0.000029785066,0.006625174,0.005574506,0.9732683],"study_design_scores_gemma":[0.0013849102,0.00060965156,0.35828978,0.00021911332,0.00001566079,0.00034528374,0.003908871,0.055114042,0.00012576618,0.038730223,0.54103273,0.00022393343],"about_ca_topic_score_codex":9.4326174e-7,"about_ca_topic_score_gemma":1.3893673e-7,"teacher_disagreement_score":0.97304434,"about_ca_system_score_codex":0.000024755593,"about_ca_system_score_gemma":0.00053392816,"threshold_uncertainty_score":0.99919486},"labels":[],"label_agreement":null},{"id":"W2885881976","doi":"10.1332/030557318x15333033508220","title":"Is it time to give up on evidence-based policy? Four answers","year":2018,"lang":"en","type":"article","venue":"Policy & Politics","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":63,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Rationality; GRASP; Perspective (graphical); Government (linguistics); Task (project management); Political science; Public relations; Discipline; Public administration; Sociology; Engineering ethics; Economics; Management; Computer science; Law; Engineering","score_opus":0.4824637774321112,"score_gpt":0.5706544681213398,"score_spread":0.08819069068922858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2885881976","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1920117,0.000018915765,0.0014079172,0.5589288,0.00075764017,0.0007049652,0.00023886721,0.00012580448,0.24580544],"genre_scores_gemma":[0.71619433,0.000007779852,0.0005666367,0.18407018,0.0025106294,0.000020890931,0.000003337679,0.00002321724,0.09660301],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99504966,0.00028412684,0.00073406997,0.00058566657,0.0024668803,0.0008795745],"domain_scores_gemma":[0.9952858,0.0015405392,0.00022563203,0.0012157563,0.0010701141,0.0006621407],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0021536152,0.00028110688,0.000339845,0.0013244359,0.0003695084,0.0003698482,0.001026789,0.00012278857,0.009258363],"category_scores_gemma":[0.0076166657,0.00022447384,0.00018645529,0.0014985922,0.00027213583,0.00039730748,0.0001438698,0.0001697726,0.0648947],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000105732695,0.00011205031,0.004742636,0.000012087826,0.000038623275,0.0000036464162,0.0079881195,0.00035433442,0.00048201904,0.059620697,0.90963274,0.016907295],"study_design_scores_gemma":[0.00070287177,0.0012309593,0.022234222,0.00017191359,0.000024628036,0.0000064908677,0.00056173484,0.017385459,0.0089393845,0.020884335,0.92733777,0.0005202109],"about_ca_topic_score_codex":0.0016321895,"about_ca_topic_score_gemma":0.00007402419,"teacher_disagreement_score":0.5241826,"about_ca_system_score_codex":0.0005910522,"about_ca_system_score_gemma":0.002951272,"threshold_uncertainty_score":0.9916473},"labels":[],"label_agreement":null},{"id":"W2887789865","doi":"","title":"Canadian Universities: Emerging Hubs for International Parliamentary Research and Training","year":2018,"lang":"en","type":"article","venue":"Canadian parliamentary review","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Training (meteorology); Political science; Work (physics); Public administration; Kingdom; Library science; Management; Geography; Engineering; Economics","score_opus":0.37141597683645045,"score_gpt":0.5226837868251532,"score_spread":0.1512678099887027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2887789865","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2799154,0.055100743,0.0004381901,0.40481842,0.009843207,0.0067445817,0.0026344853,0.000092076894,0.2404129],"genre_scores_gemma":[0.85149926,0.02561006,0.0039790887,0.09331882,0.0021827968,0.0003157371,0.0006832075,0.00007301108,0.022338025],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971399,0.00019508984,0.0005281252,0.0005115522,0.000943821,0.00068156223],"domain_scores_gemma":[0.99705106,0.00035721838,0.000106726104,0.00040732892,0.0010193419,0.0010583017],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0057508354,0.00015663319,0.00028751418,0.000858769,0.00082390505,0.00023691905,0.00074805267,0.0000530399,0.016737424],"category_scores_gemma":[0.00029506328,0.00014411895,0.00007398985,0.0006724815,0.00024350196,0.00056943746,0.00005938066,0.00017352312,0.00044378222],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000988304,0.000008043639,0.0075989272,0.00007220571,0.00006267663,0.000013253191,0.001753913,0.0000024494918,0.000003971757,0.0013005065,0.6820695,0.3071047],"study_design_scores_gemma":[0.00026155557,0.00012741656,0.0011744518,0.00051105284,0.000018309876,0.000009451904,0.019895693,0.00081663515,0.000006203764,0.0015903872,0.97542167,0.00016718218],"about_ca_topic_score_codex":0.626185,"about_ca_topic_score_gemma":0.9758155,"teacher_disagreement_score":0.57158387,"about_ca_system_score_codex":0.0017787684,"about_ca_system_score_gemma":0.004416489,"threshold_uncertainty_score":0.98416144},"labels":[],"label_agreement":null},{"id":"W2888883283","doi":"","title":"A Practicum of Fairness: Smart Practices for Undergraduate Professional Program Practicum Assessment","year":2018,"lang":"en","type":"article","venue":"UVic’s Research and Learning Repository (University of Victoria)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Victoria","keywords":"Practicum; Medical education; Pedagogy; Psychology; Engineering ethics; Engineering; Medicine","score_opus":0.1748805649291392,"score_gpt":0.49833154315853967,"score_spread":0.3234509782294005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2888883283","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93369955,0.00013143479,0.0037560367,0.008652354,0.0015757658,0.0018648057,0.000008928912,0.00008385529,0.050227277],"genre_scores_gemma":[0.96257114,0.00005603481,0.010739882,0.000009426472,0.00025547133,0.000011323954,0.000010538377,0.000011490158,0.026334664],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99396205,0.0017342691,0.00043866923,0.000563252,0.0029068033,0.00039492865],"domain_scores_gemma":[0.987869,0.0052158246,0.001555537,0.00043282905,0.0047144,0.000212364],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.011440058,0.00014014119,0.00034033664,0.00040920937,0.0015669112,0.00023275727,0.00055120396,0.00014564994,0.00027996447],"category_scores_gemma":[0.005249628,0.0001254823,0.000099809506,0.0008443119,0.00073018024,0.0013968111,0.0003169922,0.00072076824,0.000030278945],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0069036805,0.005644197,0.7234482,0.00089670526,0.0010441622,0.00006786966,0.021894602,0.00016635151,0.045160472,0.020019632,0.04986371,0.1248904],"study_design_scores_gemma":[0.0023550682,0.008234454,0.13460092,0.0002258345,0.00009690591,0.000029580659,0.045834683,0.027444717,0.0013153432,0.0051844376,0.7743519,0.000326153],"about_ca_topic_score_codex":0.00038763435,"about_ca_topic_score_gemma":0.00019116847,"teacher_disagreement_score":0.7244882,"about_ca_system_score_codex":0.00011834518,"about_ca_system_score_gemma":0.001389776,"threshold_uncertainty_score":0.9997329},"labels":[],"label_agreement":null},{"id":"W2889109094","doi":"10.1186/s13584-018-0247-7","title":"A fragile but critical link: a commentary on the importance of government-academy relationships","year":2018,"lang":"en","type":"letter","venue":"Israel Journal of Health Policy Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland; Institute of Health Economics; Public Health Ontario; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Government (linguistics); Politics; Public policy; Public relations; Value (mathematics); Social policy; Public finance; Political science; Health services research; Public administration; Sociology; Law; Health care; Computer science","score_opus":0.6987615077441945,"score_gpt":0.6640791493357352,"score_spread":0.034682358408459346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889109094","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0069257403,0.0005969701,0.0000938887,0.98768914,0.00037845093,0.0004921352,0.00024488394,0.000004267125,0.0035745169],"genre_scores_gemma":[0.055292238,0.00051173515,0.00035444213,0.92964244,0.012103279,0.000025062682,0.0000069144025,0.00003505111,0.0020288178],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97055316,0.009859195,0.0033133626,0.00040785968,0.014871773,0.0009946304],"domain_scores_gemma":[0.966617,0.028135078,0.0021687543,0.0009208907,0.001846253,0.00031204984],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07708099,0.00024921398,0.0008125096,0.0009996803,0.001032355,0.0002268077,0.002352132,0.00049526716,0.0014762137],"category_scores_gemma":[0.024678083,0.00014482441,0.00029813632,0.0014190227,0.00096101436,0.00033305882,0.00032005282,0.009009668,0.0003235217],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008027652,0.00006479877,0.0059473906,0.00006947718,0.000035978264,0.00001738684,0.00054190354,0.0000059030554,0.000004687398,0.0028250923,0.9879408,0.0024663457],"study_design_scores_gemma":[0.00037224242,0.0011577992,0.0057914257,0.00044979743,0.000008363541,0.00004897486,0.001627301,0.0002685344,0.000035828863,0.026615718,0.9635062,0.00011780239],"about_ca_topic_score_codex":0.0003121837,"about_ca_topic_score_gemma":0.00004633411,"teacher_disagreement_score":0.058046687,"about_ca_system_score_codex":0.0011641033,"about_ca_system_score_gemma":0.0033297576,"threshold_uncertainty_score":0.99943656},"labels":[],"label_agreement":null},{"id":"W2889852576","doi":"","title":"Creswell, J. W. (2013). Qualitative inquiry and research design. Choosing among five approaches (3e éd.). London : Sage.","year":2015,"lang":"fr","type":"article","venue":"Approches inductives Travail intellectuel et construction des connaissances","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":963,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"SAGE; Qualitative research; Sociology; Social science; Physics","score_opus":0.6383697011419519,"score_gpt":0.5228253934375306,"score_spread":0.11554430770442126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889852576","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66494584,0.11718949,0.19788243,0.0057008103,0.003767533,0.0021541805,0.000044877586,0.00017352284,0.008141285],"genre_scores_gemma":[0.9603761,0.009681649,0.022627212,0.00022958152,0.0006971447,0.00032400448,0.000020452288,0.000087854765,0.0059560454],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.97863656,0.012639214,0.0018548024,0.0021741209,0.0033163694,0.0013789067],"domain_scores_gemma":[0.98515826,0.009162313,0.0009442307,0.00089995,0.002937301,0.00089794194],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","sts"],"category_scores_codex":[0.02977441,0.0009168424,0.0011576038,0.0015176126,0.0015927186,0.001912313,0.0011041682,0.00074135984,0.0010756276],"category_scores_gemma":[0.011176693,0.0008319388,0.0002260822,0.0033161654,0.061825924,0.005333652,0.00052381656,0.002180059,0.00027045142],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007474014,0.00031293643,0.0025564688,0.00019065016,0.00036243908,0.000012135708,0.4967475,0.0014638313,0.00017677485,0.016201407,0.0098664705,0.471362],"study_design_scores_gemma":[0.0017679782,0.0013836096,0.0053048986,0.0010889244,0.00012881676,0.00035163842,0.84645283,0.016505098,0.00591357,0.09393272,0.026031518,0.0011384166],"about_ca_topic_score_codex":0.0006787247,"about_ca_topic_score_gemma":0.00034069933,"teacher_disagreement_score":0.47022358,"about_ca_system_score_codex":0.00062225485,"about_ca_system_score_gemma":0.0016867954,"threshold_uncertainty_score":0.9998375},"labels":[],"label_agreement":null},{"id":"W2889888295","doi":"10.23889/ijpds.v3i4.759","title":"Policy advocacy to enable administrative data linking: building a civil society coalition","year":2018,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Civil society; Public relations; Government (linguistics); Beneficiary; Policy advocacy; Public administration; Legislature; Business; Politics; Service delivery framework; License; Service provider; Political science; Service (business); Marketing","score_opus":0.5364738345692184,"score_gpt":0.6357405057252014,"score_spread":0.09926667115598298,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889888295","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15109167,0.000021077742,0.7954987,0.036930844,0.009446911,0.0008357416,0.002065374,0.00007309924,0.004036565],"genre_scores_gemma":[0.9282518,0.000017457158,0.06500138,0.0023363833,0.002988858,0.000008062754,0.00070011435,0.000009393754,0.00068652246],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9933272,0.000092876726,0.00096026814,0.0009034624,0.004340263,0.00037590406],"domain_scores_gemma":[0.993534,0.00047731504,0.0006729246,0.0014980793,0.0035208226,0.00029680764],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.014798786,0.00014813872,0.00017118602,0.00066662475,0.0012087547,0.0025187652,0.008240783,0.000049851646,0.00043977695],"category_scores_gemma":[0.00951501,0.000118607684,0.00006735867,0.0015106425,0.00026002206,0.008601453,0.00188665,0.00017223589,0.00012777298],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00068307074,0.00059227395,0.08777229,0.000016467036,0.00024965868,0.000010177198,0.0084442,0.0050243908,0.01663494,0.17679363,0.31980133,0.38397756],"study_design_scores_gemma":[0.000885112,0.0002894519,0.034097746,0.00011265976,0.000018585384,0.00011193952,0.0013328157,0.5095879,0.0008589176,0.0643171,0.3880509,0.0003368699],"about_ca_topic_score_codex":0.00017852076,"about_ca_topic_score_gemma":0.00035545806,"teacher_disagreement_score":0.77716017,"about_ca_system_score_codex":0.00034654277,"about_ca_system_score_gemma":0.002345976,"threshold_uncertainty_score":0.9988283},"labels":[],"label_agreement":null},{"id":"W2890484320","doi":"","title":"Towards sustainable water governance","year":2015,"lang":"en","type":"article","venue":"Canadian Water Resources Journal / Revue canadienne des ressources hydriques","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Watershed; Corporate governance; Watershed management; Credibility; Business; Environmental resource management; Social learning; Process (computing); Knowledge management; Public relations; Process management; Environmental planning; Political science; Economics; Geography; Computer science","score_opus":0.09078846548632517,"score_gpt":0.33843107987220433,"score_spread":0.24764261438587915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2890484320","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9533724,0.0010036665,0.000099381476,0.008313238,0.00065821846,0.0002909402,0.00003348443,0.000054224627,0.036174405],"genre_scores_gemma":[0.9537268,0.00016441825,0.0002865109,0.0013717465,0.0009242465,0.00002792723,0.00002424186,0.00006816977,0.043405924],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9929189,0.0007390516,0.0013539752,0.00076986465,0.001273367,0.0029448066],"domain_scores_gemma":[0.9916788,0.00011619315,0.0003477493,0.00096933934,0.0025217128,0.0043662107],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010280402,0.00049927447,0.0006993145,0.0011090912,0.0015876057,0.0024632677,0.0022437274,0.00024697284,0.0025008142],"category_scores_gemma":[0.001509707,0.0002986961,0.0002902998,0.0006565821,0.0004937817,0.0016444322,0.00021982686,0.00074858824,0.0006728248],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014511953,0.000039532773,0.01089397,0.00006058314,0.00012573521,0.0028816897,0.945279,0.0059868055,0.0003799132,0.00018446596,0.0036054722,0.030417694],"study_design_scores_gemma":[0.0005799303,0.00028704677,0.0015416251,0.0000788368,0.00002865532,0.0012808936,0.009166011,0.0011087502,0.0033021276,0.019878248,0.96221185,0.0005360436],"about_ca_topic_score_codex":0.2021141,"about_ca_topic_score_gemma":0.568273,"teacher_disagreement_score":0.95860636,"about_ca_system_score_codex":0.0028764845,"about_ca_system_score_gemma":0.00013840792,"threshold_uncertainty_score":0.99994653},"labels":[],"label_agreement":null},{"id":"W2891116187","doi":"10.18438/eblip29491","title":"Time to Move EBLIP Forward with an Organizational Lens","year":2018,"lang":"en","type":"article","venue":"Evidence Based Library and Information Practice","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Lens (geology); Through-the-lens metering; Computer science; Optics; Physics","score_opus":0.055870816396963376,"score_gpt":0.38005887967270324,"score_spread":0.32418806327573985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2891116187","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14180881,0.00008698199,0.102525555,0.55919933,0.00049948477,0.0016863967,0.00008379073,0.00048422292,0.19362544],"genre_scores_gemma":[0.4753629,0.00008579113,0.06665418,0.45142236,0.0004642391,0.000046446512,0.00015411337,0.000022834622,0.00578715],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975233,0.00027993447,0.0005186445,0.00022332474,0.0012922727,0.00016252491],"domain_scores_gemma":[0.9964807,0.001842717,0.00036423412,0.00040757374,0.00070606056,0.00019870664],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["scholarly_communication","insufficient_payload"],"category_scores_codex":[0.0021741362,0.00012475213,0.0001258228,0.00035144936,0.00032335427,0.0011629303,0.0003627,0.000052653428,0.017355168],"category_scores_gemma":[0.0040689497,0.00008769684,0.000017015038,0.0014095051,0.00010062965,0.30749685,0.00009346946,0.00010592966,0.006852302],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009156672,0.00048051297,0.020140402,0.00008269984,0.00010305368,0.00000833386,0.008978023,0.009721303,0.00057574816,0.47370175,0.23248419,0.2445673],"study_design_scores_gemma":[0.00036026243,0.0010224197,0.024151878,0.00006243603,0.000015252333,0.000018914667,0.001005968,0.053642303,0.0013532831,0.00035294608,0.9178185,0.00019586599],"about_ca_topic_score_codex":0.0000013713241,"about_ca_topic_score_gemma":1.154929e-7,"teacher_disagreement_score":0.68533427,"about_ca_system_score_codex":0.000012169781,"about_ca_system_score_gemma":0.00057319057,"threshold_uncertainty_score":0.99987394},"labels":[],"label_agreement":null},{"id":"W2891656379","doi":"10.1002/ev.20346","title":"The Evolving Market for Systematic Evaluation in Canada","year":2018,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Accreditation; Professionalization; Context (archaeology); Supply and demand; Government (linguistics); Supply side; Business; Exploratory research; Affect (linguistics); Public relations; Marketing; Economics; Political science; Economic growth; Sociology; Social science","score_opus":0.1834456181021273,"score_gpt":0.4959395639226441,"score_spread":0.3124939458205168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2891656379","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41836742,0.0061579496,0.22318864,0.038059477,0.041391246,0.10270749,0.00021633905,0.00029810375,0.16961336],"genre_scores_gemma":[0.9877036,0.000012046026,0.0012804323,0.00018338757,0.00044263963,0.0039826515,0.000027533262,0.000015735643,0.0063519394],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9941405,0.0009443959,0.0010449042,0.00040011416,0.0031749427,0.00029515845],"domain_scores_gemma":[0.9890132,0.0055111474,0.00047506476,0.0005685717,0.004353782,0.00007822949],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.038302407,0.00013575707,0.00023300492,0.00025401052,0.0009370116,0.00031913872,0.00036372023,0.000050148443,0.0014594729],"category_scores_gemma":[0.025401084,0.00009128386,0.00009584875,0.0009488863,0.000034456723,0.0004608813,0.000023618535,0.00006540828,0.000040592287],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002174891,0.00006305654,0.0070759673,0.00026505307,0.00008390297,4.7255096e-8,0.0014814213,0.0056862626,0.000134621,0.0017108815,0.42640573,0.5568756],"study_design_scores_gemma":[0.001457052,0.000084952786,0.027425444,0.0002014257,0.00010786698,0.0000013431214,0.0017519824,0.9301785,0.00014258845,0.020584507,0.017945861,0.00011843412],"about_ca_topic_score_codex":0.07362279,"about_ca_topic_score_gemma":0.9436849,"teacher_disagreement_score":0.9244923,"about_ca_system_score_codex":0.0021972624,"about_ca_system_score_gemma":0.0076341,"threshold_uncertainty_score":0.9994533},"labels":[],"label_agreement":null},{"id":"W2891858155","doi":"","title":"Rethinking how success is measured","year":2017,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.7603481037702164,"score_gpt":0.6951971962935525,"score_spread":0.06515090747666397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2891858155","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9240063,0.0042887465,0.0013571114,0.010309346,0.0028399818,0.00065864436,0.000048465834,0.000045371642,0.056446075],"genre_scores_gemma":[0.9906757,0.002755469,0.00047978814,0.0011792057,0.00031042995,0.000028802206,0.0000036862205,0.00003474371,0.004532204],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9912721,0.0006556178,0.0013484352,0.00079034694,0.0054327203,0.00050079526],"domain_scores_gemma":[0.9908911,0.0009226462,0.0033869913,0.002354129,0.0020642607,0.00038090302],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017651463,0.0003575419,0.000981569,0.0010134586,0.0018714806,0.020030292,0.013376986,0.00017486565,0.043975305],"category_scores_gemma":[0.0056301043,0.00026879463,0.00033761884,0.0008653204,0.00031006653,0.011597089,0.0022221846,0.0005877731,0.00018909095],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009253564,0.00009394379,0.7891871,0.000016761862,0.00009558845,0.0000153911,0.0008656792,0.00006370869,0.009139369,0.00022365019,0.1321135,0.068092816],"study_design_scores_gemma":[0.00064181053,0.000009737408,0.8686528,0.00023683612,0.000045518038,0.000008101716,0.00016851186,0.0009884913,0.017080009,0.06589581,0.045882694,0.0003896361],"about_ca_topic_score_codex":0.000537874,"about_ca_topic_score_gemma":0.00028689994,"teacher_disagreement_score":0.08623081,"about_ca_system_score_codex":0.000120367535,"about_ca_system_score_gemma":0.00053618685,"threshold_uncertainty_score":0.9999764},"labels":[],"label_agreement":null},{"id":"W2893680775","doi":"10.7202/1050974ar","title":"Validation du cadre de référence PIEA des pratiques d’évaluation des apprentissages en classe dans une approche par compétences selon la perception d’étudiants du collégial 1","year":2018,"lang":"fr","type":"article","venue":"Revue des sciences de l éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université du Québec à Montréal; Université du Québec à Trois-Rivières","funders":"","keywords":"Humanities; Political science; Art","score_opus":0.3025284611874781,"score_gpt":0.4743802764943142,"score_spread":0.17185181530683608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2893680775","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8522444,0.00034751723,0.13270324,0.004497332,0.0014823931,0.0006881372,0.000022093018,0.00009354692,0.007921343],"genre_scores_gemma":[0.88268906,0.0025030167,0.110865004,0.00012632828,0.0011115092,0.000159186,0.000066395114,0.00002314408,0.0024563377],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9911857,0.0040474543,0.0011376562,0.0010868402,0.0017012813,0.0008410221],"domain_scores_gemma":[0.9947123,0.0016175109,0.00084714347,0.00058780273,0.0019236094,0.0003116509],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["sts"],"category_scores_codex":[0.020253621,0.0004367765,0.00042553004,0.0005146624,0.003970554,0.0017381042,0.001408581,0.00038749058,0.0010662806],"category_scores_gemma":[0.0057534636,0.00040792132,0.00015416807,0.0033319683,0.006831046,0.0046232054,0.00019756047,0.00031634135,0.0003956144],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058670208,0.0006917842,0.30614862,0.00030621747,0.00003845843,0.0000045468887,0.4646568,0.0054983837,0.024976073,0.0024933782,0.00457947,0.1905476],"study_design_scores_gemma":[0.0005103343,0.0009413625,0.5319977,0.00078755413,0.00016360823,0.00032394254,0.1182672,0.27265733,0.0069985827,0.06501431,0.0017558561,0.0005822456],"about_ca_topic_score_codex":0.001650906,"about_ca_topic_score_gemma":0.006032725,"teacher_disagreement_score":0.3463896,"about_ca_system_score_codex":0.0025080857,"about_ca_system_score_gemma":0.0038436798,"threshold_uncertainty_score":0.9998469},"labels":[],"label_agreement":null},{"id":"W2895028371","doi":"10.7179/psri_2014.24.06","title":"Intersecciones entre evaluación participativa y pedagogía social","year":2014,"lang":"es","type":"article","venue":"Pedagogia Social Revista Interuniversitaria","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Citizen journalism; Sociology; Intersection (aeronautics); Set (abstract data type); Selection (genetic algorithm); Participatory action research; Order (exchange); Through-the-lens metering; Epistemology; Political science; Lens (geology); Geography; Computer science; Anthropology; Engineering; Cartography","score_opus":0.14922127261642823,"score_gpt":0.4838247521468176,"score_spread":0.3346034795303894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2895028371","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80942506,0.00029428385,0.0074242787,0.028127743,0.0029107756,0.0010386881,0.00020380788,0.0002406088,0.15033475],"genre_scores_gemma":[0.98728955,0.00007237481,0.00017828411,0.00076579064,0.0016162097,0.000015331749,0.00006956812,0.000053967906,0.009938909],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9913594,0.0021306141,0.0014582811,0.001221648,0.0028123413,0.0010176952],"domain_scores_gemma":[0.99552196,0.00096033013,0.0011681017,0.000649043,0.0013555207,0.0003450576],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0046427925,0.0007114639,0.0011826287,0.00057190657,0.0020260413,0.0015889849,0.0018071879,0.0004720696,0.033578224],"category_scores_gemma":[0.0014401143,0.00067797606,0.0008780896,0.0010713825,0.0006410755,0.0012509469,0.0008900128,0.0007939034,0.0050386945],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008844392,0.00066132226,0.031660106,0.00028083072,0.00062132685,0.00002849111,0.09677782,0.00004561764,0.0006938991,0.61351734,0.09912221,0.15570661],"study_design_scores_gemma":[0.0024388982,0.00058601587,0.05449827,0.00023481542,0.00062735827,0.0000054565758,0.07085839,0.008916095,0.00007600638,0.0022534549,0.8583268,0.0011784412],"about_ca_topic_score_codex":0.00016457328,"about_ca_topic_score_gemma":0.00010643697,"teacher_disagreement_score":0.75920457,"about_ca_system_score_codex":0.0007923243,"about_ca_system_score_gemma":0.0009525673,"threshold_uncertainty_score":0.99956715},"labels":[],"label_agreement":null},{"id":"W2895860424","doi":"","title":"Almost everyone in New York is raising PRICEs","year":2018,"lang":"en","type":"article","venue":"ScholarlyCommons (University of Pennsylvania)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Raising (metalworking); Economics; Mathematics","score_opus":0.2690505038872297,"score_gpt":0.4196276618596106,"score_spread":0.15057715797238092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2895860424","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94283706,0.00022857431,0.006799337,0.0037100788,0.00033694608,0.0002120825,0.000017241802,0.000036992544,0.045821678],"genre_scores_gemma":[0.97836083,0.000023624836,0.0073888735,0.00033447045,0.00008013078,1.0391207e-7,0.000004161155,0.000008275702,0.013799539],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.997205,0.00020880665,0.00037420157,0.00046692762,0.0014448899,0.00030014542],"domain_scores_gemma":[0.9978926,0.00035999445,0.00035819417,0.0007470296,0.00044471773,0.00019745965],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002887244,0.00014747755,0.00033511294,0.00070832885,0.0004164955,0.00022006506,0.0013494043,0.00012139763,0.010444318],"category_scores_gemma":[0.00035929048,0.00015613432,0.00012777754,0.001939628,0.00024450556,0.002333633,0.00032919907,0.00031876465,0.0019510451],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040818378,0.00037523566,0.640591,0.00001565366,0.00007467325,0.00003147009,0.0327103,0.000052996867,0.006250607,0.0044634747,0.18385501,0.13117138],"study_design_scores_gemma":[0.0017445051,0.00027067255,0.69037914,0.00007525427,0.000026747537,0.000007309608,0.010881392,0.0017639771,0.0005415435,0.0073709204,0.28662267,0.0003158442],"about_ca_topic_score_codex":0.0011930077,"about_ca_topic_score_gemma":0.006757151,"teacher_disagreement_score":0.13085553,"about_ca_system_score_codex":0.000096338714,"about_ca_system_score_gemma":0.0005222697,"threshold_uncertainty_score":0.998826},"labels":[],"label_agreement":null},{"id":"W2896181538","doi":"","title":"Chapter 2. Prelude to intervention","year":2009,"lang":"fr","type":"book-chapter","venue":"OpenEdition (OpenEdition)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Intervention (counseling); Psychology; Psychiatry","score_opus":0.11944104066317213,"score_gpt":0.40619658577614715,"score_spread":0.286755545112975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2896181538","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010421813,0.00063661666,0.015326604,0.14128724,0.008921216,0.0031220042,0.0010236264,0.00019861775,0.8284419],"genre_scores_gemma":[0.19773382,0.0011376652,0.006348445,0.085899174,0.0029507093,0.0005261628,0.0028042563,0.00016778258,0.702432],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.98835236,0.00041554254,0.0032315692,0.002171766,0.0048686354,0.00096013653],"domain_scores_gemma":[0.99236953,0.0006384916,0.0016751419,0.0018233261,0.0024562392,0.0010372694],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["scholarly_communication","insufficient_payload"],"category_scores_codex":[0.005199406,0.001242266,0.0013318765,0.0014214782,0.001154487,0.0015937574,0.001940121,0.00087523874,0.24900411],"category_scores_gemma":[0.0006482168,0.0012132204,0.0009949054,0.00051020423,0.00042124806,0.01847774,0.0006047312,0.001016215,0.10143582],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017605464,0.00023336755,0.000039437724,0.00003778676,0.00008571295,0.000035565314,0.00011191882,0.0005804139,0.00008345079,0.6447826,0.0082275495,0.34560615],"study_design_scores_gemma":[0.001668393,0.0017271884,0.013997844,0.0016865601,0.00022705074,0.00008953671,0.00017655398,0.0010474751,0.00061812374,0.05841622,0.91893137,0.0014137124],"about_ca_topic_score_codex":0.00007535802,"about_ca_topic_score_gemma":0.0021619233,"teacher_disagreement_score":0.9107038,"about_ca_system_score_codex":0.0007193853,"about_ca_system_score_gemma":0.00041457204,"threshold_uncertainty_score":0.9994427},"labels":[],"label_agreement":null},{"id":"W2897671883","doi":"10.1111/1911-3838.12181","title":"Barriers to Transferring Auditing Research to Standard Setters","year":2018,"lang":"en","type":"article","venue":"Accounting Perspectives","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Audit; Context (archaeology); Sketch; Knowledge transfer; Business; Knowledge management; Investment (military); Accounting; Public relations; Computer science; Political science","score_opus":0.24358999342399623,"score_gpt":0.5699568654846144,"score_spread":0.3263668720606182,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2897671883","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9361987,0.000017001554,0.007335934,0.022975234,0.00043167055,0.0003936113,0.000012801985,0.00007877364,0.032556232],"genre_scores_gemma":[0.99227047,0.0000027070066,0.0037408844,0.002229666,0.00080106023,0.000040378207,4.878002e-7,0.00002109679,0.0008932544],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99445665,0.0003399039,0.00046695102,0.0008025239,0.00327399,0.00065996597],"domain_scores_gemma":[0.995381,0.0009902304,0.00007070415,0.000577981,0.002562714,0.00041735976],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.015519457,0.00015693948,0.00023532576,0.000973086,0.0012438818,0.00090989703,0.0008654574,0.000053453095,0.004580601],"category_scores_gemma":[0.012615839,0.00013106261,0.00007895055,0.002436657,0.00020234036,0.00071895175,0.00021269078,0.00028440298,0.0021106778],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00063630333,0.00005273562,0.203385,0.00001539954,0.00008343295,0.000011916356,0.5300997,0.0011810298,0.030953912,0.012823122,0.122609936,0.098147504],"study_design_scores_gemma":[0.0007794032,0.0012682477,0.13123575,0.00017328085,0.000014144061,0.0000072988287,0.5669884,0.002174475,0.013640135,0.005873462,0.27709138,0.0007539771],"about_ca_topic_score_codex":0.000085609434,"about_ca_topic_score_gemma":0.0003669306,"teacher_disagreement_score":0.15448146,"about_ca_system_score_codex":0.000374039,"about_ca_system_score_gemma":0.00043105215,"threshold_uncertainty_score":0.9986663},"labels":[],"label_agreement":null},{"id":"W2899268585","doi":"","title":"L’évaluation des apprentissages à distance. Qu’en est-il à l’Université TÉLUQ ?","year":2018,"lang":"fr","type":"article","venue":"R-libre (Université Téluq)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Humanities; Political science; Art","score_opus":0.08437949900162679,"score_gpt":0.35919428421460464,"score_spread":0.27481478521297786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2899268585","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8922219,0.0031586925,0.017216312,0.012723955,0.0034769117,0.0006634357,0.00021467397,0.00020184895,0.070122264],"genre_scores_gemma":[0.73954576,0.0028478906,0.0038479315,0.00030988405,0.0007576889,0.000005050527,0.000094392504,0.000051906685,0.2525395],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99366456,0.00083894754,0.000681052,0.0011859292,0.0026358543,0.0009936545],"domain_scores_gemma":[0.99573463,0.00077304424,0.00056149886,0.0011548133,0.0012541617,0.0005218461],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0028330893,0.000565045,0.00061564706,0.00037001644,0.0018594265,0.00056532444,0.0017388768,0.0004474891,0.02026224],"category_scores_gemma":[0.00027848757,0.00060052326,0.0003874166,0.0026651307,0.0013208026,0.0040692156,0.00068813615,0.000459364,0.005897249],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023360309,0.00022044034,0.00656595,0.00006239852,0.00013660519,0.000055828084,0.013037532,0.00030854144,0.00045338855,0.0066583976,0.022587324,0.94968],"study_design_scores_gemma":[0.0019324305,0.0007619112,0.32498017,0.00029714825,0.0002970454,0.000044999906,0.009273839,0.030829152,0.00092596764,0.007998207,0.62195855,0.00070057897],"about_ca_topic_score_codex":0.00037748765,"about_ca_topic_score_gemma":0.0018612632,"teacher_disagreement_score":0.94897944,"about_ca_system_score_codex":0.00079891895,"about_ca_system_score_gemma":0.00095929275,"threshold_uncertainty_score":0.99964464},"labels":[],"label_agreement":null},{"id":"W2900793418","doi":"10.1177/0892020618783817","title":"Human resource policy and teacher appraisal in Ontario in the era of professional accountability","year":2018,"lang":"en","type":"article","venue":"Management in Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Concordia University","funders":"","keywords":"Accountability; Performance appraisal; Human resources; Professional development; Organisation climate; Resource (disambiguation); Human resource management; Pedagogy; Psychology; Sociology; Political science; Public relations; Management; Economics; Computer science","score_opus":0.1325735098704282,"score_gpt":0.5319026791754441,"score_spread":0.3993291693050159,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2900793418","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9129457,0.000008385607,0.000005622993,0.0033929541,0.00016854044,0.00036048846,2.4134107e-7,0.000002102992,0.083115965],"genre_scores_gemma":[0.99550986,0.0000015931685,0.00020087692,0.0005521589,0.00006833972,0.00008026335,0.0000058356723,0.0000021814628,0.0035788638],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99827945,0.00031247223,0.0004370384,0.00021791062,0.00064069533,0.000112437105],"domain_scores_gemma":[0.99932235,0.00016534583,0.00012101908,0.00032139098,0.000055488304,0.000014399339],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0058593852,0.000061128485,0.00009129972,0.0003593602,0.00005536032,0.00005522521,0.00030028756,0.00003071924,0.0005978657],"category_scores_gemma":[0.00017042743,0.00004110301,0.000012763509,0.00065905106,0.000079650534,0.00022640824,0.00008762272,0.00017212189,0.000016503856],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001704803,0.0006297931,0.8909251,0.0000073083925,0.0000015574213,8.197045e-8,0.023875559,0.00002153999,0.000008189874,0.010987759,0.0028332896,0.07069275],"study_design_scores_gemma":[0.00024234003,0.00002648805,0.93631905,0.00002779782,0.0000014920541,1.789506e-7,0.02080694,0.00016551766,0.0000032605406,0.008908967,0.033456948,0.000041027204],"about_ca_topic_score_codex":0.019388193,"about_ca_topic_score_gemma":0.21682708,"teacher_disagreement_score":0.1974389,"about_ca_system_score_codex":0.00021985118,"about_ca_system_score_gemma":0.00028475243,"threshold_uncertainty_score":0.9871418},"labels":[],"label_agreement":null},{"id":"W2901688885","doi":"10.1177/1098214018796319","title":"Honoring Lived Experience: Life Histories as a Realist Evaluation Method","year":2018,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of British Columbia; Impact; St. Michael's Hospital","funders":"Tehran University of Medical Sciences and Health Services","keywords":"Lived experience; Context (archaeology); Set (abstract data type); Psychology; Indigenous; Sociology; Epistemology; Computer science; History; Psychotherapist","score_opus":0.365242125327843,"score_gpt":0.5972764607902662,"score_spread":0.2320343354624232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2901688885","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9412824,0.00022063652,0.041305788,0.0026121202,0.0020413834,0.0004106675,0.0000017064361,0.000015982596,0.012109328],"genre_scores_gemma":[0.97877294,0.000029210303,0.019077454,0.0008598754,0.0009621045,0.000039688497,0.000004570396,0.000013610221,0.00024054649],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9871544,0.0027854333,0.0016004019,0.00038106355,0.0078237755,0.00025492083],"domain_scores_gemma":[0.9846693,0.0010605569,0.0028508175,0.00055696804,0.010598964,0.00026334843],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04510768,0.00018251284,0.00047010163,0.00061655336,0.0003340753,0.00026575255,0.00052797364,0.000048155405,0.0064059496],"category_scores_gemma":[0.020226767,0.00013850529,0.00017148687,0.0014595479,0.0003943392,0.0012161782,0.000058379395,0.00019820487,0.00022215524],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003641899,0.00009501248,0.009795102,0.000001919874,0.00006848305,0.0000016070768,0.039443724,0.0029291546,0.0027423848,0.0005268288,0.00399789,0.9400337],"study_design_scores_gemma":[0.0050085704,0.008353051,0.22183608,0.00015478441,0.00082241715,0.00028563317,0.14142163,0.5060673,0.006270869,0.046609193,0.062226076,0.0009444193],"about_ca_topic_score_codex":0.00015616823,"about_ca_topic_score_gemma":0.00005856277,"teacher_disagreement_score":0.9390893,"about_ca_system_score_codex":0.0006580432,"about_ca_system_score_gemma":0.0026842689,"threshold_uncertainty_score":0.9945023},"labels":[],"label_agreement":null},{"id":"W2902333961","doi":"10.3138/cjpe.31156","title":"Applications of Social Network Analysis in Evaluation: Challenges, Suggestions, and Opportunities for the Future","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Scope (computer science); Social network analysis; Value (mathematics); Social network (sociolinguistics); Work (physics); Computer science; Network analysis; Data science; Coding (social sciences); Management science; Knowledge management; Sociology; World Wide Web; Engineering; Social media; Social science","score_opus":0.41063426937091085,"score_gpt":0.5169534008564959,"score_spread":0.10631913148558503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902333961","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38970292,0.12976791,0.08812535,0.3430818,0.005487611,0.028525766,0.00026713006,0.0000451266,0.014996394],"genre_scores_gemma":[0.99616253,0.00030990673,0.0017310063,0.00012816994,0.0010889475,0.0004936965,0.000023659126,0.0000054396887,0.000056635945],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99674386,0.0006173459,0.0008363725,0.00015899219,0.0014581089,0.0001853282],"domain_scores_gemma":[0.99302846,0.00050718774,0.00074601336,0.00022539403,0.0053512105,0.00014170687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.028573781,0.00008793011,0.00024377427,0.00071820075,0.00041024128,0.00014337662,0.000317808,0.00007941323,0.0007180628],"category_scores_gemma":[0.00061463774,0.00006122147,0.00012521812,0.0012306742,0.00022732149,0.00027834467,0.000010294542,0.00010994487,0.000002131532],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013599276,0.00001823754,0.0042043077,0.000003878431,0.00009982216,1.246814e-7,0.0016285463,0.001422014,4.5254282e-7,0.0074631493,0.0019193756,0.9832265],"study_design_scores_gemma":[0.0010312013,0.00038701142,0.3371518,0.000020281619,0.0012824682,0.0000072768194,0.015342525,0.21549246,0.0000031427346,0.032955617,0.39619476,0.00013146627],"about_ca_topic_score_codex":0.00009044239,"about_ca_topic_score_gemma":0.06934499,"teacher_disagreement_score":0.98309505,"about_ca_system_score_codex":0.00016176306,"about_ca_system_score_gemma":0.0030386378,"threshold_uncertainty_score":0.9903159},"labels":[],"label_agreement":null},{"id":"W2902608297","doi":"10.3138/cjpe.42195","title":"One-Room School: The Summer Institute in Program Evaluation","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"General partnership; Medical education; Program evaluation; Community service; Service-learning; Service (business); Psychology; Sociology; Pedagogy; Political science; Public relations; Business; Medicine; Public administration; Marketing","score_opus":0.5726173863159311,"score_gpt":0.5775178005696558,"score_spread":0.004900414253724783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902608297","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9569183,0.0006618337,0.0006776168,0.011977748,0.003135796,0.007272449,0.0000039621705,0.00002414537,0.019328145],"genre_scores_gemma":[0.9943823,0.000011138792,0.0037983507,0.000546677,0.0006614618,0.0004012694,0.00001871875,0.000013493477,0.00016655854],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99191654,0.001380231,0.0013880923,0.00031828592,0.004550449,0.00044639682],"domain_scores_gemma":[0.9920212,0.00018444234,0.0008788648,0.000552563,0.005845926,0.0005169774],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.043301262,0.0001686297,0.0002718938,0.0008518868,0.0003986523,0.00080015353,0.00085718906,0.0001265022,0.006005001],"category_scores_gemma":[0.0079377545,0.00011768917,0.0001378748,0.002052488,0.00032424534,0.0015062948,0.000028528377,0.00040501315,0.00047547976],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002242133,0.00009095615,0.05424099,0.0000017344258,0.000022343065,0.0000013620232,0.001035823,0.0019507059,0.00001153321,0.00023606942,0.0050763725,0.9373097],"study_design_scores_gemma":[0.0019656373,0.0011448793,0.4624439,0.00009577483,0.00016729887,0.000025418927,0.0011693275,0.22397609,0.00006966419,0.017795136,0.29091918,0.00022771144],"about_ca_topic_score_codex":0.0014360775,"about_ca_topic_score_gemma":0.22115166,"teacher_disagreement_score":0.937082,"about_ca_system_score_codex":0.0010139961,"about_ca_system_score_gemma":0.01021763,"threshold_uncertainty_score":0.9953935},"labels":[],"label_agreement":null},{"id":"W2902911821","doi":"10.3138/cjpe.42238","title":"Readiness in Evaluation: Three Prompts for Evaluators","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Agency (philosophy); Process (computing); Tacit knowledge; Psychology; Knowledge management; Power (physics); Public relations; Process management; Computer science; Business; Sociology; Political science","score_opus":0.5904033203647878,"score_gpt":0.6029827397166689,"score_spread":0.012579419351881116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902911821","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.974455,0.0006214544,0.004366106,0.0042742123,0.003394602,0.006868071,0.000014665269,0.000014090732,0.005991822],"genre_scores_gemma":[0.9922478,0.000002455108,0.006028073,0.0001818686,0.0007800759,0.000612942,0.000021829956,0.000017605775,0.00010732543],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9925593,0.0008169703,0.0015730489,0.00037048152,0.004219698,0.00046046352],"domain_scores_gemma":[0.9834032,0.00042138976,0.000971183,0.0004668885,0.014282627,0.00045468996],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.063497104,0.00018392658,0.00036253623,0.001427281,0.00029207984,0.00043687422,0.00071096094,0.00013516708,0.0045139906],"category_scores_gemma":[0.011495357,0.00014558913,0.00016386225,0.0016242337,0.0002010507,0.00096285314,0.000014890153,0.00018898059,0.0001271397],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058497266,0.000055500383,0.053284712,0.000005511319,0.000023490213,0.0000014415118,0.0011127853,0.0012200288,0.00003359584,0.0005938663,0.0047049485,0.9389056],"study_design_scores_gemma":[0.0039932807,0.0017148533,0.2812471,0.00012298237,0.0001966492,0.00003758544,0.00090690714,0.56305295,0.0002200274,0.09448003,0.05374289,0.00028475016],"about_ca_topic_score_codex":0.0003880509,"about_ca_topic_score_gemma":0.124534816,"teacher_disagreement_score":0.93862087,"about_ca_system_score_codex":0.0009836396,"about_ca_system_score_gemma":0.013365749,"threshold_uncertainty_score":0.99683124},"labels":[],"label_agreement":null},{"id":"W2903094745","doi":"10.3138/cjpe.42205","title":"L’implication des parties prenantes dans la démarche évaluative : facteurs de succès et leçons à retenir","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; École Nationale d'Administration Publique","funders":"","keywords":"Stakeholder; Thematic analysis; Key (lock); Political science; Public relations; Business; Psychology; Sociology; Knowledge management; Computer science; Qualitative research; Social science","score_opus":0.4102600005407451,"score_gpt":0.539958481627281,"score_spread":0.12969848108653592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2903094745","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97662634,0.0002226841,0.008569239,0.0037658336,0.0003152077,0.00087462395,0.000017138025,0.00001964352,0.009589287],"genre_scores_gemma":[0.9923123,0.00002917872,0.006955755,0.00017452195,0.00018061796,0.00011688642,0.000015913834,0.000014532102,0.00020031042],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9943791,0.002193024,0.00089503796,0.00025775217,0.0018631608,0.00041193597],"domain_scores_gemma":[0.99262106,0.00071948237,0.0007717054,0.00035185856,0.005006821,0.00052908243],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.027883003,0.0001595814,0.00023711976,0.00057352206,0.00045384438,0.0006168356,0.0005629035,0.000107230815,0.0010655256],"category_scores_gemma":[0.008218068,0.00012066512,0.00013537647,0.0008608154,0.00067395944,0.001044375,0.000021296759,0.0002572313,0.00008624572],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038226477,0.000060825158,0.10918338,0.0000059042472,0.00005410992,0.0000033785898,0.026036035,0.0007300276,0.0013110123,0.002643142,0.002723782,0.85721016],"study_design_scores_gemma":[0.0008858505,0.0013111995,0.8154436,0.00012308669,0.00015420669,0.0001347727,0.009967046,0.042537358,0.0045674457,0.07781396,0.046813548,0.00024797476],"about_ca_topic_score_codex":0.0008304385,"about_ca_topic_score_gemma":0.047647312,"teacher_disagreement_score":0.8569622,"about_ca_system_score_codex":0.0007755132,"about_ca_system_score_gemma":0.009789729,"threshold_uncertainty_score":0.99984765},"labels":[],"label_agreement":null},{"id":"W2903255761","doi":"10.3138/cjpe.42202","title":"Où en sommes-nous avec l’implication des parties prenantes?","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Theme (computing); Value (mathematics); Selection (genetic algorithm); Process (computing); Business; Political science; Psychology; Sociology; Knowledge management; Computer science","score_opus":0.23400314505815445,"score_gpt":0.493716958982599,"score_spread":0.25971381392444454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2903255761","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9862912,0.0005325228,0.0034401685,0.0030045772,0.0009113044,0.0009506615,0.0000066801244,0.000018967256,0.0048438804],"genre_scores_gemma":[0.9942583,0.000020173855,0.0046801423,0.0001831505,0.000528773,0.000070739276,0.0000087567105,0.000010760923,0.00023921828],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9960597,0.00060031895,0.0009482897,0.0002127676,0.001801183,0.00037772144],"domain_scores_gemma":[0.9931751,0.00026352322,0.000728655,0.00036404026,0.004955831,0.0005128528],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016074164,0.00012816628,0.0002093578,0.00058068667,0.00040481574,0.00053529994,0.00053884863,0.0000858601,0.0029916372],"category_scores_gemma":[0.0048389705,0.000094982635,0.00011289928,0.0007522766,0.00029746242,0.0009388545,0.000015338575,0.00016023594,0.0003397349],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015234046,0.000037192167,0.03615075,0.0000035731994,0.0000217872,0.0000016750705,0.007449638,0.00022045741,0.0001377707,0.00041916655,0.004403139,0.9511396],"study_design_scores_gemma":[0.001708612,0.002648927,0.655597,0.00015773585,0.00019237498,0.00021637544,0.005439134,0.07684338,0.0031000064,0.075677395,0.17802893,0.00039018554],"about_ca_topic_score_codex":0.00029590502,"about_ca_topic_score_gemma":0.018703792,"teacher_disagreement_score":0.95074946,"about_ca_system_score_codex":0.00048714064,"about_ca_system_score_gemma":0.0044645364,"threshold_uncertainty_score":0.9992023},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W2903412726","doi":"10.3138/cjpe.53091","title":"Chris Fox, Robert Grimm, and Rute Caldeira. (2017). <i>An Introduction to Evaluation</i> .","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Law and economics; Economics","score_opus":0.31517400767919956,"score_gpt":0.5246237159077208,"score_spread":0.20944970822852127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2903412726","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9581528,0.00076053414,0.0034144947,0.026602188,0.0044811065,0.0027252417,0.000013570102,0.000022985345,0.003827112],"genre_scores_gemma":[0.98982704,0.000009393306,0.0064064935,0.00078746217,0.0025463742,0.000118299926,0.00003136172,0.000016558923,0.00025703214],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99356186,0.001014976,0.0011063475,0.00046269392,0.0034641528,0.00038995003],"domain_scores_gemma":[0.9883607,0.00012056514,0.0006646491,0.0005637801,0.009413137,0.0008771641],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.032562997,0.00018716094,0.000294466,0.0010474768,0.0005016501,0.0007887737,0.0004912984,0.00011417064,0.004276345],"category_scores_gemma":[0.0050625326,0.00015203221,0.00008463969,0.0011175085,0.00018109458,0.001503692,0.000025006808,0.00021531027,0.00022532536],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035348497,0.000042255557,0.00478878,0.000002365624,0.000025039131,0.0000014947403,0.0018610748,0.00087997474,0.00022225778,0.0005099515,0.034462847,0.95716864],"study_design_scores_gemma":[0.0021974768,0.0035944714,0.16613711,0.000049062055,0.00032993444,0.00023260122,0.0017113676,0.14282677,0.00064990966,0.021870352,0.65994114,0.00045978805],"about_ca_topic_score_codex":0.0007660686,"about_ca_topic_score_gemma":0.036319513,"teacher_disagreement_score":0.95670885,"about_ca_system_score_codex":0.0005678689,"about_ca_system_score_gemma":0.004797442,"threshold_uncertainty_score":0.9966339},"labels":[],"label_agreement":null},{"id":"W2904361790","doi":"10.4324/9781315680361-7","title":"Developing High-Quality Public Education in Canada","year":2016,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Investment (military); Public investment; Quality (philosophy); Public sector; Reading (process); Private sector; School system; Service (business); Political science; Public service; Public administration; Economic growth; Business; Public relations; Economics; Marketing; Sociology; Public fund; Politics; Pedagogy; Law","score_opus":0.3843093435818527,"score_gpt":0.5090660011246513,"score_spread":0.12475665754279858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2904361790","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001578455,0.00006057475,0.0011267585,0.0145922,0.001403254,0.00019790867,0.000014893811,0.000011993955,0.98101395],"genre_scores_gemma":[0.08643881,0.000074882926,0.0009324709,0.0030241176,0.00013329525,0.000012852906,0.000021687407,0.000011774594,0.9093501],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961429,0.00008130277,0.0010172237,0.00043388797,0.0021289717,0.00019570459],"domain_scores_gemma":[0.997604,0.0006299572,0.00043702783,0.0005436099,0.00068380265,0.00010158337],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0029673986,0.00017655877,0.0003162734,0.0003644275,0.0000655717,0.00013654813,0.00053825404,0.00010978437,0.025820594],"category_scores_gemma":[0.0004238186,0.00011195725,0.00004282942,0.00009630056,0.000025025594,0.00032771923,0.00009855026,0.00014967153,0.0010721519],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012811618,0.0000022972872,0.0026613409,0.000002488266,0.0000032461319,2.8350112e-7,0.000008251026,6.309235e-7,7.070599e-7,0.6969641,0.013902531,0.28645283],"study_design_scores_gemma":[0.00011515421,0.000004006913,0.025737662,0.000053682284,0.000001497871,7.41619e-7,0.00010285171,0.00001000693,0.000009972581,0.25145346,0.7223004,0.00021053164],"about_ca_topic_score_codex":0.37203977,"about_ca_topic_score_gemma":0.9855853,"teacher_disagreement_score":0.7083979,"about_ca_system_score_codex":0.0022350282,"about_ca_system_score_gemma":0.05767583,"threshold_uncertainty_score":0.9997056},"labels":[],"label_agreement":null},{"id":"W2904455770","doi":"10.15402/esj.2015.1.a014","title":"Book Review: LearningLearning and Teaching Community-Based Research: Linking Pedagogy to Practice by Etmanski, C., Budd, L.H., and Dawson, T. (ed.) 2014. University of Toronto Press. Toronto, ON. 388pp.","year":2015,"lang":"en","type":"article","venue":"Engaged Scholar Journal Community-Engaged Research Teaching and Learning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Participatory action research; Action research; Citizen journalism; Community-based participatory research; Sight; Sociology; Action (physics); Quality (philosophy); Dissemination; Set (abstract data type); Medical education; Pedagogy; Psychology; Political science; Medicine; Computer science; World Wide Web","score_opus":0.4174538899888977,"score_gpt":0.5398404844604143,"score_spread":0.12238659447151662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2904455770","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.52495813,0.41510248,0.004398778,0.0129833985,0.00033150928,0.001571551,0.000018136789,0.00022235139,0.040413648],"genre_scores_gemma":[0.9434754,0.03777142,0.0066838805,0.0031150195,0.00015238857,0.000009548654,0.000040246592,0.000079384445,0.008672699],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.24385555,0.7498047,0.00087210163,0.00050473027,0.0041047554,0.0008581962],"domain_scores_gemma":[0.67447,0.32067132,0.0006502793,0.0011009318,0.0019900152,0.001117451],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.91290945,0.00042400477,0.00084182573,0.00044191696,0.22906911,0.0019855374,0.001890176,0.00028652835,0.0005588498],"category_scores_gemma":[0.7264486,0.00038578734,0.00012391242,0.000228032,0.0005834769,0.0044262987,0.0017328669,0.43206608,0.000025263178],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007171449,0.0005329368,0.0018127769,0.00027921566,0.00012639418,0.000027824175,0.4933105,0.0019223441,0.0016090526,0.00007319259,0.38821903,0.11136958],"study_design_scores_gemma":[0.0010472629,0.0016258098,0.00060302333,0.0012688994,0.000027396358,0.0000503252,0.42332932,0.0011538924,0.00001693696,0.000023537572,0.5706285,0.00022508876],"about_ca_topic_score_codex":0.019284135,"about_ca_topic_score_gemma":0.0010571264,"teacher_disagreement_score":0.43177956,"about_ca_system_score_codex":0.00073772535,"about_ca_system_score_gemma":0.000678433,"threshold_uncertainty_score":0.9998594},"labels":[],"label_agreement":null},{"id":"W2904511429","doi":"10.4000/ced.745","title":"Les raisons du faible usage des résultats d’évaluation externe par les enseignants. Étude croisée dans trois contextes éducatifs","year":2017,"lang":"fr","type":"article","venue":"Contextes et didactiques","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Humanities; Political science; Valuation (finance); Art; Business","score_opus":0.278966682574041,"score_gpt":0.47761216878829127,"score_spread":0.19864548621425027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2904511429","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9165168,0.010836533,0.023823403,0.0149259,0.0025538285,0.001098461,0.00023078045,0.0001938163,0.029820487],"genre_scores_gemma":[0.9558409,0.007228009,0.0048913257,0.0009534164,0.00050565216,0.00024788687,0.00005650158,0.00009310431,0.030183196],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9910757,0.0024176603,0.0019611744,0.001305019,0.0021360265,0.0011044472],"domain_scores_gemma":[0.9886754,0.004327393,0.0020585174,0.0021816425,0.0022595818,0.0004974262],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["sts","insufficient_payload"],"category_scores_codex":[0.01039906,0.0009009922,0.0011824473,0.00042223558,0.00460109,0.004450168,0.0023461848,0.00049713237,0.0061517917],"category_scores_gemma":[0.010686731,0.0007788092,0.000539529,0.00035515404,0.0027381706,0.0051327464,0.0005204116,0.0007400778,0.00087277923],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017006708,0.0006915196,0.22128254,0.00009594661,0.00019001101,0.00002615478,0.099308774,0.00012907834,0.009631591,0.008682239,0.0070196553,0.6527724],"study_design_scores_gemma":[0.002447908,0.00072777545,0.80548406,0.0012307367,0.0002616149,0.000058698977,0.03110032,0.009804612,0.02596673,0.017378049,0.10438328,0.0011562038],"about_ca_topic_score_codex":0.016510101,"about_ca_topic_score_gemma":0.0377027,"teacher_disagreement_score":0.6516162,"about_ca_system_score_codex":0.00047106866,"about_ca_system_score_gemma":0.001184589,"threshold_uncertainty_score":0.9999758},"labels":[],"label_agreement":null},{"id":"W2904539426","doi":"10.6000/1929-7092.2018.07.89","title":"The Politics of Youth Participation in Social Intervention Programmes in Ghana: Implications for Participatory Monitoring and Evaluation (PM&amp;E)","year":2018,"lang":"en","type":"article","venue":"Journal of Reviews on Global Economics","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Citizen journalism; Politics; Intervention (counseling); Participatory evaluation; Monitoring and evaluation; Political science; Economic growth; Socioeconomics; Sociology; Public administration; Economics; Medicine; Nursing","score_opus":0.5076047388678964,"score_gpt":0.5914271920399726,"score_spread":0.08382245317207626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2904539426","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9959797,0.0014487485,0.0004470233,0.0011773008,0.00030960835,0.00048211578,0.000011854846,9.964825e-7,0.00014259896],"genre_scores_gemma":[0.9983399,0.000686077,0.0006568615,0.000037132366,0.00021909979,0.000047592443,0.0000018616558,0.000002550981,0.000008918399],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9977,0.00033700018,0.0015039778,0.000112033646,0.00020558333,0.00014140143],"domain_scores_gemma":[0.99776155,0.00025651918,0.0012635298,0.00013911154,0.0005360617,0.000043233882],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012585626,0.00006878055,0.0002651498,0.00010223331,0.00011949562,0.000087461776,0.00017602628,0.000039240625,0.0000074636073],"category_scores_gemma":[0.0014646923,0.00004664965,0.00011033585,0.00020997415,0.00007493179,0.00026162213,0.000021635973,0.00006132374,0.0000041390117],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007996427,0.00014816155,0.30199134,0.000017396454,0.00001359607,1.4153814e-8,0.0017934267,0.00021341916,0.0000053051463,0.008778337,0.00020916488,0.6867499],"study_design_scores_gemma":[0.0015494964,0.00054121355,0.92788625,0.00022376867,0.000080815866,0.0000015288629,0.0030615309,0.0063153435,0.00007847314,0.042608432,0.017542541,0.00011063587],"about_ca_topic_score_codex":0.000010467968,"about_ca_topic_score_gemma":0.00048320013,"teacher_disagreement_score":0.68663925,"about_ca_system_score_codex":0.00030851533,"about_ca_system_score_gemma":0.00015670725,"threshold_uncertainty_score":0.4361952},"labels":[],"label_agreement":null},{"id":"W2905234520","doi":"10.4324/9781315130132-15","title":"Getting Good Data to Evaluate Employment Equity Initiatives: An Example from Canada","year":2017,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Equity (law); Business; Public economics; Political science; Economics; Law","score_opus":0.7119180553691533,"score_gpt":0.5548941161604064,"score_spread":0.1570239392087469,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2905234520","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021099334,0.00007369792,0.0014582119,0.001566776,0.0012008803,0.00069070794,0.0013833357,0.000045145818,0.9914713],"genre_scores_gemma":[0.14254093,0.00006938845,0.004985782,0.0076985774,0.0010409155,0.00003820486,0.0027436528,0.000082100836,0.84080046],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9905667,0.00017970921,0.0012415282,0.0016781988,0.0059100017,0.00042390212],"domain_scores_gemma":[0.990576,0.001090407,0.0009891159,0.0060439855,0.0008035021,0.00049696193],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008546172,0.0004494757,0.0007104104,0.00019486749,0.0006097507,0.0010117227,0.0052151317,0.00017291975,0.03753969],"category_scores_gemma":[0.0007260564,0.00033657489,0.00007292996,0.000038269172,0.00006888397,0.0013923009,0.003372439,0.0003636862,0.0010941154],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009970709,0.00008949827,0.001969625,0.000012656437,0.00040505605,0.000053621654,0.0029624766,0.00026118394,0.00010498277,0.050958734,0.28111324,0.66196924],"study_design_scores_gemma":[0.0005640726,0.00015184972,0.011752344,0.000116771465,0.00008664227,0.0000013056211,0.00064521655,0.003965666,0.000058392343,0.0329321,0.9489779,0.0007477514],"about_ca_topic_score_codex":0.7128357,"about_ca_topic_score_gemma":0.96960616,"teacher_disagreement_score":0.6678647,"about_ca_system_score_codex":0.00043760543,"about_ca_system_score_gemma":0.00506829,"threshold_uncertainty_score":0.9999086},"labels":[],"label_agreement":null},{"id":"W2906039525","doi":"10.15402/esj.v3i2.333","title":"Developing an Evaluation Capacity Building Network in the Field of Early Childhood Development","year":2018,"lang":"en","type":"article","venue":"Engaged Scholar Journal Community-Engaged Research Teaching and Learning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Capacity building; Citizen journalism; Context (archaeology); Field (mathematics); Early childhood; Work (physics); Capacity development; Stakeholder engagement; Community development; Stakeholder; Sociology; Engineering ethics; Political science; Public relations; Psychology; Computer science; Engineering; Environmental planning; Developmental psychology; Geography; World Wide Web","score_opus":0.5309831729930177,"score_gpt":0.5467348984614054,"score_spread":0.015751725468387767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2906039525","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9901244,0.00017006179,0.00679273,0.0007472473,0.00018668277,0.00031146835,2.6593605e-7,0.000021266665,0.0016458943],"genre_scores_gemma":[0.9729524,0.00003200253,0.026348125,0.0002909179,0.00029775125,0.000015691698,0.0000032768069,0.000016717871,0.00004309064],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.13549863,0.85884464,0.0009812331,0.00026529035,0.0038219471,0.0005882916],"domain_scores_gemma":[0.6989662,0.2983455,0.00043187747,0.00063834863,0.0014421059,0.0001759182],"candidate_categories":["metaresearch","sts","scholarly_communication","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.9582144,0.00019208422,0.00032061213,0.000859839,0.25926715,0.0016402373,0.00158253,0.00014091986,0.00015861758],"category_scores_gemma":[0.7119093,0.00013213189,0.00006612566,0.0012056956,0.00020373591,0.0015843206,0.00035494915,0.37926918,0.000016289227],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043656448,0.00010561088,0.026344422,0.0000066309,0.000025669344,0.0000017792468,0.7585791,0.0014920264,0.00081992056,0.00014195056,0.00011935694,0.21231991],"study_design_scores_gemma":[0.00067123485,0.0006765254,0.4243174,0.00027898492,0.00000811348,0.000037130754,0.56121755,0.0033687255,0.00027781667,0.0033665954,0.005611104,0.00016886981],"about_ca_topic_score_codex":0.0002675763,"about_ca_topic_score_gemma":0.00037152527,"teacher_disagreement_score":0.5634676,"about_ca_system_score_codex":0.00021070389,"about_ca_system_score_gemma":0.00078875606,"threshold_uncertainty_score":0.99939615},"labels":[],"label_agreement":null},{"id":"W2907253172","doi":"","title":"Initial Teacher Education in Ontario: The first year of four-semester teacher education programs","year":2017,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Teacher education; Mathematics education; Pedagogy; Medical education; Psychology; Medicine","score_opus":0.2456635140041077,"score_gpt":0.4999106561532072,"score_spread":0.2542471421490995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2907253172","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7609081,0.000008568876,0.000068052,0.0038042814,0.0006418563,0.00035890096,2.0189356e-7,0.0000067100996,0.2342033],"genre_scores_gemma":[0.9185538,0.0000018359218,0.0005570941,0.00030876714,0.00012567687,0.000078164194,0.0000053677886,0.000005518412,0.08036373],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99827534,0.00009792412,0.00045706765,0.00022764006,0.0008081182,0.00013390665],"domain_scores_gemma":[0.99838394,0.000061584615,0.00034564716,0.0008798303,0.00028764302,0.000041385134],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0025886595,0.000091482776,0.00013193321,0.00011541981,0.00021697374,0.0003854616,0.0007244292,0.00006416482,0.004742317],"category_scores_gemma":[0.00034182175,0.000052797124,0.000059410555,0.000106686064,0.00010137013,0.0006410509,0.00009276203,0.00017980723,0.00026029145],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010893077,0.00037807724,0.8055224,0.0000016057717,0.0000022169913,3.9569493e-8,0.0014502885,0.0000032439893,0.0000037949721,0.0008906642,0.00861922,0.18311757],"study_design_scores_gemma":[0.00021835792,0.000043760057,0.886762,0.000023421213,0.000005761999,0.0000011492789,0.0027035933,0.00029716056,0.00003173955,0.0032726151,0.10656845,0.00007195606],"about_ca_topic_score_codex":0.026494356,"about_ca_topic_score_gemma":0.44911543,"teacher_disagreement_score":0.42262104,"about_ca_system_score_codex":0.00011875484,"about_ca_system_score_gemma":0.0023427946,"threshold_uncertainty_score":0.9961675},"labels":[],"label_agreement":null},{"id":"W2908468726","doi":"10.56645/jmde.v14i31.497","title":"Seeking Culturally Safe Developmental Evaluation: Supporting the Shift in Services for Indigenous Children","year":2018,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Concordia University","funders":"Health Canada","keywords":"Indigenous; Participatory action research; Mainstream; Psychosocial; Traditional knowledge; Context (archaeology); Intervention (counseling); Citizen journalism; Community-based participatory research; Nursing; Sociology; Psychology; Medical education; Medicine; Political science; Geography; Psychotherapist","score_opus":0.1359810264428348,"score_gpt":0.4949917022111761,"score_spread":0.35901067576834134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2908468726","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9920376,0.00019564632,0.0018693588,0.0027488025,0.000785093,0.0017072167,0.00000703115,0.0000067628216,0.0006425186],"genre_scores_gemma":[0.99392897,0.000010764853,0.004988817,0.00015675719,0.00073136785,0.000072624076,0.00003665345,0.0000125767565,0.000061452825],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9915394,0.0009352744,0.0020260985,0.00033048153,0.0048382278,0.0003304713],"domain_scores_gemma":[0.9930476,0.0008120599,0.002076857,0.00026956454,0.003707135,0.00008680556],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.056312807,0.00019219793,0.00031955543,0.000446208,0.00079067715,0.00030635466,0.0008510069,0.00009414906,0.0010168969],"category_scores_gemma":[0.0015895113,0.00011270109,0.00016697649,0.0007572734,0.000090610025,0.0014210998,0.00014955406,0.00023150274,0.00008264642],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003829511,0.00022252167,0.6181486,0.00001402192,0.00008863457,0.0000014965965,0.091939114,0.010685379,0.0015638154,0.00003289183,0.00031647162,0.27660406],"study_design_scores_gemma":[0.0020772498,0.00034977082,0.78273183,0.00008175994,0.00008753181,0.000058739628,0.011145844,0.19492055,0.00033676747,0.007876771,0.00019169766,0.00014148925],"about_ca_topic_score_codex":0.000019850566,"about_ca_topic_score_gemma":0.0009070319,"teacher_disagreement_score":0.27646255,"about_ca_system_score_codex":0.00061766116,"about_ca_system_score_gemma":0.0019038232,"threshold_uncertainty_score":0.9998963},"labels":[],"label_agreement":null},{"id":"W2910756251","doi":"10.4324/9781351322447-7","title":"Auditing the Evaluation Function in Canada","year":2018,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Audit; Function (biology); Computer science; Business; Accounting; Biology; Evolutionary biology","score_opus":0.3244702428377306,"score_gpt":0.46265586023821387,"score_spread":0.13818561740048324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2910756251","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020000746,0.00007114006,0.00027038148,0.0017040073,0.0013581757,0.00038585588,0.0000055977216,0.0000077459,0.994197],"genre_scores_gemma":[0.29267722,0.000017569066,0.0000383412,0.0018095834,0.00038641275,0.000023495038,0.00002527654,0.000011896723,0.70501024],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9946348,0.00011881797,0.0006878436,0.00034222772,0.004075152,0.00014116864],"domain_scores_gemma":[0.99745584,0.000688061,0.00043009533,0.00052212516,0.00086613634,0.000037766895],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008920063,0.0001443197,0.00017991046,0.0001640552,0.00013944112,0.00011740931,0.00037596127,0.000080089434,0.118341826],"category_scores_gemma":[0.00051124545,0.000079733734,0.000050621198,0.00010468685,0.00003723959,0.0001631083,0.000065612825,0.00021215805,0.0016453741],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020383754,0.000004222734,0.0019727894,0.000003021087,0.000023842691,0.0000011032073,0.00024776105,0.00085375545,0.0000031290383,0.038959622,0.4109315,0.5469789],"study_design_scores_gemma":[0.00022665839,0.000036173427,0.020726334,0.000036441124,0.000029554456,0.0000016004577,0.00072419934,0.053714152,0.0000040196323,0.12542942,0.7988941,0.00017731887],"about_ca_topic_score_codex":0.20500888,"about_ca_topic_score_gemma":0.9872586,"teacher_disagreement_score":0.78224975,"about_ca_system_score_codex":0.0009190085,"about_ca_system_score_gemma":0.005114265,"threshold_uncertainty_score":0.999132},"labels":[],"label_agreement":null},{"id":"W2911457407","doi":"10.22230/ijepl.2019v14n1a866","title":"Preparing Instructional Leaders: Evaluating a Regional Program to Gauge Perceived Effectiveness","year":2019,"lang":"en","type":"article","venue":"International Journal of Education Policy and Leadership","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"St. Francis Xavier University; Acadia University","funders":"","keywords":"Socioemotional selectivity theory; Sample (material); Set (abstract data type); Poverty; Psychology; Focus group; Mental health; Medical education; Nova scotia; Educational leadership; Instructional leadership; Public relations; Political science; Pedagogy; Sociology; Medicine; Computer science","score_opus":0.45679863126794124,"score_gpt":0.5810869148325457,"score_spread":0.12428828356460447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2911457407","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97166735,0.000104975246,0.00039266993,0.02235876,0.0019286419,0.0003634624,0.0000033018596,0.000013158342,0.0031676746],"genre_scores_gemma":[0.9899525,0.000011493696,0.003939918,0.0029452138,0.0011159916,0.000028570024,0.000007102222,0.000010085584,0.0019891004],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99622864,0.00038682835,0.00075120805,0.0002794342,0.002155442,0.00019845723],"domain_scores_gemma":[0.99599123,0.0010215271,0.00054188597,0.0001789944,0.0020706777,0.0001956676],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036708117,0.00013940681,0.00022714326,0.0010603622,0.00008820174,0.00034261256,0.00058912503,0.000069259426,0.00052115595],"category_scores_gemma":[0.0027972576,0.000113271424,0.00012890407,0.0004680823,0.00009187347,0.0009015251,0.000054613516,0.00024100077,0.0001487229],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009887564,0.0006433242,0.09893364,0.0000559993,0.00023279352,0.0000014256043,0.014379508,0.002787181,0.006102962,0.02655954,0.006520346,0.84279454],"study_design_scores_gemma":[0.001843882,0.00094418,0.8427104,0.0005747963,0.000027977863,0.0005191994,0.026339943,0.0020502536,0.00030473756,0.016739141,0.10762826,0.0003172538],"about_ca_topic_score_codex":0.00004147382,"about_ca_topic_score_gemma":0.000011705787,"teacher_disagreement_score":0.84247726,"about_ca_system_score_codex":0.00030825724,"about_ca_system_score_gemma":0.0018795176,"threshold_uncertainty_score":0.5706292},"labels":[],"label_agreement":null},{"id":"W2911470978","doi":"","title":"Working Group Symposium I: Ethics in Action Research: Process, Responsibilities, and Strategies","year":2018,"lang":"en","type":"article","venue":"2018 Conference of the Canadian Society for the Study of Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bishop's University; Nipissing University","funders":"","keywords":"Action (physics); Process (computing); Action research; Engineering ethics; Group (periodic table); Group process; Research ethics; Political science; Public relations; Sociology; Environmental ethics; Psychology; Social psychology; Computer science; Engineering; Pedagogy; Philosophy","score_opus":0.6245943110450399,"score_gpt":0.5662039350939082,"score_spread":0.05839037595113172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2911470978","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98473805,0.0000585624,0.000047112495,0.010326593,0.0008100788,0.0010926658,0.0000060892676,0.0000026085327,0.0029182322],"genre_scores_gemma":[0.99819225,0.000035490608,0.00012569419,0.00013303095,0.00009704375,0.00009283666,0.0000014743599,0.0000045913453,0.0013176067],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9978664,0.00040708916,0.00037260633,0.00022353385,0.00093857205,0.00019177691],"domain_scores_gemma":[0.99596655,0.0015639691,0.00023872197,0.0004776871,0.0016952784,0.00005781252],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012151508,0.00007273354,0.00012650766,0.00013207586,0.0008852222,0.00019739497,0.0006086828,0.00008730915,0.00006232894],"category_scores_gemma":[0.0014109445,0.000044085726,0.00005783065,0.0007178387,0.0007000888,0.00027633022,0.00004987599,0.00028736182,0.0000015868617],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022256198,0.0005659048,0.1091501,0.00012442612,0.000109305925,2.3862603e-8,0.7476674,0.00015390385,0.0013581018,0.08605736,0.018518578,0.036072385],"study_design_scores_gemma":[0.00031632345,0.0004249491,0.15099151,0.00010970514,0.00002113867,4.4263786e-7,0.774027,0.0025719067,0.00017787,0.0621214,0.009154241,0.00008349878],"about_ca_topic_score_codex":0.047535155,"about_ca_topic_score_gemma":0.78910625,"teacher_disagreement_score":0.74157107,"about_ca_system_score_codex":0.00020603971,"about_ca_system_score_gemma":0.0075868736,"threshold_uncertainty_score":0.9980392},"labels":[],"label_agreement":null},{"id":"W2912843544","doi":"10.22230/ijepl.2019v14n6a859","title":"Addressing Wicked Educational Problems through Inter-Sectoral Policy Development: Lessons from Manitoba's Healthy Child Initiative","year":2019,"lang":"en","type":"article","venue":"International Journal of Education Policy and Leadership","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Operationalization; Context (archaeology); Government (linguistics); Horizontal and vertical; Policy development; Political science; Economic growth; Business; Public administration; Economics; Geography","score_opus":0.6128154306527833,"score_gpt":0.5551728586631098,"score_spread":0.057642571989673486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912843544","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5961689,0.0011210854,0.0016130222,0.37665644,0.0045653745,0.00033704314,0.000042734384,0.000015504962,0.019479897],"genre_scores_gemma":[0.9773712,0.00008188256,0.0017833355,0.015878672,0.003304345,0.000013811974,0.000061704646,0.000015690452,0.0014893273],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9962886,0.0003206136,0.0011804664,0.00032066138,0.0016219254,0.00026775658],"domain_scores_gemma":[0.9957245,0.0010012264,0.0012743969,0.0002119033,0.0015960657,0.0001919118],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013970168,0.00020226518,0.00029627187,0.0010952957,0.00019538343,0.00047480382,0.0008162697,0.000101268655,0.0015249683],"category_scores_gemma":[0.0017882052,0.00016614489,0.00011292175,0.00053931505,0.00016009899,0.0016450763,0.00007980499,0.0004143939,0.0002485327],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009636685,0.0024336686,0.28499988,0.00011021299,0.0009167156,0.0000038974395,0.20602214,0.00071442797,0.0005297093,0.17439903,0.029483033,0.2994236],"study_design_scores_gemma":[0.0026818672,0.00029943633,0.5391096,0.0012173302,0.000030556035,0.00023161795,0.07066877,0.0002839596,0.0007255693,0.10294701,0.28124225,0.00056205754],"about_ca_topic_score_codex":0.0005945895,"about_ca_topic_score_gemma":0.00036616068,"teacher_disagreement_score":0.38120234,"about_ca_system_score_codex":0.0006142442,"about_ca_system_score_gemma":0.0072889836,"threshold_uncertainty_score":0.9993878},"labels":[],"label_agreement":null},{"id":"W2913022484","doi":"10.22230/ijepl.2019v14n10a887","title":"Education Research in the Canadian Context","year":2019,"lang":"en","type":"article","venue":"International Journal of Education Policy and Leadership","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Acadia University; University of Saskatchewan; Queen's University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Political science; Public administration; Public relations; Context (archaeology); Public policy; Sociology; Policy analysis; Government (linguistics); Law","score_opus":0.6685152480991206,"score_gpt":0.6222147943227643,"score_spread":0.046300453776356276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913022484","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5791879,0.00067410903,0.000009573735,0.34594032,0.0026206665,0.00019769826,0.0000022488584,0.0000012619694,0.0713662],"genre_scores_gemma":[0.97953403,0.00003403706,0.000050591058,0.014170475,0.00087759225,0.0000066961757,0.0000031120564,0.00000308004,0.005320397],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969927,0.0005321468,0.00047772584,0.000115786126,0.0017218173,0.0001597947],"domain_scores_gemma":[0.99652207,0.0010760427,0.00023060356,0.00016763012,0.0018887996,0.00011486917],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008510362,0.00005586458,0.00009081965,0.0018726913,0.00009275943,0.0004652544,0.00081294624,0.000050826162,0.0006290843],"category_scores_gemma":[0.0018716636,0.00003622818,0.000041357514,0.0006329593,0.00008025776,0.00053123804,0.000014736652,0.00035369457,0.00023523932],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006219607,0.00029106002,0.16407344,0.000007789816,0.000022210577,0.0000016749896,0.030372275,0.000054428594,0.00004415502,0.3065378,0.057720132,0.44081283],"study_design_scores_gemma":[0.00030814632,0.00007737599,0.26693052,0.00009399999,0.0000022345828,0.00011561148,0.111890316,0.00008981147,0.000026518495,0.050702777,0.569698,0.00006473757],"about_ca_topic_score_codex":0.02093703,"about_ca_topic_score_gemma":0.04664698,"teacher_disagreement_score":0.51197785,"about_ca_system_score_codex":0.00039461916,"about_ca_system_score_gemma":0.010919684,"threshold_uncertainty_score":0.9946875},"labels":[],"label_agreement":null},{"id":"W2913175367","doi":"","title":"Closing the loop: evaluating and acting in university learning and teaching","year":2011,"lang":"en","type":"article","venue":"Asian Social Science","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Closing (real estate); Loop (graph theory); Mathematics education; Psychology; Computer science; Control theory (sociology); Artificial intelligence; Political science; Mathematics; Control (management); Law","score_opus":0.23134455203453927,"score_gpt":0.49130878154475016,"score_spread":0.2599642295102109,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913175367","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70259684,0.000009054965,0.00031826436,0.00063052383,0.000055227036,0.00006376724,1.3472643e-7,0.000009436159,0.29631674],"genre_scores_gemma":[0.99841624,0.0000036177457,0.0011683987,0.00007092697,0.000029147288,4.0278383e-7,5.8410166e-8,0.0000018701602,0.0003093085],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9981128,0.00039087268,0.0001627654,0.00027714862,0.0008511282,0.00020528921],"domain_scores_gemma":[0.99933267,0.00031593104,0.00014094263,0.00007587654,0.000084600535,0.000049956536],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.014446983,0.000055682063,0.000083624764,0.00013330327,0.0020669727,0.00022650075,0.0003104325,0.000025455922,0.00006856533],"category_scores_gemma":[0.0015792148,0.000039523933,0.000014653327,0.00054031814,0.0004779911,0.00083019055,0.00021421893,0.00026745774,0.0000067412584],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000045774946,0.0000050660187,0.10483079,6.552675e-7,6.699985e-7,8.463221e-7,0.03530818,0.0000010970986,0.0005467545,0.010340377,0.000004317322,0.84895664],"study_design_scores_gemma":[0.00021143163,0.000043840082,0.8495473,0.000014449987,0.0000046225946,0.0000030850777,0.13676846,0.008124618,0.00006938862,0.0038455063,0.0012707117,0.00009653778],"about_ca_topic_score_codex":0.000117105585,"about_ca_topic_score_gemma":0.000088909306,"teacher_disagreement_score":0.84886014,"about_ca_system_score_codex":0.00006273285,"about_ca_system_score_gemma":0.00015081963,"threshold_uncertainty_score":0.9992322},"labels":[],"label_agreement":null},{"id":"W2913663231","doi":"10.1177/1356389019827035","title":"Combining internal and external evaluations within a multilevel evaluation framework: Computational text analysis of lessons from the Asian Development Bank","year":2019,"lang":"en","type":"article","venue":"Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Lee Kuan Yew School of Public Policy, National University of Singapore; Whitney and Betty MacMillan Center for International and Area Studies; Yale University","keywords":"Macro; Psychological intervention; Micro level; Scenario analysis; Political science; Computer science; Process management; Psychology; Business; Economics; Finance; Microeconomics","score_opus":0.23131795111349623,"score_gpt":0.5268569038509368,"score_spread":0.2955389527374405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913663231","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86836123,0.00018722734,0.12593582,0.002374948,0.00055713125,0.0010760957,0.000041421725,0.000016815926,0.0014493029],"genre_scores_gemma":[0.97846675,0.000004444834,0.020460628,0.00040655572,0.00006133234,0.00013802675,0.0002860427,0.000012482489,0.0001637499],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9881575,0.0018628136,0.0015288497,0.0006789352,0.007554268,0.00021763478],"domain_scores_gemma":[0.9914562,0.003700934,0.0011900467,0.00064768374,0.0029106722,0.00009443977],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.028343145,0.00022424606,0.0004417207,0.00065050396,0.00035500125,0.00033284345,0.0005607258,0.00012312042,0.009750921],"category_scores_gemma":[0.0042338576,0.00015981836,0.0001540067,0.0014077937,0.00011082527,0.0005883819,0.0001599292,0.0002821353,0.0002558053],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057703735,0.00010779811,0.17847937,0.0000025431675,0.0005105262,1.0276973e-7,0.019573038,0.3695074,0.0003901339,0.003953611,0.00015101292,0.42726675],"study_design_scores_gemma":[0.0006807516,0.00003299894,0.47326377,0.00005620252,0.00047290899,5.5681335e-7,0.0015411783,0.5043526,0.00009519552,0.019336695,0.00006954982,0.00009759523],"about_ca_topic_score_codex":0.00010668513,"about_ca_topic_score_gemma":0.00042452302,"teacher_disagreement_score":0.42716914,"about_ca_system_score_codex":0.00028342596,"about_ca_system_score_gemma":0.0013497504,"threshold_uncertainty_score":0.9911543},"labels":[],"label_agreement":null},{"id":"W2913712334","doi":"10.1332/policypress/9781447334910.003.0011","title":"Commissions of inquiry and policy analysis","year":2018,"lang":"en","type":"book-chapter","venue":"Policy Press eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.4370931175856895,"score_gpt":0.5451051383542824,"score_spread":0.10801202076859295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913712334","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00046409946,0.00020808335,0.00031624586,0.000572176,0.000104455416,0.00023206355,0.00015855246,0.000027164067,0.9979172],"genre_scores_gemma":[0.042499937,0.00015086663,0.00031522932,0.00065263256,0.00092813105,0.000013146199,0.000016889653,0.000027735634,0.95539546],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965056,0.00011475876,0.0010220361,0.00051145675,0.0015912799,0.0002548667],"domain_scores_gemma":[0.9964965,0.00056826556,0.00083430274,0.0012545584,0.0005874097,0.00025897322],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014483382,0.00030310315,0.0007815236,0.0021364226,0.0001607705,0.00015062059,0.000744606,0.00028360976,0.001571419],"category_scores_gemma":[0.00056507054,0.00022523638,0.000320602,0.00012660855,0.0006444822,0.000092148155,0.00051177276,0.00022803717,0.00008429201],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004003452,0.000021528256,0.00029040343,0.000034394772,0.0008018671,0.0000017113182,0.00692977,0.00004450132,0.00003557925,0.8976154,0.030124815,0.06406003],"study_design_scores_gemma":[0.00025985538,0.000084424806,0.0012328909,0.00006264279,0.00037984058,0.0000029732182,0.00006025902,0.00081955903,0.00016190209,0.12943876,0.8672327,0.00026424736],"about_ca_topic_score_codex":0.0010588911,"about_ca_topic_score_gemma":0.00022609848,"teacher_disagreement_score":0.83710784,"about_ca_system_score_codex":0.000058303005,"about_ca_system_score_gemma":0.00066584715,"threshold_uncertainty_score":0.9993413},"labels":[],"label_agreement":null},{"id":"W2913752047","doi":"10.22230/cjnser.2018v9n2a299","title":"Funding Policies and the Nonprofit Sector in Western Canada: Evolving Relationships in a Changing Environment","year":2019,"lang":"en","type":"article","venue":"Canadian journal of nonprofit and social economy research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Nonprofit sector; Nonprofit organization; Political science; Economics; Business; Public administration","score_opus":0.2974494367090924,"score_gpt":0.43046504604016456,"score_spread":0.13301560933107215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913752047","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9802191,0.00043935646,0.0000063125553,0.013362,0.00008940386,0.000266217,0.000003097735,4.5507662e-7,0.0056140483],"genre_scores_gemma":[0.9982013,0.000027510408,0.00001581258,0.00020521569,0.00011660772,0.000008933135,5.576618e-7,0.0000054676234,0.0014185844],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99776095,0.00062706246,0.00052052515,0.00015425323,0.0005031878,0.00043401183],"domain_scores_gemma":[0.9982068,0.0011827142,0.00015990471,0.00010356855,0.00014589317,0.0002011308],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016748708,0.00007505737,0.0002545641,0.0011771575,0.0004872692,0.00033982948,0.00026890772,0.000059256217,0.00038489173],"category_scores_gemma":[0.00035116644,0.000054797278,0.000030304496,0.00049888936,0.00020011845,0.00041161117,0.00005459331,0.00061103667,0.000013893761],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017321678,0.0000018200201,0.9816343,0.0000067965243,0.000006313973,0.0000074541445,0.012440493,0.00006759365,0.0000030068293,0.004023463,0.00018334185,0.001608067],"study_design_scores_gemma":[0.0013259482,0.00003868804,0.93562144,0.00004668559,0.000002623307,0.000012692831,0.04247681,0.0030060355,0.000004443638,0.0042699226,0.013094151,0.00010053058],"about_ca_topic_score_codex":0.21252874,"about_ca_topic_score_gemma":0.927117,"teacher_disagreement_score":0.7145882,"about_ca_system_score_codex":0.0007658612,"about_ca_system_score_gemma":0.003082136,"threshold_uncertainty_score":0.7927151},"labels":[],"label_agreement":null},{"id":"W2913905446","doi":"10.37074/jalt.2018.1.2.3","title":"Modernised learning delivery strategies: The Canada School of Public Service technology integration project","year":2018,"lang":"en","type":"article","venue":"Journal of Applied Learning & Teaching","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Mandate; Service delivery framework; Service (business); Set (abstract data type); Key (lock); Order (exchange); Knowledge management; Business; Process management; Engineering management; Computer science; Public relations; Engineering; Marketing; Political science","score_opus":0.1090902932119772,"score_gpt":0.41131865165051795,"score_spread":0.30222835843854073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913905446","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.954051,0.000043758933,0.024508437,0.0027381408,0.00020888455,0.00015767668,3.9271916e-7,0.000024786397,0.018266914],"genre_scores_gemma":[0.996725,0.000011780988,0.0024706132,0.00028696025,0.00023257144,0.0000050977487,0.0000015517264,0.000013048002,0.00025334774],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99606496,0.00059497874,0.0010622521,0.00020772361,0.0018111685,0.00025889213],"domain_scores_gemma":[0.9956606,0.00074136665,0.0017974047,0.00026444162,0.0014607691,0.00007539932],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011234782,0.00015141015,0.00032362965,0.0005661014,0.00073696557,0.00038325353,0.0008973457,0.00009595183,0.0002567271],"category_scores_gemma":[0.0025453775,0.000091096095,0.000069320464,0.00085632177,0.000094573166,0.0006547773,0.00011099878,0.0019985915,0.000026081361],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004479903,0.00015922889,0.03540867,0.000043274922,0.00022997681,0.000008459236,0.026376415,0.20199166,0.06482127,0.01882542,0.005267742,0.6464199],"study_design_scores_gemma":[0.0020666486,0.0012407826,0.016436026,0.00026442631,0.00010946545,0.00010370982,0.50163865,0.3128438,0.0034339828,0.007788564,0.15353692,0.0005370377],"about_ca_topic_score_codex":0.0065858704,"about_ca_topic_score_gemma":0.036261667,"teacher_disagreement_score":0.64588284,"about_ca_system_score_codex":0.00022334338,"about_ca_system_score_gemma":0.003865866,"threshold_uncertainty_score":0.995591},"labels":[],"label_agreement":null},{"id":"W2913947001","doi":"10.17605/osf.io/gvr7y","title":"Understanding collaborative approaches to research: A synthesis of the research partnership literature","year":2018,"lang":"en","type":"article","venue":"OSF Preprints (OSF Preprints)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"General partnership; Engineering ethics; Management science; Political science; Sociology; Knowledge management; Computer science; Engineering","score_opus":0.7926587396929876,"score_gpt":0.5311719087284376,"score_spread":0.26148683096455005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913947001","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0961941,0.0000022058919,0.0011726693,0.008214248,0.00022350861,0.0014844578,0.000021911868,0.000024496148,0.8926624],"genre_scores_gemma":[0.8896496,0.000015599513,0.0008849045,0.00009990739,0.00012565362,0.00029625985,0.0000013802094,0.000016717271,0.10890997],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9822552,0.009177357,0.00084683916,0.0018983552,0.005148511,0.000673713],"domain_scores_gemma":[0.9800868,0.011195375,0.00028344244,0.005216733,0.002919089,0.0002985563],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.11749327,0.00019199148,0.00036408548,0.00082677713,0.0010561055,0.00073656027,0.0032477381,0.0002029491,0.17024478],"category_scores_gemma":[0.06855333,0.00013097154,0.00014544939,0.0061482578,0.0012455169,0.0004649593,0.0027589672,0.0008644825,0.30960223],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011619459,0.0007517008,0.08709449,0.00011563682,0.00022972027,0.0000080851805,0.12383297,0.0016641172,0.005805801,0.29600263,0.45482817,0.028504744],"study_design_scores_gemma":[0.0007815624,0.000028100503,0.054818224,0.00092016166,0.00003865308,0.000014306897,0.060438395,0.0067406157,0.14783986,0.36830366,0.35945264,0.000623822],"about_ca_topic_score_codex":0.000040891013,"about_ca_topic_score_gemma":0.00035921938,"teacher_disagreement_score":0.7934555,"about_ca_system_score_codex":0.0005821015,"about_ca_system_score_gemma":0.0010444893,"threshold_uncertainty_score":0.93929267},"labels":[],"label_agreement":null},{"id":"W2914432530","doi":"10.22230/ijepl.2019v14n4a865","title":"Using the EBAM Across Educational Contexts: Calibrating for Technical, Policy, Leadership Influences","year":2019,"lang":"en","type":"article","venue":"International Journal of Education Policy and Leadership","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Western University","funders":"","keywords":"Context (archaeology); Jurisdiction; Process (computing); Calibration; Computer science; Management science; Political science; Engineering ethics; Engineering; Law; Mathematics","score_opus":0.5718712951317529,"score_gpt":0.5983565528934374,"score_spread":0.026485257761684422,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2914432530","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5826356,0.0012584368,0.0035567917,0.40539217,0.0035600658,0.00057897397,0.000053701147,0.000013426268,0.0029508814],"genre_scores_gemma":[0.9760381,0.000023883564,0.001680085,0.014907305,0.0030147587,0.000015657253,0.0000059644067,0.000011532826,0.00430274],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9968299,0.00022845656,0.001012568,0.00023189705,0.0014088725,0.00028829766],"domain_scores_gemma":[0.9937195,0.0029478197,0.0010829694,0.00023462491,0.0018782438,0.00013685292],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037009055,0.00015233557,0.00022715749,0.0005602937,0.00025040357,0.00071465754,0.0010345897,0.00009640268,0.00038901818],"category_scores_gemma":[0.006636065,0.00010010924,0.00016784808,0.0005223237,0.0002560152,0.0011258953,0.000059485817,0.0002739245,0.000028639544],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00077361,0.000935557,0.22658794,0.00013183423,0.00045630356,0.0000011061449,0.04919179,0.0060392884,0.01245861,0.48300448,0.0318396,0.18857987],"study_design_scores_gemma":[0.0038921742,0.00066787534,0.30120158,0.0009172916,0.000086494074,0.0010508904,0.2575961,0.006376047,0.0023558058,0.17629226,0.2486426,0.00092088187],"about_ca_topic_score_codex":0.00012858013,"about_ca_topic_score_gemma":0.000052067215,"teacher_disagreement_score":0.39340252,"about_ca_system_score_codex":0.00026301297,"about_ca_system_score_gemma":0.004253961,"threshold_uncertainty_score":0.7944469},"labels":[],"label_agreement":null},{"id":"W2914639037","doi":"10.1332/policypress/9781447334910.003.0019","title":"Academics and public policy","year":2018,"lang":"en","type":"book-chapter","venue":"Policy Press eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Process (computing); Public policy; Work (physics); Context (archaeology); Public relations; Political science; Public administration; Computer science; Engineering; Law; History","score_opus":0.4497419301711354,"score_gpt":0.5104092433340465,"score_spread":0.060667313162911074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2914639037","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020283321,0.00034682712,0.00012131564,0.0025711975,0.00022682517,0.0003645358,0.00011846608,0.000079599355,0.9959684],"genre_scores_gemma":[0.004909828,0.0004480215,0.0002813045,0.0041901106,0.003423741,0.000029743045,0.000012582836,0.000060567083,0.9866441],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99561834,0.00009898442,0.0009460229,0.00074803596,0.0020716249,0.00051701034],"domain_scores_gemma":[0.99676555,0.00047657604,0.0006698591,0.0010732304,0.00058666314,0.00042814598],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0018727195,0.00042648436,0.0005400412,0.001170452,0.00025347737,0.00066039164,0.0011206553,0.000623242,0.0011668152],"category_scores_gemma":[0.0011592244,0.0003327537,0.00015936626,0.00004642918,0.0005680404,0.0002500418,0.0007226218,0.0005981874,0.0006975154],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009224468,0.000003919155,0.000043037588,0.000011310571,0.00003550244,0.0000010401969,0.00064339413,6.12653e-7,0.000006895873,0.86127645,0.03566386,0.10230474],"study_design_scores_gemma":[0.0002033051,0.00004584946,0.00006991242,0.00002901728,0.000015510566,0.0000136691,0.000014007376,0.0002780531,0.000035312845,0.27534682,0.72369546,0.0002530934],"about_ca_topic_score_codex":0.00043256037,"about_ca_topic_score_gemma":0.00010637388,"teacher_disagreement_score":0.68803155,"about_ca_system_score_codex":0.00015013538,"about_ca_system_score_gemma":0.0014779646,"threshold_uncertainty_score":0.99991244},"labels":[],"label_agreement":null},{"id":"W2914742855","doi":"","title":"68: Friends don’t let friends believe in impact factors (with Nathan Hall)","year":2019,"lang":"en","type":"article","venue":"OSF Preprints (OSF Preprints)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Psychology; Social psychology; Sociology","score_opus":0.05518876961169717,"score_gpt":0.39535187547202305,"score_spread":0.3401631058603259,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2914742855","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6185919,0.0000012683005,0.00038980824,0.00031380355,0.0002831834,0.0005436064,0.000018013343,0.00005417969,0.37980425],"genre_scores_gemma":[0.8856244,0.000021818687,0.0004918527,0.0001875784,0.000039750747,0.000081421495,0.000025711948,0.00003491481,0.11349255],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99169695,0.0009089798,0.0012214708,0.002660592,0.0027425054,0.00076949503],"domain_scores_gemma":[0.9923419,0.0014846388,0.0005701523,0.0047700084,0.0004518324,0.0003815005],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.01482374,0.00048004524,0.000718914,0.00070992636,0.00018141937,0.0004718302,0.0022475815,0.00026491264,0.7582222],"category_scores_gemma":[0.0018115294,0.00035208464,0.00029377922,0.0012551651,0.00016048829,0.0012534972,0.001136127,0.000715888,0.6591428],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002020455,0.0002962143,0.9699498,0.0000139028925,0.00009746969,0.000012356026,0.0049275667,0.008595928,0.0012315297,0.00086680724,0.0038821865,0.0099242125],"study_design_scores_gemma":[0.0018228998,0.000019288549,0.91770923,0.000073618554,0.00003102117,0.000024344223,0.0031146442,0.0059884745,0.0040665874,0.004770687,0.061704233,0.00067499914],"about_ca_topic_score_codex":0.00075705256,"about_ca_topic_score_gemma":0.00081512344,"teacher_disagreement_score":0.2670325,"about_ca_system_score_codex":0.0005298161,"about_ca_system_score_gemma":0.00068176055,"threshold_uncertainty_score":0.9998931},"labels":[],"label_agreement":null},{"id":"W2915645638","doi":"","title":"Exploring Equity in Ontario: A Provincial Scan of Equity Policies across School Boards.","year":2018,"lang":"en","type":"article","venue":"QSpace (Queen's University Library)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Equity (law); Political science; Economic growth; Public relations; Business; Public administration; Sociology; Economics","score_opus":0.1938802959884429,"score_gpt":0.39817551053889816,"score_spread":0.20429521455045527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2915645638","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9208363,0.0000021457101,0.00017848915,0.011192383,0.00031308725,0.00027506615,0.00003450495,0.00007360638,0.067094386],"genre_scores_gemma":[0.95626366,0.000023056527,0.000982815,0.0002166338,0.000106012885,0.0000018840881,0.0000062754184,0.000011348507,0.04238831],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99678963,0.00023621705,0.00041986452,0.00050155056,0.0015099718,0.0005427689],"domain_scores_gemma":[0.99830896,0.00019998806,0.00032436074,0.0006466307,0.00024960635,0.00027045832],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010875128,0.00020036625,0.00038263053,0.000510681,0.00033353482,0.00024855026,0.0012873119,0.00010256142,0.003259526],"category_scores_gemma":[0.00029840393,0.00018884074,0.00014000766,0.0013683533,0.00038511184,0.0057097552,0.0022523154,0.00033259948,0.00022719505],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004124495,0.00017720973,0.9385909,0.000018161365,0.000022969178,0.000018818931,0.01075346,0.000100596444,0.0000645191,0.0048311534,0.03666008,0.008349721],"study_design_scores_gemma":[0.0008336994,0.00025638862,0.8930503,0.00006047622,0.000009620753,2.1474149e-7,0.009263146,0.00006652119,0.0036006381,0.0013860348,0.09121419,0.00025876157],"about_ca_topic_score_codex":0.27009904,"about_ca_topic_score_gemma":0.26610357,"teacher_disagreement_score":0.054554112,"about_ca_system_score_codex":0.0006254982,"about_ca_system_score_gemma":0.002349653,"threshold_uncertainty_score":0.99765164},"labels":[],"label_agreement":null},{"id":"W2915704712","doi":"10.7202/1055898ar","title":"Et si la validation était plus qu’une suite de procédures techniques ?","year":2019,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Humanities; Physics; Philosophy","score_opus":0.1443381996319608,"score_gpt":0.5195502806199485,"score_spread":0.37521208098798764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2915704712","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.72153556,0.0008805179,0.06152723,0.13139516,0.004299672,0.0032899932,0.00005188525,0.00030413666,0.07671584],"genre_scores_gemma":[0.94443285,0.00083108584,0.01019562,0.0022177147,0.00033683397,0.00029539235,0.00049522147,0.00005374464,0.041141514],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98174083,0.012475579,0.0013070054,0.00087823044,0.0030984262,0.0004999323],"domain_scores_gemma":[0.9932676,0.003207139,0.0009016924,0.00085952913,0.0016110425,0.00015300798],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.07734883,0.0003957579,0.0004452551,0.00061290595,0.00023588,0.00086513633,0.00057631574,0.00048761696,0.006937015],"category_scores_gemma":[0.0040479978,0.0003788327,0.00018589389,0.0014521676,0.00010559187,0.0026757612,0.00010347228,0.000571658,0.003055668],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020433264,0.0010679126,0.104639396,0.00045018742,0.00015975116,0.0000026992655,0.29606938,0.029502543,0.01465528,0.091180086,0.060083963,0.40198448],"study_design_scores_gemma":[0.0015732864,0.00045289492,0.5551477,0.00052389124,0.00020594629,0.00006197049,0.0068188696,0.0813714,0.01158231,0.036349934,0.305038,0.0008737794],"about_ca_topic_score_codex":0.00047356775,"about_ca_topic_score_gemma":0.00052996946,"teacher_disagreement_score":0.45050833,"about_ca_system_score_codex":0.0012154168,"about_ca_system_score_gemma":0.007337548,"threshold_uncertainty_score":0.99986637},"labels":[],"label_agreement":null},{"id":"W2916149165","doi":"10.7202/1055173ar","title":"L’évaluation de l’efficacité de la bibliothèque : cadre théorique et méthodologique","year":2019,"lang":"fr","type":"article","venue":"Documentation et bibliothèques","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Cegep de Trois-Rivieres","funders":"","keywords":"Valuation (finance); Humanities; Political science; Philosophy; Business","score_opus":0.11888599097301433,"score_gpt":0.4916958754512399,"score_spread":0.37280988447822555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2916149165","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.65613353,0.0050907442,0.20224696,0.031862598,0.0019563742,0.0014972264,0.00007976284,0.00027600478,0.10085679],"genre_scores_gemma":[0.7810716,0.058101248,0.052408546,0.015627565,0.00036310646,0.00024326034,0.00013396493,0.000089558016,0.091961145],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9817638,0.012864492,0.0013560428,0.0009557572,0.0022218986,0.00083802646],"domain_scores_gemma":[0.9869561,0.010252277,0.00077769614,0.0008075714,0.0008618574,0.00034449247],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["scholarly_communication","insufficient_payload"],"category_scores_codex":[0.041671388,0.0005095025,0.00058175315,0.007813045,0.00024173681,0.010443641,0.00084370037,0.00067724317,0.069009244],"category_scores_gemma":[0.0031200773,0.00048156525,0.00029186546,0.011077089,0.00027375625,0.015950046,0.000196459,0.0009571571,0.002274533],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003324278,0.00080989365,0.3226128,0.00028066477,0.00020731885,0.00003170266,0.021999558,0.055160046,0.021113373,0.4065384,0.09371105,0.07720276],"study_design_scores_gemma":[0.003699043,0.001054456,0.36043286,0.00058855664,0.00014432764,0.00022007384,0.0057673897,0.059038263,0.023783935,0.22205524,0.32195634,0.0012595328],"about_ca_topic_score_codex":0.0011009802,"about_ca_topic_score_gemma":0.0003516168,"teacher_disagreement_score":0.22824527,"about_ca_system_score_codex":0.00081287837,"about_ca_system_score_gemma":0.004890136,"threshold_uncertainty_score":0.9997636},"labels":[],"label_agreement":null},{"id":"W2916584022","doi":"10.1111/mcn.12683","title":"Contribution of the <scp>A</scp>live &amp; <scp>T</scp>hrive–<scp>UNICEF</scp> advocacy efforts to improve infant and young child feeding policies in Southeast Asia","year":2019,"lang":"en","type":"article","venue":"Maternal and Child Nutrition","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Université de Sherbrooke","funders":"Government of Canada; UNICEF; Bill and Melinda Gates Foundation; Institute of Museum and Library Services","keywords":"Flexibility (engineering); Medicine; Government (linguistics); Set (abstract data type); Public relations; Economic growth; Political science; Economics; Management; Computer science","score_opus":0.017744145570122164,"score_gpt":0.31187907027209943,"score_spread":0.2941349247019773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2916584022","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9868393,0.00051222055,0.00008683345,0.00072154665,0.0004916355,0.0010725455,0.00011233431,0.000028896782,0.01013472],"genre_scores_gemma":[0.9971846,0.00031374887,0.000074871015,0.00029653023,0.00021437276,0.000051553947,0.000028216364,0.000017389151,0.0018187178],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9968893,0.00016001011,0.0008123172,0.000523922,0.0011607909,0.00045364883],"domain_scores_gemma":[0.9980079,0.00055444264,0.0005163564,0.00038502496,0.00036025932,0.00017605281],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015980926,0.0002887845,0.00045717962,0.0003921069,0.00032623194,0.00038845724,0.0003804187,0.00015707313,0.00002301572],"category_scores_gemma":[0.0008896237,0.00020180337,0.00012369988,0.00047470105,0.00011688889,0.0005701819,0.0002799543,0.0003070331,0.000113805174],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035386445,0.00027181534,0.96694237,0.00017534362,0.000055587858,0.000002587496,0.011901586,0.00016183352,0.010322732,0.006910216,0.0017925699,0.0014279914],"study_design_scores_gemma":[0.002326634,0.00024308536,0.9599723,0.00075807143,0.000032462438,0.00008607407,0.0071475888,0.0007360661,0.010923085,0.005192082,0.0125281485,0.000054409116],"about_ca_topic_score_codex":0.00028996228,"about_ca_topic_score_gemma":0.00031179158,"teacher_disagreement_score":0.010735578,"about_ca_system_score_codex":0.00007293828,"about_ca_system_score_gemma":0.00006009246,"threshold_uncertainty_score":0.8229302},"labels":[],"label_agreement":null},{"id":"W2917104096","doi":"","title":"Assigning Value to Peel's Regional Police’s School Resource Officer Program","year":2018,"lang":"en","type":"article","venue":"Carleton University's Institutional Repository (MacOdrum Library, Carleton University)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Officer; Public relations; Scrutiny; Valuation (finance); Value (mathematics); Resource (disambiguation); Service (business); Business; Marketing; Political science; Computer science; Finance","score_opus":0.05362349949275562,"score_gpt":0.3313314256432079,"score_spread":0.27770792615045226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2917104096","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34473562,0.00004118645,0.002701325,0.003411007,0.0014037356,0.0008673978,0.00007419043,0.00061419135,0.64615136],"genre_scores_gemma":[0.7739199,0.000028998853,0.0048970887,0.0029595187,0.0015309919,0.0000025683528,0.000108638415,0.000049714366,0.21650258],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9932314,0.0008323131,0.00066348206,0.0015376954,0.002908465,0.0008266525],"domain_scores_gemma":[0.99555624,0.00047508237,0.00049982034,0.0011788151,0.000994995,0.0012950314],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008475157,0.0005409918,0.0005547331,0.0024883684,0.0028489032,0.0006359011,0.0025652044,0.00038916568,0.0014932534],"category_scores_gemma":[0.00019101278,0.00057926006,0.0004770244,0.004248914,0.0011715343,0.0041527143,0.0011287576,0.00061605073,0.00090083195],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0038935435,0.0011263781,0.06458514,0.000069405716,0.000672322,0.0018071416,0.0050405296,0.01813643,0.009770666,0.27390516,0.59813976,0.02285351],"study_design_scores_gemma":[0.001434335,0.00049856433,0.016152533,0.000110882145,0.00010420592,0.0000984884,0.006326807,0.0017443093,0.0019167353,0.000095145435,0.97082233,0.00069568865],"about_ca_topic_score_codex":0.0004647989,"about_ca_topic_score_gemma":0.000099215176,"teacher_disagreement_score":0.4296488,"about_ca_system_score_codex":0.001233726,"about_ca_system_score_gemma":0.0036918833,"threshold_uncertainty_score":0.9998771},"labels":[],"label_agreement":null},{"id":"W2918217012","doi":"10.3138/cjpe.33.3.v","title":"Editor’s Remarks","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"École Nationale d'Administration Publique","funders":"","keywords":"Biography; Bourgeoisie; Library science; Administration (probate law); Art; Sociology; Classics; Art history; Political science; Law; Computer science; Politics","score_opus":0.1939142377051118,"score_gpt":0.5103476077944012,"score_spread":0.31643337008928946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2918217012","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8903803,0.0007796113,0.0010940575,0.007369858,0.033882048,0.0024164557,0.000007655057,0.000017961283,0.064052045],"genre_scores_gemma":[0.9945535,0.0000042425263,0.002310582,0.00024660016,0.0017992201,0.000018256687,0.0000062085837,0.0000073997803,0.0010539576],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957334,0.0003893848,0.000780041,0.00016049185,0.002708953,0.00022775575],"domain_scores_gemma":[0.99502933,0.0002124901,0.0006084361,0.00031886273,0.0034112644,0.0004195894],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.017465403,0.000087109074,0.00019397795,0.000594865,0.000100492136,0.00037638712,0.0004689298,0.00007643017,0.013963623],"category_scores_gemma":[0.0023161462,0.00006435177,0.000121319354,0.0005989142,0.0000420602,0.0006992981,0.000008622969,0.00019573164,0.0009399457],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011668981,0.000021642663,0.07553242,0.000002787023,0.000017781982,0.0000024716303,0.0005119273,0.0016953893,0.0000516872,0.00043413255,0.086646706,0.8350714],"study_design_scores_gemma":[0.001007516,0.00060231244,0.11905751,0.000044720116,0.000044218355,0.000034789133,0.0010668371,0.044468597,0.00006800765,0.009475812,0.82398474,0.00014493152],"about_ca_topic_score_codex":0.00019767114,"about_ca_topic_score_gemma":0.005671551,"teacher_disagreement_score":0.8349264,"about_ca_system_score_codex":0.00031822285,"about_ca_system_score_gemma":0.0057051787,"threshold_uncertainty_score":0.9999316},"labels":[],"label_agreement":null},{"id":"W2918531645","doi":"10.3138/cjpe.53007","title":"Can’t See the Wood for the Logframe: Integrating Logframes and Theories of Change in Development Evaluation","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Theory of change; Development theory; Context (archaeology); Development (topology); Computer science; Management science; Epistemology; Engineering ethics; Process management; Sociology; Business; Engineering; History; Economics; Economic growth","score_opus":0.41664340785434323,"score_gpt":0.5285682281708979,"score_spread":0.11192482031655465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2918531645","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9814272,0.002256337,0.0008935125,0.009641843,0.0008040027,0.0044940864,0.000006350735,0.0000028394895,0.00047382698],"genre_scores_gemma":[0.9975199,0.000019264464,0.0016331354,0.00028150543,0.00009056255,0.00040018006,0.0000073926976,0.0000068764,0.00004116578],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99642843,0.0006255941,0.0008747222,0.00016358547,0.0016905587,0.00021710877],"domain_scores_gemma":[0.994965,0.0013373848,0.0007830294,0.00025090892,0.0025634773,0.000100189354],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03489376,0.00011216264,0.00021644677,0.0003493059,0.00020887855,0.0002453584,0.000416894,0.000068899935,0.0005709764],"category_scores_gemma":[0.0041038324,0.000057377383,0.0000649528,0.0005354771,0.00013033075,0.00036448086,0.00001831719,0.00020022038,0.0000057391135],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018516563,0.000014146167,0.07169965,0.000008256921,0.000023538107,1.2439425e-7,0.013799457,0.00097314274,0.000015876896,0.0029626687,0.000104562765,0.91038007],"study_design_scores_gemma":[0.002063588,0.00066532724,0.5796239,0.000187103,0.00016002795,0.000018104038,0.029431442,0.31715912,0.0002969416,0.054930437,0.015267801,0.0001962089],"about_ca_topic_score_codex":0.00060900784,"about_ca_topic_score_gemma":0.072579734,"teacher_disagreement_score":0.91018385,"about_ca_system_score_codex":0.0003027027,"about_ca_system_score_gemma":0.0042320355,"threshold_uncertainty_score":0.99377996},"labels":[],"label_agreement":null},{"id":"W2918728998","doi":"10.3138/cjpe.53008","title":"Does Your Implementation Fit Your Theory of Change?","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Coding (social sciences); Action (physics); Theory of change; Domain (mathematical analysis); Management science; Computer science; Psychology; Epistemology; Sociology; Mathematics; Social science; Economics","score_opus":0.6341084431107532,"score_gpt":0.590531744540158,"score_spread":0.04357669857059521,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2918728998","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99262387,0.00025631985,0.0003059684,0.0020418856,0.0017399305,0.0015187337,0.000020654661,0.0000053651843,0.0014872565],"genre_scores_gemma":[0.9979985,0.0000130167655,0.0011163095,0.00019478735,0.00022055572,0.000052041138,0.000015030971,0.000008791767,0.00038097362],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.995879,0.0006088117,0.000997297,0.00017245168,0.0021064973,0.00023597614],"domain_scores_gemma":[0.9953947,0.0001842591,0.0011260464,0.00029220877,0.0027337743,0.00026901427],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017324403,0.000107509295,0.00024370993,0.00070464343,0.00009210351,0.00017833315,0.0004155836,0.00006325653,0.014674017],"category_scores_gemma":[0.00075004896,0.00006369216,0.00013894949,0.0005764769,0.000052155083,0.0008901159,0.000012735531,0.00013272253,0.00013909933],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019545325,0.000022393879,0.14117639,0.000006584108,0.000026766362,8.9606226e-7,0.0030798123,0.00020239544,0.00011810056,0.0009821492,0.0005172043,0.85384774],"study_design_scores_gemma":[0.0026434797,0.0014155568,0.8455896,0.00010393392,0.00018894553,0.000021829892,0.028685048,0.012956357,0.0013210052,0.0469795,0.059818845,0.00027592696],"about_ca_topic_score_codex":0.00051435875,"about_ca_topic_score_gemma":0.008799,"teacher_disagreement_score":0.85357183,"about_ca_system_score_codex":0.00023004354,"about_ca_system_score_gemma":0.0025075749,"threshold_uncertainty_score":0.9862267},"labels":[],"label_agreement":null},{"id":"W2919316438","doi":"10.3138/cjpe.52946","title":"Using Actor-Based Theories of Change to Conduct Robust Evaluation in Complex Settings","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Theory of change; Democracy; Management science; Computer science; Psychological intervention; Process management; Sociology; Operations research; Business; Risk analysis (engineering); Political science; Economics; Psychology; Management; Mathematics; Law","score_opus":0.8242816801062659,"score_gpt":0.5913763997790368,"score_spread":0.23290528032722912,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2919316438","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99249005,0.0001423871,0.00090859155,0.0022231971,0.00063527666,0.0026914706,0.000013263653,0.000004061136,0.0008917177],"genre_scores_gemma":[0.9892964,9.1057893e-7,0.0100545,0.00043291895,0.000104139894,0.000060899692,0.000024607289,0.000010769389,0.00001487729],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9941851,0.0010733135,0.0011359302,0.00023342537,0.0030871928,0.00028505654],"domain_scores_gemma":[0.99334073,0.00030242527,0.0009710562,0.0003228837,0.0047645583,0.00029831912],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02935395,0.00013656079,0.00035426617,0.0013700267,0.00008731398,0.00019568374,0.0004205964,0.00008156753,0.0051683895],"category_scores_gemma":[0.0030540356,0.000111795154,0.00010506507,0.0013844414,0.000070241455,0.0007741345,0.000013495534,0.0001642238,0.00004565926],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000086323744,0.00009187051,0.23291358,0.000029403365,0.000028110888,0.0000021015053,0.0056777806,0.16465184,0.0032307147,0.00079433364,0.00065428007,0.5918397],"study_design_scores_gemma":[0.0019713049,0.00067215326,0.26882827,0.00018975577,0.00008196938,0.000010167144,0.0034029854,0.7147289,0.00052002195,0.0040310663,0.0053707864,0.00019262913],"about_ca_topic_score_codex":0.001092077,"about_ca_topic_score_gemma":0.013825445,"teacher_disagreement_score":0.591647,"about_ca_system_score_codex":0.0007504324,"about_ca_system_score_gemma":0.0055170534,"threshold_uncertainty_score":0.99948436},"labels":[],"label_agreement":null},{"id":"W2919963961","doi":"10.7202/1058413ar","title":"UNDERSTANDING HOW THE IMPLEMENTATION OF THE SPECIALIST HIGH SKILLS MAJOR PROGRAM CONTRIBUTES TO STUDENT OUTCOMES","year":2019,"lang":"en","type":"article","venue":"McGill Journal of Education / Revue des sciences de l éducation de McGill","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"CLARITY; Graduation (instrument); Affect (linguistics); Student achievement; Medical education; Conceptual framework; Simplicity; Psychology; Mathematics education; Academic achievement; Medicine; Sociology; Engineering","score_opus":0.5866328441512301,"score_gpt":0.5730136387845263,"score_spread":0.013619205366703802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2919963961","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95005137,0.000038450053,0.00096385996,0.041596666,0.00416256,0.0009349883,0.000032989585,0.000008741421,0.0022103598],"genre_scores_gemma":[0.9924201,0.000026001333,0.0035932218,0.0022742602,0.000120721685,0.000043584507,0.0000020634159,0.000008692063,0.0015113859],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9961361,0.0006532178,0.0010287937,0.00027858844,0.0015850471,0.00031821788],"domain_scores_gemma":[0.9953129,0.0010205241,0.001592364,0.00045935292,0.0014805162,0.00013433665],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0093760975,0.00015835576,0.00030946254,0.0004910282,0.0011699538,0.00041233504,0.0014946188,0.000051354116,0.00053547596],"category_scores_gemma":[0.0015837704,0.00008827585,0.00020090009,0.0019548424,0.00032066958,0.000775318,0.00011123313,0.00017178658,0.000027931921],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033943084,0.00094756944,0.76812303,0.00004421152,0.00011177808,3.8791381e-7,0.010987685,0.0041275523,0.0013318185,0.1624566,0.015169043,0.036666356],"study_design_scores_gemma":[0.0005036243,0.00036586475,0.8453957,0.00012344062,0.00006958479,0.00005618346,0.0794603,0.00018978555,0.0028876015,0.03390066,0.03689071,0.00015656346],"about_ca_topic_score_codex":0.00008768931,"about_ca_topic_score_gemma":0.0006581419,"teacher_disagreement_score":0.12855594,"about_ca_system_score_codex":0.0019379518,"about_ca_system_score_gemma":0.0011513646,"threshold_uncertainty_score":0.8998458},"labels":[],"label_agreement":null},{"id":"W2920077988","doi":"10.3138/cjpe.53070","title":"How We Model Matters: A Manifesto for the Next Generation of Program Theorizing","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Manifesto; Sociology; Epistemology; Scale (ratio); Engineering ethics; Computer science; Political science; Law; Philosophy; Engineering","score_opus":0.63617589694431,"score_gpt":0.5222816882781216,"score_spread":0.11389420866618838,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2920077988","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7653458,0.0029399346,0.091503456,0.120403744,0.003802947,0.014759521,0.000038428076,0.00003263684,0.0011735184],"genre_scores_gemma":[0.97999334,0.00002482475,0.018571932,0.00034587987,0.0002812015,0.00027379097,0.000012369602,0.000013359978,0.0004833028],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967915,0.00028127787,0.00074674294,0.00019366242,0.001729505,0.00025735216],"domain_scores_gemma":[0.9952627,0.00036819524,0.00094800285,0.00036417152,0.0028633534,0.00019359117],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011904376,0.00012453682,0.00023121016,0.00039006557,0.00019970303,0.0008930155,0.0005328915,0.0000733669,0.00034662455],"category_scores_gemma":[0.00091945,0.00007754261,0.00019229857,0.00044322494,0.000073382835,0.0010497767,0.000011603154,0.00014418284,0.000018752175],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002237348,0.0000403628,0.0012313017,0.000014926434,0.000039863826,3.6024744e-7,0.0013742368,0.029753353,0.0009324981,0.0024893174,0.005059359,0.9590421],"study_design_scores_gemma":[0.00075117557,0.0006346413,0.0010831871,0.00004762301,0.00009995811,0.000013992449,0.0023600745,0.94673336,0.0002726646,0.008275365,0.039629653,0.00009833817],"about_ca_topic_score_codex":0.000078239274,"about_ca_topic_score_gemma":0.0033183105,"teacher_disagreement_score":0.9589437,"about_ca_system_score_codex":0.00021335023,"about_ca_system_score_gemma":0.002761089,"threshold_uncertainty_score":0.86113685},"labels":[],"label_agreement":null},{"id":"W2920130717","doi":"10.3138/cjpe.56900","title":"The Current Landscape of Program Theorizing","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Current (fluid); Sociology; Epistemology; Environmental resource management; Environmental planning; Geography; Engineering; Environmental science; Philosophy","score_opus":0.2918100568654653,"score_gpt":0.5403306206497496,"score_spread":0.24852056378428428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2920130717","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97421235,0.0041946545,0.00025894112,0.0025999674,0.0037185408,0.0028202506,0.0000058724236,0.00001299443,0.012176403],"genre_scores_gemma":[0.99868745,0.000043315747,0.00088190124,0.000028749197,0.00014968136,0.000055762368,0.0000048190786,0.000006896895,0.00014141068],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957864,0.0005308062,0.00096995995,0.00014588445,0.0023034487,0.0002634435],"domain_scores_gemma":[0.9949149,0.00046074303,0.000980477,0.00035411623,0.0030308736,0.00025892988],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.019763533,0.00009758104,0.00020732557,0.00035508163,0.00019631007,0.00039627164,0.0006150327,0.000040628165,0.0011592256],"category_scores_gemma":[0.0018362779,0.000055600212,0.00015354918,0.0007179559,0.000092528455,0.00039178447,0.000014679746,0.00024168925,0.00011407867],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013198411,0.000030785835,0.047659647,0.0000042640972,0.00001585896,3.3870063e-7,0.00043738543,0.000544439,0.00001221604,0.0013676899,0.0013778592,0.94853634],"study_design_scores_gemma":[0.0015096443,0.0015630123,0.18109518,0.00014738954,0.00010505905,0.000021537098,0.0025627138,0.10402803,0.00013503616,0.026763093,0.68187094,0.00019838697],"about_ca_topic_score_codex":0.00005809148,"about_ca_topic_score_gemma":0.0033131791,"teacher_disagreement_score":0.9483379,"about_ca_system_score_codex":0.00012954845,"about_ca_system_score_gemma":0.0041720234,"threshold_uncertainty_score":0.99975383},"labels":[],"label_agreement":null},{"id":"W2920560310","doi":"","title":"International knowledge transfer between Canada and Israel validation of the EASI tool","year":2018,"lang":"en","type":"article","venue":"Journal of Aging Science","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Knowledge transfer; Medicine; Knowledge management","score_opus":0.12521867633656844,"score_gpt":0.4593522350997752,"score_spread":0.3341335587632067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2920560310","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9908767,0.00001444033,0.0019228281,0.0025186304,0.0010320758,0.00003157787,0.0000024113729,8.757271e-7,0.0036004717],"genre_scores_gemma":[0.9989804,0.0000048260044,0.000533513,0.0001260125,0.0001533042,1.6367896e-7,5.5360932e-8,0.0000011962485,0.00020054847],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9974239,0.00006202019,0.00045471915,0.0001013181,0.00187024,0.00008781525],"domain_scores_gemma":[0.99795955,0.00023377237,0.0002302875,0.00013854932,0.0013880819,0.0000497541],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0055255205,0.000041801002,0.0000955405,0.00016160042,0.00018056866,0.00012907635,0.00081029587,0.000010606099,0.00009910496],"category_scores_gemma":[0.0007347215,0.000022729806,0.00003092522,0.0006259763,0.00032985362,0.0006726277,0.00006046741,0.00007924318,0.0000024572971],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000067653923,0.000018134588,0.9421909,0.0000027089914,0.000010395337,3.75282e-7,0.002308504,0.00010023139,0.006611569,0.001210631,0.0011151648,0.046424646],"study_design_scores_gemma":[0.00023729817,0.000057118923,0.95202035,0.000046725912,0.000009681684,0.00001498872,0.00055577274,0.0019292505,0.033978827,0.0010116627,0.010088361,0.000049942977],"about_ca_topic_score_codex":0.0016565351,"about_ca_topic_score_gemma":0.0054848418,"teacher_disagreement_score":0.0463747,"about_ca_system_score_codex":0.00008519645,"about_ca_system_score_gemma":0.0015845163,"threshold_uncertainty_score":0.30606705},"labels":[],"label_agreement":null},{"id":"W2920826759","doi":"10.4135/9781526435446.n16","title":"Qualitative Ethics in aPositivist Frame: The Canadian Experience 1998–2014","year":2018,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Positivism; Frame (networking); Qualitative research; Sociology; Epistemology; Social science; Philosophy; Engineering; Mechanical engineering","score_opus":0.5033969129477542,"score_gpt":0.5995199402144964,"score_spread":0.09612302726674216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2920826759","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00063052285,0.00006175986,0.0007030194,0.010478993,0.00060399924,0.00037784106,0.00004231206,0.000015945423,0.9870856],"genre_scores_gemma":[0.2231877,0.0000624179,0.00047049267,0.009575303,0.00017762856,0.000039029514,0.000021784965,0.000021221977,0.76644444],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9947896,0.00048348866,0.0008311599,0.0005966203,0.0029724466,0.00032665642],"domain_scores_gemma":[0.99374324,0.0041060527,0.00034581195,0.0009176804,0.00067583704,0.0002113969],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.013177493,0.000273406,0.00034432294,0.00045280848,0.0005684692,0.00052262965,0.0011417851,0.00050843647,0.027461825],"category_scores_gemma":[0.0013600328,0.00015646644,0.00011334806,0.00016483275,0.0007994419,0.000250256,0.0001172075,0.0012106647,0.009937602],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013734987,0.000009941749,0.00025377408,0.0000047534663,0.00002031659,0.000008260515,0.31283566,0.00002147751,0.0000020170078,0.56740737,0.11556356,0.0038591304],"study_design_scores_gemma":[0.000111572655,0.00006487731,0.00059410743,0.00006217121,0.000005492584,0.0000027381625,0.015457292,0.0008286955,0.000010400167,0.15447478,0.8281098,0.00027807648],"about_ca_topic_score_codex":0.04777743,"about_ca_topic_score_gemma":0.8932883,"teacher_disagreement_score":0.84551084,"about_ca_system_score_codex":0.0003751707,"about_ca_system_score_gemma":0.0026406038,"threshold_uncertainty_score":0.9908333},"labels":[],"label_agreement":null},{"id":"W2922707278","doi":"10.16922/wje.21.1.6","title":"The Collaborative Institute for Education Research, Evidence and Impact: a Case Study in Developing Regional Research Capacity in Wales","year":2019,"lang":"en","type":"article","venue":"Cylchgrawn Addysg Cymru / Wales Journal of Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact","funders":"","keywords":"Capacity building; Work (physics); Relevance (law); Political science; Pedagogy; Sociology; Medical education; Medicine; Engineering","score_opus":0.6896387064002589,"score_gpt":0.6605205650327058,"score_spread":0.029118141367553085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2922707278","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98561925,0.0023456395,0.000041456704,0.008993901,0.0009424248,0.0018351383,0.0000038674166,0.0000024417388,0.00021588022],"genre_scores_gemma":[0.9967797,0.00060924055,0.001454579,0.00008296466,0.00023175361,0.00019462394,0.000003469436,0.00000959095,0.00063412235],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9936403,0.0020410402,0.0012386421,0.00039327904,0.0022794656,0.00040724775],"domain_scores_gemma":[0.9838721,0.0071385545,0.00059576094,0.0004392528,0.0077957897,0.00015851048],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.039238848,0.00015175418,0.00031193448,0.001841472,0.00089811557,0.00059378473,0.0006413049,0.00008501214,0.000038668746],"category_scores_gemma":[0.011961863,0.000097591845,0.000062758954,0.0032691304,0.0003757682,0.0020665731,0.00012679564,0.00069667917,0.000016589614],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00080301554,0.0020799546,0.7250037,0.00007298738,0.000051820807,0.00002306818,0.09526213,0.0005480296,0.000527707,0.012548592,0.023103595,0.1399754],"study_design_scores_gemma":[0.0013125911,0.0016565126,0.53795034,0.0011458596,0.000012079437,0.0006125358,0.4004658,0.00084727927,0.00013790185,0.032025144,0.02358899,0.0002449917],"about_ca_topic_score_codex":0.001034224,"about_ca_topic_score_gemma":0.018431392,"teacher_disagreement_score":0.30520368,"about_ca_system_score_codex":0.0012016714,"about_ca_system_score_gemma":0.01688356,"threshold_uncertainty_score":0.99947965},"labels":[],"label_agreement":null},{"id":"W2923174012","doi":"","title":"Assessing teachers’ interpretation of Canadian large scale assessment results: An innovative approach to piloting a questionnaire","year":2019,"lang":"en","type":"article","venue":"2019 Conference of the Canadian Society for the Study of Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université du Québec en Abitibi-Témiscamingue; University of Ottawa","funders":"","keywords":"Cognitive dissonance; Psychology; Perception; Interpretation (philosophy); Scale (ratio); Cognition; Social psychology; Presentation (obstetrics); Applied psychology; Computer science","score_opus":0.1451326791833945,"score_gpt":0.4531347117191755,"score_spread":0.308002032535781,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2923174012","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98183334,0.000016280066,0.0022359164,0.0031153131,0.0007151469,0.0022804928,0.00011614636,0.000004309226,0.009683049],"genre_scores_gemma":[0.9952544,0.0000016224573,0.003469821,0.00034861386,0.00003685424,0.00008490424,0.00003757618,0.000009566582,0.000756629],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99756455,0.00027228144,0.0007664507,0.00032744542,0.0008218822,0.0002473783],"domain_scores_gemma":[0.9952552,0.00028282622,0.0007916638,0.0007702624,0.0027389284,0.00016115844],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006384308,0.00013076175,0.000266575,0.00037269376,0.00044565758,0.0001871716,0.0009610181,0.00007254071,0.00004009534],"category_scores_gemma":[0.0007810978,0.0000862536,0.00012841291,0.0017251341,0.000090296635,0.00058007817,0.00005237095,0.00017566759,0.0000035797034],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057318208,0.0012712359,0.23294772,0.00007691357,0.0002701205,1.2370238e-8,0.6528594,0.0070797545,0.0009229249,0.014161869,0.012764647,0.0775881],"study_design_scores_gemma":[0.0006053029,0.0003410124,0.53413576,0.00014752675,0.00005000917,3.6232822e-7,0.41444436,0.048051264,0.000097457305,0.0006183725,0.0013707604,0.00013783619],"about_ca_topic_score_codex":0.4201759,"about_ca_topic_score_gemma":0.8055256,"teacher_disagreement_score":0.3853497,"about_ca_system_score_codex":0.00057782995,"about_ca_system_score_gemma":0.0095938,"threshold_uncertainty_score":0.9960209},"labels":[],"label_agreement":null},{"id":"W2923254025","doi":"10.15694/mep.2019.000065.1","title":"An Evaluation of the Scholarly Activity Guidance and Evaluative (SAGE) Program","year":2019,"lang":"en","type":"article","venue":"MedEdPublish","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Children's Hospital of Eastern Ontario; University of Ottawa","funders":"","keywords":"SAGE; Medical education; Psychology; Gerontology; Medicine","score_opus":0.20494365692617844,"score_gpt":0.5243964167231666,"score_spread":0.3194527597969882,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2923254025","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98037976,0.00012737694,0.00015805116,0.0014811602,0.0005752407,0.0013701608,0.000008296183,0.000026514577,0.015873466],"genre_scores_gemma":[0.9979754,0.000005008801,0.00059967383,0.00019920617,0.000045781897,0.000100409954,0.000003022959,0.000007162567,0.0010643151],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9914177,0.0018358435,0.00044049064,0.00045782595,0.005660932,0.00018721742],"domain_scores_gemma":[0.9950129,0.000367649,0.00047597542,0.001035809,0.0030347826,0.0000729089],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.030190641,0.000120058794,0.0002165365,0.0001549537,0.0001539005,0.0011527892,0.0008058995,0.00008036471,0.0023056774],"category_scores_gemma":[0.00480795,0.000070627524,0.000067659574,0.0010411654,0.0001244401,0.005401729,0.00014766943,0.00021746471,0.0000684083],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018564013,0.00014447577,0.21431088,0.000004476418,0.000010895506,2.7004893e-8,0.0008945189,0.00029673692,0.0022803305,0.0005462186,0.0006206535,0.7808722],"study_design_scores_gemma":[0.0007717427,0.0002151517,0.86202633,0.00002364183,0.000029424826,9.841788e-7,0.00065912056,0.12383194,0.0026055682,0.0063439794,0.0033955034,0.00009660321],"about_ca_topic_score_codex":0.000037275757,"about_ca_topic_score_gemma":0.00011818966,"teacher_disagreement_score":0.7807756,"about_ca_system_score_codex":0.000086536405,"about_ca_system_score_gemma":0.0006939629,"threshold_uncertainty_score":0.9998841},"labels":[],"label_agreement":null},{"id":"W2923725345","doi":"10.3389/feduc.2019.00020","title":"Development and Examination of a Tool to Assess Score Report Quality","year":2019,"lang":"en","type":"article","venue":"Frontiers in Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Generalizability theory; Reliability (semiconductor); Scale (ratio); Quality (philosophy); Stakeholder; Rating scale; Standards for Educational and Psychological Testing; Psychology; Sample (material); Applied psychology; Accountability; Medical education; Medicine; Political science; Higher education; Public relations; Geography","score_opus":0.2202473128127325,"score_gpt":0.5037553939418976,"score_spread":0.28350808112916515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2923725345","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98371726,0.00003777545,0.0077697593,0.00031177147,0.0017057072,0.00034809613,6.9762785e-7,0.0000050900544,0.006103844],"genre_scores_gemma":[0.9261335,0.000004360299,0.070452936,0.00015373199,0.000020910911,0.000040845298,0.000014303979,0.00000301713,0.0031763902],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99797577,0.00014263138,0.0007066407,0.00026033755,0.0008300351,0.000084576925],"domain_scores_gemma":[0.9989453,0.000095327276,0.00029473487,0.00029775244,0.00032819837,0.000038714126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006772508,0.00006004625,0.00016412021,0.0003593472,0.000028080598,0.000049910006,0.0001406082,0.000037931655,0.00014715378],"category_scores_gemma":[0.0009654555,0.000051941486,0.000014509297,0.000494643,0.000014265529,0.00032720607,0.000034224813,0.000045734363,0.000031099215],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000075783846,0.000054503274,0.6113175,0.00001228195,0.0000022531558,9.930377e-8,0.003798033,0.00003952871,0.00020449738,0.00063472835,0.0023613863,0.3815676],"study_design_scores_gemma":[0.000121284356,0.000016594018,0.9610681,0.000029398698,0.0000014723003,0.0000015689315,0.010083941,0.0004135921,0.0010255149,0.0009446161,0.02621934,0.000074586445],"about_ca_topic_score_codex":0.00001454128,"about_ca_topic_score_gemma":0.000026519729,"teacher_disagreement_score":0.38149303,"about_ca_system_score_codex":0.0001491182,"about_ca_system_score_gemma":0.0007158009,"threshold_uncertainty_score":0.23472296},"labels":[],"label_agreement":null},{"id":"W2926438317","doi":"10.47678/cjhe.v29i1.188483","title":"Book review of \"A Guide to Decision Making in Student Affairs: A Case Study Approach\"","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Higher Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Student affairs; Higher education; Psychology; Management science; Sociology; Mathematics education; Political science; Economics; Law","score_opus":0.12864754780220106,"score_gpt":0.5455073106887084,"score_spread":0.41685976288650733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2926438317","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8101667,0.14592409,0.0018304964,0.007816558,0.0062793875,0.0020550122,0.0000069363687,0.0000053357508,0.025915453],"genre_scores_gemma":[0.9859129,0.0001383534,0.002932157,0.0073358673,0.00029697106,0.000015048035,4.876339e-7,0.0000073278543,0.003360851],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971043,0.00027180847,0.001269409,0.00018498437,0.0009991326,0.00017035402],"domain_scores_gemma":[0.9969824,0.00018235382,0.0005671319,0.0003832839,0.0015561873,0.00032863594],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0050957007,0.00009434011,0.0002869753,0.0009430677,0.00008546097,0.000096522905,0.00048630912,0.000029764336,0.0051599722],"category_scores_gemma":[0.0005697854,0.00007102126,0.00006430061,0.0009954191,0.000036261386,0.00038059553,0.000022625776,0.00011196452,0.00006263975],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013001192,0.00027141214,0.073950425,0.00004047715,0.000014152016,0.000067809575,0.007135754,0.00007114921,0.0000032806763,0.000059209524,0.8800835,0.03828985],"study_design_scores_gemma":[0.0003704475,0.00053629134,0.15795961,0.0021425127,0.000034247234,0.00042784362,0.018973522,0.000028467897,0.0000062592107,0.0001989757,0.81919706,0.00012475731],"about_ca_topic_score_codex":0.0009799049,"about_ca_topic_score_gemma":0.0109121315,"teacher_disagreement_score":0.17574622,"about_ca_system_score_codex":0.00039501657,"about_ca_system_score_gemma":0.0037251953,"threshold_uncertainty_score":0.9957495},"labels":[],"label_agreement":null},{"id":"W292912147","doi":"10.3138/cjpe.0023.007","title":"Informing Evaluation Capacity Building Through Profiling Organizational Capacity for Evaluation: An Empirical Examination of four Canadian Federal Government Organizations","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"National Research Council Canada; University of Ottawa","funders":"","keywords":"Organization development; Government (linguistics); Capacity building; Evaluation methods; Knowledge management; Organizational effectiveness; Order (exchange); Business; Organizational performance; Process management; Computer science; Political science; Finance; Engineering","score_opus":0.43136025450021587,"score_gpt":0.49320319992613026,"score_spread":0.0618429454259144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W292912147","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96257776,0.00010753138,0.026954634,0.0015845749,0.0010402565,0.0047394773,0.000114798924,0.00001870385,0.0028622583],"genre_scores_gemma":[0.93372524,0.0000042007964,0.06513943,0.00035139653,0.00034136453,0.0001530328,0.00024093466,0.00002384734,0.000020587893],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9890794,0.0013611984,0.0020397787,0.00045729493,0.0065244283,0.000537857],"domain_scores_gemma":[0.9726164,0.00035447848,0.0017248876,0.00044526538,0.02412206,0.0007369062],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03494162,0.0002917699,0.00044475333,0.0008179623,0.00089793175,0.0005133454,0.00064041634,0.0002475207,0.0019789713],"category_scores_gemma":[0.021273157,0.0002728158,0.00015247424,0.0022839366,0.000122062695,0.0028506843,0.000013187531,0.00028680038,0.000008773877],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00004452928,0.00025195343,0.057077993,0.000025874782,0.000107715525,0.0000014461366,0.0111073395,0.029975351,0.0011084991,0.007622771,0.00071500806,0.8919615],"study_design_scores_gemma":[0.003482548,0.0017048524,0.3033331,0.00011555928,0.00054087205,0.00007850716,0.0031794973,0.6312014,0.003301753,0.049142353,0.0034211685,0.0004984108],"about_ca_topic_score_codex":0.0039387695,"about_ca_topic_score_gemma":0.14069767,"teacher_disagreement_score":0.8914631,"about_ca_system_score_codex":0.0040651406,"about_ca_system_score_gemma":0.018856525,"threshold_uncertainty_score":0.9999724},"labels":[],"label_agreement":null},{"id":"W2931117118","doi":"10.1007/978-3-030-14774-7_10","title":"Evaluating Change in Nonprofit Organizations","year":2019,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Process (computing); Task (project management); Process management; Quality (philosophy); Work (physics); Computer science; Theory of change; Evaluation methods; Management science; Knowledge management; Engineering; Management; Systems engineering","score_opus":0.5299131690056686,"score_gpt":0.565761391980439,"score_spread":0.035848222974770305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2931117118","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006183538,0.00010895395,0.00031242237,0.001626487,0.0007023157,0.00080028357,0.000016483958,0.00003728308,0.9957774],"genre_scores_gemma":[0.01749806,0.00007039265,0.0012641271,0.0016203186,0.00022556366,0.000021421469,0.000057802306,0.000036313028,0.979206],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99578637,0.00006204992,0.00089147006,0.00056414586,0.0025001147,0.00019584542],"domain_scores_gemma":[0.997167,0.0005546178,0.00039780946,0.0007775105,0.0010384518,0.00006459945],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0040909196,0.00022625155,0.00039190985,0.00063853664,0.00007699333,0.00017621198,0.0005751025,0.0002399855,0.1266444],"category_scores_gemma":[0.0006696816,0.00016853499,0.00007475501,0.00034721725,0.00003141993,0.00037327784,0.00019317862,0.0002891799,0.02546213],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000125147735,0.000035589983,0.019648906,0.000023004211,0.000027563006,0.0000046879395,0.0019493237,0.0005032154,0.0000425615,0.703576,0.010732095,0.26344454],"study_design_scores_gemma":[0.001698832,0.0004186226,0.033342708,0.00039744322,0.00006691536,0.000010043012,0.00042717604,0.124845766,0.00005575708,0.112485826,0.7248476,0.0014033226],"about_ca_topic_score_codex":0.000038405888,"about_ca_topic_score_gemma":0.000667012,"teacher_disagreement_score":0.7141155,"about_ca_system_score_codex":0.00013450572,"about_ca_system_score_gemma":0.00067812455,"threshold_uncertainty_score":0.9752967},"labels":[],"label_agreement":null},{"id":"W2934622413","doi":"10.24452/sjer.41.1.5","title":"La médiation par les pairs en milieu scolaire: recherche d’un programme pour une école primaire valaisanne. Revue systématique réalisée selon les critères «Evidence-Based Practice»","year":2019,"lang":"fr","type":"article","venue":"Swiss Journal of Educational Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Humanities; Art","score_opus":0.49338946929160254,"score_gpt":0.5719806834098161,"score_spread":0.07859121411821357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2934622413","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41318557,0.024303397,0.00070928276,0.5537981,0.0013619635,0.0012581658,0.000017015429,0.000010898086,0.0053556226],"genre_scores_gemma":[0.93883824,0.005498671,0.03842843,0.0006136043,0.0017129837,0.00015261795,0.000023543853,0.00005221133,0.014679704],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.97059256,0.019487843,0.002163598,0.00069417467,0.0061682826,0.0008935592],"domain_scores_gemma":[0.903112,0.08191066,0.0015730897,0.00074759807,0.012070694,0.0005859564],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.09432648,0.0003715151,0.0006332074,0.001219504,0.0009755461,0.0011344235,0.0016331066,0.00070577674,0.008181696],"category_scores_gemma":[0.11220312,0.00031765012,0.00037287397,0.003057315,0.0005470103,0.0034775592,0.00017906622,0.0031704109,0.0009972627],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001598477,0.004950025,0.22434714,0.0018323688,0.00046291752,0.000047000914,0.014677959,0.010310253,0.0038941929,0.046235044,0.082287684,0.60935694],"study_design_scores_gemma":[0.0036761602,0.0037066678,0.47144067,0.015672112,0.0003461839,0.00081592856,0.08092032,0.027826345,0.006150713,0.08794558,0.30029154,0.0012077882],"about_ca_topic_score_codex":0.00210107,"about_ca_topic_score_gemma":0.00051413587,"teacher_disagreement_score":0.6081492,"about_ca_system_score_codex":0.0023853143,"about_ca_system_score_gemma":0.03476188,"threshold_uncertainty_score":0.9999276},"labels":[],"label_agreement":null},{"id":"W293512544","doi":"10.3138/cjpe.23.012","title":"Latent Profiles of Evaluators’ Self-Reported Practices","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Facilitator; Latent class model; Stakeholder; Psychology; Class (philosophy); Degree (music); Social psychology; Applied psychology; Computer science; Artificial intelligence; Machine learning; Political science; Public relations","score_opus":0.5814887145472366,"score_gpt":0.5616080822872708,"score_spread":0.019880632259965836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W293512544","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99293286,0.0006430646,0.0001482256,0.0014110977,0.0008322634,0.0011823389,0.000005123616,0.000013569769,0.0028314618],"genre_scores_gemma":[0.99154526,0.00005252934,0.007916519,0.000074526724,0.00016564688,0.000053252672,0.000009888255,0.000010707884,0.0001716425],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9926705,0.00089791714,0.0017381602,0.00023115968,0.0041855094,0.0002767981],"domain_scores_gemma":[0.9849579,0.0003603647,0.006011795,0.0003982901,0.007799379,0.00047230473],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.022268007,0.00014197422,0.00034496628,0.00085312274,0.00024868644,0.00013648976,0.0004982556,0.00009855489,0.0028093366],"category_scores_gemma":[0.012050672,0.00010516012,0.0001811323,0.0010621985,0.00013897486,0.0009972592,0.000014213339,0.00022328961,0.00007210086],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052074774,0.00027899176,0.6419588,0.000016823877,0.0002813472,0.000049860788,0.0048400243,0.0023293616,0.00032184017,0.00029596346,0.009152956,0.340422],"study_design_scores_gemma":[0.0022883597,0.0016992621,0.84812826,0.00009793846,0.00059849967,0.0007575934,0.0015673955,0.079181805,0.0016727896,0.004581058,0.059105992,0.00032104773],"about_ca_topic_score_codex":0.00062972895,"about_ca_topic_score_gemma":0.003488513,"teacher_disagreement_score":0.34010097,"about_ca_system_score_codex":0.00032250004,"about_ca_system_score_gemma":0.013678312,"threshold_uncertainty_score":0.99810225},"labels":[],"label_agreement":null},{"id":"W2935865076","doi":"10.2147/amep.s188164","title":"&lt;p&gt;Faculty development program evaluation: a need to embrace complexity&lt;/p&gt;","year":2019,"lang":"en","type":"article","venue":"Advances in Medical Education and Practice","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Faculty development; Relevance (law); Professional development; Medical education; Situated; Program evaluation; Psychology; Computer science; Knowledge management; Political science; Medicine; Artificial intelligence","score_opus":0.20073143573546473,"score_gpt":0.5870656963922686,"score_spread":0.3863342606568039,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2935865076","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38320872,0.006274005,0.003588517,0.18007971,0.0059811412,0.0056633353,0.000006363752,0.00014826312,0.41504994],"genre_scores_gemma":[0.7963248,0.0010550313,0.16325073,0.02921601,0.00038868168,0.0016254329,0.00016219818,0.000026335772,0.007950779],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99271834,0.0009214702,0.00091695326,0.0006311549,0.0045080567,0.00030401183],"domain_scores_gemma":[0.9950552,0.002439851,0.0003996968,0.0004522126,0.0012014175,0.00045164747],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.015847033,0.00018513575,0.00028976498,0.00029690046,0.00018453761,0.00026919882,0.0005079219,0.00011233775,0.009683019],"category_scores_gemma":[0.028655205,0.00014486673,0.000034106808,0.0013194808,0.000110459456,0.0020765897,0.00013652696,0.0002784108,0.0014849128],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001066169,0.0007232741,0.0024470857,0.000017213339,0.000008129073,7.5590026e-7,0.0031299824,0.00014894218,0.000024697729,0.009911664,0.0062637813,0.97721785],"study_design_scores_gemma":[0.0007831125,0.00013680618,0.029850757,0.00008222883,0.000013026013,0.000032061627,0.003569328,0.010184219,0.000017203416,0.0030893532,0.95203954,0.00020237677],"about_ca_topic_score_codex":0.000007415799,"about_ca_topic_score_gemma":0.00032598214,"teacher_disagreement_score":0.9770155,"about_ca_system_score_codex":0.00018314578,"about_ca_system_score_gemma":0.0036898493,"threshold_uncertainty_score":0.99929255},"labels":[],"label_agreement":null},{"id":"W2938338133","doi":"10.1016/s0021-8502(19)30148-x","title":"PRELIMINARY ANSWERS TO POLICY-RELEVANT QUESTIONS FROM THE PACIFIC 2001 STUDY, VANCOUVER, BRITISH COLUMBIA, CANADA","year":2004,"lang":"en","type":"article","venue":"Journal of Aerosol Science","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Environment and Climate Change Canada","funders":"","keywords":"Geography; Political science; Oceanography; History; Library science; Regional science; Geology; Computer science","score_opus":0.052820530014249474,"score_gpt":0.3845019081019117,"score_spread":0.33168137808766224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2938338133","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9861682,0.00007247352,0.00075892796,0.009270426,0.0022652505,0.00032951293,0.000035212295,0.0000067402875,0.0010932777],"genre_scores_gemma":[0.995003,0.00003746276,0.0014271865,0.0016646,0.00025703275,0.00000621874,2.4559534e-7,0.000005545291,0.0015987257],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9932982,0.00016264252,0.00091056735,0.00034292229,0.0048668096,0.00041886594],"domain_scores_gemma":[0.9965002,0.0005686313,0.00054223515,0.0005246132,0.0014082403,0.0004560779],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0065669925,0.00009926819,0.00024864552,0.00015645256,0.0010090907,0.0014822165,0.0020221276,0.000026831785,0.00043165826],"category_scores_gemma":[0.0037852468,0.00008196011,0.00007501181,0.0030471988,0.0003012016,0.0010125653,0.00018488556,0.00027104738,0.000029116558],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000085585096,0.00085118925,0.19918583,0.0000018740658,0.000042562344,0.0002146748,0.007401456,0.037486423,0.002509995,0.00003567471,0.7070085,0.045176256],"study_design_scores_gemma":[0.0022188223,0.0028220788,0.9105287,0.00026510187,0.000054032083,0.00022043566,0.054450836,0.0008056312,0.0004760761,0.0029507212,0.024707371,0.00050017145],"about_ca_topic_score_codex":0.8121253,"about_ca_topic_score_gemma":0.9898396,"teacher_disagreement_score":0.7113429,"about_ca_system_score_codex":0.0008373483,"about_ca_system_score_gemma":0.013108549,"threshold_uncertainty_score":0.99955434},"labels":[],"label_agreement":null},{"id":"W2939670165","doi":"","title":"Implementation Frameworks for International Summits or Conferences","year":2018,"lang":"en","type":"article","venue":"Figshare","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Business; Political science; Process management","score_opus":0.5171174621900531,"score_gpt":0.6121564078619133,"score_spread":0.09503894567186022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2939670165","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021110842,0.00010445278,0.01306002,0.028710593,0.009674684,0.004071065,0.7189686,0.00036620352,0.20393357],"genre_scores_gemma":[0.94825506,0.0000024856852,0.0026255592,0.0030092082,0.001434085,0.00042451054,0.03962697,0.000008715309,0.0046134056],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984502,0.000037208036,0.00032764013,0.00022782673,0.0008228901,0.0001341919],"domain_scores_gemma":[0.99679625,0.00077026524,0.00019330991,0.00018150934,0.0020083585,0.000050329767],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005441062,0.000069482165,0.00008520722,0.000106655665,0.00013863588,0.00053562765,0.000516754,0.00009037087,0.80886316],"category_scores_gemma":[0.006334207,0.0000453887,0.00004508173,0.00020894941,0.000010063195,0.00058253034,0.000073359144,0.00008427569,0.0048391586],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027007321,0.0000082145625,0.0012157504,0.0000024030958,0.00000699249,1.546335e-7,0.00027005764,0.000003736566,0.000003952495,0.0004120724,0.8602047,0.13784496],"study_design_scores_gemma":[0.00039454093,0.0001439069,0.016071783,0.000076157405,0.0000022202794,6.446253e-7,0.001459232,0.01012177,0.00075048395,0.00316966,0.9677262,0.000083444684],"about_ca_topic_score_codex":0.0000039140727,"about_ca_topic_score_gemma":0.00048714108,"teacher_disagreement_score":0.9271442,"about_ca_system_score_codex":0.000026093658,"about_ca_system_score_gemma":0.00029749976,"threshold_uncertainty_score":0.9959357},"labels":[],"label_agreement":null},{"id":"W2940688599","doi":"10.4018/978-1-4666-8324-2.ch012","title":"The Evolution of Online Learning and Related Tools and Techniques toward MOOCs","year":2015,"lang":"en","type":"book-chapter","venue":"Advances in educational technologies and instructional design book series","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Mainstream; Online learning; Massive open online course; Learning design; Engineering ethics; Computer science; Data science; Multimedia; Mathematics education; Engineering; World Wide Web; Psychology; Political science","score_opus":0.09880733559121367,"score_gpt":0.41062810958836576,"score_spread":0.3118207739971521,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2940688599","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01162056,0.650973,0.002304082,0.042632945,0.0023942222,0.0027586774,0.00035117273,0.00062781165,0.2863375],"genre_scores_gemma":[0.081145965,0.57268447,0.07213261,0.00006582866,0.00020666554,0.00022599542,0.00013451953,0.00006003987,0.27334392],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979759,0.000057127065,0.00071167207,0.00039724563,0.0007222548,0.00013579505],"domain_scores_gemma":[0.9976275,0.0010529278,0.0005432088,0.00019064744,0.00055434695,0.00003134342],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001185052,0.00021656542,0.0003086139,0.00037483824,0.00027222862,0.00010598861,0.00024182392,0.00026439055,0.00008137007],"category_scores_gemma":[0.0014594945,0.00015104252,0.000031682634,0.00014927148,0.0014879296,0.0015991112,0.00019397415,0.00041569152,0.0000020642024],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043959884,0.000006992803,0.0007487399,0.000012647921,0.0000112282205,2.0537689e-7,0.000059385984,0.000056811903,0.000021982232,0.61153424,0.0001910578,0.38731274],"study_design_scores_gemma":[0.0000866438,0.00015821493,0.0015489311,0.00008537055,0.000007620419,0.00007043258,0.0030816982,0.00008786807,0.000043452543,0.6317402,0.36296552,0.00012402513],"about_ca_topic_score_codex":0.000003988227,"about_ca_topic_score_gemma":0.000025409294,"teacher_disagreement_score":0.38718873,"about_ca_system_score_codex":0.00016269373,"about_ca_system_score_gemma":0.00046023665,"threshold_uncertainty_score":0.61593354},"labels":[],"label_agreement":null},{"id":"W2942533009","doi":"10.1051/pmed/2019002","title":"Jugement évaluatif : confrontation d’un modèle conceptuel à des données empiriques","year":2018,"lang":"fr","type":"article","venue":"Pédagogie médicale","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Humanities; Philosophy","score_opus":0.49047896040028177,"score_gpt":0.5006863150093198,"score_spread":0.010207354609038044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2942533009","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6529414,0.020728305,0.13265479,0.044614665,0.0078621255,0.0015286747,0.0001546159,0.0002953821,0.13922001],"genre_scores_gemma":[0.81303453,0.003156393,0.02784385,0.0054114885,0.0017162169,0.00015855725,0.000054579203,0.000051898176,0.14857247],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99275637,0.0011049544,0.0013746187,0.0009331759,0.0029765915,0.00085428404],"domain_scores_gemma":[0.9954647,0.000885956,0.00049225177,0.00090785144,0.0017985954,0.0004506438],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.006508288,0.0004232534,0.0005442583,0.00025862092,0.0010226556,0.0007013837,0.00095981424,0.0002854434,0.07478848],"category_scores_gemma":[0.0014054977,0.00036336618,0.00023343893,0.0008180041,0.0029056836,0.0013429974,0.0003324293,0.0003140264,0.009556578],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009351805,0.00046351925,0.014127672,0.000058626316,0.000093706156,0.000008895254,0.01712457,0.000207317,0.0008728474,0.0071422793,0.050453845,0.9093532],"study_design_scores_gemma":[0.0018207132,0.0012414899,0.035284117,0.00027342635,0.00013975138,0.000014584846,0.012700881,0.076386444,0.011940913,0.0600416,0.79950356,0.0006525305],"about_ca_topic_score_codex":0.00023254374,"about_ca_topic_score_gemma":0.00066392426,"teacher_disagreement_score":0.90870064,"about_ca_system_score_codex":0.00036894958,"about_ca_system_score_gemma":0.0012154795,"threshold_uncertainty_score":0.9998818},"labels":[],"label_agreement":null},{"id":"W2943061696","doi":"","title":"British Columbia School Trustees' Use of Research and Information Seeking in Decision Making.","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Educational Administration and Policy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Newspaper; Christian ministry; Public relations; Sociology; Political science; Psychology; Library science; Medical education; Medicine; Media studies; Law","score_opus":0.14226133903155253,"score_gpt":0.4937033357361036,"score_spread":0.35144199670455106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2943061696","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99124205,0.00007273563,0.000023460982,0.005010562,0.00021178213,0.00014955287,0.000022014341,5.564443e-7,0.0032672724],"genre_scores_gemma":[0.99692845,0.000048334052,0.0008126531,0.00048068597,0.00011467272,0.0000024310475,0.0000069298057,0.0000027999197,0.0016030651],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99808496,0.00012379765,0.00079418515,0.00010111921,0.00074292335,0.00015299676],"domain_scores_gemma":[0.9966923,0.0012672114,0.00035086938,0.00012035374,0.001239484,0.00032975312],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0026435184,0.0000481137,0.00014695883,0.0010081693,0.00011440325,0.0012428908,0.00015211751,0.000061581086,0.0049317586],"category_scores_gemma":[0.0053456705,0.000057077392,0.00002499649,0.00066160195,0.000109657456,0.002173772,0.000013160307,0.00018666002,0.000025293291],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027819027,0.00002263639,0.95487905,0.000013097163,0.000004409489,0.000001193301,0.00071916956,0.00006171105,0.000010168481,0.0081223585,0.010309474,0.025828935],"study_design_scores_gemma":[0.00031563733,0.00019689485,0.9425739,0.00017247893,0.0000016563906,0.00013959201,0.0009854818,0.00045413204,0.0000025521963,0.017184982,0.037917644,0.000055053304],"about_ca_topic_score_codex":0.016463133,"about_ca_topic_score_gemma":0.29289135,"teacher_disagreement_score":0.27642822,"about_ca_system_score_codex":0.0001466524,"about_ca_system_score_gemma":0.009401687,"threshold_uncertainty_score":0.9997939},"labels":[],"label_agreement":null},{"id":"W2943156028","doi":"10.1007/s10671-018-09244-z","title":"Teacher learning, accountability and policy enactment in Ontario: the centrality of trust","year":2018,"lang":"en","type":"article","venue":"Educational Research for Policy and Practice","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Lakehead University","funders":"Australian Research Council","keywords":"Centrality; Accountability; Policy learning; Political science; Corporate governance; Public administration; Psychology; Public relations; Business; Sociology; Law; Finance; Computer science","score_opus":0.5731599645379885,"score_gpt":0.6726193309531374,"score_spread":0.09945936641514896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2943156028","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7606779,0.00007597778,0.000021013158,0.18534504,0.000069365065,0.0004669832,0.000009481196,0.0000017042115,0.053332593],"genre_scores_gemma":[0.9819318,0.0000610666,0.00033397795,0.000732114,0.00045950589,0.00007361332,0.000005527199,0.000003470352,0.016398927],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.996557,0.0013398438,0.0003598099,0.00026529937,0.0012033627,0.00027471574],"domain_scores_gemma":[0.97273886,0.025374556,0.0001864883,0.000312641,0.0012663224,0.00012110015],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.025571978,0.00006862529,0.00011326152,0.0002883943,0.0004201779,0.00019003736,0.00024690788,0.00004598802,0.0013660836],"category_scores_gemma":[0.085124075,0.00004356934,0.000025818174,0.0006192076,0.0005809607,0.0006292247,0.00011012317,0.00035179532,0.000029042096],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012264902,0.0009733188,0.51044375,0.0000291588,0.000043569795,7.1294906e-8,0.057024967,0.000020311774,0.00024128094,0.36308825,0.023282535,0.043626305],"study_design_scores_gemma":[0.00020769058,0.00014128274,0.47215006,0.000004529763,0.0000024955414,0.0000035676117,0.0048369104,0.00016219541,0.000039883453,0.038259655,0.4841591,0.00003260502],"about_ca_topic_score_codex":0.19016676,"about_ca_topic_score_gemma":0.08431594,"teacher_disagreement_score":0.46087658,"about_ca_system_score_codex":0.00037950193,"about_ca_system_score_gemma":0.0049786177,"threshold_uncertainty_score":0.9995468},"labels":[],"label_agreement":null},{"id":"W2943409634","doi":"10.14288/1.0305852","title":"Enhancing Organizational Capacity for Program Evaluation : The Case of the Neighbourhood Small Grants Program","year":2017,"lang":"en","type":"article","venue":"Open Collections","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Neighbourhood (mathematics); Business; Program evaluation; Political science; Public administration; Mathematics","score_opus":0.3254052423149156,"score_gpt":0.5133457641586304,"score_spread":0.18794052184371485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2943409634","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45489386,0.00004921825,0.020867968,0.017680645,0.0055753733,0.058478147,0.0004690196,0.00014202921,0.44184375],"genre_scores_gemma":[0.9657234,0.0000025739514,0.010944357,0.000099261626,0.00010567974,0.0035066816,0.000008490979,0.000011092103,0.019598495],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979868,0.00033023328,0.00048909354,0.00028270745,0.00074078917,0.00017037823],"domain_scores_gemma":[0.99551135,0.0005667684,0.0006339767,0.0009910228,0.0022492248,0.000047658305],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006276938,0.00010025499,0.00015843076,0.000047755264,0.010729918,0.0038379086,0.0014134685,0.00005289925,0.0015941022],"category_scores_gemma":[0.0053840703,0.00005328778,0.000104134335,0.00095017144,0.00017230296,0.0004436682,0.0002996734,0.00011335933,0.000008777136],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009057453,0.0015893064,0.008488189,0.000019977346,0.00016784122,0.0000016384281,0.0025501943,0.001622371,0.00039884218,0.0059648138,0.053135812,0.92597044],"study_design_scores_gemma":[0.0068741636,0.0013965617,0.13438381,0.00014038642,0.0006006764,0.00043988717,0.0070483354,0.48265842,0.011477063,0.15068954,0.20357285,0.000718304],"about_ca_topic_score_codex":0.0022570214,"about_ca_topic_score_gemma":0.06799019,"teacher_disagreement_score":0.92525214,"about_ca_system_score_codex":0.00008488804,"about_ca_system_score_gemma":0.0010137712,"threshold_uncertainty_score":0.9993186},"labels":[],"label_agreement":null},{"id":"W2943504252","doi":"10.25761/anaisihmt.54","title":"Equity in evaluative research focusing on health cooperation and development","year":2018,"lang":"en","type":"article","venue":"Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Equity (law); Context (archaeology); Political science; Sociology; Theme (computing); Relevance (law); Engineering ethics; Public relations; Pedagogy; Geography; Engineering; Computer science; Law","score_opus":0.5010817385905801,"score_gpt":0.6174556186010127,"score_spread":0.11637388001043258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2943504252","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9434194,0.0012408075,0.002121288,0.02015699,0.0003513329,0.00394673,0.000054727057,0.00009648546,0.02861225],"genre_scores_gemma":[0.99363023,0.00030444015,0.0038218126,0.00012032315,0.00008343417,0.0004495017,0.000021624832,0.000010457721,0.0015581805],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98940605,0.00049481273,0.00081541744,0.0012135523,0.006861317,0.0012088304],"domain_scores_gemma":[0.99006057,0.0018693965,0.00019126292,0.00032698066,0.0073387236,0.00021304628],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch","sts"],"category_scores_codex":[0.10859455,0.00016716086,0.00027013768,0.007261609,0.0033656426,0.00048583176,0.0008977084,0.00015375417,0.000082599574],"category_scores_gemma":[0.019217907,0.00013017643,0.00001784022,0.009097868,0.0032130575,0.00089543185,0.0007491225,0.0006420604,0.000057550747],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014278581,0.00030069522,0.00961842,0.000027703707,0.00001174959,0.0000016845273,0.00273233,0.000004541508,0.0046113776,0.11239022,0.009744609,0.8604139],"study_design_scores_gemma":[0.0048623094,0.013143269,0.07509914,0.0006221871,0.0000044553813,0.000052936804,0.012112667,0.06439264,0.045696963,0.67441726,0.10847862,0.0011175636],"about_ca_topic_score_codex":0.00007356947,"about_ca_topic_score_gemma":0.0004004288,"teacher_disagreement_score":0.8592963,"about_ca_system_score_codex":0.001201261,"about_ca_system_score_gemma":0.009485814,"threshold_uncertainty_score":0.9994996},"labels":[],"label_agreement":null},{"id":"W2943685433","doi":"","title":"Évaluation des interventions axées sur la réinsertion sociale","year":2019,"lang":"fr","type":"article","venue":"CIRANO Project Reports","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Humanities; Political science; Art","score_opus":0.3101919921716498,"score_gpt":0.5033955633709689,"score_spread":0.19320357119931914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2943685433","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8825304,0.0031021503,0.0037796588,0.0016747627,0.005837817,0.0013966104,0.000014316609,0.00009068283,0.101573594],"genre_scores_gemma":[0.81492335,0.00045717775,0.001974681,0.00014806687,0.00022838864,0.00009840803,0.00006272061,0.000026161028,0.18208107],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9941084,0.001139817,0.0016784758,0.0007466844,0.0018944124,0.00043225044],"domain_scores_gemma":[0.996488,0.00070385664,0.0009693058,0.0007644411,0.0009799994,0.00009441214],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.011215351,0.00026372037,0.00042495405,0.00044200302,0.00036006817,0.0006537151,0.00025131417,0.0002663129,0.008089597],"category_scores_gemma":[0.0018469836,0.00024261307,0.00053843204,0.0011066889,0.00027008235,0.0018541095,0.00012211254,0.0002762598,0.0011891655],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034852925,0.00054503157,0.16253127,0.0003741647,0.00008594243,0.000056318124,0.0055135665,0.00061166444,0.0018258884,0.00089474063,0.01412426,0.8134023],"study_design_scores_gemma":[0.0014829136,0.0007293591,0.3950941,0.0020532727,0.00032141214,0.0007657654,0.0030992848,0.017217072,0.0028646314,0.04498101,0.53046054,0.0009306662],"about_ca_topic_score_codex":0.0008674212,"about_ca_topic_score_gemma":0.00093545695,"teacher_disagreement_score":0.8124716,"about_ca_system_score_codex":0.00023614756,"about_ca_system_score_gemma":0.002568549,"threshold_uncertainty_score":0.99958855},"labels":[],"label_agreement":null},{"id":"W2944454729","doi":"10.15353/cjo.77.498","title":"What an Ounce of Prevention can do for your Practice","year":2015,"lang":"en","type":"article","venue":"Canadian journal of optometry/CJO. Canadian journal of optometry","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Fluid ounce (US); Medicine; Psychology; History; Political science","score_opus":0.25578327270492673,"score_gpt":0.5523109170390313,"score_spread":0.2965276443341046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2944454729","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9722512,0.005406928,0.0051012905,0.007751902,0.0069958083,0.00042049674,0.00021284136,0.000003894429,0.0018556763],"genre_scores_gemma":[0.98329526,0.00018463028,0.013762766,0.00092289934,0.0007753384,0.0000035813289,0.000009249678,0.00005360403,0.0009926426],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9911237,0.0007882759,0.0032856348,0.00040627908,0.0033865145,0.0010096434],"domain_scores_gemma":[0.9723558,0.0010749523,0.0049735527,0.00071735994,0.014149514,0.0067288117],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.023004096,0.00042231043,0.0011950801,0.009193439,0.00039339962,0.0018095248,0.0024300257,0.00032273596,0.0012718494],"category_scores_gemma":[0.01148275,0.00036233268,0.0006300886,0.004655466,0.00033446305,0.007231699,0.000027806338,0.00091728364,0.00003207709],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046752085,0.00019804067,0.88040733,0.00007266585,0.00065537845,0.0004748547,0.009198179,0.007354332,0.000111858215,0.00014086503,0.06325188,0.03766711],"study_design_scores_gemma":[0.009456435,0.0065948674,0.63010514,0.0015860297,0.0008772706,0.0074198833,0.13440028,0.0020698155,0.0011211762,0.00090057956,0.20392153,0.0015470303],"about_ca_topic_score_codex":0.0016887346,"about_ca_topic_score_gemma":0.0062745856,"teacher_disagreement_score":0.2503022,"about_ca_system_score_codex":0.0017919111,"about_ca_system_score_gemma":0.03379245,"threshold_uncertainty_score":0.9998829},"labels":[],"label_agreement":null},{"id":"W2944986807","doi":"10.5931/djim.v15i0.8978","title":"Curriculum Risk Management: Improving student outcomes with a system for risk exploration","year":2019,"lang":"en","type":"article","venue":"Dalhousie Journal of Interdisciplinary Management","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Risk management; Context (archaeology); Risk communication; Curriculum; Risk management framework; Knowledge management; Business; Risk analysis (engineering); IT risk management; Process management; Computer science; Psychology; Pedagogy; Finance","score_opus":0.03750832687466257,"score_gpt":0.40533100979479386,"score_spread":0.3678226829201313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2944986807","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8191378,0.00007906232,0.16233334,0.00057802733,0.0021341504,0.0019071442,0.00002284869,0.00004514765,0.013762438],"genre_scores_gemma":[0.9840487,0.000072823896,0.012872912,0.000054446245,0.00013495372,0.000102296064,0.00000629812,0.00003130278,0.0026762653],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9945391,0.0002871282,0.0017011075,0.0005023452,0.0026207627,0.00034958226],"domain_scores_gemma":[0.9953866,0.00022448569,0.0027412116,0.00078127405,0.0007274075,0.00013903191],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007487865,0.00031189487,0.0006163548,0.00088836456,0.0003977344,0.00050270243,0.0011780721,0.000049639446,0.00014331582],"category_scores_gemma":[0.00004161102,0.00018510385,0.00036501337,0.00056829577,0.00003692196,0.0014920342,0.0009751738,0.0002672243,0.00023379052],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010598346,0.0012495599,0.6747052,0.0007396504,0.0024960306,0.0001852002,0.009223866,0.06133706,0.000011892775,0.009653105,0.006100946,0.23323767],"study_design_scores_gemma":[0.014990223,0.006429794,0.32500556,0.0013322699,0.0020986635,0.00010180377,0.5334336,0.096138515,0.00007991284,0.007104999,0.012091873,0.0011927688],"about_ca_topic_score_codex":0.0000055784617,"about_ca_topic_score_gemma":0.000035631485,"teacher_disagreement_score":0.52420974,"about_ca_system_score_codex":0.00030752076,"about_ca_system_score_gemma":0.00004013055,"threshold_uncertainty_score":0.7548316},"labels":[],"label_agreement":null},{"id":"W2945068297","doi":"10.3138/cjpe.42239","title":"20 Years Later: Reflections on the CES Student Evaluation Case Competition","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Memorial University of Newfoundland; University of Waterloo","funders":"","keywords":"Competition (biology); Teamwork; Psychology; Computer-assisted web interviewing; Medical education; Social psychology; Applied psychology; Marketing; Management; Medicine; Business; Economics","score_opus":0.44939411653968636,"score_gpt":0.5776639702248278,"score_spread":0.1282698536851415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945068297","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9789716,0.00013211329,0.00008415222,0.0049438532,0.0018195275,0.0020791965,0.000009155751,0.000009293989,0.011951136],"genre_scores_gemma":[0.9985334,0.0000069631355,0.000326697,0.0004500573,0.00021407862,0.00011779294,0.000017668259,0.000010090428,0.0003232264],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9936551,0.0014545912,0.0008274062,0.00023279172,0.00358929,0.00024081246],"domain_scores_gemma":[0.9948979,0.000471921,0.00068348466,0.00042665948,0.0032624174,0.00025760574],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02542967,0.00012576167,0.00018885329,0.00065622677,0.0003478065,0.000628839,0.00040729943,0.000075484306,0.010573201],"category_scores_gemma":[0.0012415783,0.000083462255,0.00013862333,0.00082682696,0.000069060465,0.0005393895,0.000012778354,0.00028965127,0.0007281159],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004867686,0.00019914132,0.031515446,0.0000048133074,0.00013741199,0.000060476385,0.007351899,0.040245887,0.0002253376,0.0062595713,0.008096869,0.90585446],"study_design_scores_gemma":[0.0046717892,0.0040882183,0.4377646,0.00022808967,0.0006627877,0.0015411051,0.028565425,0.23492722,0.0003385663,0.03249306,0.25407,0.0006491061],"about_ca_topic_score_codex":0.00028917153,"about_ca_topic_score_gemma":0.027114308,"teacher_disagreement_score":0.90520537,"about_ca_system_score_codex":0.0007010905,"about_ca_system_score_gemma":0.0028614542,"threshold_uncertainty_score":0.9906383},"labels":[],"label_agreement":null},{"id":"W2945107123","doi":"10.3138/cjpe.43216","title":"Scaling Up Programs: Reflections on the Importance of Process Evaluation","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"General partnership; Scale (ratio); Process (computing); Program evaluation; Public relations; Process management; Computer science; Psychology; Business; Political science; Medical education; Public administration; Medicine; Finance","score_opus":0.569979886420681,"score_gpt":0.6000537481211533,"score_spread":0.030073861700472326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945107123","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9822758,0.00022808254,0.00012959873,0.0030712285,0.0013266329,0.0029974524,0.00000368896,0.0000087007675,0.0099588465],"genre_scores_gemma":[0.99869084,0.0000050078734,0.0005214552,0.00024853455,0.00013459877,0.00019875726,0.00001342946,0.000011970893,0.00017539803],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9927678,0.0008966335,0.0012745698,0.00026000367,0.0045195026,0.000281486],"domain_scores_gemma":[0.989517,0.00045469345,0.0015260866,0.0005027297,0.0077579673,0.00024155353],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.030280655,0.00014318166,0.0002662771,0.00061000127,0.00025037103,0.0003013512,0.00061499036,0.00008893325,0.004272085],"category_scores_gemma":[0.005381511,0.00008963368,0.0001699629,0.0015521661,0.00011050127,0.0006012254,0.000009154422,0.0002987204,0.00011771631],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044303397,0.000093228846,0.11744577,0.00001267294,0.000053093296,6.2073036e-7,0.0034874715,0.013808727,0.00007848767,0.0022817403,0.00086256716,0.8618313],"study_design_scores_gemma":[0.004249359,0.0036771758,0.28124124,0.00071991375,0.0005864564,0.000088102635,0.035927888,0.515883,0.0017677472,0.10899662,0.0462128,0.0006496539],"about_ca_topic_score_codex":0.00013058631,"about_ca_topic_score_gemma":0.007188798,"teacher_disagreement_score":0.8611817,"about_ca_system_score_codex":0.0004575102,"about_ca_system_score_gemma":0.0070746485,"threshold_uncertainty_score":0.9985543},"labels":[],"label_agreement":null},{"id":"W2945434485","doi":"10.56645/jmde.v15i32.513","title":"Communication for Social Change","year":2019,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Deci-; Capacity building; Public relations; Political science; Knowledge management; Business; Computer science","score_opus":0.4924261702304836,"score_gpt":0.5826940578875175,"score_spread":0.09026788765703392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945434485","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9856999,0.00026842084,0.0022295127,0.008198777,0.0009391094,0.0010166653,0.0000067755027,0.000006264741,0.0016345578],"genre_scores_gemma":[0.9948933,0.000028903376,0.004010875,0.000108350694,0.00039527752,0.000050550025,0.000017517055,0.000008720059,0.00048648886],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99561864,0.00055359845,0.0009776225,0.00015311474,0.002565712,0.00013129842],"domain_scores_gemma":[0.99440616,0.0008718073,0.0013431086,0.00031065728,0.0030177638,0.00005050527],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.022881348,0.000092626346,0.00025606496,0.00032254364,0.00023915368,0.00010314258,0.0005155214,0.00007341976,0.0012028703],"category_scores_gemma":[0.0008582454,0.00006663739,0.00020380424,0.00032805584,0.000029985542,0.0012494719,0.000081420134,0.00013769868,0.0001852765],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010975952,0.0006816748,0.11209722,0.000043255037,0.000102707025,6.485616e-7,0.038618006,0.0058883126,0.0059068743,0.0043867133,0.011270645,0.81990635],"study_design_scores_gemma":[0.003499868,0.00058157416,0.6264889,0.0000466118,0.00008027095,0.000011443477,0.0041201185,0.32666063,0.00023909533,0.029523138,0.008601354,0.00014696016],"about_ca_topic_score_codex":0.0000018349867,"about_ca_topic_score_gemma":0.000015182361,"teacher_disagreement_score":0.81975937,"about_ca_system_score_codex":0.00016887265,"about_ca_system_score_gemma":0.00029191453,"threshold_uncertainty_score":0.99971014},"labels":[],"label_agreement":null},{"id":"W2945573974","doi":"10.3138/cjpe.42118","title":"Community, Theory, and Guidance: Benefits and Lessons Learned in Evaluation Peer Mentoring","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Peer mentoring; Psychology; Professional development; Work (physics); Medical education; Peer review; Field (mathematics); Empirical research; Public relations; Pedagogy; Political science; Medicine; Engineering","score_opus":0.5039995996250785,"score_gpt":0.5605583430272246,"score_spread":0.05655874340214617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945573974","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98806876,0.002138193,0.000046283712,0.0050463043,0.00043423058,0.0010164857,0.0000039945403,0.000003950654,0.0032418042],"genre_scores_gemma":[0.99891293,0.00004709651,0.0005223871,0.00011131919,0.000051556108,0.000043612003,0.0000092017035,0.000008259383,0.00029362997],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9933965,0.0028238653,0.0007374327,0.00018902127,0.0026064466,0.00024669606],"domain_scores_gemma":[0.99568325,0.00055200385,0.00047319612,0.00028631097,0.0027165462,0.00028868427],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.09360075,0.00011425745,0.0002288172,0.0007116532,0.0002286931,0.00048011515,0.00028923282,0.00008059616,0.0009964942],"category_scores_gemma":[0.0058898046,0.00009444395,0.000040678126,0.0005097326,0.00007593689,0.000767669,0.000033314325,0.00035189747,0.000024202294],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021230246,0.000021152186,0.13945095,0.000005020059,0.000011196041,4.483416e-7,0.003949973,0.0024729073,0.000054714754,0.002685616,0.00015975306,0.851167],"study_design_scores_gemma":[0.002634881,0.0005229262,0.83827204,0.00019083843,0.00008870807,0.000030003594,0.009006835,0.077206425,0.00007135074,0.06131295,0.010476469,0.00018660194],"about_ca_topic_score_codex":0.000731035,"about_ca_topic_score_gemma":0.025972513,"teacher_disagreement_score":0.85098046,"about_ca_system_score_codex":0.00037276716,"about_ca_system_score_gemma":0.001969437,"threshold_uncertainty_score":0.99991673},"labels":[],"label_agreement":null},{"id":"W2945587103","doi":"10.3138/cjpe.42190","title":"Evaluation Literacy: Perspectives of Internal Evaluators in Non-Government Organizations","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Context (archaeology); Conversation; Narrative; Literacy; Public relations; Psychology; Knowledge management; Sociology; Political science; Pedagogy; Computer science","score_opus":0.11217340830553922,"score_gpt":0.49166201961879946,"score_spread":0.3794886113132602,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945587103","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.988338,0.0005250182,0.00096734683,0.0003672165,0.00072740985,0.0019031598,0.000010092537,0.0000037115324,0.0071580214],"genre_scores_gemma":[0.99765503,0.000011888241,0.001982821,0.000055116216,0.00008194984,0.000056636152,0.000008067348,0.000014285508,0.0001342282],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99063265,0.0010884447,0.0015130106,0.00029044788,0.0062136995,0.00026176544],"domain_scores_gemma":[0.9866698,0.00022772785,0.0012894727,0.0003903839,0.011148372,0.00027428873],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03273753,0.00015611255,0.0003470908,0.00096450356,0.000071383656,0.00020202358,0.0005638409,0.00009066147,0.013834994],"category_scores_gemma":[0.0063263634,0.0001297231,0.00012694576,0.0018757058,0.00007851945,0.001103741,0.00002421308,0.0002389864,0.000113253845],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042638552,0.00019767939,0.35430497,0.000008992573,0.000071447015,0.000002043431,0.024654655,0.014929004,0.00042007217,0.0004715461,0.00045493853,0.604442],"study_design_scores_gemma":[0.0023781375,0.00085058715,0.6150318,0.00015501617,0.00018722026,0.00001861289,0.0155196525,0.356939,0.0004990225,0.006571633,0.0016613477,0.00018801285],"about_ca_topic_score_codex":0.0005865979,"about_ca_topic_score_gemma":0.006461604,"teacher_disagreement_score":0.604254,"about_ca_system_score_codex":0.0016860537,"about_ca_system_score_gemma":0.0074044554,"threshold_uncertainty_score":0.99822265},"labels":[],"label_agreement":null},{"id":"W2945590379","doi":"10.3138/cjpe.53169","title":"Anne Markiewicz and Ian Patrick. (2016). <i>Developing Monitoring and Evaluation Frameworks</i> .","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Sociology; Psychology; Environmental ethics; Philosophy","score_opus":0.2223609311383748,"score_gpt":0.4917329420662098,"score_spread":0.269372010927835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945590379","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9865752,0.005018654,0.00066642644,0.0031961564,0.001669073,0.0014953176,0.000003321999,0.000008852363,0.0013670406],"genre_scores_gemma":[0.9917065,0.00013384712,0.007566867,0.00014069796,0.0002675623,0.00004560436,0.000006529002,0.000012434208,0.0001199735],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9952849,0.00064872246,0.0008971205,0.0003091275,0.002547225,0.0003128797],"domain_scores_gemma":[0.9948875,0.0003241504,0.00070722814,0.00027024758,0.0033565739,0.0004543059],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.023412876,0.0001583682,0.00028341424,0.00071277365,0.00024046651,0.0007321034,0.00025860858,0.00018316432,0.00093629357],"category_scores_gemma":[0.002396365,0.00012858973,0.00006141421,0.00071926607,0.00006983977,0.0010867199,0.000023804236,0.00038124545,0.000051989133],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010285377,0.000008045622,0.16664045,0.0000083885825,0.00001887262,0.0000013332643,0.00092660997,0.0005010816,0.000046006244,0.00012405614,0.00058136345,0.83113354],"study_design_scores_gemma":[0.002341093,0.00063661544,0.81088686,0.0003854809,0.00022092678,0.000104843195,0.004346906,0.11532637,0.00014480254,0.019364638,0.045841347,0.0004001174],"about_ca_topic_score_codex":0.00016726648,"about_ca_topic_score_gemma":0.00079487223,"teacher_disagreement_score":0.8307334,"about_ca_system_score_codex":0.00041690498,"about_ca_system_score_gemma":0.004007644,"threshold_uncertainty_score":0.999977},"labels":[],"label_agreement":null},{"id":"W2946091993","doi":"10.1007/978-3-030-16454-6_10","title":"Differentiated Evaluation Policy for Professionals in Alberta Canada Schools: Local Policy Characteristics and Budget Implications","year":2019,"lang":"en","type":"book-chapter","venue":"Palgrave studies on leadership and learning in teacher education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Environmental planning; Political science; Public administration; Business; Geography","score_opus":0.20683724451744684,"score_gpt":0.47600935253307725,"score_spread":0.2691721080156304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946091993","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36209092,0.008705004,0.0005462002,0.48529467,0.0043382426,0.013768671,0.00018619132,0.000105278734,0.12496482],"genre_scores_gemma":[0.88921994,0.00021953054,0.000035014153,0.0013795622,0.00031670037,0.00029741734,0.00027876018,0.00003157594,0.1082215],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99662155,0.00050823647,0.0009363334,0.0007127217,0.00089482596,0.00032634972],"domain_scores_gemma":[0.9961367,0.0020054237,0.0007066283,0.00033922918,0.00070458447,0.00010738263],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0035972707,0.0003543616,0.0005744877,0.0010001475,0.00026281163,0.00011332465,0.00020171488,0.00025059094,0.000084072184],"category_scores_gemma":[0.007151897,0.00029717587,0.000054279466,0.00025940232,0.000119833014,0.00007768343,0.00006730925,0.0009055634,0.000022066264],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016581846,0.00020692237,0.18545307,0.0004201499,0.00017622577,2.7036805e-7,0.029912423,0.00037199276,0.000008727455,0.15073939,0.0041510873,0.62839395],"study_design_scores_gemma":[0.0013692545,0.0002398666,0.8518744,0.0012885411,0.0001038674,0.0000028901313,0.071118705,0.0063584717,0.0000037536547,0.04801541,0.01888441,0.0007404379],"about_ca_topic_score_codex":0.027277078,"about_ca_topic_score_gemma":0.20077373,"teacher_disagreement_score":0.66642135,"about_ca_system_score_codex":0.001113866,"about_ca_system_score_gemma":0.0067928717,"threshold_uncertainty_score":0.999948},"labels":[],"label_agreement":null},{"id":"W2946489075","doi":"10.3138/cjpe.43050","title":"Principles, Approaches, and Methods for Evaluation in Indigenous Contexts: A Grey Literature Scoping Review","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Toronto; Public Health Ontario","funders":"","keywords":"Grey literature; Indigenous; Interpretation (philosophy); Management science; Engineering ethics; Sociology; Psychology; Computer science; MEDLINE; Political science; Engineering; Ecology","score_opus":0.47385647968230576,"score_gpt":0.5813766564612814,"score_spread":0.10752017677897568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946489075","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41089696,0.509248,0.011964579,0.0071091764,0.0025603173,0.05472733,0.0000317711,0.000022475804,0.0034393815],"genre_scores_gemma":[0.86594206,0.0027798393,0.12681027,0.0014155649,0.00030615166,0.0021820306,0.00017572124,0.00004563891,0.00034271402],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9945547,0.0018850226,0.0013968758,0.0003221797,0.0015410224,0.00030017958],"domain_scores_gemma":[0.99394125,0.00058617507,0.0010157336,0.00031231242,0.0038492791,0.00029523432],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.076048516,0.00015139609,0.00045894596,0.0007774321,0.00012376843,0.0005091424,0.00032607507,0.00011581561,0.00048710444],"category_scores_gemma":[0.008845795,0.00011712507,0.00011231565,0.0009619015,0.000042289885,0.0009457357,0.00001425945,0.00024040678,0.000010938573],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001655477,0.000022462222,0.01280837,0.00036322477,0.000015017811,6.6132185e-7,0.001959103,0.0006451087,0.000007874664,0.00026581992,0.00008643279,0.98380935],"study_design_scores_gemma":[0.01474622,0.0032930507,0.17256986,0.07188507,0.00084114546,0.00033776442,0.0022124392,0.61992586,0.00015067127,0.028791813,0.08408332,0.001162786],"about_ca_topic_score_codex":0.0000841212,"about_ca_topic_score_gemma":0.008692618,"teacher_disagreement_score":0.9826466,"about_ca_system_score_codex":0.0005066055,"about_ca_system_score_gemma":0.007721358,"threshold_uncertainty_score":0.99950314},"labels":[],"label_agreement":null},{"id":"W2946538741","doi":"10.3138/cjpe.56975","title":"David M. Fetterman, Liliana Rodríguez-Campos, Ann P. Zukoski, et al. (2018). <i>Collaborative, Participatory, and Empowerment Evaluation: Stakeholder Involvement Approaches</i> .","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Ontario Tobacco Research Unit; University of Toronto","funders":"","keywords":"Empowerment; Sociology; Citizen journalism; Stakeholder; Participatory evaluation; Humanities; Social science; Management; Computer science; Political science; Philosophy; Economics; World Wide Web","score_opus":0.5392699120588643,"score_gpt":0.4912646171455749,"score_spread":0.04800529491328942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946538741","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9574175,0.0032217093,0.00031267293,0.027545234,0.0019325389,0.0051903464,0.000039251063,0.000019373261,0.004321414],"genre_scores_gemma":[0.99119514,0.00007281698,0.002323682,0.0054337997,0.00013616301,0.00036606358,0.000083405015,0.000027388338,0.00036156052],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9901044,0.0019624152,0.0016024994,0.00060502987,0.0051780557,0.00054759695],"domain_scores_gemma":[0.9930749,0.0002386558,0.0012665966,0.0007015519,0.0038876703,0.00083064387],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.036944594,0.00031495735,0.00047906235,0.00072415336,0.00030060313,0.0009874084,0.00055080355,0.00012100073,0.0043748477],"category_scores_gemma":[0.00097305776,0.00025466757,0.00012931488,0.001027682,0.00016015432,0.0015778227,0.000048175392,0.00038629887,0.00019915603],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008175473,0.00027977565,0.14124162,0.00002684485,0.00019737725,0.0000113777805,0.0081537375,0.0069123763,0.00019219119,0.00051848346,0.13863748,0.703747],"study_design_scores_gemma":[0.004360776,0.0014598891,0.22410859,0.00015145652,0.00031762538,0.000035146884,0.006468556,0.0945344,0.00020427426,0.0029644922,0.66484416,0.0005506665],"about_ca_topic_score_codex":0.00018084633,"about_ca_topic_score_gemma":0.0071782987,"teacher_disagreement_score":0.7031963,"about_ca_system_score_codex":0.0007814866,"about_ca_system_score_gemma":0.007334775,"threshold_uncertainty_score":0.9999906},"labels":[],"label_agreement":null},{"id":"W2946565475","doi":"10.1016/j.evalprogplan.2019.05.001","title":"Mapping the practice of developmental evaluation: Insights from a concept mapping study","year":2019,"lang":"en","type":"article","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Social Sciences and Humanities Research Council of Canada; University of Ottawa","keywords":"Concept map; Space (punctuation); Bounding overwatch; Computer science; Sociology; Engineering ethics; Data science; Management science; Psychology; Engineering; Mathematics education; Artificial intelligence","score_opus":0.3264165257885451,"score_gpt":0.5309375826977315,"score_spread":0.20452105690918643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946565475","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97351915,0.0017398315,0.0004842801,0.00071824127,0.0004708166,0.0036224776,0.0000033302806,0.00003637071,0.019405508],"genre_scores_gemma":[0.99412876,0.000006358479,0.004925704,0.00037814362,0.000079659665,0.00027679314,0.00005042215,0.000008128432,0.00014600577],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99202037,0.0018879584,0.00091510714,0.0004891882,0.0045127054,0.00017469561],"domain_scores_gemma":[0.9949445,0.002296022,0.00069220865,0.00037040334,0.0016330617,0.000063802974],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01458992,0.00016527163,0.00027044452,0.00024036325,0.00032778495,0.00036734657,0.00034767663,0.000061373685,0.002262613],"category_scores_gemma":[0.0027521187,0.00010708169,0.00004939245,0.00092237507,0.00006944101,0.0008095224,0.00012916092,0.00019379766,0.00014976862],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058710597,0.00026493927,0.15000743,0.0000049615724,0.00013975597,0.000001018923,0.13628991,0.0034858761,0.00031342392,0.00015604799,0.00051672047,0.7087612],"study_design_scores_gemma":[0.0024246396,0.00029280587,0.34170058,0.000097857206,0.000082480845,0.000006147636,0.31640947,0.30257374,0.000085021544,0.0016169667,0.034508817,0.00020147412],"about_ca_topic_score_codex":0.00005072918,"about_ca_topic_score_gemma":0.000013475802,"teacher_disagreement_score":0.70855975,"about_ca_system_score_codex":0.000102106926,"about_ca_system_score_gemma":0.00057562825,"threshold_uncertainty_score":0.9986495},"labels":[],"label_agreement":null},{"id":"W2946568746","doi":"10.1177/0144739419846193","title":"Impact of a course in evidence-informed policy-making on the acquisition of methodological knowledge: Findings from before-and-after studies conducted on three consecutive cohorts of master students","year":2019,"lang":"en","type":"article","venue":"Teaching Public Administration","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université Laval","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Empirical evidence; Psychology; Test (biology); Medical education; Task (project management); Public policy; Evidence-based policy; Hindsight bias; Bureaucracy; Empirical research; Evidence-based practice; Public relations; Political science; Social psychology; Medicine; Economics; Management","score_opus":0.4416246202657931,"score_gpt":0.5970242627858634,"score_spread":0.15539964252007032,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946568746","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99671036,0.00004424556,0.0001650868,0.0017552787,0.00010337129,0.00060933357,0.000029407916,0.000008412696,0.0005744736],"genre_scores_gemma":[0.99945796,0.00000872003,0.00026869104,0.00013438013,0.000026827083,0.000031102096,0.000011451079,0.0000053565145,0.000055535336],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99619573,0.0010928548,0.0009849198,0.00030065377,0.0012510819,0.0001747505],"domain_scores_gemma":[0.99126184,0.0071018436,0.00076562364,0.0003784828,0.00044874466,0.00004349297],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008997201,0.00016592904,0.00050456286,0.00037506627,0.00007115702,0.00009417823,0.00034999714,0.00009883492,0.00037662088],"category_scores_gemma":[0.007575506,0.00009169291,0.00010988922,0.00038544805,0.00021687223,0.0005685017,0.000117065734,0.00025931516,0.000012430835],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005811089,0.00026195837,0.9753819,0.000016347274,0.000108602406,5.665279e-7,0.009868139,0.000027380169,0.000433713,0.010003932,0.000070429196,0.003245899],"study_design_scores_gemma":[0.0006192701,0.0018755938,0.98656833,0.00043939758,0.000022921426,0.0000014610672,0.003981742,0.0010662564,0.00036660698,0.004969408,0.000008091124,0.00008092636],"about_ca_topic_score_codex":0.0000545796,"about_ca_topic_score_gemma":0.00050603756,"teacher_disagreement_score":0.011186401,"about_ca_system_score_codex":0.00016736807,"about_ca_system_score_gemma":0.0006845437,"threshold_uncertainty_score":0.9069136},"labels":[],"label_agreement":null},{"id":"W2946660538","doi":"10.3917/ems.cheva.2018.01.0451","title":"Les méthodes de recherche du DBA","year":2018,"lang":"fr","type":"book-chapter","venue":"EMS Editions eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Humanities; Philosophy; Political science","score_opus":0.7772148982647953,"score_gpt":0.5804881829503692,"score_spread":0.1967267153144261,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946660538","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017250393,0.00016745925,0.04193875,0.0027651675,0.0047146734,0.00046702012,0.00028416156,0.0001171331,0.9478206],"genre_scores_gemma":[0.014923151,0.00031086296,0.056289677,0.0016278966,0.008157895,0.00013744738,0.00011258103,0.00008001413,0.9183605],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9943849,0.0013162879,0.0011680335,0.0008144097,0.0017546327,0.0005617344],"domain_scores_gemma":[0.99192095,0.0047413562,0.000586666,0.0010534369,0.0013397399,0.0003578816],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.014315015,0.0005287983,0.00054030295,0.00052888016,0.0012466137,0.00048289323,0.0009917462,0.00126623,0.11273299],"category_scores_gemma":[0.0020499448,0.00047115557,0.00041558698,0.00010059158,0.0013464477,0.00029208834,0.00022600289,0.0013550308,0.010954829],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002037322,0.000055607186,0.00022522587,0.0000234531,0.00008581813,0.000015774063,0.002181467,0.000026469046,0.00012948185,0.6755781,0.076682836,0.24497536],"study_design_scores_gemma":[0.00024996384,0.00016605035,0.00040573056,0.00024896246,0.00008512288,0.00005249483,0.00046824178,0.001105726,0.00024159606,0.35073477,0.6458622,0.00037913452],"about_ca_topic_score_codex":0.00018468389,"about_ca_topic_score_gemma":0.0006364184,"teacher_disagreement_score":0.56917936,"about_ca_system_score_codex":0.00082169846,"about_ca_system_score_gemma":0.0017772542,"threshold_uncertainty_score":0.99977404},"labels":[],"label_agreement":null},{"id":"W2946752631","doi":"10.3138/cjpe.43118","title":"Perceived Facilitators and Barriers to Evaluative Thinking in a Small Development NGO","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Work (physics); Sustainability; Process (computing); Psychology; Quality (philosophy); Political science; Public relations; Business; Computer science; Epistemology","score_opus":0.2243927961696357,"score_gpt":0.47516494741048165,"score_spread":0.25077215124084595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946752631","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99456257,0.0001415243,0.00019002036,0.0019013648,0.00050804036,0.0016951979,0.0000023196217,0.000004559406,0.0009944065],"genre_scores_gemma":[0.98975265,0.0000028381742,0.0095756,0.00039078484,0.000030459198,0.000076387965,0.0000027276567,0.000007577778,0.00016096952],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9960177,0.0006608391,0.00092835765,0.00028338615,0.001798287,0.00031141398],"domain_scores_gemma":[0.99634886,0.00026339563,0.00036004285,0.00020368153,0.0019069611,0.00091703306],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.021451585,0.00013765013,0.0002734676,0.001143197,0.00019334063,0.0003481035,0.00038041174,0.000071128314,0.0027582573],"category_scores_gemma":[0.0052909874,0.00010994935,0.000056327626,0.00079870323,0.00004676431,0.00044840085,0.00002366146,0.00020948969,0.00015992235],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020681402,0.000011571871,0.34001687,0.000004828294,0.00002013628,0.0000031728155,0.042144794,0.0036845508,0.00005971524,0.00013869638,0.00020283014,0.61369216],"study_design_scores_gemma":[0.0015280568,0.0007237788,0.92706126,0.0001516088,0.000027374928,0.000011803174,0.01818771,0.021630462,0.00006725837,0.0057293116,0.024638088,0.00024327585],"about_ca_topic_score_codex":0.00041600727,"about_ca_topic_score_gemma":0.043125454,"teacher_disagreement_score":0.61344886,"about_ca_system_score_codex":0.00077939616,"about_ca_system_score_gemma":0.009304243,"threshold_uncertainty_score":0.9981533},"labels":[],"label_agreement":null},{"id":"W2946872779","doi":"10.1111/capa.12321","title":"L'élaboration et la mise en œuvre des recommandations issues d'évaluations de programmes au gouvernement du Canada","year":2019,"lang":"fr","type":"article","venue":"Canadian Public Administration","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Humanities; Philosophy","score_opus":0.07521125889336751,"score_gpt":0.41877451342942185,"score_spread":0.34356325453605435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946872779","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4611745,0.00039863292,0.0023552945,0.47306365,0.0027088874,0.0015902881,0.00064170803,0.00005456467,0.05801247],"genre_scores_gemma":[0.94755244,0.0002919505,0.0032919564,0.0018918642,0.00032644387,0.00017559963,0.0011622324,0.000024949615,0.04528257],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9951015,0.0014629462,0.00088418444,0.00053971505,0.0012717419,0.00073992665],"domain_scores_gemma":[0.9960369,0.0007447303,0.00036191105,0.0005817055,0.0012849917,0.0009897739],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005625493,0.00028963867,0.0002626911,0.0004088172,0.0008379269,0.0015877638,0.00052650325,0.00025241618,0.01100615],"category_scores_gemma":[0.0019502128,0.00030924208,0.000082553335,0.0009718535,0.00017716197,0.002041546,0.00003807877,0.000246525,0.00042615458],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000020762425,0.00027928688,0.24867332,0.00008564837,0.000108872744,0.000023616203,0.0068083857,0.00050083065,0.00003666065,0.27322698,0.1438278,0.32640782],"study_design_scores_gemma":[0.00038210544,0.0002030319,0.048681114,0.000056767076,0.000042166463,0.0000348667,0.0062544825,0.023327138,0.00006593708,0.0021919208,0.91843694,0.0003235135],"about_ca_topic_score_codex":0.6812516,"about_ca_topic_score_gemma":0.99931854,"teacher_disagreement_score":0.77460915,"about_ca_system_score_codex":0.005379573,"about_ca_system_score_gemma":0.12775436,"threshold_uncertainty_score":0.999936},"labels":[],"label_agreement":null},{"id":"W2947353856","doi":"10.22215/timreview/1239","title":"How to Develop an Impactful Action Research Program: Insights and Lessons from a Case Study","year":2019,"lang":"en","type":"article","venue":"Technology Innovation Management Review","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Action (physics); Epistemology; Work (physics); Engineering ethics; Sociology; Management science; Public relations; Political science; Economics; Philosophy","score_opus":0.5328687065185753,"score_gpt":0.6244230607151147,"score_spread":0.09155435419653934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2947353856","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9618522,0.0010823195,0.00085525296,0.029875088,0.0001316778,0.0049276007,0.0000020379964,0.00019019717,0.0010836486],"genre_scores_gemma":[0.989804,0.001678464,0.005226364,0.00097314833,0.000021527041,0.0007643178,0.000021984653,0.0000111752815,0.0014989796],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965514,0.0003984466,0.00071305124,0.0007306341,0.001340183,0.0002663004],"domain_scores_gemma":[0.9963587,0.00012956001,0.0002786499,0.0011221501,0.0020573928,0.000053542153],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007481319,0.00016249139,0.00034476502,0.0023706725,0.0002584817,0.00039515377,0.0005424269,0.00009365353,0.00029398227],"category_scores_gemma":[0.0008344832,0.00011917793,0.000015012991,0.017411603,0.00006552839,0.00077741727,0.00044982036,0.0003078454,0.00043253458],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000060355073,0.00020969305,0.011785873,0.00008944341,0.000036717796,0.00005490231,0.00027310828,0.0000011841211,0.00009468489,0.023906639,0.0028108966,0.96073085],"study_design_scores_gemma":[0.0011992189,0.0017211395,0.04339682,0.00070019823,0.00008106859,0.000100342535,0.05378065,0.00056833297,0.00015725652,0.02234304,0.87546176,0.00049014593],"about_ca_topic_score_codex":0.000044116572,"about_ca_topic_score_gemma":0.0003365926,"teacher_disagreement_score":0.96024066,"about_ca_system_score_codex":0.00010548456,"about_ca_system_score_gemma":0.000085739935,"threshold_uncertainty_score":0.8365697},"labels":[],"label_agreement":null},{"id":"W2947696336","doi":"10.32799/ijih.v14i1.32726","title":"Moving and Enhancing System Change","year":2019,"lang":"en","type":"article","venue":"International Journal of Indigenous Health","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Indigenous; Oppression; Colonialism; Relocation; Racism; Criminology; Mental health; Welfare; Poverty; Health care; Economic growth; Gender studies; Sociology; Political science; Ethnology; Socioeconomics; Medicine; Law; Psychiatry; Ecology","score_opus":0.1428598683004525,"score_gpt":0.4893789235701313,"score_spread":0.3465190552696788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2947696336","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9902332,0.00068318145,0.0020195502,0.002760112,0.0026179757,0.00018460922,0.000005506598,0.000007696012,0.0014881754],"genre_scores_gemma":[0.99686,0.00019053232,0.0009048029,0.0013561306,0.00045414024,0.0000015577452,0.0000010008363,0.0000055118276,0.00022629065],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99674153,0.00014304374,0.0009055035,0.00012640325,0.0019206121,0.00016290581],"domain_scores_gemma":[0.9975193,0.00027890332,0.0010123089,0.00012146568,0.0009408902,0.00012714259],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0060184277,0.00007098045,0.00023419419,0.00043678973,0.00010179902,0.00017568163,0.000467504,0.000030084539,0.00023202703],"category_scores_gemma":[0.00012982187,0.000050360053,0.00005891242,0.00013505283,0.000012827087,0.00054893724,0.000051423962,0.00015165136,0.0001487661],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012279059,0.00010771884,0.39688033,0.000066829874,0.00011857493,0.00004458806,0.05152376,0.00021698757,0.0005422734,0.0039651473,0.0004100275,0.54600096],"study_design_scores_gemma":[0.003376407,0.0021025264,0.8870999,0.0014306301,0.000016396822,0.0026407465,0.043371994,0.009928361,0.0010006065,0.0020445068,0.04654057,0.00044730402],"about_ca_topic_score_codex":0.00021207558,"about_ca_topic_score_gemma":0.00016129066,"teacher_disagreement_score":0.5455537,"about_ca_system_score_codex":0.00037078682,"about_ca_system_score_gemma":0.0007506677,"threshold_uncertainty_score":0.25405332},"labels":[],"label_agreement":null},{"id":"W2948770661","doi":"10.1002/ev.20365","title":"Sustainability‐Ready Evaluation: A Call to Action","year":2019,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Evaluation Society","funders":"","keywords":"Sustainability; Transformative learning; Sustainability science; Sustainability organizations; Relevance (law); Process management; Sustainable development; Social sustainability; Environmental resource management; Checklist; Natural resource; Action (physics); Business; Engineering ethics; Management science; Environmental planning; Computer science; Risk analysis (engineering); Political science; Sociology; Engineering; Psychology; Economics; Ecology","score_opus":0.30589920481363936,"score_gpt":0.5825784932667877,"score_spread":0.2766792884531483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2948770661","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83559984,0.00019866828,0.04872486,0.027987193,0.007995368,0.016761953,0.000041432497,0.00028262852,0.06240806],"genre_scores_gemma":[0.9581212,0.0000068356494,0.0020481322,0.00057507347,0.00049277797,0.0015924507,0.00014739559,0.000024503172,0.036991633],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.992732,0.00071975694,0.0008573946,0.0008293165,0.004516198,0.000345329],"domain_scores_gemma":[0.98970264,0.0010164471,0.00031406948,0.00095054065,0.0077840574,0.00023221648],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.021227662,0.00020381423,0.00028512196,0.0007400702,0.00038946548,0.00035308406,0.00035382668,0.0001286374,0.009956214],"category_scores_gemma":[0.009593405,0.00017861587,0.00017561366,0.0017560208,0.000022362945,0.0010064319,0.000053098385,0.00013104638,0.002598305],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013637483,0.00011490639,0.0045897816,0.000010249631,0.000028245351,3.1901962e-8,0.001018908,0.048995893,0.00068390474,0.0018771377,0.0689676,0.87357694],"study_design_scores_gemma":[0.002839396,0.00045823984,0.063536875,0.000014235476,0.00017161571,0.0000039128554,0.0019603206,0.36249912,0.00089678785,0.043063417,0.52425504,0.00030105785],"about_ca_topic_score_codex":0.00020871444,"about_ca_topic_score_gemma":0.001072809,"teacher_disagreement_score":0.87327594,"about_ca_system_score_codex":0.001652014,"about_ca_system_score_gemma":0.002891407,"threshold_uncertainty_score":0.9987492},"labels":[],"label_agreement":null},{"id":"W2948902521","doi":"10.1057/s41307-019-00146-0","title":"Correction to: Much Ado About Nothing? An Analysis of Prioritization at Six Canadian Universities","year":2019,"lang":"en","type":"article","venue":"Higher Education Policy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Regina; Wilfrid Laurier University; Toronto Metropolitan University","funders":"","keywords":"Higher education policy; Nothing; Prioritization; Political science; Higher education; Education policy; Medical education; Public administration; Library science; Medicine; Computer science; Economics; Law; Management science; Philosophy; Epistemology","score_opus":0.054317468792912285,"score_gpt":0.46288373612557565,"score_spread":0.4085662673326634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2948902521","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93442076,0.000018449737,0.00007081645,0.004480823,0.0027136947,0.00019472919,0.000025642545,0.000019022595,0.05805606],"genre_scores_gemma":[0.844144,0.0000043916507,0.00013671015,0.0022513773,0.0001618734,0.000006414301,0.000099786084,0.0000062713502,0.15318918],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99829453,0.00013287217,0.00036664653,0.00029252525,0.000734272,0.00017915627],"domain_scores_gemma":[0.9980832,0.00015983358,0.00021425514,0.00049711554,0.00078750355,0.00025809562],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006651491,0.00009548338,0.00019337467,0.0024732032,0.00015961842,0.00011419315,0.00029070745,0.0000589774,0.013118652],"category_scores_gemma":[0.00010280747,0.00009095895,0.00007846725,0.0033962864,0.000024932351,0.0005700859,0.000029281025,0.000057087887,0.00086817506],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030544525,0.00014326941,0.85438687,0.000008855247,0.00010124774,1.1459067e-7,0.020044478,0.016093535,0.000629674,0.05121563,0.045575093,0.011770678],"study_design_scores_gemma":[0.00008278838,0.00004333696,0.80993116,0.000009298202,0.000051268114,3.384014e-7,0.003036516,0.0047348025,0.00013312546,0.00013705679,0.18174487,0.000095449985],"about_ca_topic_score_codex":0.13008302,"about_ca_topic_score_gemma":0.08796922,"teacher_disagreement_score":0.13616978,"about_ca_system_score_codex":0.001144382,"about_ca_system_score_gemma":0.0033429703,"threshold_uncertainty_score":0.99990976},"labels":[],"label_agreement":null},{"id":"W2949179306","doi":"10.7202/1060004ar","title":"L’utilisation d’outils standardisés en intervention sociale : les points de vue des intervenants, des gestionnaires et des familles sur le Protocole d’évaluation familiale en protection de la jeunesse","year":2019,"lang":"fr","type":"article","venue":"Revue de psychoéducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université du Québec à Trois-Rivières; Université du Québec en Outaouais; Centre Jeunesse de Quebec","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.1456143609182405,"score_gpt":0.4635894300699927,"score_spread":0.3179750691517522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949179306","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8404674,0.00083048904,0.1459338,0.005743349,0.00084453844,0.004575345,0.000044399338,0.00010191195,0.0014587396],"genre_scores_gemma":[0.97945654,0.0012126269,0.010586425,0.00009094787,0.0004080076,0.0027727576,0.00007899356,0.00006053761,0.005333161],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.988771,0.0077418154,0.001222107,0.00074300414,0.00090245396,0.00061960105],"domain_scores_gemma":[0.99602574,0.0010394395,0.0007887711,0.0005355143,0.0014226995,0.00018781351],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.024326727,0.00038695507,0.00041777568,0.0005033814,0.000699042,0.0007408285,0.00044458883,0.0005274605,0.0010160125],"category_scores_gemma":[0.0050210566,0.00040938915,0.0003372638,0.00089046446,0.00047599408,0.0023829413,0.000085084364,0.0005197309,0.00024235944],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003124736,0.0008978407,0.16632907,0.0010698736,0.00006491209,9.3288133e-7,0.09931463,0.0031095466,0.0056080474,0.0027538256,0.00071094383,0.7198279],"study_design_scores_gemma":[0.0018375793,0.00042802663,0.8118645,0.0030883222,0.000083787185,0.00006044684,0.030499866,0.03966711,0.0028768645,0.09848587,0.010698419,0.0004092342],"about_ca_topic_score_codex":0.0061487663,"about_ca_topic_score_gemma":0.008054455,"teacher_disagreement_score":0.7194187,"about_ca_system_score_codex":0.0031060895,"about_ca_system_score_gemma":0.002284587,"threshold_uncertainty_score":0.9998972},"labels":[],"label_agreement":null},{"id":"W2950302099","doi":"","title":"Employee Engagement That Works: Continuous Improvement in New Brunswick","year":2015,"lang":"en","type":"article","venue":"Journal of government financial management","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Employee engagement; Business; Public relations; Political science","score_opus":0.13013357389110622,"score_gpt":0.38766774649708796,"score_spread":0.25753417260598177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950302099","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.916898,0.000697507,0.033346817,0.005635448,0.0042361584,0.0012074861,0.0000049325054,0.000021029378,0.03795263],"genre_scores_gemma":[0.97884977,0.00039279184,0.0051552765,0.0018148847,0.00044587842,0.000010035991,8.899855e-7,0.000018675477,0.01331179],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99014986,0.00022177333,0.0017442879,0.0003689292,0.0070744855,0.00044068415],"domain_scores_gemma":[0.99736863,0.00017083007,0.0013361897,0.00052132184,0.00024443452,0.00035861434],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011147325,0.00026408062,0.00056424015,0.0003196932,0.00007945095,0.00036688114,0.001034097,0.00007472695,0.0005543825],"category_scores_gemma":[0.0007188837,0.00020015947,0.0002190001,0.0006631045,0.000036014575,0.0008900765,0.00042198953,0.0003649846,0.00016298359],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005490494,0.0004024872,0.24767326,0.000014862519,0.00006788507,0.00018797633,0.0013602199,0.002151061,0.000034615197,0.0077930307,0.13407026,0.6056953],"study_design_scores_gemma":[0.006339783,0.0013494713,0.46257052,0.00023516976,0.00006844548,0.000009730558,0.007264857,0.00026365588,0.00033825747,0.0095232595,0.5116911,0.00034575936],"about_ca_topic_score_codex":0.000103234524,"about_ca_topic_score_gemma":0.0006856491,"teacher_disagreement_score":0.60534954,"about_ca_system_score_codex":0.0013159715,"about_ca_system_score_gemma":0.001008461,"threshold_uncertainty_score":0.8162266},"labels":[],"label_agreement":null},{"id":"W2950364436","doi":"10.54656/daks8546","title":"Navigating International, Interdisciplinary, and Indigenous Collaborative Inquiry","year":2011,"lang":"en","type":"article","venue":"Journal of Community Engagement and Scholarship","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Participatory action research; Indigenous; Transformative learning; Negotiation; Sociology; Circumpolar star; Citizen journalism; Action research; Face (sociological concept); Traditional knowledge; Community-based participatory research; Public relations; Engineering ethics; Political science; Pedagogy; Social science; Engineering; Anthropology; Ecology","score_opus":0.5396540634778364,"score_gpt":0.5398450749856408,"score_spread":0.00019101150780442833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950364436","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9945109,0.00028813982,0.00032188126,0.0008101615,0.00047201477,0.000094408984,0.0000020810166,0.0000055101455,0.0034948885],"genre_scores_gemma":[0.99715966,0.00021967893,0.002170107,0.00032928004,0.00007648109,0.0000021181932,0.0000015819268,0.0000050479534,0.00003605574],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99615395,0.0021153353,0.00068488973,0.000072975,0.0008606251,0.000112237845],"domain_scores_gemma":[0.99722993,0.0009423339,0.00062479626,0.00023406315,0.0008567908,0.00011206254],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022086173,0.000100979225,0.00020847045,0.00016234671,0.00083431456,0.00035717172,0.00065661815,0.000046713685,0.0003055151],"category_scores_gemma":[0.0013840516,0.00007286874,0.000044099277,0.000259037,0.00012954102,0.0014064608,0.00054216204,0.0016182952,0.000008593565],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014247387,0.00020245842,0.26237905,0.0000080094915,0.00009248681,0.00000966393,0.55450934,0.000008226863,0.0002822475,0.0005339106,0.00040015668,0.18143193],"study_design_scores_gemma":[0.00088461506,0.0006846267,0.7014509,0.00012323336,0.000027308415,0.000050468952,0.26647958,0.000059418937,0.0005261549,0.027370382,0.0022155938,0.00012773807],"about_ca_topic_score_codex":0.0000039330343,"about_ca_topic_score_gemma":0.00002083838,"teacher_disagreement_score":0.4390718,"about_ca_system_score_codex":0.00004199707,"about_ca_system_score_gemma":0.00008339839,"threshold_uncertainty_score":0.76546705},"labels":[],"label_agreement":null},{"id":"W2950418435","doi":"10.1007/s11013-019-09637-6","title":"Finding “What Works”: Theory of Change, Contingent Universals, and Virtuous Failure in Global Mental Health","year":2019,"lang":"en","type":"article","venue":"Culture Medicine and Psychiatry","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":38,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; McGill University; Douglas Mental Health University Institute","funders":"","keywords":"Scholarship; Global mental health; Epistemology; Theory of change; Reflexivity; Sociology; Mental health; Empirical evidence; Psychological intervention; Paradigm shift; Psychology; Political science; Social science","score_opus":0.12582835468657397,"score_gpt":0.44727591882042694,"score_spread":0.321447564133853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950418435","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91517895,0.036215447,0.000078630466,0.043787632,0.0018394176,0.00048085672,0.000008909294,0.000010658421,0.0023994665],"genre_scores_gemma":[0.9902543,0.0045954767,0.00038098957,0.004118285,0.00018699245,0.000003360772,0.000014324994,0.0000038217413,0.000442485],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9984778,0.00016932828,0.0003820943,0.00026667473,0.00054702646,0.0001570369],"domain_scores_gemma":[0.99934995,0.0000814996,0.00023671423,0.00017328507,0.000056247525,0.00010228787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021644754,0.000116131974,0.0003138097,0.00010758889,0.00007444913,0.00005754453,0.0001379108,0.00006960125,0.00042043335],"category_scores_gemma":[0.0000485193,0.00007039178,0.00002747617,0.00041740373,0.00009256568,0.0005143773,0.00004644166,0.0001281795,0.000009952957],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013277787,0.000068679336,0.681072,0.00007554733,0.000026563443,7.8806977e-7,0.03571663,0.000003109956,0.000030123432,0.023968613,0.021797914,0.23710728],"study_design_scores_gemma":[0.0059902333,0.0012052461,0.22528091,0.003840508,0.000028093686,0.00003573433,0.6599535,0.00047026135,0.0000055273986,0.016313404,0.08657466,0.00030193367],"about_ca_topic_score_codex":0.000031285534,"about_ca_topic_score_gemma":0.0004753598,"teacher_disagreement_score":0.6242369,"about_ca_system_score_codex":0.000030447376,"about_ca_system_score_gemma":0.00008203228,"threshold_uncertainty_score":0.46034506},"labels":[],"label_agreement":null},{"id":"W2950855139","doi":"10.7202/1060047ar","title":"Non-publics et MTE : étudier les raisons de ne pas visiter des organismes culturels selon une démarche enracinée","year":2019,"lang":"fr","type":"article","venue":"Approches inductives Travail intellectuel et construction des connaissances","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Humanities; Philosophy; Political science","score_opus":0.12802087030402168,"score_gpt":0.40411989100294793,"score_spread":0.2760990206989262,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950855139","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8885621,0.010325663,0.060310517,0.0117839305,0.0027024255,0.0012757299,0.00011010745,0.00021307313,0.024716461],"genre_scores_gemma":[0.9627689,0.005929993,0.018427271,0.0016160106,0.00038644925,0.00014583067,0.00006069477,0.00010035501,0.0105644595],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99168986,0.0018665796,0.0016625,0.0017440853,0.0017477965,0.0012891612],"domain_scores_gemma":[0.9927603,0.0024326125,0.0009831219,0.00095080386,0.0023925072,0.00048066987],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["sts"],"category_scores_codex":[0.005687129,0.001041971,0.0011885003,0.0007636262,0.0014418109,0.0015726906,0.0012442529,0.0007793234,0.0077652037],"category_scores_gemma":[0.0024625582,0.0008899715,0.00045493132,0.0033395141,0.015925383,0.0043695793,0.0003729576,0.0017777578,0.0006571375],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000503653,0.00061810226,0.06290911,0.00049295306,0.0009857242,0.0000126609075,0.17017777,0.0009991712,0.019757548,0.05943065,0.0088032605,0.6753094],"study_design_scores_gemma":[0.0031055233,0.0015536653,0.089111365,0.0014968594,0.00039701935,0.0012597566,0.39339894,0.00695753,0.05560181,0.06186979,0.38273045,0.0025172988],"about_ca_topic_score_codex":0.00039626096,"about_ca_topic_score_gemma":0.0009966788,"teacher_disagreement_score":0.6727921,"about_ca_system_score_codex":0.00057111745,"about_ca_system_score_gemma":0.0016095191,"threshold_uncertainty_score":0.9998582},"labels":[],"label_agreement":null},{"id":"W2956533597","doi":"10.1017/9789048513086.016","title":"Is Evidence-based Policy Making Really Possible? Reflections for Policymakers and Academics on Making use of Research in the Work of Policy","year":2012,"lang":"en","type":"other","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Work (physics); Policy making; Political science; Evidence-based policy; Public administration; Policy analysis; Public relations; Public economics; Economics; Engineering; Medicine","score_opus":0.8169556110143538,"score_gpt":0.679569774821513,"score_spread":0.13738583619284073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2956533597","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003830057,0.0013151354,0.0026038128,0.08022804,0.00034115757,0.0039468626,0.000243046,0.00007473508,0.9074172],"genre_scores_gemma":[0.6707067,0.002420063,0.020470904,0.015052435,0.002249887,0.0003200929,0.000011585967,0.0002968975,0.28847146],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9945558,0.0008938171,0.0009510398,0.00046629884,0.0025912586,0.0005418177],"domain_scores_gemma":[0.98919845,0.008538632,0.00076521933,0.0009541768,0.00046977663,0.00007374354],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011738078,0.00023142416,0.0004534547,0.0053470605,0.00016717333,0.00019320083,0.0008886782,0.00042449412,0.0006920182],"category_scores_gemma":[0.0058813686,0.00014359993,0.00014486871,0.00528129,0.00035603502,0.00030174095,0.00013460993,0.0005929056,0.000022117225],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007417304,0.00029634952,0.049088124,0.0004377916,0.00009902682,0.0000010277062,0.008482283,0.00054287055,0.00011004096,0.22160241,0.59377766,0.12482072],"study_design_scores_gemma":[0.0011623743,0.0006984948,0.04099095,0.008461654,0.000056203666,0.0000073838905,0.004015387,0.0016113401,0.00021161993,0.020985814,0.9212276,0.00057118415],"about_ca_topic_score_codex":0.0023258938,"about_ca_topic_score_gemma":0.0011015678,"teacher_disagreement_score":0.6668766,"about_ca_system_score_codex":0.00022770467,"about_ca_system_score_gemma":0.0018838387,"threshold_uncertainty_score":0.75771135},"labels":[],"label_agreement":null},{"id":"W2959432429","doi":"10.1016/j.evalprogplan.2019.101680","title":"Engaging children and youth in research and evaluation using group concept mapping","year":2019,"lang":"en","type":"article","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":25,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Concept map; Group (periodic table); Psychology; Qualitative research; Qualitative property; Applied psychology; Computer science; Mathematics education; Sociology","score_opus":0.6061936208842512,"score_gpt":0.6163892333094394,"score_spread":0.010195612425188183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2959432429","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.993451,0.0025314095,0.0001938742,0.0002100963,0.00013487609,0.0019622,0.0000045512156,0.00002592163,0.001486097],"genre_scores_gemma":[0.9975138,0.000035069737,0.002140085,0.00007203548,0.000061528444,0.000051807107,0.000080532554,0.0000094439665,0.000035751407],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9941574,0.0015736036,0.0005364745,0.0006030363,0.0028150198,0.0003144777],"domain_scores_gemma":[0.998198,0.000649671,0.0001813818,0.0002248045,0.0006458334,0.00010032913],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04229927,0.00013778424,0.00022061677,0.00066402776,0.00036243748,0.00065184874,0.00012665465,0.00008919364,0.0003014687],"category_scores_gemma":[0.0009319472,0.00011754172,0.000017496692,0.0008106504,0.00012533387,0.0007153652,0.00012923888,0.0003360497,0.000012795751],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017652521,0.000025884925,0.54003894,0.0000053543463,0.000007587253,1.7745046e-7,0.01404304,0.0014459237,0.00012982704,0.00020149977,0.000015443617,0.44406867],"study_design_scores_gemma":[0.0012975907,0.00013050433,0.5130426,0.00012198313,0.000015758416,0.000005162915,0.014644928,0.46838382,0.000014095062,0.002140604,0.00009049711,0.000112414324],"about_ca_topic_score_codex":0.00009136713,"about_ca_topic_score_gemma":0.000023722627,"teacher_disagreement_score":0.4669379,"about_ca_system_score_codex":0.00009213559,"about_ca_system_score_gemma":0.00016760059,"threshold_uncertainty_score":0.98615444},"labels":[],"label_agreement":null},{"id":"W2961231708","doi":"10.4000/ries.7490","title":"Collaborative professionalism and Leading from the Middle in an era of complex policy change","year":2019,"lang":"en","type":"article","venue":"Revue internationale d éducation de Sèvres","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.5210321666774004,"score_gpt":0.5420649186312531,"score_spread":0.02103275195385268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2961231708","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97881186,0.00020209591,0.000048851114,0.017413318,0.00029084954,0.00034124072,0.00006251635,0.0000058942883,0.002823379],"genre_scores_gemma":[0.9956818,0.00006874111,0.0005657995,0.0011158844,0.00020590008,0.00006492103,0.000066632834,0.0000053672375,0.0022249436],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984611,0.00030749597,0.0003984142,0.00021816672,0.00052136113,0.00009342491],"domain_scores_gemma":[0.9977036,0.0012504271,0.0002918835,0.00024940382,0.00047266594,0.000032013984],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013697572,0.0000724467,0.00014160568,0.00018261757,0.00005541715,0.000091695365,0.0003667784,0.00003794566,0.0012943617],"category_scores_gemma":[0.0007074173,0.00005166696,0.000024290093,0.0004704419,0.000049695675,0.0005332506,0.00005703242,0.00011248207,0.000081424645],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004491909,0.00015460135,0.82369906,0.0000130006965,0.000017470571,3.3010375e-7,0.0682365,0.00031620238,0.0026125116,0.06519311,0.0009797502,0.03873253],"study_design_scores_gemma":[0.00029365392,0.000031590258,0.94874674,0.00013401148,0.0000023440848,0.0000015500232,0.008608363,0.014667601,0.00023076373,0.017409112,0.009806046,0.000068220616],"about_ca_topic_score_codex":0.00068482687,"about_ca_topic_score_gemma":0.0019405477,"teacher_disagreement_score":0.12504767,"about_ca_system_score_codex":0.0001320797,"about_ca_system_score_gemma":0.00034802817,"threshold_uncertainty_score":0.9996186},"labels":[],"label_agreement":null},{"id":"W2963149541","doi":"","title":"Transferts de connaissances informels des titulaires de Chaires de recherche du Canada en éducation: les facteurs géographiques, linguistiques et systémiques qui influencent le rayonnement de la recherche","year":2014,"lang":"fr","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Humanities; Art","score_opus":0.5189630633902506,"score_gpt":0.5475320728073907,"score_spread":0.028569009417140134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963149541","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77738804,0.007579564,0.10704718,0.041401453,0.0006478412,0.0007230969,0.000028757118,0.00023557078,0.064948514],"genre_scores_gemma":[0.9157448,0.019408539,0.055594046,0.005922407,0.00036581414,0.00019410439,0.000016841988,0.00003818708,0.0027152698],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.97794044,0.017983329,0.0012483891,0.0006147405,0.0011658508,0.0010472343],"domain_scores_gemma":[0.9826161,0.014812156,0.00035022243,0.00056979124,0.0010469413,0.00060473476],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06256196,0.00050556357,0.00055298285,0.0002818285,0.0006324411,0.0007828993,0.00105473,0.0009333866,0.0009843402],"category_scores_gemma":[0.020522323,0.00043881685,0.00020362894,0.000680474,0.0010023259,0.0007988349,0.00009256312,0.0012300728,0.000013093431],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00011440285,0.00046612564,0.2864164,0.00055269233,0.00020118858,0.000020882984,0.109691024,0.0039737173,0.00066660956,0.21084194,0.020152854,0.36690217],"study_design_scores_gemma":[0.0013018746,0.00052950316,0.18210562,0.0014958965,0.00013426044,0.00013959312,0.041598536,0.014382326,0.03302991,0.16751407,0.5566152,0.0011532138],"about_ca_topic_score_codex":0.6950998,"about_ca_topic_score_gemma":0.8209428,"teacher_disagreement_score":0.53646237,"about_ca_system_score_codex":0.006144615,"about_ca_system_score_gemma":0.028386226,"threshold_uncertainty_score":0.9999289},"labels":[],"label_agreement":null},{"id":"W2967863356","doi":"10.4102/aej.v7i1.400","title":"Evaluation2 – Evaluating the national evaluation system in South Africa: What has been achieved in the first 5 years?","year":2019,"lang":"en","type":"article","venue":"African Evaluation Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Department for International Development","keywords":"Mandate; Cabinet (room); Benchmarking; Government (linguistics); Monitoring and evaluation; Legislation; Business; Political science; Economic growth; Public administration; Geography; Economics; Marketing","score_opus":0.39139637284341017,"score_gpt":0.48634111677156405,"score_spread":0.09494474392815389,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2967863356","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9627309,0.00095637655,0.00029279763,0.017424397,0.0017639669,0.0039924746,0.000009824623,0.00002718438,0.012802112],"genre_scores_gemma":[0.9974146,0.000017539216,0.00027676122,0.000901949,0.00056544907,0.000559713,0.00002518781,0.000026072652,0.00021273948],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.96365017,0.009360575,0.0025539307,0.00082530314,0.022942634,0.0006673922],"domain_scores_gemma":[0.9887059,0.003931684,0.0017127971,0.0008553282,0.004675426,0.00011887679],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.20797452,0.00034386464,0.0004804532,0.0011739098,0.0008539211,0.0031009165,0.0019143499,0.00015896295,0.003924074],"category_scores_gemma":[0.009228479,0.00020734333,0.0002463419,0.0035938525,0.00015840464,0.0027962308,0.00013906043,0.00095113384,0.0013451383],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036280818,0.00030339067,0.06292093,0.000021173453,0.00010672469,0.000004903452,0.19444755,0.5095,0.00021284881,0.0025499528,0.0039911056,0.22557856],"study_design_scores_gemma":[0.0029359742,0.00023186591,0.3027067,0.00013967803,0.000087172484,0.000041857682,0.07172666,0.6111258,0.0000043249997,0.0072104484,0.0035709732,0.0002185556],"about_ca_topic_score_codex":0.000016998047,"about_ca_topic_score_gemma":0.00024476543,"teacher_disagreement_score":0.23978575,"about_ca_system_score_codex":0.00200534,"about_ca_system_score_gemma":0.0036963848,"threshold_uncertainty_score":0.99943244},"labels":[],"label_agreement":null},{"id":"W2967915433","doi":"10.33524/cjar.v16i3.225","title":"REFLECTING ON EVIDENCE: LEADERS USE ACTION RESEARCH TO IMPROVE THEIR TEACHER PERFORMANCE REVIEWS","year":2015,"lang":"en","type":"article","venue":"The Canadian Journal of Action Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Royal Roads University","funders":"","keywords":"Action research; Tracking (education); Data collection; Action (physics); Psychology; Interpretation (philosophy); Focus group; Medical education; Public relations; Pedagogy; Political science; Computer science; Sociology; Business; Medicine; Marketing","score_opus":0.9756114478842192,"score_gpt":0.7395469278414039,"score_spread":0.2360645200428153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2967915433","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9494251,0.0003783281,0.0000855108,0.040611085,0.0013132977,0.00073288,0.0000019025629,0.0000061756655,0.007445724],"genre_scores_gemma":[0.98130363,0.00057811453,0.00013862425,0.0005228297,0.0008372732,0.000028709766,4.4022752e-7,0.00001574284,0.01657461],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9879909,0.0050276835,0.0008748771,0.00032208525,0.005018462,0.0007659973],"domain_scores_gemma":[0.9887258,0.0029108871,0.00033797638,0.0007834153,0.0060798903,0.0011620473],"candidate_categories":["metaresearch","sts","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1263735,0.00013555931,0.00026973776,0.002207357,0.0016594777,0.001278711,0.0012901805,0.00011394508,0.0008288038],"category_scores_gemma":[0.032868803,0.000075654,0.000109949615,0.003051777,0.00034653494,0.0018499902,0.00006678186,0.0025671346,0.0015001893],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005785044,0.00003778286,0.010012715,0.000017829965,0.00002582901,0.000008715249,0.013165256,0.0023083314,0.0024748996,0.0001292918,0.3041441,0.66709673],"study_design_scores_gemma":[0.00044066884,0.002439297,0.022045719,0.0004907797,0.000007866694,0.000074857635,0.04374272,0.0032545626,0.0044512553,0.0013777433,0.9214859,0.00018864345],"about_ca_topic_score_codex":0.0069312444,"about_ca_topic_score_gemma":0.071497165,"teacher_disagreement_score":0.6669081,"about_ca_system_score_codex":0.002342602,"about_ca_system_score_gemma":0.006472549,"threshold_uncertainty_score":0.99975806},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W2968825767","doi":"","title":"Have we forgotten what accountability means","year":2018,"lang":"en","type":"article","venue":"Nottingham Trent University's Institutional Repository (Nottingham Trent Repository)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Trent University; British Academy of Management; Nottingham Trent University","keywords":"Accountability; Business; Computer science; Political science; Law","score_opus":0.08860124463589068,"score_gpt":0.3755069439778014,"score_spread":0.2869056993419107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2968825767","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7695047,0.00041982334,0.005472341,0.0024928716,0.01043962,0.00089954626,0.000036344714,0.00055020116,0.21018453],"genre_scores_gemma":[0.95592064,0.00010000776,0.002053827,0.00031938346,0.0019469956,0.000016179898,0.000047346002,0.000040386927,0.039555244],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.98871297,0.0009519619,0.001956416,0.002198495,0.0051224907,0.0010576824],"domain_scores_gemma":[0.9920366,0.001212376,0.0014945979,0.0019866312,0.002591044,0.00067877263],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003089082,0.00081953185,0.00086938724,0.0011069125,0.0050692256,0.001806897,0.0022257152,0.00046010007,0.00078145455],"category_scores_gemma":[0.00077991805,0.00074062485,0.0007881846,0.0015043928,0.001693187,0.0048457067,0.0007643345,0.0007719265,0.00051211665],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0030144323,0.005377627,0.6237579,0.0002708168,0.0013833394,0.0016654672,0.029686002,0.008699869,0.030574545,0.029234787,0.04264139,0.22369385],"study_design_scores_gemma":[0.0037552204,0.0008930399,0.06528975,0.0007294772,0.00037679277,0.0005095568,0.018168794,0.02277264,0.030025138,0.0009099254,0.854777,0.0017926635],"about_ca_topic_score_codex":0.0003567144,"about_ca_topic_score_gemma":0.00025557072,"teacher_disagreement_score":0.81213564,"about_ca_system_score_codex":0.0020365997,"about_ca_system_score_gemma":0.0019593155,"threshold_uncertainty_score":0.9995045},"labels":[],"label_agreement":null},{"id":"W2969398614","doi":"10.36591/se-4202-02","title":"How Journals and Publishers Can Help to Reform Research Assessment","year":2019,"lang":"en","type":"article","venue":"Science Editor","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Computer science; Library science; Data science","score_opus":0.31864303919757925,"score_gpt":0.58884405904664,"score_spread":0.2702010198490607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2969398614","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73407334,0.000025863199,0.00022277974,0.1393676,0.042228553,0.00069058756,0.000008540197,0.00003014009,0.08335262],"genre_scores_gemma":[0.9747657,0.000009588592,0.0019248185,0.0007712246,0.006156463,0.00002723449,6.804231e-7,0.0000064745677,0.0163378],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9871344,0.00019103865,0.00036564068,0.00072352344,0.010917146,0.00066826184],"domain_scores_gemma":[0.99520224,0.00048657088,0.00013925336,0.0007861751,0.0027717294,0.0006140427],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.045465194,0.000111023524,0.00019487453,0.0012282823,0.000710732,0.009205863,0.0018539113,0.000056592125,0.0014535369],"category_scores_gemma":[0.0035479644,0.00007043026,0.0000362884,0.00402223,0.00043533943,0.0045568654,0.00055946264,0.0003878343,0.00037499153],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021224534,0.000076752745,0.12679577,0.00000855399,0.0000068052154,0.0000033534034,0.0021849847,0.000059435824,0.021490421,0.005007933,0.71893364,0.12541112],"study_design_scores_gemma":[0.0003634816,0.0004802378,0.1636153,0.000033330478,0.0000019265885,0.0000063719476,0.027258107,0.0030745696,0.0012448754,0.0045567206,0.7991349,0.00023017765],"about_ca_topic_score_codex":0.000061894454,"about_ca_topic_score_gemma":0.000091341135,"teacher_disagreement_score":0.24069239,"about_ca_system_score_codex":0.0006359396,"about_ca_system_score_gemma":0.00204527,"threshold_uncertainty_score":0.99945927},"labels":[],"label_agreement":null},{"id":"W2969787057","doi":"10.33524/cjar.v19i1.376","title":"Rowell, L. L., Bruce, C. D., Shosh, J. S. &amp; Riel, M. M. (Eds.). (2017). The Palgrave international handbook of action research. NY: Palgrave Macmillan.","year":2018,"lang":"en","type":"article","venue":"The Canadian Journal of Action Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Compendium; Action research; Action (physics); Political science; Sociology; Library science; Graduate education; Globalization; Management; Law; Pedagogy; History","score_opus":0.5902017837826642,"score_gpt":0.5835563244385205,"score_spread":0.006645459344143734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2969787057","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6092132,0.0051733577,0.003445552,0.19208965,0.012525072,0.002346521,0.0001654861,0.000031860094,0.17500934],"genre_scores_gemma":[0.9930877,0.0014119819,0.00018627665,0.00028365385,0.0014299336,0.0000132049845,0.000005858264,0.000016951393,0.0035644528],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9886433,0.0027625677,0.0010302028,0.00030745214,0.0065468885,0.0007096188],"domain_scores_gemma":[0.9849674,0.0025215915,0.0005995376,0.000930113,0.0104094045,0.0005719553],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.044019878,0.0001535163,0.00026706353,0.0019988215,0.0020469967,0.0008290688,0.0024688917,0.00015724119,0.009418254],"category_scores_gemma":[0.0052323597,0.0000851586,0.0001879346,0.0017953163,0.0018548056,0.00018095077,0.00014604072,0.0016542064,0.0010625372],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011522421,0.000045200755,0.010625013,0.000021061349,0.00039115135,0.0000413443,0.01019447,0.00047807852,0.009881528,0.01856802,0.62893647,0.3196654],"study_design_scores_gemma":[0.00092715624,0.0007931798,0.041079633,0.00016732578,0.000023694382,0.0002612481,0.009250811,0.0018727495,0.009543614,0.13176984,0.80410844,0.00020231187],"about_ca_topic_score_codex":0.01210558,"about_ca_topic_score_gemma":0.2434312,"teacher_disagreement_score":0.3838745,"about_ca_system_score_codex":0.0006313863,"about_ca_system_score_gemma":0.0050903754,"threshold_uncertainty_score":0.99971527},"labels":[],"label_agreement":null},{"id":"W2971517022","doi":"10.1177/1098214019866260","title":"Evaluations in the English-Speaking Commonwealth Caribbean Region: Lessons From the Field","year":2019,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; University of Ottawa","funders":"","keywords":"Commonwealth; Pride; Nexus (standard); Face (sociological concept); Public relations; Political science; Sociology; Psychology; Social psychology; Social science; Law","score_opus":0.20495958925068822,"score_gpt":0.5292134531119421,"score_spread":0.3242538638612539,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2971517022","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91273504,0.00020971148,0.0020967936,0.07606922,0.00084254274,0.0005031081,0.0000036836068,0.000004821316,0.0075350897],"genre_scores_gemma":[0.9932316,0.000050197083,0.00031372087,0.0059343935,0.0004095969,0.000014655533,0.000006444624,0.0000065048325,0.00003286759],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9907645,0.0036130566,0.0010746862,0.00021558342,0.0041422704,0.00018991041],"domain_scores_gemma":[0.9852945,0.01037187,0.0015503844,0.0007366632,0.001993438,0.000053126903],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.029395761,0.00011813524,0.00030202253,0.00021120647,0.00020477705,0.00026032544,0.0009626947,0.000033797016,0.0011200215],"category_scores_gemma":[0.0074388906,0.000059264818,0.00014723004,0.0012770247,0.00010055754,0.00057333196,0.000048243448,0.00046522776,0.00008212418],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001102214,0.00010131536,0.21321988,0.0000010753503,0.000043170163,0.00000269485,0.048313692,0.014094652,0.000044233064,0.0017990483,0.014594885,0.7076751],"study_design_scores_gemma":[0.0014319227,0.0009020899,0.8187229,0.00009469385,0.00012729222,0.000025974019,0.08027123,0.05187843,0.000037389083,0.011557493,0.034782104,0.0001684932],"about_ca_topic_score_codex":0.00038360927,"about_ca_topic_score_gemma":0.0009055299,"teacher_disagreement_score":0.70750666,"about_ca_system_score_codex":0.0001541922,"about_ca_system_score_gemma":0.0008171258,"threshold_uncertainty_score":0.9997931},"labels":[],"label_agreement":null},{"id":"W2973147484","doi":"10.33137/ijidi.v3i4.32996","title":"Book Review: Measuring Research: What Everyone Needs to Know","year":2019,"lang":"en","type":"article","venue":"The International Journal of Information Diversity & Inclusion (IJIDI)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Need to know; Data science; Computer science; Psychology; Sociology; Engineering ethics; Engineering; Computer security","score_opus":0.17837602429737093,"score_gpt":0.45148832782493514,"score_spread":0.2731123035275642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2973147484","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4074604,0.06022799,0.008449284,0.46770775,0.016246576,0.0025964524,0.000039388022,0.0000762167,0.03719593],"genre_scores_gemma":[0.73254263,0.05957784,0.00059456524,0.18780032,0.00069630926,0.0000078911735,0.000024290995,0.0000142918225,0.018741839],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9877512,0.00040390156,0.0012562212,0.00011459207,0.0102504315,0.00022368017],"domain_scores_gemma":[0.9900138,0.0009217532,0.001000143,0.00042473263,0.0074629495,0.00017662541],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.021331435,0.0001299633,0.0002688832,0.0013882907,0.00092321046,0.00072202587,0.0036018214,0.000057354402,0.009120742],"category_scores_gemma":[0.002378902,0.000081905615,0.00021842505,0.0010099994,0.000061194034,0.009464188,0.007001244,0.00046898884,0.004542322],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026150158,0.000045062734,0.0019510007,0.00001728183,0.00006096018,0.0000029138748,0.011715413,0.0028377597,0.0001707886,0.00041522973,0.944999,0.037523128],"study_design_scores_gemma":[0.0006313004,0.00014240123,0.002997728,0.00093525025,0.000013972826,0.000042545533,0.0054417537,0.0012669633,0.0005266824,0.0006913426,0.98719865,0.000111429435],"about_ca_topic_score_codex":0.00002413364,"about_ca_topic_score_gemma":0.0000074654713,"teacher_disagreement_score":0.32508227,"about_ca_system_score_codex":0.00055712037,"about_ca_system_score_gemma":0.000367019,"threshold_uncertainty_score":0.99623275},"labels":[],"label_agreement":null},{"id":"W2973640600","doi":"10.1177/1356389019870213","title":"Rapid impact evaluation","year":2019,"lang":"en","type":"article","venue":"Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Summative assessment; Impact evaluation; Formative assessment; Counterfactual thinking; Credibility; Stakeholder; Stakeholder engagement; Impact assessment; Ex-ante; Salience (neuroscience); Program evaluation; Theory of change; Process management; Legitimacy; Computer science; Management science; Knowledge management; Psychology; Business; Political science; Public relations; Economics; Social psychology; Artificial intelligence","score_opus":0.3381382875021545,"score_gpt":0.5894724107344181,"score_spread":0.2513341232322636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2973640600","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8863718,0.00028897144,0.00055439863,0.0009726254,0.0012486198,0.0015233598,0.0000050410285,0.00003679221,0.10899839],"genre_scores_gemma":[0.99724853,0.000012762353,0.00022987991,0.0002972326,0.00016141542,0.0001095081,0.00009319406,0.000011159888,0.0018363221],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9881693,0.0014467104,0.00071780395,0.000521596,0.008897135,0.0002474397],"domain_scores_gemma":[0.9952343,0.00057084224,0.00039116936,0.0008702323,0.002838637,0.00009480512],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.04635462,0.00015459766,0.00021967468,0.00039141305,0.00012441498,0.00028017693,0.00039328306,0.00008488656,0.17223346],"category_scores_gemma":[0.0031270778,0.00010883505,0.0001618908,0.00092568423,0.000023749735,0.0010793101,0.00005027773,0.0001221302,0.018877393],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042894277,0.000059049464,0.052304924,0.000002071212,0.000024129013,8.1862545e-8,0.0006016649,0.038213342,0.001619306,0.0005133395,0.011670101,0.8949491],"study_design_scores_gemma":[0.0011409542,0.00015091256,0.34132248,0.0000070984884,0.0000395946,0.0000019114352,0.0002934946,0.6352287,0.00031824218,0.012769017,0.0086043505,0.00012326778],"about_ca_topic_score_codex":0.000017152603,"about_ca_topic_score_gemma":0.00001884264,"teacher_disagreement_score":0.8948258,"about_ca_system_score_codex":0.00047147486,"about_ca_system_score_gemma":0.0011256437,"threshold_uncertainty_score":0.9819786},"labels":[],"label_agreement":null},{"id":"W2973743400","doi":"","title":"Analysis of Sustainability Education Policy across Canadian Ministries of Education: Implications for Critical Policy Scholarship.","year":2016,"lang":"en","type":"article","venue":"AERA Online Paper Repository","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Scholarship; Sustainability; Political science; Education policy; Policy analysis; Public administration; Higher education; Public policy; Economic growth; Economics","score_opus":0.08585643302074783,"score_gpt":0.5541999764770683,"score_spread":0.46834354345632045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2973743400","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.880929,0.00021491402,0.00089712057,0.11340975,0.0003793855,0.00051294395,0.0007028759,0.000015458529,0.0029385588],"genre_scores_gemma":[0.9939268,0.000016588017,0.0015775249,0.00097277854,0.00037289696,0.00013572932,0.00007374142,0.0000085206075,0.0029153696],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9975507,0.0001761943,0.0010463094,0.00040197582,0.0005325887,0.0002922253],"domain_scores_gemma":[0.9919527,0.001388628,0.00035629666,0.0010571445,0.004958,0.00028720943],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0015010338,0.00012929895,0.00034241937,0.0008714071,0.00032161167,0.000092715774,0.0005185141,0.0001047581,0.000107242195],"category_scores_gemma":[0.011137042,0.000092898525,0.00025131798,0.002197175,0.000333773,0.00058358227,0.00005120429,0.00006690323,0.0000034750826],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034624554,0.00074373756,0.66814566,0.000042335694,0.00013343591,6.8174174e-8,0.0009564785,0.0000347639,0.0030680029,0.11179053,0.0011925569,0.2138578],"study_design_scores_gemma":[0.0001428844,0.00007138262,0.9370613,0.000019751693,0.00012080252,0.0000034132006,0.0022149645,0.000033731743,0.0008625433,0.02159171,0.037762363,0.00011513515],"about_ca_topic_score_codex":0.018396225,"about_ca_topic_score_gemma":0.02705611,"teacher_disagreement_score":0.26891565,"about_ca_system_score_codex":0.00070016144,"about_ca_system_score_gemma":0.027047336,"threshold_uncertainty_score":0.99719256},"labels":[],"label_agreement":null},{"id":"W2974976319","doi":"10.1177/0840470419869035","title":"Pathway to professionalizing health leadership in Canada: The two faces of Janus","year":2019,"lang":"en","type":"article","venue":"Healthcare Management Forum","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Canadian Thoracic Society; Canadian Paediatric Society; Canadian Cardiovascular Society","funders":"","keywords":"Professionalization; Certification; Licensure; Public relations; Political science; Leadership style; Servant leadership; State (computer science); Transactional leadership; Psychology; Sociology; Law","score_opus":0.3660940326675887,"score_gpt":0.4755288157903315,"score_spread":0.1094347831227428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2974976319","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31810328,0.0008283414,0.00029910557,0.6633707,0.0016832288,0.0032931955,0.000027942762,0.000019919258,0.012374225],"genre_scores_gemma":[0.96462965,0.00003077127,0.00027579043,0.030058986,0.000016128872,0.00007248723,0.0000061973683,0.000008129645,0.004901857],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9954844,0.00048820645,0.0008980556,0.00038422,0.0021489498,0.0005961714],"domain_scores_gemma":[0.9983945,0.000322093,0.0003455757,0.00064870494,0.00014969302,0.00013943446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00528301,0.00012935748,0.00030175966,0.0002762732,0.0001605629,0.00004082789,0.00068243686,0.000021663596,0.00047011947],"category_scores_gemma":[0.00006538951,0.00008042975,0.000044342174,0.0009841233,0.000017895374,0.00014721288,0.00024520548,0.00017546241,0.00016701719],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051257124,0.00004022332,0.62467086,0.00030484138,0.000013803832,0.0000034204174,0.0021770734,0.0024973757,0.000005041709,0.055435646,0.022289151,0.2925113],"study_design_scores_gemma":[0.00091585465,0.00022540841,0.58671117,0.00049736875,0.0000023809596,0.0000012101357,0.18404299,0.0035157946,0.00006928414,0.003181782,0.22060943,0.0002273303],"about_ca_topic_score_codex":0.42080545,"about_ca_topic_score_gemma":0.9514739,"teacher_disagreement_score":0.6465264,"about_ca_system_score_codex":0.0006123662,"about_ca_system_score_gemma":0.0021583391,"threshold_uncertainty_score":0.58305144},"labels":[],"label_agreement":null},{"id":"W2977861442","doi":"10.1332/174426414x14165770542276","title":"Examining the feasibility and impact of a graduate public administration course in evidence-informed policy","year":2014,"lang":"en","type":"article","venue":"Evidence & Policy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de Santé Publique du Québec; Université Laval","funders":"","keywords":"Test (biology); Treatment and control groups; Medical education; Test score; Course (navigation); Outcome (game theory); Psychology; Medicine; Mathematics education; Engineering; Standardized test; Economics; Internal medicine","score_opus":0.6319748366212998,"score_gpt":0.6052834449616719,"score_spread":0.026691391659627972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2977861442","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.971006,0.00025261517,0.00018242806,0.02696299,0.000060590562,0.00041894114,0.000004343324,0.000017706416,0.001094396],"genre_scores_gemma":[0.99838024,0.00043458684,0.000111531335,0.00060598797,0.0002376599,0.0000337601,0.0000013747131,0.0000069832527,0.00018789097],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99551576,0.0008695193,0.0010378953,0.0004166212,0.0017438806,0.00041633705],"domain_scores_gemma":[0.9916961,0.005862999,0.00064787164,0.000999301,0.00057886774,0.0002148446],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0142344935,0.00019141345,0.0003433124,0.0005806927,0.00018078454,0.00043570244,0.0007683987,0.00007433658,0.00016958786],"category_scores_gemma":[0.0558722,0.000111880654,0.000111242676,0.0021916316,0.00035487371,0.002522136,0.00016116389,0.00021923512,0.00006032493],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008338153,0.00005752611,0.9030455,0.000018809327,0.000009361633,4.743987e-7,0.00337606,0.00012330046,0.00020427986,0.0070025064,0.0006128386,0.085466],"study_design_scores_gemma":[0.00033507185,0.0006452254,0.9805338,0.00021173338,0.000007640495,0.000011580464,0.00093731773,0.008225907,0.000095427684,0.008683713,0.00019177297,0.00012084032],"about_ca_topic_score_codex":0.0018681992,"about_ca_topic_score_gemma":0.002046183,"teacher_disagreement_score":0.08534516,"about_ca_system_score_codex":0.00035695333,"about_ca_system_score_gemma":0.0053307773,"threshold_uncertainty_score":0.9520806},"labels":[],"label_agreement":null},{"id":"W2978531705","doi":"10.2196/10075","title":"Identification of Complex Health Interventions Suitable for Evaluation: Development and Validation of the 8-Step Scoping Framework","year":2018,"lang":"en","type":"article","venue":"JMIR Research Protocols","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Psychological intervention; General partnership; Identification (biology); Program evaluation; Management science; Computer science; Work (physics); Process management; Set (abstract data type); Knowledge management; Medicine; Psychology; Nursing; Business; Political science; Engineering","score_opus":0.8342529023173826,"score_gpt":0.7521430368537263,"score_spread":0.08210986546365628,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2978531705","genre_codex":"protocol","genre_gemma":"protocol","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"protocol","genre_consensus":"protocol","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0786986,0.000022778497,0.09861643,0.0040963623,0.000076939235,0.8175614,0.00003088727,0.000017385515,0.0008792407],"genre_scores_gemma":[0.4253203,5.969013e-7,0.007888651,0.000033140048,0.000054378605,0.56617445,0.000008670863,0.000006489964,0.00051330257],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9943205,0.0012169082,0.0012158209,0.0002746188,0.0027549372,0.00021722839],"domain_scores_gemma":[0.9939372,0.0009827695,0.0006927894,0.000545394,0.0037860675,0.000055809436],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03768575,0.0000641312,0.00018953058,0.00025946242,0.0005766844,0.00016797511,0.00051486684,0.00004999464,0.0005972286],"category_scores_gemma":[0.0034165273,0.000043218963,0.0000659136,0.00093315775,0.0002706998,0.00028692238,0.00020068881,0.00012399399,0.00002213786],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00060666946,0.0019381213,0.068070464,0.0071264114,0.00010154796,5.1193545e-8,0.028631637,0.00037553746,0.014031618,0.06892538,0.036890667,0.7733019],"study_design_scores_gemma":[0.005526031,0.003174493,0.4315662,0.033289503,0.0000118158305,0.0000022927777,0.0076163663,0.060705557,0.27619088,0.093749315,0.0877615,0.0004060227],"about_ca_topic_score_codex":0.0000065473673,"about_ca_topic_score_gemma":0.000064552536,"teacher_disagreement_score":0.7728959,"about_ca_system_score_codex":0.00011624396,"about_ca_system_score_gemma":0.001231821,"threshold_uncertainty_score":0.99090505},"labels":[],"label_agreement":null},{"id":"W2979655445","doi":"10.12927/hcpap.2019.25921","title":"Promising Practices in Equity in Mental Healthcare: Health Equity Impact Assessment","year":2019,"lang":"en","type":"article","venue":"A Nudge Too Far? A Nudge at All? On Paying People to Be Healthy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Centre for Addiction and Mental Health","funders":"","keywords":"Mental health; Equity (law); Health equity; Disadvantaged; Health care; Business; Nursing; Economic growth; Public relations; Psychology; Medicine; Political science; Psychiatry; Economics","score_opus":0.44110558553415996,"score_gpt":0.630762178302321,"score_spread":0.189656592768161,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2979655445","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5525152,0.00016348236,0.00006062192,0.44123283,0.00071937696,0.0023645102,0.00005406966,0.00006973103,0.0028201588],"genre_scores_gemma":[0.5564703,0.00023295335,0.00094263966,0.44165573,0.000021352716,0.00020137736,0.00006644494,0.000042441963,0.00036678996],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9853426,0.0025447211,0.0030818488,0.002034917,0.004674415,0.0023214843],"domain_scores_gemma":[0.9920816,0.0023400728,0.0023571213,0.0016350886,0.00033912528,0.0012470094],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.029134173,0.0006914338,0.0015258299,0.0012715723,0.00059310807,0.00064598885,0.0014392216,0.00027494715,0.001709098],"category_scores_gemma":[0.001565555,0.00056654547,0.00028806756,0.003032178,0.00004737056,0.0014853993,0.0014616079,0.0012239752,0.0013462156],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.0023350874,0.0019200344,0.6195232,0.00024894002,0.000050864914,0.000025554471,0.029420624,0.00091359444,0.0006420376,0.0022085411,0.23529442,0.107417054],"study_design_scores_gemma":[0.005770402,0.0060200384,0.8469191,0.000015979567,0.000011294914,0.000046683057,0.005111584,0.025131952,0.000056720673,0.0010913566,0.10880548,0.0010193782],"about_ca_topic_score_codex":0.011388807,"about_ca_topic_score_gemma":0.045553308,"teacher_disagreement_score":0.22739589,"about_ca_system_score_codex":0.010989391,"about_ca_system_score_gemma":0.0063779852,"threshold_uncertainty_score":0.9997107},"labels":[],"label_agreement":null},{"id":"W2979695716","doi":"10.1177/1609406918788237","title":"Reflection/Commentary on a Past Article: “Verification Strategies for Establishing Reliability and Validity in Qualitative Research”","year":2018,"lang":"en","type":"article","venue":"International Journal of Qualitative Methods","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":33,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reflection (computer programming); Reliability (semiconductor); Psychology; Reliability engineering; Computer science; Data science; Engineering; Physics; Programming language","score_opus":0.9163415305983555,"score_gpt":0.7965018843991819,"score_spread":0.11983964619917364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2979695716","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5740052,0.000026609448,0.39602754,0.027514722,0.000931081,0.00023038508,0.000025117442,0.000005422989,0.0012339457],"genre_scores_gemma":[0.7907241,0.000016871609,0.20774291,0.00086756644,0.0005230477,0.000026584323,0.0000037337945,0.0000068826384,0.00008830644],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97442126,0.021213178,0.0014355239,0.00035860055,0.0023584384,0.00021297703],"domain_scores_gemma":[0.956617,0.035180178,0.0008185623,0.00022418548,0.0070612966,0.00009878871],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.17308348,0.000117292344,0.00028519155,0.0008843406,0.00019709175,0.00048985326,0.00055763725,0.00006135056,0.00016025695],"category_scores_gemma":[0.029643308,0.00008695778,0.00009422203,0.0006918447,0.0004767398,0.0017283929,0.00007765764,0.00041306487,0.000009578643],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0033517214,0.0006592225,0.0033356657,0.000018636916,0.00013864634,0.000003815114,0.7318237,0.00063335756,0.00857183,0.075495616,0.024045844,0.15192199],"study_design_scores_gemma":[0.0010410666,0.0012737472,0.009031121,0.000075968725,0.0000068146087,0.0000052379055,0.3116349,0.004050041,0.0037414676,0.65458685,0.014446558,0.00010621305],"about_ca_topic_score_codex":0.000081784965,"about_ca_topic_score_gemma":0.000096302676,"teacher_disagreement_score":0.57909125,"about_ca_system_score_codex":0.00038875025,"about_ca_system_score_gemma":0.0002749362,"threshold_uncertainty_score":0.9785304},"labels":[],"label_agreement":null},{"id":"W2979837196","doi":"10.35502/jcswb.104","title":"First nation policing program and policy-making","year":2019,"lang":"en","type":"article","venue":"Journal of Community Safety and Well-Being","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Indigenous; Government (linguistics); Public relations; Delphi method; Political science; Economic Justice; Public administration; Community policing; Relevance (law); Law","score_opus":0.08537945815547178,"score_gpt":0.4428680334027833,"score_spread":0.35748857524731154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2979837196","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94653285,0.000065324806,0.00084002817,0.009723831,0.00018894677,0.00014869637,5.7517326e-7,0.000011288342,0.042488437],"genre_scores_gemma":[0.9974301,0.00035454662,0.0009111333,0.0008962892,0.00014093817,6.2527687e-7,9.3163203e-7,0.0000060320954,0.00025940558],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99774414,0.00052497955,0.0007092205,0.00006878367,0.0007914831,0.00016138985],"domain_scores_gemma":[0.9972262,0.0014840214,0.0005789521,0.00025770895,0.0003641153,0.000089031004],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0075394465,0.00010091937,0.00026473572,0.00041796124,0.00067960523,0.00029230307,0.00034055748,0.00006021374,0.00012279641],"category_scores_gemma":[0.00062710186,0.00007467044,0.00006545687,0.00039939,0.00006230918,0.0008177584,0.00018066078,0.00055975665,0.000018125293],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003485466,0.00024998843,0.29499388,0.00010274517,0.0000908459,0.0000032593935,0.0550339,0.0041702604,0.00029913711,0.046323054,0.0004188973,0.5979655],"study_design_scores_gemma":[0.0021010374,0.0009895077,0.7138415,0.00057479594,0.00004129611,0.0002742528,0.014761614,0.028179897,0.00012924883,0.084061064,0.15475044,0.00029533354],"about_ca_topic_score_codex":0.00018905218,"about_ca_topic_score_gemma":0.00022841673,"teacher_disagreement_score":0.5976702,"about_ca_system_score_codex":0.000067694826,"about_ca_system_score_gemma":0.00012020984,"threshold_uncertainty_score":0.5227043},"labels":[],"label_agreement":null},{"id":"W2980068289","doi":"","title":"Striving for excellence and equity : The value of OECD assessment programs for policy in Canada","year":2010,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Excellence; Equity (law); Value (mathematics); Accounting; Public economics; Economics; Actuarial science; Political science; Business; Computer science","score_opus":0.20205833123164185,"score_gpt":0.5397394104740714,"score_spread":0.3376810792424295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2980068289","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.968037,0.000014332731,0.013318569,0.011348183,0.00034763693,0.001403787,0.000023323104,0.0000057773973,0.0055013583],"genre_scores_gemma":[0.99073607,0.0000060927846,0.008297284,0.00028289764,0.000048752925,0.00014075171,0.0000022744111,0.0000032865166,0.0004826168],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99834955,0.000047867714,0.00042483807,0.0001979439,0.00077549805,0.0002043136],"domain_scores_gemma":[0.99772376,0.0015826154,0.00016261911,0.0002823897,0.00019234796,0.00005625907],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047703907,0.00007002225,0.00014624195,0.000071518305,0.00010860707,0.000091192676,0.00039757448,0.00002588687,0.000126788],"category_scores_gemma":[0.00055630284,0.000038470214,0.000033604327,0.00018650299,0.000058752386,0.00014088226,0.00012141315,0.00008740848,6.654976e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016598713,0.00005494588,0.22245555,0.00002535476,0.000006844104,8.5573056e-8,0.000287039,0.00022775262,0.001061729,0.079623245,0.002249944,0.6939909],"study_design_scores_gemma":[0.0013669459,0.00025620285,0.492114,0.000020209258,0.000011652268,0.0000019408335,0.0043424107,0.3742288,0.0019961467,0.071775764,0.053676438,0.00020948984],"about_ca_topic_score_codex":0.32541192,"about_ca_topic_score_gemma":0.9198332,"teacher_disagreement_score":0.69378144,"about_ca_system_score_codex":0.00009936928,"about_ca_system_score_gemma":0.0033601301,"threshold_uncertainty_score":0.67908025},"labels":[],"label_agreement":null},{"id":"W2980669435","doi":"","title":"평가자의 직업윤리 : 주요국의 평가윤리 원칙과 평가표준 비교","year":2014,"lang":"ko","type":"article","venue":"한국비교정부학보","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Professionalization; Engineering ethics; Compliance (psychology); Political science; Institutionalisation; Evaluation methods; Enforcement; Research ethics; Process (computing); Quality (philosophy); Psychology; Engineering; Law; Computer science; Social psychology","score_opus":0.19216225859925426,"score_gpt":0.5106255152756245,"score_spread":0.3184632566763702,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2980669435","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6452165,0.0006256728,0.011806279,0.019563599,0.007995262,0.00083741953,0.000059017253,0.00021525087,0.31368095],"genre_scores_gemma":[0.9542374,0.00022728175,0.0013627952,0.003652362,0.0008015155,0.000028253991,0.000023612636,0.000035867768,0.039630897],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99287707,0.0007512789,0.0012776781,0.0009864976,0.003309098,0.0007983735],"domain_scores_gemma":[0.99548364,0.0012794284,0.00054258027,0.0015902208,0.0006573826,0.00044673771],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.007946436,0.0004259721,0.0006136899,0.000397233,0.00058351597,0.0008146149,0.0013679807,0.00029148426,0.03171904],"category_scores_gemma":[0.0015993774,0.00033899187,0.00030827764,0.0011286754,0.00024804106,0.0008260255,0.00032919494,0.0004865895,0.034921292],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000098117125,0.00041520398,0.12170272,0.000054097563,0.0000860697,0.000008938657,0.00393274,0.0006646333,0.0006569863,0.027013252,0.18239741,0.6629698],"study_design_scores_gemma":[0.0012035259,0.0004122472,0.0967913,0.00009459913,0.000060104572,0.000014854751,0.000903103,0.06514254,0.0006628314,0.011815197,0.8223208,0.00057890906],"about_ca_topic_score_codex":0.00011887986,"about_ca_topic_score_gemma":0.00026253666,"teacher_disagreement_score":0.6623909,"about_ca_system_score_codex":0.00013568508,"about_ca_system_score_gemma":0.00057096616,"threshold_uncertainty_score":0.9999062},"labels":[],"label_agreement":null},{"id":"W2981183307","doi":"10.7202/1064725ar","title":"La sociologie de l’éducation au croisement de la sociologie de l’action publique : apports des cadres pour une typologie des systèmes d’accountability","year":2019,"lang":"fr","type":"article","venue":"Cahiers de recherche sociologique","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.6426646181634836,"score_gpt":0.585617930475322,"score_spread":0.05704668768816168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2981183307","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.903871,0.0037058748,0.043887313,0.009847546,0.0009602911,0.00095507404,0.000046847195,0.00031275133,0.036413275],"genre_scores_gemma":[0.9436051,0.02094675,0.02507436,0.0020202391,0.0003612206,0.00045645313,0.000072524475,0.000057024048,0.0074062934],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.93588686,0.05894012,0.0012658908,0.0012097497,0.0006420515,0.002055325],"domain_scores_gemma":[0.95115864,0.045671944,0.00088126084,0.0008724556,0.0009186169,0.0004970851],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.14513367,0.00068037113,0.0008991808,0.0002899209,0.0009535952,0.00040034758,0.001216715,0.009970028,0.00098009],"category_scores_gemma":[0.05266628,0.00059288135,0.0005370427,0.00075486227,0.006574742,0.000978689,0.00021923716,0.0071615144,0.00032716012],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00017586228,0.0006269876,0.75099677,0.00052416616,0.00029026868,0.000023426575,0.055918243,0.0023989894,0.0069443486,0.038428877,0.0060256603,0.1376464],"study_design_scores_gemma":[0.0004935877,0.0002951679,0.32450303,0.0001286442,0.00010227576,0.00009419473,0.106449105,0.001324785,0.00202536,0.56139183,0.0027025505,0.0004894929],"about_ca_topic_score_codex":0.0037962908,"about_ca_topic_score_gemma":0.0007233807,"teacher_disagreement_score":0.5229629,"about_ca_system_score_codex":0.052798484,"about_ca_system_score_gemma":0.04076761,"threshold_uncertainty_score":0.9999331},"labels":[],"label_agreement":null},{"id":"W2982230197","doi":"10.4095/315337","title":"Getting a survey done","year":2014,"lang":"en","type":"report","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Geography","score_opus":0.6422379800816382,"score_gpt":0.6126830773174127,"score_spread":0.029554902764225566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2982230197","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004470986,0.00013734722,0.008148602,0.0006027311,0.0029963828,0.00020542588,0.000027203356,0.000061996856,0.9833493],"genre_scores_gemma":[0.32743368,0.00032645123,0.0014760069,0.0011380726,0.0010983428,0.000026901558,0.00022015104,0.00003437544,0.66824603],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9890288,0.00071088277,0.0012929803,0.0006263296,0.008071623,0.00026940208],"domain_scores_gemma":[0.9917235,0.0028715988,0.00083597726,0.0010572689,0.0033896149,0.00012207871],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.06730484,0.0002136548,0.00057842396,0.00037250866,0.00013905951,0.0004471879,0.0008049721,0.00024204317,0.022686237],"category_scores_gemma":[0.015790414,0.00013249488,0.00016790487,0.0005629074,0.00004125079,0.00015867881,0.00019229812,0.00031862324,0.005733854],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034865307,0.000016006094,0.0814959,0.000009334176,0.000017417682,0.0000011010482,0.000035042303,0.000030289646,0.000004228697,0.000084701394,0.78973943,0.12856306],"study_design_scores_gemma":[0.00009205757,0.000025116042,0.25654137,0.00002108644,0.0000075411867,0.000007396637,0.000030795298,0.0011636623,0.000010942929,0.000576644,0.7413402,0.00018316759],"about_ca_topic_score_codex":0.0019082959,"about_ca_topic_score_gemma":0.006600973,"teacher_disagreement_score":0.32296267,"about_ca_system_score_codex":0.00014216034,"about_ca_system_score_gemma":0.0024859689,"threshold_uncertainty_score":0.9950403},"labels":[],"label_agreement":null},{"id":"W2984199337","doi":"10.34051/p/2019.3","title":"Public Impact-Focused Research Survey Results","year":2019,"lang":"en","type":"report","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Survey research; Institution; Research council; Path (computing); Order (exchange); Land grant; Public administration; Political science; Public relations; Business; Library science; Computer science; Sociology; Socioeconomics; Law","score_opus":0.9371288775499866,"score_gpt":0.7065502798683398,"score_spread":0.2305785976816468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2984199337","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009913173,0.00021079957,0.0001093492,0.003343205,0.0030030594,0.0008447116,0.00073494663,0.00006506278,0.9817757],"genre_scores_gemma":[0.4353878,0.0006141463,0.00012270268,0.000084244086,0.0004294305,0.00002822066,0.0009375423,0.000035443274,0.56236047],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9583153,0.0048534973,0.0026987998,0.0016708882,0.03132599,0.001135518],"domain_scores_gemma":[0.9569991,0.013186359,0.00095208583,0.0036241459,0.024805052,0.0004332621],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.26169708,0.00036390798,0.0009104055,0.0023858151,0.00036721962,0.0022039202,0.002591672,0.00062267104,0.025137577],"category_scores_gemma":[0.08851038,0.000210143,0.00036715955,0.003813811,0.00017052695,0.0007317145,0.0006992935,0.0014093169,0.027619867],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000063808046,0.000055706467,0.04949236,0.000007225121,0.00004036195,0.0000026153746,0.00006532261,0.000016440794,0.0000032908924,0.000079336816,0.9039794,0.046194103],"study_design_scores_gemma":[0.00046347175,0.00019930533,0.34689665,0.000020181447,0.000003561701,0.000005990967,0.00008097613,0.0008021172,0.000009649062,0.0006362812,0.65064764,0.0002342093],"about_ca_topic_score_codex":0.0064353007,"about_ca_topic_score_gemma":0.0071177306,"teacher_disagreement_score":0.4254746,"about_ca_system_score_codex":0.0011124128,"about_ca_system_score_gemma":0.028062828,"threshold_uncertainty_score":0.99883187},"labels":[],"label_agreement":null},{"id":"W2985665214","doi":"10.33524/cjar.v20i1.443","title":"Action Research, Ethics, the Politics of Academia, and People","year":2019,"lang":"en","type":"article","venue":"The Canadian Journal of Action Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Bishop's University","funders":"","keywords":"Action research; Politics; Action (physics); Engineering ethics; Political science; Sociology; Research ethics; Pedagogy; Law; Engineering","score_opus":0.7974501253666637,"score_gpt":0.6760370855040544,"score_spread":0.12141303986260932,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2985665214","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8901274,0.00022897334,0.000027988403,0.103995614,0.00045744667,0.00022259683,0.000004984007,0.000001163735,0.0049337903],"genre_scores_gemma":[0.990821,0.00031342875,0.00002473681,0.00027011303,0.00024522818,0.000002377914,3.9465516e-7,0.0000059985414,0.008316727],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9911053,0.0033850507,0.000518763,0.00013154952,0.0044471505,0.00041219222],"domain_scores_gemma":[0.9873315,0.007080262,0.00025695487,0.00042027506,0.00455914,0.00035184948],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.07762414,0.000057629455,0.00015275349,0.00094566337,0.0014267988,0.00035697513,0.0008979897,0.00020120296,0.00163974],"category_scores_gemma":[0.007874809,0.000029538416,0.00005825667,0.0013213919,0.000638787,0.00042320823,0.00006333836,0.004514503,0.0001794397],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042271244,0.00009058577,0.30208334,0.00014739219,0.00021535055,0.000013401644,0.08764147,0.0031878785,0.00952706,0.14023283,0.32335764,0.13308035],"study_design_scores_gemma":[0.00058769854,0.0006373436,0.38753918,0.00009413988,0.000012425023,0.00013766177,0.08898111,0.0031782528,0.0035236476,0.074968,0.4402325,0.000108050954],"about_ca_topic_score_codex":0.021212675,"about_ca_topic_score_gemma":0.157021,"teacher_disagreement_score":0.13580832,"about_ca_system_score_codex":0.00036066957,"about_ca_system_score_gemma":0.0064294552,"threshold_uncertainty_score":0.9998732},"labels":[],"label_agreement":null},{"id":"W2985992387","doi":"10.1108/jhom-05-2019-0139","title":"Evaluating complex transformation","year":2019,"lang":"en","type":"article","venue":"Journal of Health Organization and Management","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Government of British Columbia; Nutrasource; Golder Associates (Canada); University of British Columbia","funders":"","keywords":"Scope (computer science); Summative assessment; Originality; Process management; Government (linguistics); Scale (ratio); Theory of change; Medicine; Management science; Computer science; Sociology; Business; Formative assessment; Engineering; Qualitative research","score_opus":0.30082943846713167,"score_gpt":0.5477147668902765,"score_spread":0.24688532842314487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2985992387","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77733254,0.0003786285,0.15743554,0.04688881,0.0014891713,0.0011981316,0.00000233702,0.000029400808,0.015245462],"genre_scores_gemma":[0.98968834,0.00060892844,0.0059612268,0.0029985984,0.000034961988,6.6062745e-7,0.0000052810205,0.0000059369168,0.00069604814],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9973767,0.00020004153,0.0010014406,0.00009885667,0.0012206195,0.00010236178],"domain_scores_gemma":[0.9983344,0.000077568555,0.0007714484,0.00012267062,0.0006261402,0.000067776644],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007123902,0.00006004591,0.00018996808,0.0002942497,0.00013191509,0.00012530737,0.00015247236,0.000016951684,0.0021907282],"category_scores_gemma":[0.00013666508,0.00004283527,0.000023873861,0.000583096,0.000008988263,0.00047805542,0.000029332014,0.000060097667,0.0001410069],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032303862,0.00010557666,0.02195007,0.00020773076,0.00004595878,0.0000010536219,0.0050408584,0.0053881793,0.00029581314,0.049063075,0.012256389,0.905613],"study_design_scores_gemma":[0.004128738,0.0011364726,0.6260483,0.00012338103,0.000036346195,0.00007175881,0.009815283,0.04273198,0.00011325448,0.0052279546,0.31034058,0.00022594431],"about_ca_topic_score_codex":0.0000013175267,"about_ca_topic_score_gemma":0.0000014630746,"teacher_disagreement_score":0.90538704,"about_ca_system_score_codex":0.00007059697,"about_ca_system_score_gemma":0.000117037336,"threshold_uncertainty_score":0.9987214},"labels":[],"label_agreement":null},{"id":"W2990196625","doi":"","title":"Building Better Opportunities: Working Progress – Evaluation Overview","year":2019,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact","funders":"","keywords":"Computer science; Risk analysis (engineering); Data science; Business","score_opus":0.5970579034647109,"score_gpt":0.5547462024424069,"score_spread":0.04231170102230397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990196625","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82256997,0.0005909608,0.0017843223,0.007219651,0.0011285653,0.0007485469,0.0000011214654,0.00006628282,0.16589057],"genre_scores_gemma":[0.98541903,0.000036653084,0.0056168973,0.0027310832,0.00011565735,0.00005051775,0.0000056281656,0.000008693993,0.006015837],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9953975,0.0002942613,0.00053755444,0.00034990013,0.0032052998,0.00021546413],"domain_scores_gemma":[0.9982796,0.0003713255,0.00022419673,0.0005365381,0.0005138999,0.00007446257],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.01033817,0.00011202598,0.0001850194,0.00022269672,0.00009987983,0.0004023027,0.00042024796,0.000050374023,0.04232854],"category_scores_gemma":[0.00017341346,0.00007588636,0.0000796091,0.0004362482,0.000031607502,0.00064152665,0.00010216661,0.000090155154,0.0019263895],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000049634377,0.000019600091,0.09764979,0.0000043799273,0.000009035386,4.6825554e-7,0.00019685486,0.00019987287,0.000056292858,0.016376752,0.0038443333,0.88163763],"study_design_scores_gemma":[0.0009681639,0.00010283536,0.09031093,0.00013524765,0.000031130756,0.0000055051983,0.0017003946,0.24906407,0.00036568273,0.034612082,0.62234235,0.00036161017],"about_ca_topic_score_codex":0.000004175054,"about_ca_topic_score_gemma":0.0000086510545,"teacher_disagreement_score":0.8812761,"about_ca_system_score_codex":0.000074190706,"about_ca_system_score_gemma":0.00023406882,"threshold_uncertainty_score":0.9988507},"labels":[],"label_agreement":null},{"id":"W2990359457","doi":"10.1016/j.evalprogplan.2019.101761","title":"A scoping review of knowledge syntheses in the field of evaluation across four decades of practice","year":2019,"lang":"en","type":"review","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Fonds de Recherche du Québec-Société et Culture","keywords":"Field (mathematics); Mainstream; Diversity (politics); Knowledge production; Management science; Engineering ethics; Knowledge management; Political science; Computer science; Engineering; Mathematics","score_opus":0.6277469839766735,"score_gpt":0.7080220660359516,"score_spread":0.08027508205927814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990359457","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014303393,0.9870978,0.000078507335,0.00021526971,0.00018354447,0.006462233,0.000012062849,0.0000063676653,0.005801155],"genre_scores_gemma":[0.0028779958,0.99521047,0.00094999577,0.00013994756,0.00003923663,0.00071023306,0.000040829596,0.000010781459,0.000020501058],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.98710394,0.005693142,0.0026853548,0.00045577326,0.0038463022,0.00021547204],"domain_scores_gemma":[0.9728336,0.021094512,0.0031329326,0.00060899864,0.0022978138,0.00003217742],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07912925,0.00023426014,0.0014444558,0.00034493374,0.00007385607,0.00008717692,0.00049328175,0.000181905,0.00038565163],"category_scores_gemma":[0.048321154,0.00014111103,0.0002492594,0.0014645046,0.000082179045,0.00042437346,0.000104194965,0.00028724296,0.000014634367],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000102026015,0.0000877837,0.00017791337,0.043745574,0.000039876162,2.1058432e-7,0.0021784499,0.00003955527,1.5314063e-7,0.000049367358,0.00020504929,0.9534659],"study_design_scores_gemma":[0.00043493736,0.0004440558,0.00032579125,0.7633232,0.0015922193,0.00002323298,0.002150545,0.007237448,0.000006467246,0.00017034983,0.22405533,0.00023645672],"about_ca_topic_score_codex":0.00001301237,"about_ca_topic_score_gemma":0.000019515339,"teacher_disagreement_score":0.9532294,"about_ca_system_score_codex":0.000047449637,"about_ca_system_score_gemma":0.0017410616,"threshold_uncertainty_score":0.9596952},"labels":[],"label_agreement":null},{"id":"W2990615065","doi":"10.22329/csw.v7i1.5780","title":"Program Evaluation Re-Imagined","year":2019,"lang":"en","type":"article","venue":"Critical Social Work","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Downtown; Sociology; Focus group; Process (computing); Service (business); Public relations; Pedagogy; Computer science; Political science; History; Business; Marketing; Archaeology","score_opus":0.3105850894803213,"score_gpt":0.5963229018200544,"score_spread":0.2857378123397331,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990615065","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44795948,0.00014037208,0.0015317653,0.089706235,0.0033403689,0.0023501543,0.0000060143884,0.00024267599,0.45472294],"genre_scores_gemma":[0.9946159,7.0061657e-7,0.0014390729,0.00093675,0.00032731373,0.00014496066,0.000008276468,0.0000074164964,0.0025196143],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99613196,0.00034657712,0.00039427448,0.00031892906,0.0025407274,0.00026754526],"domain_scores_gemma":[0.99789554,0.00085550826,0.000055353536,0.00025320138,0.0008474689,0.000092929244],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0049118088,0.000090501744,0.00017986646,0.00006602076,0.0002998334,0.000346368,0.00030023593,0.00008335516,0.031108167],"category_scores_gemma":[0.0030252459,0.00006997284,0.00010386763,0.0010905375,0.000122804,0.00030314663,0.000060048536,0.00015366118,0.007926056],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040845614,0.00019372668,0.028172068,0.0000059801687,0.000008110177,9.2329117e-7,0.00086424226,0.000031748365,0.000029072295,0.051255602,0.023040017,0.89635766],"study_design_scores_gemma":[0.0011175987,0.00021219444,0.27960885,0.000026215663,0.000053680455,8.9093925e-7,0.002284635,0.023106242,0.000056924444,0.15866221,0.53450596,0.00036459297],"about_ca_topic_score_codex":0.0000016370684,"about_ca_topic_score_gemma":0.0000035001165,"teacher_disagreement_score":0.89599305,"about_ca_system_score_codex":0.000062969084,"about_ca_system_score_gemma":0.00016664139,"threshold_uncertainty_score":0.99284637},"labels":[],"label_agreement":null},{"id":"W2990803423","doi":"10.1007/978-3-319-14877-9_16","title":"Measuring Progress Towards Sustainability: A View of the Main Approaches to Evaluation","year":2019,"lang":"en","type":"book-chapter","venue":"Natural resource management in transition","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact","funders":"","keywords":"Sustainability; Set (abstract data type); Context (archaeology); Management science; Observational study; Computer science; Measure (data warehouse); Engineering ethics; Engineering; Mathematics; Geography; Data mining","score_opus":0.3252138017810178,"score_gpt":0.399639627141426,"score_spread":0.0744258253604082,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990803423","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011796293,0.002283912,0.0024444384,0.025449475,0.0007323603,0.013823929,0.000043879263,0.00005403203,0.94337165],"genre_scores_gemma":[0.9338889,0.000030843894,0.00027773925,0.0004414854,0.00004743495,0.00014971905,0.000048183283,0.00002761511,0.06508806],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9922733,0.00045650458,0.00102605,0.0007242895,0.005242047,0.00027783067],"domain_scores_gemma":[0.99788576,0.00015206887,0.00042467983,0.0009887961,0.000496024,0.00005266348],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01022753,0.00031253547,0.0004699003,0.0007164452,0.00009873078,0.00013571208,0.0008711207,0.00019529718,0.00038464024],"category_scores_gemma":[0.00015703352,0.00020953697,0.0002856179,0.00050585595,0.00012356968,0.00018129832,0.00020223949,0.00045078475,0.00005599121],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013454034,0.00004252186,0.00004595598,0.00036266033,0.000056440134,0.0000019936422,0.001647141,0.017876737,0.0000018747077,0.053889412,0.00036346974,0.9255773],"study_design_scores_gemma":[0.004057082,0.0004348219,0.039385583,0.0034782207,0.0008762231,0.000007715438,0.013255213,0.11282539,0.00019817379,0.26100776,0.5627934,0.0016804255],"about_ca_topic_score_codex":0.000009117234,"about_ca_topic_score_gemma":0.00010718693,"teacher_disagreement_score":0.92389685,"about_ca_system_score_codex":0.0009853911,"about_ca_system_score_gemma":0.00027380895,"threshold_uncertainty_score":0.854467},"labels":[],"label_agreement":null},{"id":"W2991358546","doi":"10.2478/sjs-2019-0020","title":"The Implementation of Results-Based Management in Quebec: Between School Principals’ Optimism and Teachers’ Skepticism","year":2019,"lang":"en","type":"article","venue":"Swiss Journal of Sociology","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Skepticism; Optimism; Perception; Psychology; Social psychology; Mathematics education; Pedagogy; Epistemology","score_opus":0.10241377920370906,"score_gpt":0.4956319665747695,"score_spread":0.3932181873710604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2991358546","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99047834,0.00017547894,0.0003414401,0.0076427376,0.00018884274,0.00021182856,0.000004602145,0.0000018232776,0.00095488963],"genre_scores_gemma":[0.99778706,0.00010426304,0.0012091561,0.00018759588,0.000049258837,0.0000033028703,0.0000026120406,0.0000037514483,0.00065299385],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9973749,0.00046997677,0.0011723709,0.00014153226,0.000674513,0.00016670821],"domain_scores_gemma":[0.9974808,0.001038689,0.0009604346,0.00020806203,0.00025019085,0.00006182574],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009400188,0.00007869653,0.00026830187,0.00022081948,0.00006760147,0.00004356173,0.000359674,0.00006810825,0.0002383527],"category_scores_gemma":[0.00023881541,0.00004676697,0.000070377086,0.00014337485,0.00015116147,0.00019868943,0.00005899041,0.00022955128,0.000027756092],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000166448,0.000043747674,0.8525253,0.000010159936,0.00012855636,0.0000046523064,0.011464378,0.0016704128,0.0003933206,0.0041332846,0.0021838096,0.12727591],"study_design_scores_gemma":[0.0025120524,0.00028362294,0.9638861,0.000021740534,0.000020968268,0.0000016024677,0.019428574,0.0001988848,0.00021197197,0.009562596,0.0038124262,0.000059451006],"about_ca_topic_score_codex":0.00014956783,"about_ca_topic_score_gemma":0.00041105115,"teacher_disagreement_score":0.12721646,"about_ca_system_score_codex":0.0001032684,"about_ca_system_score_gemma":0.00024599314,"threshold_uncertainty_score":0.32579362},"labels":[],"label_agreement":null},{"id":"W2991575284","doi":"10.1007/s11213-019-09504-w","title":"Examining Conditions that Influence Evaluation use within a Humanitarian Non-Governmental Organization in Burkina Faso (West Africa)","year":2019,"lang":"en","type":"article","venue":"Systemic Practice and Action Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Fonds de Recherche du Québec-Société et Culture; European Commission","keywords":"Public relations; Knowledge transfer; Accountability; Business; Citizen journalism; Perception; Interpersonal communication; Knowledge management; Qualitative research; Political science; Psychology; Sociology; Social psychology","score_opus":0.4443246029649782,"score_gpt":0.5427046587320105,"score_spread":0.09838005576703224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2991575284","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9900038,0.00004218837,0.00019193337,0.00064868724,0.00034804764,0.0011389091,0.000009426096,0.000020083355,0.0075969268],"genre_scores_gemma":[0.99796283,0.000076560034,0.000096290794,0.00010192252,0.000047364905,0.0000934875,0.00003162037,0.000013864144,0.0015760453],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9922214,0.0019204163,0.00060835725,0.0005484445,0.0044125435,0.00028885124],"domain_scores_gemma":[0.9931156,0.003593576,0.00047374424,0.00047795012,0.0022411323,0.000097981174],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.02190814,0.00012859967,0.00019998518,0.000632642,0.00044774282,0.0010040108,0.00028037277,0.000117528034,0.0010639544],"category_scores_gemma":[0.011604278,0.00011096162,0.000014644459,0.0019864163,0.00007932383,0.0057870457,0.00014241056,0.0005059118,0.0010582883],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001300149,0.00021599642,0.9023664,0.00006985393,0.000036569676,0.000009972415,0.012131387,0.0034475145,0.07509925,0.0023729021,0.0010453492,0.0030747775],"study_design_scores_gemma":[0.001574018,0.0003382096,0.71447694,0.00031632226,0.000032589003,0.00014478275,0.24670252,0.031170348,0.001262964,0.000504192,0.0032113676,0.00026573287],"about_ca_topic_score_codex":0.0006408359,"about_ca_topic_score_gemma":0.00033964773,"teacher_disagreement_score":0.23457113,"about_ca_system_score_codex":0.0008786764,"about_ca_system_score_gemma":0.0006321963,"threshold_uncertainty_score":0.9998492},"labels":[],"label_agreement":null},{"id":"W2991723122","doi":"10.2175/193864713813504377","title":"Taking up The Challenge of CSO Monitoring: The City of Winnipeg Experience in Setting up an Ambitious Program","year":2013,"lang":"en","type":"article","venue":"Proceedings of the Water Environment Federation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Gerontology; Architectural engineering; Aeronautics; Environmental planning; Engineering; Medicine; Environmental science","score_opus":0.146532229426722,"score_gpt":0.40250756108561153,"score_spread":0.2559753316588895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2991723122","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9928509,0.000018947692,0.000040093102,0.005230437,0.00017584725,0.00090020045,6.737065e-7,0.000008331706,0.0007745952],"genre_scores_gemma":[0.99906915,0.00002672347,0.00029885818,0.000049217946,0.000055342334,0.00022894586,9.4349963e-7,0.0000068142767,0.00026400734],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99750614,0.000064329965,0.00071113184,0.0002498401,0.0012827783,0.00018577339],"domain_scores_gemma":[0.9988485,0.000080868864,0.0006369699,0.00025873666,0.00014998166,0.000024970559],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025869026,0.00011913948,0.00016541696,0.00005664063,0.00030486798,0.00020382227,0.00066045334,0.00004866911,0.0002754891],"category_scores_gemma":[0.00014409343,0.000046343986,0.000063554115,0.00013283362,0.00020288765,0.00081822806,0.00021006334,0.0001368159,0.000008391057],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049854072,0.00043101487,0.4334461,0.000051130326,0.000022978322,4.9772005e-8,0.17965253,0.0013135113,0.2718281,0.00049728533,0.00012222292,0.11258523],"study_design_scores_gemma":[0.00039686647,0.00022952714,0.3724718,0.000072997675,0.0000127529065,0.0000013759985,0.03270278,0.012942004,0.57584876,0.0046504196,0.0005388254,0.00013187605],"about_ca_topic_score_codex":0.00010509235,"about_ca_topic_score_gemma":0.0000087476565,"teacher_disagreement_score":0.30402067,"about_ca_system_score_codex":0.000049042,"about_ca_system_score_gemma":0.000013242577,"threshold_uncertainty_score":0.30164123},"labels":[],"label_agreement":null},{"id":"W2992485618","doi":"10.3138/cjpe.024.001","title":"The Lay of the Land: Evaluation Practice in Canada in 2009","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Public Health Agency of Canada; University of Victoria; Ministère des Ressources naturelles et des Forêts (Québec)","funders":"","keywords":"CLARITY; Certification; Public relations; Sophistication; Psychology; Business; Political science; Sociology; Law; Social science","score_opus":0.2269249594352962,"score_gpt":0.5186252407657015,"score_spread":0.29170028133040526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2992485618","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95909154,0.0019888359,0.000022318227,0.030077958,0.0010505493,0.001746175,0.000005010187,0.0000013176827,0.0060163136],"genre_scores_gemma":[0.99914694,0.00003004908,0.00021285658,0.00049115135,0.00005270179,0.000025798934,0.0000020186628,0.0000030215717,0.000035445802],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9929708,0.0018526858,0.0011424373,0.00013054762,0.0036564649,0.00024704504],"domain_scores_gemma":[0.9947879,0.00088501495,0.0010098121,0.0003206749,0.0028545652,0.00014208855],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.037399307,0.00008436508,0.0001689367,0.0003030457,0.00014624007,0.0001501726,0.00058783364,0.00004300949,0.00027069834],"category_scores_gemma":[0.014444146,0.000046782687,0.000058601556,0.0012919919,0.00004515422,0.00050596695,0.000007518226,0.00027451722,0.000004201376],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002127575,0.000024845347,0.093446024,6.7706657e-7,0.0000054518728,0.000002164742,0.00066036347,0.024111876,0.000006605267,0.00012133274,0.0021844564,0.8794149],"study_design_scores_gemma":[0.0010121004,0.00016098021,0.8824714,0.000054980974,0.000039768307,0.00001861807,0.0021578704,0.07850322,0.00004098916,0.007083922,0.028385468,0.00007069565],"about_ca_topic_score_codex":0.41859367,"about_ca_topic_score_gemma":0.99549276,"teacher_disagreement_score":0.8793442,"about_ca_system_score_codex":0.0015295643,"about_ca_system_score_gemma":0.03426833,"threshold_uncertainty_score":0.9938576},"labels":[],"label_agreement":null},{"id":"W2994567589","doi":"10.56645/jmde.v13i28.462","title":"Translating Project Achievements into Strategic Plans: A Case Study in Utilization-Focused Evaluation","year":2017,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Process management; Program evaluation; Strategic planning; Management science; Engineering management; Business; Political science; Engineering; Public administration; Marketing","score_opus":0.6383590666042548,"score_gpt":0.6091607377580164,"score_spread":0.02919832884623841,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2994567589","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9935336,0.00011591861,0.0009634929,0.0008810454,0.00078786066,0.0025183454,0.0000061307505,0.000008322869,0.001185297],"genre_scores_gemma":[0.9977452,0.000013999273,0.0018762558,0.000012480999,0.0001813725,0.000104042025,0.00001411817,0.000016582688,0.00003590645],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98722184,0.0026646357,0.002483182,0.0004787017,0.0068858755,0.00026574792],"domain_scores_gemma":[0.99233377,0.0005140776,0.0030239057,0.0008478293,0.003177431,0.00010299824],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.06284669,0.00024718296,0.00047326324,0.0010655824,0.0010645181,0.0007153057,0.0008495991,0.00011074107,0.0004268962],"category_scores_gemma":[0.0032782767,0.00018439103,0.00015408834,0.00057551975,0.0000728055,0.002836868,0.00012573319,0.0003680126,0.000022700176],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040621747,0.0015145864,0.5862045,0.000017302686,0.00008119552,0.0002621842,0.051615775,0.0469554,0.0005534938,0.000032445925,0.000041367635,0.31231552],"study_design_scores_gemma":[0.00665824,0.0008977189,0.31392455,0.000087943205,0.00016208642,0.00016546168,0.061092723,0.6107671,0.00003843828,0.0060330727,0.000008946207,0.00016371894],"about_ca_topic_score_codex":0.00028524216,"about_ca_topic_score_gemma":0.009234397,"teacher_disagreement_score":0.5638117,"about_ca_system_score_codex":0.0005173789,"about_ca_system_score_gemma":0.0022399146,"threshold_uncertainty_score":0.9649966},"labels":[],"label_agreement":null},{"id":"W2994626447","doi":"10.3138/cjpe.68444","title":"Increasing Cultural Competence in Support of Indigenous-Led Evaluation: A Necessary Step toward Indigenous-Led Evaluation","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Indigenous; Aotearoa; Competence (human resources); Traditional knowledge; Sociology; Political science; Psychology; Gender studies; Social psychology","score_opus":0.23459713410538083,"score_gpt":0.4965004891018339,"score_spread":0.2619033549964531,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2994626447","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9883426,0.0008667771,0.00016476431,0.00081442756,0.0013594069,0.0054914006,0.000019748628,0.000012602982,0.0029282856],"genre_scores_gemma":[0.99554497,0.00002824983,0.0035477236,0.00024389407,0.00017323153,0.00022095816,0.00015115683,0.000024477393,0.00006532084],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98294663,0.004004569,0.0028889873,0.0005613554,0.008903108,0.00069531705],"domain_scores_gemma":[0.9835783,0.0005971664,0.002608703,0.0006444506,0.012018427,0.00055294344],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.07576697,0.00034001734,0.00080697954,0.001982501,0.0002648956,0.00051849446,0.0010683374,0.00024690517,0.00821133],"category_scores_gemma":[0.005116344,0.00028336412,0.0002720531,0.0023534186,0.00016673312,0.0021276455,0.000044467022,0.0005204178,0.0001879124],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014709767,0.00017521658,0.3895294,0.00003430238,0.00008108084,0.0000074580653,0.019461432,0.015890762,0.00049540465,0.000060102433,0.00044166474,0.57367605],"study_design_scores_gemma":[0.0071242787,0.0019528256,0.7230923,0.00028526736,0.00047842457,0.00019704588,0.013789161,0.24381931,0.00034957632,0.003905556,0.004450884,0.0005553263],"about_ca_topic_score_codex":0.0030234598,"about_ca_topic_score_gemma":0.030246148,"teacher_disagreement_score":0.5731208,"about_ca_system_score_codex":0.0022026543,"about_ca_system_score_gemma":0.024563756,"threshold_uncertainty_score":0.99996185},"labels":[],"label_agreement":null},{"id":"W2994755788","doi":"","title":"The Ouranos 2015 Synthesis on Climate Change Knowledge in Quebec: The Journey of a Regional Contribution to an Ensemble of Complementing Climate Change Assessments.","year":2018,"lang":"en","type":"article","venue":"AGU Fall Meeting Abstracts","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Climate change; Geography; Environmental resource management; Regional science; Climatology; Environmental science; Geology","score_opus":0.3072101793707857,"score_gpt":0.49285999496825655,"score_spread":0.18564981559747085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2994755788","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98772573,0.00010426083,0.00001909044,0.004813287,0.00041340842,0.00075166096,0.000036692385,0.000017855607,0.0061180177],"genre_scores_gemma":[0.9985926,0.0001496703,0.00024261455,0.00048055526,0.0003182031,0.00015454135,0.000008966504,0.000014129084,0.000038730595],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99540013,0.0008053463,0.0013444822,0.00038608714,0.0014740042,0.0005899649],"domain_scores_gemma":[0.9935337,0.0034193364,0.0012178143,0.000606784,0.0011022347,0.00012017769],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018927911,0.00019660078,0.0003714213,0.00026665282,0.0005753332,0.00021029852,0.0007750597,0.0000779783,0.000026217936],"category_scores_gemma":[0.0018344515,0.000115493895,0.00010005246,0.00060197595,0.00014701573,0.00051563577,0.00018433477,0.00019319866,0.00014879552],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014069434,0.0017006188,0.53442883,0.00013731344,0.00012692636,0.000008835832,0.030211342,0.0007256016,0.008943661,0.018758211,0.0054398994,0.3981118],"study_design_scores_gemma":[0.0007310993,0.0005182436,0.9679895,0.0009283478,0.000035444402,0.0000029334517,0.007344021,0.007187268,0.004817616,0.00045008614,0.009763918,0.00023151729],"about_ca_topic_score_codex":0.006857295,"about_ca_topic_score_gemma":0.16277413,"teacher_disagreement_score":0.43356067,"about_ca_system_score_codex":0.000108081935,"about_ca_system_score_gemma":0.00011311703,"threshold_uncertainty_score":0.99975616},"labels":[],"label_agreement":null},{"id":"W2994882198","doi":"10.3138/cjpe.67976","title":"Creating New Stories: The Role of Evaluation in Truth and Reconciliation","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Indigenous; Status quo; Commission; Environmental ethics; Sociology; Truth telling; Political science; Natural (archaeology); Public relations; Engineering ethics; Law; Psychology; History; Archaeology","score_opus":0.25760580415152334,"score_gpt":0.4974978039906295,"score_spread":0.23989199983910614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2994882198","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99083614,0.0013029111,0.0000838405,0.0008101741,0.00055178645,0.0012275261,0.0000020435423,0.0000021353396,0.005183435],"genre_scores_gemma":[0.9988111,0.000013432769,0.00089716766,0.0000426826,0.000103117076,0.000024985862,0.000005565466,0.0000051994853,0.0000967511],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9957664,0.00075931865,0.0009447525,0.00016060258,0.0022082129,0.00016071011],"domain_scores_gemma":[0.9956576,0.00061986,0.00092485116,0.00023008691,0.0023923721,0.0001752038],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.027874209,0.00008496038,0.00020505846,0.0004868151,0.00008961497,0.0001879236,0.0002135285,0.00006341657,0.0016667311],"category_scores_gemma":[0.006205806,0.00005768594,0.0000563129,0.000716829,0.00004630179,0.0006852831,0.00000883512,0.00015786405,0.00001797004],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001420644,0.000009271231,0.16499883,0.0000023572745,0.0000087881135,1.3155972e-7,0.0051982547,0.0041885483,0.00008142915,0.0006637444,0.00008685907,0.82474756],"study_design_scores_gemma":[0.0018113762,0.00054554275,0.51075685,0.000105100225,0.00008740577,0.000015183851,0.016732162,0.41414517,0.00027898586,0.043682627,0.01172129,0.00011831416],"about_ca_topic_score_codex":0.0019669363,"about_ca_topic_score_gemma":0.024470696,"teacher_disagreement_score":0.82462925,"about_ca_system_score_codex":0.00041603003,"about_ca_system_score_gemma":0.006260116,"threshold_uncertainty_score":0.9993735},"labels":[],"label_agreement":null},{"id":"W2994909761","doi":"","title":"Indigenous Education Leads' Stories of Policy Enactment: A Sociomaterial Inquiry.","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Educational Administration and Policy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Indigenous; Indigenous education; Mandate; Sociology; Metis; General partnership; Narrative; Public relations; Pedagogy; Public administration; Political science; Law","score_opus":0.09117982866877412,"score_gpt":0.4825227576825535,"score_spread":0.3913429290137794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2994909761","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.967055,0.00022826223,0.00001046379,0.023767,0.0014580004,0.00016076866,0.000037940863,0.0000012644239,0.007281259],"genre_scores_gemma":[0.99239314,0.000034149867,0.00024194321,0.00095663633,0.0017291346,0.0000051909265,0.000028848399,0.000006612456,0.004604356],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99818313,0.00012196957,0.00078274496,0.00013760437,0.00059324555,0.00018129287],"domain_scores_gemma":[0.9973529,0.0003047116,0.0007459581,0.00018297364,0.00096786226,0.0004456144],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009862196,0.000109963294,0.00021703045,0.0011408085,0.00015880294,0.00021198722,0.00026764185,0.00007366722,0.002498652],"category_scores_gemma":[0.0012913789,0.000092773036,0.00007188809,0.0005489874,0.00013985476,0.00054024474,0.000008559235,0.00009127303,0.000086770815],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013363577,0.00033521734,0.32215545,0.00006650817,0.00007886966,0.0000012383433,0.06788456,0.00008521368,0.0017267563,0.54966664,0.019046705,0.038819216],"study_design_scores_gemma":[0.0010036408,0.0011893708,0.70185757,0.000088283115,0.000028389042,0.0003230753,0.017065823,0.000024042196,0.0015087915,0.06632371,0.21025407,0.00033324532],"about_ca_topic_score_codex":0.003082948,"about_ca_topic_score_gemma":0.004416301,"teacher_disagreement_score":0.48334292,"about_ca_system_score_codex":0.0003277607,"about_ca_system_score_gemma":0.06639355,"threshold_uncertainty_score":0.9984132},"labels":[],"label_agreement":null},{"id":"W2994962470","doi":"10.3138/cjpe.67978","title":"White Privilege and the Decolonization Work Needed in Evaluation to Support Indigenous Sovereignty and Self-Determination","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Indigenous; White privilege; Aotearoa; Privilege (computing); Sovereignty; Injustice; Sociology; Colonialism; White (mutation); Economic Justice; Gender studies; Decolonization; Law; Environmental ethics; Political science; Racism; Politics","score_opus":0.1310915805611923,"score_gpt":0.4568472619130539,"score_spread":0.3257556813518616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2994962470","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9914626,0.00018266797,0.000315216,0.0020145143,0.00047128438,0.0039577,0.000002496274,0.000006673958,0.0015868476],"genre_scores_gemma":[0.9974996,0.00001700502,0.0017899034,0.00038568032,0.00006643281,0.0001445218,0.000013495923,0.000009673773,0.000073702584],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99540925,0.0010812597,0.00088797614,0.0002536018,0.0020892033,0.0002786938],"domain_scores_gemma":[0.9962924,0.00036034975,0.0006272521,0.0002469846,0.0021892905,0.00028373013],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.033757873,0.00013029414,0.00025781788,0.0008849495,0.00020150664,0.0005574243,0.0002637154,0.00009552192,0.0013789647],"category_scores_gemma":[0.0022264011,0.0000918598,0.00004635516,0.0012049444,0.00006322687,0.00096501014,0.000026148111,0.0001776806,0.000046898545],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006757222,0.000033416625,0.30775836,0.000006197089,0.000011926319,0.0000012271261,0.012755985,0.0031694958,0.000002894782,0.00036440272,0.00018120969,0.6756473],"study_design_scores_gemma":[0.00411493,0.0006756629,0.819358,0.00006006864,0.00010499905,0.000037616308,0.0028973157,0.1607082,0.000014401012,0.010073731,0.0017928788,0.00016218297],"about_ca_topic_score_codex":0.00019888495,"about_ca_topic_score_gemma":0.012322445,"teacher_disagreement_score":0.67548513,"about_ca_system_score_codex":0.0005412967,"about_ca_system_score_gemma":0.0031051403,"threshold_uncertainty_score":0.9995339},"labels":[],"label_agreement":null},{"id":"W2995189513","doi":"10.3138/cjpe.67977","title":"Nation-to-Nation Evaluation: Governance, Tribal Sovereignty, and Systems Thinking through Culturally Responsive Indigenous Evaluations","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Indigenous; Sovereignty; Transformative learning; Corporate governance; Colonialism; Environmental ethics; Sociology; Harm; Political science; Doctrine; Law; Politics; Management","score_opus":0.2965348623635574,"score_gpt":0.5006583896229647,"score_spread":0.2041235272594073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995189513","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9638072,0.002814789,0.0015419498,0.004953009,0.0042963317,0.008771175,0.00005483246,0.000030014207,0.013730689],"genre_scores_gemma":[0.9948762,0.00004184067,0.0033086927,0.00045599844,0.00041353973,0.00028798156,0.00007263215,0.000022129349,0.000521002],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98732865,0.0018810881,0.0017056535,0.00051832537,0.008100214,0.0004660771],"domain_scores_gemma":[0.98220885,0.00075397384,0.0017274836,0.0004915474,0.014318357,0.000499782],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.034960285,0.00027245004,0.00046783898,0.000810233,0.00066877215,0.0015308344,0.0007049016,0.00018976282,0.0030059223],"category_scores_gemma":[0.008518373,0.00022182046,0.00015302897,0.0017904718,0.00008097034,0.0024136135,0.000040741197,0.0003528431,0.00032319583],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018165636,0.00013711042,0.050341997,0.00003549753,0.00022983224,0.000008393704,0.03415691,0.15024294,0.00021925544,0.02906812,0.006938763,0.7284395],"study_design_scores_gemma":[0.007999031,0.0029275292,0.34720963,0.0006088712,0.000784237,0.00035206694,0.016739797,0.3930645,0.00015580718,0.14566414,0.08340969,0.0010847129],"about_ca_topic_score_codex":0.0010861453,"about_ca_topic_score_gemma":0.011309673,"teacher_disagreement_score":0.7273548,"about_ca_system_score_codex":0.0021142513,"about_ca_system_score_gemma":0.011347497,"threshold_uncertainty_score":0.9998333},"labels":[],"label_agreement":null},{"id":"W2995293564","doi":"","title":"Analyse de l’activité évaluative des experts pour la reconnaissance des acquis de métier au baccalauréat en enseignement professionnel de l’Université de Sherbrooke","year":2019,"lang":"fr","type":"article","venue":"Knowledge UdeS (Institutional Deposit of the University of Sherbrooke)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Humanities; Philosophy","score_opus":0.06518200321871438,"score_gpt":0.31887295608500493,"score_spread":0.25369095286629056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995293564","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8892638,0.0060605854,0.051493686,0.00062409864,0.000388873,0.0004917817,0.000021228421,0.000025072472,0.051630836],"genre_scores_gemma":[0.92541593,0.0015578127,0.022791252,0.00008387942,0.0000812163,0.000002839903,0.0000045195425,0.000018686784,0.05004389],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.995168,0.0019639758,0.0005391724,0.000583031,0.0009945058,0.00075134466],"domain_scores_gemma":[0.9969771,0.0009850257,0.0003731909,0.00062204554,0.0006750244,0.0003676018],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0038479608,0.00038679843,0.0005651346,0.0003339221,0.0014626288,0.000056594257,0.0014600133,0.0003683861,0.0028542103],"category_scores_gemma":[0.00045210772,0.00035334218,0.00054354884,0.00073071045,0.0018981654,0.000900288,0.0008093579,0.00035996686,0.00019329212],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00095089164,0.0012887472,0.5567346,0.0017839803,0.00057930767,0.000041133047,0.1644416,0.08995477,0.13566735,0.004700567,0.0056291353,0.03822789],"study_design_scores_gemma":[0.0027230957,0.00025189362,0.70112914,0.006654429,0.00048808486,0.00014304512,0.022891983,0.12989525,0.115633175,0.004051815,0.015614137,0.00052393094],"about_ca_topic_score_codex":0.0026164257,"about_ca_topic_score_gemma":0.026026398,"teacher_disagreement_score":0.14439453,"about_ca_system_score_codex":0.014779681,"about_ca_system_score_gemma":0.0035553048,"threshold_uncertainty_score":0.9998919},"labels":[],"label_agreement":null},{"id":"W2995471644","doi":"10.3138/cjpe.53365","title":"“Deliverology” and Evaluation: A Tale of Two Worlds","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université Laval","funders":"","keywords":"Corporate governance; Politics; Context (archaeology); Value (mathematics); Public value; Public management; Critical reflection; Political science; Public relations; Reflection (computer programming); Complement (music); Public administration; Sociology; Economics; Management; Law; Computer science; History","score_opus":0.2895418597302168,"score_gpt":0.5351081862029722,"score_spread":0.2455663264727554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995471644","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9895191,0.0010354174,0.00014846357,0.0014547864,0.00075663876,0.0011845322,0.0000047501862,0.0000033007245,0.0058929822],"genre_scores_gemma":[0.9972029,0.00001129433,0.0022805808,0.00014774688,0.00009443718,0.000031638752,0.0000071015334,0.000006363542,0.00021797554],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99534523,0.0007313894,0.0009349275,0.0001996878,0.0025839752,0.0002047985],"domain_scores_gemma":[0.99351025,0.00027307376,0.0008720677,0.00029221518,0.0047485894,0.00030382507],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.023854697,0.00010314461,0.00028066934,0.0007245962,0.000090406174,0.0001506062,0.0003197215,0.000065017986,0.008132076],"category_scores_gemma":[0.001372368,0.000081268554,0.00009321247,0.00066197314,0.00012354899,0.00058929046,0.00001583324,0.00015886106,0.00009447731],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022555674,0.000029260014,0.17141713,0.000005754183,0.000033868277,0.0000012258374,0.0010388236,0.004560333,0.0001661509,0.0007125015,0.0011614258,0.82085097],"study_design_scores_gemma":[0.005691311,0.00178551,0.47055805,0.00011063158,0.0003282061,0.000117759395,0.0022925683,0.4569342,0.00029920175,0.03400551,0.027616452,0.00026061578],"about_ca_topic_score_codex":0.00032130643,"about_ca_topic_score_gemma":0.008731012,"teacher_disagreement_score":0.8205904,"about_ca_system_score_codex":0.00020468554,"about_ca_system_score_gemma":0.004307778,"threshold_uncertainty_score":0.9927746},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":true,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W2995480421","doi":"10.3138/cjpe.43685","title":"Self-Evaluation Tool for Action in Partnership: Translation and Cultural Adaptation of the Original Quebec French Tool to Canadian English","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Equivalence (formal languages); Adaptation (eye); General partnership; Action (physics); Process (computing); Computer science; Linguistics; Sociology; Knowledge management; Psychology; Political science; Law","score_opus":0.3247910086417194,"score_gpt":0.4861257559367303,"score_spread":0.1613347472950109,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995480421","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99184716,0.00020975413,0.00046648923,0.0020207756,0.0010143947,0.00396321,0.000013270612,0.0000051554807,0.00045978703],"genre_scores_gemma":[0.9952596,0.0000056402573,0.0041436227,0.00011607488,0.00014601038,0.00018504281,0.000029917728,0.000008219616,0.00010591393],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961118,0.0006235496,0.00093596533,0.00023584189,0.0018161137,0.0002766961],"domain_scores_gemma":[0.9938768,0.00024706373,0.0005764444,0.00022673557,0.0048184143,0.0002545494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014080497,0.00013215614,0.0002264427,0.0007713825,0.0001637696,0.0003021826,0.0002707685,0.00011421181,0.00044574784],"category_scores_gemma":[0.0025520509,0.00009753017,0.00010427619,0.00095357414,0.00003802684,0.0011854358,0.0000047916647,0.00016796445,0.000010712111],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033721797,0.000023946192,0.069045484,0.000019958656,0.000019300487,1.8386308e-7,0.013011036,0.021486478,0.00006667981,0.00040034478,0.00060865463,0.89528424],"study_design_scores_gemma":[0.0023986346,0.00049680076,0.4117397,0.000105254025,0.00015256218,0.000007381887,0.0061705755,0.47389725,0.00017200441,0.0017891956,0.10285396,0.0002166769],"about_ca_topic_score_codex":0.07168238,"about_ca_topic_score_gemma":0.9481723,"teacher_disagreement_score":0.8950675,"about_ca_system_score_codex":0.0013684297,"about_ca_system_score_gemma":0.010800431,"threshold_uncertainty_score":0.9948074},"labels":[],"label_agreement":null},{"id":"W2995564338","doi":"10.3138/cjpe.44172","title":"Dramatizing Learning, Performing Ourselves: Stories of Theatre-Based Evaluation in Vancouver's Downtown Eastside","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of British Columbia Hospital","funders":"","keywords":"Downtown; Experiential learning; Citizen journalism; Process (computing); Sociology; Work (physics); Psychology; Visual arts; Pedagogy; Computer science; Art; History; Engineering; World Wide Web; Archaeology","score_opus":0.18181349197951518,"score_gpt":0.4904914886895171,"score_spread":0.3086779967100019,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995564338","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9855655,0.00046379643,0.00046738802,0.00044207808,0.0015601135,0.0016500336,0.0000030058397,0.000008375837,0.009839722],"genre_scores_gemma":[0.9972687,0.000004992527,0.0023384225,0.000053410186,0.00010603935,0.000061625535,0.000013721236,0.00001443405,0.00013869365],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99232984,0.0013163689,0.0015123226,0.00027466088,0.004205612,0.0003612012],"domain_scores_gemma":[0.9930707,0.0005055747,0.0015343054,0.00034268826,0.0042610457,0.00028565133],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.036004562,0.00017995702,0.0004281971,0.0015251042,0.00016065875,0.000250658,0.00046974467,0.00012006815,0.0050746603],"category_scores_gemma":[0.0036732862,0.0001455251,0.00017616311,0.0012183039,0.00008591976,0.0011396545,0.000012985259,0.00040299603,0.00005305765],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003095126,0.000038587837,0.2787705,0.000014416648,0.000016180436,0.0000011836049,0.003197883,0.13831022,0.0001033102,0.00006762804,0.0002698348,0.5791793],"study_design_scores_gemma":[0.0031385398,0.0011170144,0.14502928,0.00037817936,0.00013676978,0.000009295919,0.017680077,0.8150024,0.0004770867,0.0024769932,0.014298973,0.00025541012],"about_ca_topic_score_codex":0.0015546337,"about_ca_topic_score_gemma":0.08052174,"teacher_disagreement_score":0.6766922,"about_ca_system_score_codex":0.0010329253,"about_ca_system_score_gemma":0.010339598,"threshold_uncertainty_score":0.9958348},"labels":[],"label_agreement":null},{"id":"W2995590052","doi":"10.3138/cjpe.67854","title":"Anne Vo and Christina A. Christie (Eds.). (2015). <i>Evaluation Use and Decision Making in Society: A Tribute to Marvin C. Alkin.</i>","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Tribute; Sociology; Psychology; Art history; Art","score_opus":0.19169266228507312,"score_gpt":0.4845022894400607,"score_spread":0.2928096271549876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995590052","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9892122,0.002665345,0.0019279723,0.0029177377,0.0006654882,0.0023857716,0.000019148652,0.000007739707,0.00019860158],"genre_scores_gemma":[0.98328537,0.000090285335,0.015734907,0.0005734625,0.0001137198,0.0000773916,0.000019106594,0.000016142396,0.00008961911],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9945235,0.000560677,0.0011996992,0.00044248372,0.0028663215,0.00040728177],"domain_scores_gemma":[0.99475086,0.00075429364,0.00068533566,0.00035204442,0.0029269296,0.00053055707],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02814925,0.00020311175,0.0003983124,0.00088186574,0.00018976748,0.0010077455,0.0003078034,0.00013434829,0.0011356416],"category_scores_gemma":[0.004693377,0.0001713324,0.00009761785,0.0011246265,0.00007407059,0.0013687981,0.00004709563,0.00027666576,0.00005959097],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006330317,0.000026382186,0.100490265,0.000007847206,0.000014411098,0.0000036410233,0.0010919342,0.0024972316,0.00006644265,0.0000318404,0.01052303,0.8851837],"study_design_scores_gemma":[0.0029498588,0.0007857153,0.5986203,0.00035775735,0.00010274767,0.00007849902,0.0011042304,0.32843113,0.000025038926,0.0072170557,0.06004484,0.000282835],"about_ca_topic_score_codex":0.00060719886,"about_ca_topic_score_gemma":0.020773504,"teacher_disagreement_score":0.88490087,"about_ca_system_score_codex":0.00056851015,"about_ca_system_score_gemma":0.002841292,"threshold_uncertainty_score":0.99977744},"labels":[],"label_agreement":null},{"id":"W2995666448","doi":"10.3138/cjpe.67892","title":"Scott G. Chaplowe and J. Bradley Cousins. (2016). <i>Monitoring and Evaluation Training: A Systematic Approach.</i>","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"SAGE; Gerontology; Psychology; Training (meteorology); Sociology; Geography; Medicine","score_opus":0.3839926982165331,"score_gpt":0.4813167098258325,"score_spread":0.09732401160929943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995666448","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9872955,0.0038791357,0.00039532466,0.0006145721,0.0011494705,0.0036090838,0.0000034999186,0.000011678131,0.00304175],"genre_scores_gemma":[0.99643505,0.000045865454,0.0030065016,0.000069320624,0.00017468687,0.00012744864,0.0000060139446,0.0000151581735,0.00011996411],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9939752,0.0009991007,0.0011402321,0.00033384436,0.0032324297,0.00031918343],"domain_scores_gemma":[0.9950581,0.00035922322,0.0009910926,0.00032742246,0.0027300133,0.0005341174],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.034183476,0.00018047621,0.00046177502,0.00076517725,0.00022782579,0.00078894995,0.00029081304,0.00010737555,0.000334229],"category_scores_gemma":[0.0024638395,0.0001371327,0.00008021481,0.00055876083,0.00010242432,0.0010427341,0.000018200728,0.000220966,0.00004069405],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003799381,0.00007759279,0.061807334,0.00078916765,0.00013167995,0.0000040882956,0.018564316,0.0032491835,0.0003438074,0.000598879,0.00048797022,0.913908],"study_design_scores_gemma":[0.0050849053,0.0014172853,0.1693644,0.0031238045,0.0008223418,0.00050674344,0.0251038,0.78334564,0.000084909705,0.007182245,0.0033632661,0.00060069404],"about_ca_topic_score_codex":0.0001311894,"about_ca_topic_score_gemma":0.00054337806,"teacher_disagreement_score":0.9133073,"about_ca_system_score_codex":0.0003403353,"about_ca_system_score_gemma":0.0043828106,"threshold_uncertainty_score":0.99451137},"labels":[],"label_agreement":null},{"id":"W2995777958","doi":"10.3138/cjpe.67979","title":"Introduction to Articles Prepared by CES Calgary 2018 Keynote Panel Members on Reconciliation and Culturally Responsive Evaluation—Rhetoric or Reality?","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Rhetoric; Sociology; Psychology; Political science; Linguistics; Philosophy","score_opus":0.298192845152364,"score_gpt":0.482247239067281,"score_spread":0.184054393914917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995777958","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9761372,0.00023500859,0.00017909451,0.017889727,0.0017230528,0.0027318601,0.000017725419,0.0000145467975,0.0010717621],"genre_scores_gemma":[0.9952994,0.000027499595,0.0016232658,0.0005583528,0.0004838044,0.0001436715,0.00005880754,0.000013844937,0.001791329],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.993245,0.0015151884,0.0011384514,0.00047723515,0.003310933,0.00031319665],"domain_scores_gemma":[0.9927671,0.00047081342,0.00086730486,0.00042481304,0.0049016173,0.0005683263],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.022021532,0.00018793074,0.00030826274,0.000699971,0.00025404838,0.0005248135,0.00030064216,0.0001167867,0.004492309],"category_scores_gemma":[0.010061924,0.00013409636,0.00008185433,0.0010666715,0.000065301836,0.0011661878,0.00001621337,0.00020015302,0.00022687107],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006380213,0.000055873392,0.0048941756,0.000008929792,0.000056648598,0.0000015823399,0.0046376507,0.009062464,0.0011347575,0.000116311705,0.11601484,0.86337876],"study_design_scores_gemma":[0.0054957643,0.0073133586,0.20588025,0.00022965304,0.0004767996,0.00012550698,0.010398343,0.29143617,0.0023208032,0.00691701,0.46857592,0.0008304217],"about_ca_topic_score_codex":0.0007140054,"about_ca_topic_score_gemma":0.014762315,"teacher_disagreement_score":0.86254835,"about_ca_system_score_codex":0.001257533,"about_ca_system_score_gemma":0.0036308572,"threshold_uncertainty_score":0.99827677},"labels":[],"label_agreement":null},{"id":"W2995932983","doi":"10.3138/cjpe.56989","title":"Comparison of Canadian and American Graduate Evaluation Education Programs","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Professionalization; Graduate education; Graduate students; Population; Political science; Medical education; Program evaluation; Higher education; Library science; Sociology; Public administration; Medicine; Demography; Computer science","score_opus":0.5628449880548297,"score_gpt":0.5884740088916572,"score_spread":0.0256290208368275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995932983","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98841536,0.00045183432,0.000043712353,0.0024320518,0.0010606807,0.0022928086,0.0000047240637,0.000005103905,0.0052936957],"genre_scores_gemma":[0.997087,0.000016307999,0.002420412,0.00010174786,0.00010004623,0.000090777416,0.000048408336,0.0000122604615,0.00012305652],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99422926,0.00079220283,0.0012606959,0.00027178004,0.0031124535,0.00033362122],"domain_scores_gemma":[0.99010825,0.00013214955,0.0015076274,0.00036459192,0.0070752725,0.00081212196],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01694237,0.00015530927,0.0004243647,0.0026569616,0.00015652191,0.00033460572,0.00038861015,0.00006462626,0.0009349904],"category_scores_gemma":[0.0017376688,0.0001303522,0.0001048131,0.0022188833,0.00018314627,0.0006522115,0.0000100976895,0.00022998768,0.00006905767],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007503712,0.000046015073,0.30157816,0.0000054795,0.000016930211,1.593056e-7,0.0014368043,0.00056732184,0.000024335699,0.0001776186,0.001020863,0.6951188],"study_design_scores_gemma":[0.0009514865,0.0015771285,0.73783344,0.00012380326,0.00021716475,0.000026198019,0.012098402,0.19784367,0.00012437576,0.0042591714,0.044700127,0.0002450168],"about_ca_topic_score_codex":0.08616996,"about_ca_topic_score_gemma":0.6335765,"teacher_disagreement_score":0.6948738,"about_ca_system_score_codex":0.00063683133,"about_ca_system_score_gemma":0.020397993,"threshold_uncertainty_score":0.9999783},"labels":[],"label_agreement":null},{"id":"W2995943763","doi":"10.3138/cjpe.53185","title":"Applying the Collaborative Approaches to Evaluation (CAE) Principles in an Educational Evaluation: Reflections from the Field","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Reflection (computer programming); Context (archaeology); Field (mathematics); Engineering ethics; Pedagogy; Sociology; Computer science; Engineering","score_opus":0.7739294717178385,"score_gpt":0.5731835285755595,"score_spread":0.200745943142279,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995943763","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9156168,0.00096763956,0.0005060228,0.056760304,0.002129241,0.01417696,0.000018075996,0.000008083501,0.009816851],"genre_scores_gemma":[0.99106425,0.00000535505,0.0027874857,0.0014363214,0.0005307214,0.003986441,0.00006611864,0.000012346681,0.00011095253],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9899672,0.003352681,0.0011689557,0.0004000222,0.004810856,0.00030023],"domain_scores_gemma":[0.9903373,0.002336147,0.00079622306,0.0007047181,0.0055249343,0.00030065625],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04425557,0.00017611706,0.0002406613,0.0005537582,0.00054104027,0.000923956,0.0009380155,0.000106062515,0.005897981],"category_scores_gemma":[0.009477187,0.00010670657,0.00009865348,0.0022950734,0.00007304966,0.001075723,0.000028834682,0.00038581208,0.00015427737],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047168513,0.00008829075,0.110185996,0.0000016433381,0.000040411483,2.3552985e-7,0.009364973,0.12333262,0.00005904006,0.0027204214,0.0027823832,0.7513768],"study_design_scores_gemma":[0.0012793286,0.0005991411,0.43605182,0.00007843647,0.00019636832,0.0000075983285,0.019700248,0.42519706,0.000096506075,0.031145396,0.085421585,0.00022652697],"about_ca_topic_score_codex":0.0012480197,"about_ca_topic_score_gemma":0.18605772,"teacher_disagreement_score":0.7511503,"about_ca_system_score_codex":0.0010866381,"about_ca_system_score_gemma":0.015527327,"threshold_uncertainty_score":0.9988664},"labels":[],"label_agreement":null},{"id":"W2996036743","doi":"10.7202/1066099ar","title":"L’agentivité ou comment naviguer parmi les spécificités interculturelles et les contraintes de performance dans l’évaluation auprès des familles racisées en protection de la jeunesse","year":2019,"lang":"fr","type":"article","venue":"Nouvelles pratiques sociales","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal; Université du Québec en Outaouais","funders":"","keywords":"Political science; Humanities; Art","score_opus":0.17984428581526182,"score_gpt":0.44096885136108604,"score_spread":0.2611245655458242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996036743","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94413084,0.0038127424,0.02739825,0.013990433,0.00081397936,0.0017251566,0.000096536256,0.0001820305,0.007850039],"genre_scores_gemma":[0.9723417,0.010165624,0.007866118,0.00074819475,0.00037725404,0.00036009648,0.00008130843,0.00007506166,0.007984619],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.98814285,0.0071648024,0.001362082,0.00087045075,0.0015730251,0.0008868034],"domain_scores_gemma":[0.9941789,0.0032995571,0.0008584922,0.0005227939,0.00092837884,0.00021186488],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.013682884,0.00069249136,0.0007603794,0.00030304265,0.0012796539,0.0010351894,0.00080476684,0.0009801474,0.0013875004],"category_scores_gemma":[0.0015564016,0.0006086912,0.0003856999,0.0005779838,0.0014230508,0.0014388717,0.00025114568,0.0011488248,0.00030009347],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033204618,0.0011472098,0.18472707,0.0006533797,0.0003516766,0.000011448246,0.32727194,0.0040917145,0.025030842,0.1363091,0.0026213464,0.31745222],"study_design_scores_gemma":[0.002494717,0.0011628749,0.25049946,0.0022662093,0.00031055883,0.00008697014,0.4681573,0.08828481,0.03409814,0.017475007,0.13354726,0.0016167008],"about_ca_topic_score_codex":0.0029102424,"about_ca_topic_score_gemma":0.004480608,"teacher_disagreement_score":0.3158355,"about_ca_system_score_codex":0.001113944,"about_ca_system_score_gemma":0.0035932963,"threshold_uncertainty_score":0.9996365},"labels":[],"label_agreement":null},{"id":"W2996403399","doi":"10.29173/cjnser.2019v10n2a287","title":"Caractéristiques organisationnelles qui influencent le renforcement des capacités en évaluation chez les organismes communautaires du Québec : une recension des écrits","year":2019,"lang":"en","type":"article","venue":"Canadian journal of nonprofit and social economy research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa; École Nationale d'Administration Publique","funders":"","keywords":"Valuation (finance); Sociology; Humanities; Business; Philosophy","score_opus":0.19655548514452198,"score_gpt":0.43047281264361437,"score_spread":0.2339173274990924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996403399","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9836898,0.0006148883,0.00009631178,0.011319898,0.00009717434,0.0002884626,0.00000526486,0.0000053131507,0.003882881],"genre_scores_gemma":[0.9984898,0.00027881944,0.00036445557,0.0001537117,0.0001859573,0.0000072627518,0.000006055746,0.000013751615,0.000500214],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99691194,0.00097513193,0.0007619896,0.00021232499,0.000757147,0.00038144525],"domain_scores_gemma":[0.99574584,0.0008650205,0.00030309692,0.00018193776,0.0025796322,0.00032448888],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011011039,0.00013645347,0.00031882778,0.0005396083,0.0016895485,0.0005538933,0.000470814,0.0001272028,0.0018609738],"category_scores_gemma":[0.0011059028,0.000113304355,0.00007539105,0.00044335096,0.0007924375,0.0008785737,0.00006354476,0.00042346286,0.0000871051],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048865,0.0000241998,0.8069178,0.00005391957,0.000048595288,0.000005555387,0.08928829,0.0001386315,0.0010295665,0.0037965018,0.002320715,0.09632736],"study_design_scores_gemma":[0.00099438,0.00046706034,0.7320487,0.00015715424,0.000017847606,0.00003577944,0.20204559,0.00095464475,0.002000498,0.04019337,0.020825438,0.00025955928],"about_ca_topic_score_codex":0.18849258,"about_ca_topic_score_gemma":0.5030461,"teacher_disagreement_score":0.31455353,"about_ca_system_score_codex":0.00089919724,"about_ca_system_score_gemma":0.010549378,"threshold_uncertainty_score":0.9996101},"labels":[],"label_agreement":null},{"id":"W2996413109","doi":"10.9734/bjesbs/2016/24215","title":"The Ontario (Canada) Ministry of Education’s A Solid Foundation Document: An Extended Commentary","year":2016,"lang":"en","type":"article","venue":"British Journal of Education Society & Behavioural Science","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Brock University","funders":"","keywords":"Foundation (evidence); Christian ministry; Library science; Political science; History; Archaeology; Computer science; Law","score_opus":0.07504165500372056,"score_gpt":0.43985818379561104,"score_spread":0.36481652879189047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996413109","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97953606,0.00016701195,0.00034389773,0.015673768,0.0036592197,0.00017280177,0.0000067128844,0.0000037131692,0.0004368367],"genre_scores_gemma":[0.99158734,0.00015382218,0.0024933855,0.0016643354,0.0001766206,0.000013546036,0.000004938205,0.0000054311336,0.0039005885],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9947341,0.00017924569,0.0011974449,0.0002789444,0.003331014,0.00027921904],"domain_scores_gemma":[0.9944245,0.00034855408,0.0014294086,0.00039339685,0.003116398,0.00028770574],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0065113595,0.00011471977,0.00020117598,0.00007720128,0.0010374356,0.00071614876,0.0014251511,0.000041111547,0.0013002963],"category_scores_gemma":[0.00052185013,0.000075754724,0.00016469839,0.000663046,0.00064601045,0.0026103146,0.00008387039,0.00019774181,0.0000055799155],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018127737,0.00048205396,0.10758175,0.0000020842085,0.000012264922,6.761533e-7,0.0024816075,0.000004746728,0.002611381,0.00035534866,0.10043268,0.7860173],"study_design_scores_gemma":[0.0004175629,0.00017811079,0.9331925,0.00016330894,0.000033578108,0.00028016063,0.020476177,0.000025846346,0.0015704004,0.0048679435,0.038627896,0.00016653506],"about_ca_topic_score_codex":0.12510295,"about_ca_topic_score_gemma":0.3720264,"teacher_disagreement_score":0.8256107,"about_ca_system_score_codex":0.0015756012,"about_ca_system_score_gemma":0.024021104,"threshold_uncertainty_score":0.9996126},"labels":[],"label_agreement":null},{"id":"W2996648146","doi":"","title":"Redefining and developing professional competencies for early childhood education and care","year":2019,"lang":"en","type":"article","venue":"Institutional Repository of the University of Granada (University of Granada)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Reflexivity; Early childhood education; Professional development; Diversity (politics); Perspective (graphical); Function (biology); Pedagogy; Sociology; Medical education; Psychology; Medicine; Social science","score_opus":0.03368258615867025,"score_gpt":0.2788132370359867,"score_spread":0.24513065087731645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996648146","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9869595,0.00019138875,0.0007047281,0.0007978036,0.0004367744,0.00026447457,0.000026832324,0.0000046142563,0.010613864],"genre_scores_gemma":[0.99343336,0.000016464346,0.005057194,0.000023174702,0.000007854175,4.88618e-8,0.0000054034654,0.0000019151216,0.0014545934],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985418,0.00007699711,0.00016857666,0.00021131626,0.0009138541,0.00008745964],"domain_scores_gemma":[0.99852484,0.00021174384,0.00036085714,0.0001966089,0.0006535246,0.00005240336],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0003652729,0.00007998358,0.00021211931,0.00016454002,0.002697252,0.000009928293,0.00040460317,0.000058963662,0.000025305815],"category_scores_gemma":[0.000058373003,0.00007605718,0.00008840144,0.00021982501,0.0013274638,0.0003585768,0.00015868281,0.00007769731,5.910229e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00079541607,0.00030479298,0.6249219,0.00063063914,0.00033424943,0.0000070611977,0.06381264,0.0014749011,0.007885695,0.25530544,0.0021992822,0.042327937],"study_design_scores_gemma":[0.00095665443,0.00008854146,0.94188726,0.0002789157,0.000053984208,0.000012106373,0.04017104,0.00046796838,0.00026421275,0.0031653608,0.012530745,0.00012319416],"about_ca_topic_score_codex":0.0015287343,"about_ca_topic_score_gemma":0.0011654524,"teacher_disagreement_score":0.31696534,"about_ca_system_score_codex":0.00009187706,"about_ca_system_score_gemma":0.002013936,"threshold_uncertainty_score":0.9986011},"labels":[],"label_agreement":null},{"id":"W2996731041","doi":"10.3138/cjpe.68004","title":"Revisiting Contribution Analysis","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Operationalization; Set (abstract data type); Epistemology; Positive economics; Causal analysis; Narrative; Key (lock); Sociology; Economics; Computer science; Econometrics; Philosophy","score_opus":0.27443773986693065,"score_gpt":0.5383881020311411,"score_spread":0.2639503621642104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996731041","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9866833,0.00046629415,0.0037096005,0.002203968,0.0007378972,0.00083728903,0.0000056753033,0.0000071678496,0.005348801],"genre_scores_gemma":[0.9981985,0.0000044282547,0.0012129195,0.0001518297,0.00016783855,0.000013104472,0.00002285508,0.0000041001513,0.00022441258],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99591315,0.00055921596,0.0009378265,0.00017066041,0.0021922209,0.00022693958],"domain_scores_gemma":[0.99318534,0.00025444053,0.0009064205,0.00028257983,0.0050380845,0.0003331445],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.023719734,0.00008365711,0.00029382145,0.0012265887,0.00012999315,0.00043305822,0.00033473456,0.00006114939,0.009356517],"category_scores_gemma":[0.003447909,0.000063875035,0.0002472199,0.0021739725,0.0000301729,0.00063461316,0.0000072127737,0.0001533913,0.0003742027],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007729902,0.000008769211,0.39414802,0.0000016082862,0.00011861573,0.0000017811099,0.00023417248,0.009463499,0.000045570356,0.0009116623,0.00039593328,0.59466267],"study_design_scores_gemma":[0.0009944829,0.00027390235,0.6328114,0.000035177458,0.0006561247,0.000016848502,0.00080946204,0.29135343,0.00008634327,0.0047493842,0.0680642,0.00014919335],"about_ca_topic_score_codex":0.00022371278,"about_ca_topic_score_gemma":0.0037138762,"teacher_disagreement_score":0.5945134,"about_ca_system_score_codex":0.00038281828,"about_ca_system_score_gemma":0.0026944184,"threshold_uncertainty_score":0.9915491},"labels":[],"label_agreement":null},{"id":"W2996758909","doi":"","title":"Collaborative practitioner inquiry: Making a difference to urban schools in Leeds","year":2016,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Education and Early Childhood Development","funders":"","keywords":"Sociology; Pedagogy; Medical education; Mathematics education; Psychology; Medicine","score_opus":0.21103133366819865,"score_gpt":0.5197335258895731,"score_spread":0.30870219222137446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996758909","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85799396,0.000023276732,0.05143217,0.036634285,0.0005617305,0.00056840276,0.000011867513,0.00005230672,0.052722014],"genre_scores_gemma":[0.9820401,0.0000087611415,0.0028474964,0.002265567,0.00008109488,0.00007474137,6.2562845e-7,0.0000047377694,0.01267684],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9975886,0.00023305048,0.00045050157,0.00034881476,0.0011736011,0.00020548358],"domain_scores_gemma":[0.9982023,0.00068428315,0.000138019,0.00036322113,0.0005186202,0.0000935592],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0022828279,0.000100084806,0.00016817394,0.00039144693,0.00008103972,0.00023255477,0.00033446075,0.000045962377,0.0039203167],"category_scores_gemma":[0.0022121847,0.00005122323,0.000025010475,0.0014928442,0.000035537934,0.0005915872,0.00010149456,0.000081235085,0.0025902893],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015860822,0.00016571094,0.6017157,0.000002237806,0.000014491964,0.0000065481117,0.008460368,0.000106969244,0.010300226,0.05641648,0.07270865,0.24994402],"study_design_scores_gemma":[0.0010836598,0.00022038455,0.8051758,0.00013469337,0.0000038312637,0.0000023578814,0.010677265,0.00074712053,0.002020141,0.01357448,0.16604465,0.00031561236],"about_ca_topic_score_codex":0.000009939179,"about_ca_topic_score_gemma":0.00044828388,"teacher_disagreement_score":0.24962841,"about_ca_system_score_codex":0.00013116056,"about_ca_system_score_gemma":0.00031455388,"threshold_uncertainty_score":0.9981863},"labels":[],"label_agreement":null},{"id":"W2996900790","doi":"10.18296/em.0044","title":"Evaluation for the Anthropocene: Global environmental perspectives","year":2019,"lang":"en","type":"article","venue":"Evaluation Matters—He Take Tō Te Aromatawai","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Anthropocene; Environmental ethics; Geography; Environmental resource management; Environmental planning; History; Environmental science; Philosophy","score_opus":0.13124727385335144,"score_gpt":0.4716830494959294,"score_spread":0.34043577564257793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996900790","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89809215,0.0022185282,0.008188358,0.06894703,0.0032281552,0.008373416,0.00035089283,0.00013293946,0.010468534],"genre_scores_gemma":[0.99422675,0.00004751823,0.0007315203,0.0029909485,0.00025653036,0.00048942416,0.00014553679,0.000025557096,0.0010862042],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98873466,0.0011671203,0.000944387,0.00091186754,0.007805651,0.00043629418],"domain_scores_gemma":[0.99575835,0.0012732727,0.0006407372,0.0013234393,0.00089163973,0.00011256261],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.02534334,0.00032039557,0.00034023216,0.00016920482,0.0005966649,0.0004962052,0.0009460956,0.000108627944,0.048048723],"category_scores_gemma":[0.0011256981,0.00021552245,0.00025410502,0.0005637372,0.00021090684,0.0010950366,0.00013848006,0.00014904371,0.0063293176],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025209968,0.0005718141,0.09310652,0.000024936557,0.00049481046,5.7475677e-7,0.00654674,0.029906495,0.0025722787,0.0030219627,0.24136142,0.62214035],"study_design_scores_gemma":[0.0031916355,0.00022423755,0.36522812,0.000021055002,0.0004322637,0.000012794256,0.020815207,0.5571882,0.00027293153,0.016364371,0.035868697,0.0003804988],"about_ca_topic_score_codex":0.000027647631,"about_ca_topic_score_gemma":0.0000615924,"teacher_disagreement_score":0.62175983,"about_ca_system_score_codex":0.0009005185,"about_ca_system_score_gemma":0.00057905685,"threshold_uncertainty_score":0.9944444},"labels":[],"label_agreement":null},{"id":"W2996945182","doi":"10.56645/jmde.v15i33.609","title":"Big Shoes to Fill: An Evaluation Journey in the Footsteps of Daniel L. Stufflebeam","year":2019,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University; Laurentian University","funders":"","keywords":"Context (archaeology); Relevance (law); Foundation (evidence); Intervention (counseling); Program evaluation; Evaluation methods; Sociology; Engineering ethics; Psychology; Engineering; History; Political science; Archaeology; Law","score_opus":0.3461999936431824,"score_gpt":0.5442462073245252,"score_spread":0.19804621368134284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996945182","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.987825,0.00014714766,0.00087588996,0.005641827,0.0014034376,0.001475259,0.0000073366864,0.0000040719638,0.0026200463],"genre_scores_gemma":[0.997468,0.00002209572,0.0017057712,0.0002255411,0.0002815925,0.000034878783,0.000014403819,0.000012595932,0.000235154],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.98433954,0.0033840016,0.0022643034,0.00035931705,0.00940001,0.00025286016],"domain_scores_gemma":[0.9910341,0.0010418227,0.0017282248,0.0007794129,0.005255705,0.00016076221],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.083693266,0.0001906544,0.00045942108,0.0010631362,0.00013960527,0.00017198309,0.0011411224,0.00010242072,0.0012769642],"category_scores_gemma":[0.005191211,0.00011221919,0.00017553942,0.0016512079,0.000043203363,0.0013220574,0.0001218168,0.000333397,0.000113705915],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00088125415,0.0013894276,0.19545482,0.000029802668,0.00006514984,0.0000040106574,0.05311293,0.38796318,0.017388893,0.00029376007,0.0070519913,0.33636478],"study_design_scores_gemma":[0.002722431,0.0018133548,0.60826784,0.00014222843,0.000106861466,0.00003266642,0.025462355,0.35343394,0.00079390244,0.0060657975,0.0009931654,0.00016547822],"about_ca_topic_score_codex":0.000012910015,"about_ca_topic_score_gemma":0.00021621844,"teacher_disagreement_score":0.412813,"about_ca_system_score_codex":0.000289168,"about_ca_system_score_gemma":0.0016128757,"threshold_uncertainty_score":0.999636},"labels":[],"label_agreement":null},{"id":"W2997210638","doi":"10.18296/10.18296/em.0045","title":"Evaluation for the Anthropocene: Sustainability","year":2019,"lang":"en","type":"article","venue":"Evaluation Matters—He Take Tō Te Aromatawai","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Anthropocene; Sustainability; Environmental ethics; Geography; Environmental resource management; Earth science; Geology; Environmental science; Philosophy; Ecology; Biology","score_opus":0.1718711270403162,"score_gpt":0.5075115200045145,"score_spread":0.3356403929641983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997210638","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7251513,0.00082819094,0.020022333,0.2239525,0.0049459063,0.016516143,0.00010984476,0.00021322897,0.008260554],"genre_scores_gemma":[0.9900052,0.000014874853,0.000586456,0.005655325,0.0002475349,0.0010126365,0.0001252475,0.00003398357,0.002318739],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9864376,0.0019015264,0.0013424499,0.00097493303,0.008801852,0.00054160436],"domain_scores_gemma":[0.987066,0.0034336497,0.00078922324,0.0020390223,0.0065475507,0.00012460673],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.066886164,0.00032585821,0.0004099902,0.00032078588,0.0006815544,0.0006251174,0.0011567889,0.00012912978,0.035683613],"category_scores_gemma":[0.006321754,0.00021122028,0.00027299087,0.0009915048,0.00018929153,0.0012518629,0.00015245934,0.00020809771,0.0033475447],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016123627,0.00024994678,0.039988533,0.00006297544,0.000192992,2.948709e-7,0.0025383611,0.033083674,0.0005400509,0.0022388084,0.27137604,0.64956707],"study_design_scores_gemma":[0.0025639276,0.00017956883,0.17015041,0.000019511233,0.00035059443,0.0000050325925,0.0054455227,0.6666867,0.00036770472,0.077715546,0.07619385,0.0003216415],"about_ca_topic_score_codex":0.000058251233,"about_ca_topic_score_gemma":0.000113780196,"teacher_disagreement_score":0.64924544,"about_ca_system_score_codex":0.00080273254,"about_ca_system_score_gemma":0.0017714982,"threshold_uncertainty_score":0.9974285},"labels":[],"label_agreement":null},{"id":"W2997982357","doi":"10.20533/ijibs.2046.3626.2019.0036","title":"Special Education Funding in Nova Scotia, Canada: A Scoping Review of the Literature","year":2019,"lang":"en","type":"review","venue":"International Journal of Innovative Business Strategies","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"St. Francis Xavier University","funders":"","keywords":"Nova scotia; Nova (rocket); Political science; Library science; Geography; Computer science; Engineering; Aeronautics; Archaeology","score_opus":0.24512089600169695,"score_gpt":0.534825314225313,"score_spread":0.28970441822361603,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997982357","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001130313,0.9755504,0.000070819566,0.0013196892,0.0141982185,0.0006324332,0.000046823367,0.0000012747381,0.008067322],"genre_scores_gemma":[0.00053824595,0.9960324,0.00013540154,0.0004402893,0.0025236441,0.000006140979,0.00003703568,0.0000138873975,0.00027291328],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.99276817,0.00039070947,0.0032862986,0.00024361545,0.0031533197,0.00015790791],"domain_scores_gemma":[0.97436786,0.0006680797,0.005884979,0.00031277016,0.01873856,0.000027779917],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035599456,0.0002834441,0.0014398847,0.0010746081,0.000031570587,0.00038629427,0.0019567807,0.000109682296,0.00075466326],"category_scores_gemma":[0.0037801806,0.00015813002,0.00021579154,0.0063557723,0.00008392903,0.0011714336,0.0001778391,0.00061841216,0.0000109870625],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002606223,0.00012320664,0.000844321,0.04559081,0.00020565683,0.000017297389,0.00033379789,0.00010227,0.0000015730628,0.009626743,0.018740263,0.924388],"study_design_scores_gemma":[0.00017577484,0.00001508462,0.0023949805,0.77795076,0.00004030585,0.00012449511,0.0005937998,0.0000015786999,0.0000020686568,0.00040992702,0.21812533,0.00016588513],"about_ca_topic_score_codex":0.0036315739,"about_ca_topic_score_gemma":0.048184138,"teacher_disagreement_score":0.9242221,"about_ca_system_score_codex":0.0007177274,"about_ca_system_score_gemma":0.059761714,"threshold_uncertainty_score":0.96918404},"labels":[],"label_agreement":null},{"id":"W2998328657","doi":"10.56645/jmde.v15i33.539","title":"Using Action Research to Build Evaluation Capacity in Public Health Organizations","year":2019,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"École Nationale d'Administration Publique","funders":"","keywords":"Capacity building; Public health; Action research; Qualitative research; Data collection; Action (physics); Program evaluation; Public relations; Medical education; Psychology; Political science; Sociology; Medicine; Nursing; Public administration; Pedagogy","score_opus":0.8641173841470653,"score_gpt":0.654224582662043,"score_spread":0.20989280148502232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2998328657","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97523886,0.00008772983,0.008164819,0.012737199,0.0013491001,0.0017093526,0.000004199184,0.000007879612,0.00070085994],"genre_scores_gemma":[0.9921501,0.000024277755,0.007297126,0.00011201326,0.00024213344,0.000023050326,0.000013468288,0.000017341898,0.00012046417],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9784869,0.006539054,0.0021638141,0.0004874468,0.01183186,0.0004909032],"domain_scores_gemma":[0.9824738,0.000997468,0.0012308883,0.0005626535,0.014445614,0.0002895573],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.15076882,0.00015559653,0.0004026162,0.0028882367,0.00042480568,0.00031147854,0.0005842885,0.00011428499,0.00263456],"category_scores_gemma":[0.011875446,0.00012626244,0.000091369286,0.0054733,0.00004708282,0.0022514933,0.00017164843,0.00055754115,0.0004028584],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013963581,0.00067706883,0.27806774,0.00002236143,0.000030211422,9.623441e-7,0.017886039,0.5484121,0.018448172,0.00050660875,0.0013433989,0.1344657],"study_design_scores_gemma":[0.0014056762,0.00044359028,0.3869733,0.00008482278,0.000013765985,0.000020697997,0.0074021146,0.5974493,0.0002675965,0.0051924717,0.00063404645,0.000112610964],"about_ca_topic_score_codex":0.00006654676,"about_ca_topic_score_gemma":0.0004910512,"teacher_disagreement_score":0.13889337,"about_ca_system_score_codex":0.0032132945,"about_ca_system_score_gemma":0.0058328053,"threshold_uncertainty_score":0.9998032},"labels":[],"label_agreement":null},{"id":"W3001497035","doi":"10.1016/j.mex.2020.100788","title":"A refined method for theory-based evaluation of the societal impacts of research","year":2020,"lang":"en","type":"article","venue":"MethodsX","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":85,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Roads University","funders":"Social Sciences and Humanities Research Council of Canada; Canada Research Chairs","keywords":"Outcome (game theory); Computer science; Management science; Process (computing); Context (archaeology); Theory of change; Conceptual framework; Accountability; Set (abstract data type); Causal inference; Inference; Data science; Process management; Artificial intelligence; Engineering; Epistemology; Sociology","score_opus":0.7776038699548516,"score_gpt":0.7385389506990288,"score_spread":0.039064919255822894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3001497035","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09431129,0.0001101082,0.88569796,0.01490142,0.00022216319,0.0012388343,0.000039406645,0.000011691167,0.003467113],"genre_scores_gemma":[0.5542464,0.000001320018,0.44478288,0.0006631228,0.00005424731,0.000065832384,0.000002273432,0.0000074966233,0.00017639878],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9803027,0.01312704,0.00081582187,0.00035188047,0.005171434,0.0002311422],"domain_scores_gemma":[0.98269284,0.0129884,0.0004135284,0.00054810627,0.0032841417,0.00007299244],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1713299,0.000078738856,0.00027436367,0.00012625275,0.00014322795,0.000034668577,0.00067259715,0.00006617476,0.0008265149],"category_scores_gemma":[0.052862637,0.000043279884,0.00024602265,0.0015328466,0.00018996306,0.000110456924,0.000098837874,0.00015482694,0.000010383863],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008292786,0.00016521833,0.0036143695,0.0001309789,0.000086367494,8.3012324e-8,0.010909514,0.011664354,0.1611156,0.04725729,0.007976069,0.75625086],"study_design_scores_gemma":[0.0014338,0.00031537842,0.012578371,0.000023944871,0.00007164895,2.1850413e-7,0.0016833957,0.61360306,0.19023918,0.1746067,0.0053731897,0.00007110483],"about_ca_topic_score_codex":0.000013465569,"about_ca_topic_score_gemma":0.000008579923,"teacher_disagreement_score":0.75617975,"about_ca_system_score_codex":0.000050376082,"about_ca_system_score_gemma":0.0012026868,"threshold_uncertainty_score":0.9551155},"labels":[],"label_agreement":null},{"id":"W3003363921","doi":"10.4018/978-1-7998-2212-7.ch012","title":"The Role of Educational Developer in Supporting Research Ethics in SoTL","year":2020,"lang":"en","type":"book-chapter","venue":"Advances in educational marketing, administration, and leadership book series","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Engineering ethics; Value (mathematics); Ethical issues; Resource (disambiguation); Sociology; Knowledge management; Pedagogy; Engineering; Computer science","score_opus":0.31424826283930096,"score_gpt":0.5098224866633879,"score_spread":0.19557422382408696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3003363921","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004845174,0.048564434,0.0000057342118,0.22017752,0.00080046995,0.0011702972,0.00004112032,0.000011607074,0.72438365],"genre_scores_gemma":[0.6214354,0.015499359,0.001338518,0.0010187135,0.0006009433,0.00026604527,0.00018657786,0.000049872702,0.35960457],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99393725,0.00093065185,0.0018653766,0.0007045918,0.0021473228,0.00041481337],"domain_scores_gemma":[0.9790994,0.018718742,0.00076562027,0.0003362619,0.0009732805,0.00010667981],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017715318,0.00027264812,0.00038493532,0.0005682,0.00041277072,0.0002246703,0.0006021137,0.0002812634,0.0018735165],"category_scores_gemma":[0.017004572,0.00022842264,0.000059496033,0.0004165525,0.0009609797,0.0013528983,0.00008302855,0.0013488588,0.00003998557],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000443416,0.000090195375,0.12242852,0.00018508731,0.000010793556,0.0000014326463,0.01303877,0.000040668452,0.000010934202,0.85187024,0.0011284003,0.010751567],"study_design_scores_gemma":[0.0001826172,0.00008436406,0.061451588,0.0004352517,0.000003793575,0.0000088395755,0.027715221,0.00007286516,0.00003794558,0.31698862,0.59276676,0.00025215515],"about_ca_topic_score_codex":0.00001715789,"about_ca_topic_score_gemma":0.008761259,"teacher_disagreement_score":0.6165902,"about_ca_system_score_codex":0.00020136216,"about_ca_system_score_gemma":0.008425806,"threshold_uncertainty_score":0.99903893},"labels":[],"label_agreement":null},{"id":"W3003378069","doi":"10.7202/1066597ar","title":"Le processus de construction du jugement évaluatif par les superviseurs de stage en enseignement","year":2019,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Humanities; Philosophy","score_opus":0.10389264809654807,"score_gpt":0.4336578899609272,"score_spread":0.3297652418643791,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3003378069","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85604614,0.0007773789,0.04781036,0.065631695,0.0045109284,0.0020862292,0.00005455085,0.000097601645,0.022985144],"genre_scores_gemma":[0.9691287,0.00088152674,0.013759094,0.001136535,0.0004497872,0.0003019883,0.00031894958,0.00004913225,0.013974263],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9832784,0.010324691,0.0014515611,0.0009601939,0.0032998142,0.0006853512],"domain_scores_gemma":[0.99494416,0.0015911249,0.00080591266,0.000796064,0.0016430415,0.00021967701],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.062158875,0.00043206534,0.00046233129,0.00048516798,0.00057777966,0.0005585484,0.00059491454,0.0003772279,0.013368874],"category_scores_gemma":[0.0026738367,0.00044498726,0.00019498936,0.00089672493,0.00016495897,0.0015389149,0.00012304034,0.0004568362,0.0016906421],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015754685,0.0011589176,0.2283528,0.00043066012,0.00021058443,0.0000026890357,0.26392612,0.06940189,0.005665994,0.060383327,0.011358119,0.35895136],"study_design_scores_gemma":[0.0029603932,0.0004989581,0.6399023,0.00025336363,0.0002875074,0.000040318293,0.051490743,0.18580669,0.005918933,0.01831245,0.09373861,0.0007897633],"about_ca_topic_score_codex":0.0008891052,"about_ca_topic_score_gemma":0.00073692354,"teacher_disagreement_score":0.41154948,"about_ca_system_score_codex":0.0018757662,"about_ca_system_score_gemma":0.013072093,"threshold_uncertainty_score":0.9998002},"labels":[],"label_agreement":null},{"id":"W3003420919","doi":"10.5539/ies.v13n2p48","title":"Factors Affecting Instructional Leadership in Secondary Schools to Meet Vietnam’s General Education Innovation","year":2020,"lang":"en","type":"article","venue":"International Education Studies","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Instructional leadership; Vietnamese; Context (archaeology); Educational leadership; Government (linguistics); General partnership; Pedagogy; Autonomy; Principal (computer security); Political science; Sociology; Public relations; Mathematics education; Psychology","score_opus":0.6467725001106726,"score_gpt":0.5603658303392952,"score_spread":0.08640666977137734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3003420919","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9100378,0.00020557773,0.0005353839,0.073540434,0.0069715236,0.0003440292,0.000014413265,0.000041414452,0.00830938],"genre_scores_gemma":[0.97808826,0.000014974039,0.0042645675,0.014232084,0.0009609317,0.00012748863,0.000074057236,0.000013307014,0.0022243029],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99662167,0.00016983603,0.0009920115,0.00054704683,0.0014622338,0.00020722066],"domain_scores_gemma":[0.99503595,0.00033543215,0.00039592103,0.00019719049,0.0039181965,0.00011732238],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014468206,0.00020274587,0.00026405088,0.0010677422,0.00018030459,0.00026715524,0.00048893207,0.00006341821,0.00091506157],"category_scores_gemma":[0.0089902915,0.00017310421,0.000068442045,0.0021566872,0.000044096527,0.0011234032,0.0001314591,0.00024825204,0.00024228469],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008711191,0.0003652408,0.45714647,0.000040409483,0.00013911835,3.539208e-7,0.015469455,0.0018732161,0.0016036957,0.06984358,0.14480416,0.3086272],"study_design_scores_gemma":[0.00055439485,0.00010876578,0.73500466,0.00013745578,0.000012450776,0.0000048200163,0.13985553,0.00076957187,0.0013758687,0.01641074,0.10534409,0.00042166284],"about_ca_topic_score_codex":0.000034171495,"about_ca_topic_score_gemma":0.00013340189,"teacher_disagreement_score":0.30820552,"about_ca_system_score_codex":0.0004850488,"about_ca_system_score_gemma":0.0020601125,"threshold_uncertainty_score":0.9999982},"labels":[],"label_agreement":null},{"id":"W3003697964","doi":"10.1016/j.evalprogplan.2020.101789","title":"Assessing competency-based evaluation course impacts: A mixed methods case study","year":2020,"lang":"en","type":"article","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":31,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; University of Alberta","funders":"","keywords":"Context (archaeology); Presentation (obstetrics); Process (computing); Knowledge management; Focus group; Medical education; Computer science; Engineering ethics; Engineering; Sociology; Medicine","score_opus":0.4928499038396967,"score_gpt":0.6787705841841661,"score_spread":0.18592068034446946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3003697964","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.959688,0.0008400607,0.030086678,0.0032378219,0.0004690084,0.0034787008,0.0000045007223,0.00018438375,0.0020108134],"genre_scores_gemma":[0.9321557,0.0000015849988,0.066314645,0.00090627815,0.00012968034,0.00041133762,0.000055681005,0.00001782975,0.000007227832],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9873039,0.00605525,0.0011198968,0.0008080787,0.00436195,0.00035092127],"domain_scores_gemma":[0.9949549,0.0016826788,0.0006327132,0.00042292345,0.0019534589,0.00035334707],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.049368184,0.0002738693,0.0004115543,0.00024935804,0.0006379839,0.0017300663,0.00026686874,0.00009758817,0.0015005105],"category_scores_gemma":[0.0056468295,0.00021623062,0.00009401239,0.0012866359,0.00007764383,0.001179296,0.000081692684,0.00029404406,0.00005418792],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003676923,0.00028850208,0.04928688,0.000010497631,0.000037671532,0.00004570014,0.007974488,0.010448229,0.00012576875,0.000027640785,0.00036605625,0.9313518],"study_design_scores_gemma":[0.0026325898,0.0007811738,0.06424096,0.00003851803,0.00030532797,0.00007323865,0.057689805,0.8723553,0.0000781127,0.00057784934,0.0009797023,0.0002474248],"about_ca_topic_score_codex":0.000030224674,"about_ca_topic_score_gemma":0.00004157557,"teacher_disagreement_score":0.93110436,"about_ca_system_score_codex":0.00009613822,"about_ca_system_score_gemma":0.0015295077,"threshold_uncertainty_score":0.99941224},"labels":[],"label_agreement":null},{"id":"W3004367665","doi":"10.5206/cjsotl-rcacea.2019.3.9454","title":"Asking Critical Questions: An Introduction to Issue 10.3","year":2019,"lang":"en","type":"article","venue":"The Canadian Journal for the Scholarship of Teaching and Learning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Simon Fraser University; MacEwan University; University of Alberta; Queen's University; Trent University; Brock University; York University; Université du Québec à Montréal; Université de Sherbrooke; Cape Breton University; St. Thomas University; Kwantlen Polytechnic University; Mount Royal University; Mount Allison University; University of Toronto; St. Francis Xavier University; University of Lethbridge; Bishop's University; Dalhousie University; University of Ottawa; University of South Australia; McGill University; University of Windsor; University of Regina; McMaster University; University of Waterloo; New Mexico State University; University of Northern British Columbia; Georgetown University; Université Laval; Concordia University; Wilfrid Laurier University; National University of Singapore; University of the Fraser Valley; State University of New York","keywords":"Sociology; Epistemology; Psychology; Philosophy","score_opus":0.13622132171999365,"score_gpt":0.487161804322927,"score_spread":0.3509404826029333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3004367665","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88209605,0.00037566846,0.0043944772,0.109516956,0.0016916204,0.0002739156,0.0000027826936,0.000012150478,0.0016363619],"genre_scores_gemma":[0.98868,0.000002612275,0.0014896734,0.0006085611,0.00074977084,0.0000040550476,0.0000010069629,0.000008898091,0.008455427],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971256,0.0015852196,0.00033054565,0.00017111299,0.0005524983,0.0002350147],"domain_scores_gemma":[0.9967222,0.0021705076,0.00014129937,0.00028310943,0.00039206262,0.00029081575],"candidate_categories":["metaresearch","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03889451,0.00007905654,0.00012823309,0.00023506222,0.0039201723,0.0011292625,0.00050714717,0.000044825145,0.0013376593],"category_scores_gemma":[0.024412086,0.00004327205,0.000059205737,0.0001666337,0.000074152085,0.0006712271,0.00002121655,0.0015703264,0.000086840766],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014886032,0.00002556384,0.055821516,0.000022409517,0.00007064104,0.0000019195138,0.02670672,0.09725931,0.0012458,0.08606285,0.009891294,0.7227431],"study_design_scores_gemma":[0.0002404571,0.00047216777,0.04013587,0.00007785333,0.000040172374,0.00013589484,0.012162186,0.013700395,0.000037815968,0.015142372,0.91770715,0.0001476537],"about_ca_topic_score_codex":0.0010613418,"about_ca_topic_score_gemma":0.0037012591,"teacher_disagreement_score":0.9078159,"about_ca_system_score_codex":0.0000745277,"about_ca_system_score_gemma":0.0003352844,"threshold_uncertainty_score":0.9999077},"labels":[],"label_agreement":null},{"id":"W3004492861","doi":"10.7202/1066952ar","title":"Reconstruction du savoir-évaluer sous la contrainte : une analyse du bagage d’expériences non réinvesti dans les écoles montréalaises par des enseignants formés à l’étranger","year":2018,"lang":"fr","type":"article","venue":"Alterstice Revue internationale de la recherche interculturelle","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Humanities; Political science; Art","score_opus":0.2802378642637599,"score_gpt":0.4175816967188975,"score_spread":0.1373438324551376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3004492861","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8194368,0.004300139,0.09124086,0.014252225,0.0022584426,0.0005833316,0.00013246435,0.00010234371,0.06769342],"genre_scores_gemma":[0.94616187,0.011814612,0.025038073,0.0007629504,0.0014440134,0.00011143434,0.000035497178,0.000056969428,0.014574614],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9917229,0.004022615,0.0014807378,0.0009961342,0.0010755702,0.0007020617],"domain_scores_gemma":[0.98413295,0.012251034,0.00082316756,0.00056135474,0.0018472294,0.0003842888],"candidate_categories":["metaresearch","metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009922323,0.0006003424,0.00066387525,0.00041376182,0.0007391818,0.0008815065,0.0012968599,0.00085209095,0.0020963985],"category_scores_gemma":[0.01326046,0.00050769764,0.00048295024,0.00094980735,0.002757822,0.0014739037,0.00021923309,0.0012031593,0.0005037543],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047140394,0.0009088352,0.03413455,0.00020595094,0.0008118331,0.00019164279,0.2110591,0.0021554874,0.031293955,0.0039846078,0.0080930125,0.70668966],"study_design_scores_gemma":[0.0036417823,0.0015839305,0.03797793,0.005022017,0.0011320102,0.005341309,0.16611111,0.36972317,0.038505077,0.036789507,0.3322475,0.0019246493],"about_ca_topic_score_codex":0.0046338853,"about_ca_topic_score_gemma":0.016321817,"teacher_disagreement_score":0.70476496,"about_ca_system_score_codex":0.0015479218,"about_ca_system_score_gemma":0.0006158298,"threshold_uncertainty_score":0.9999561},"labels":[],"label_agreement":null},{"id":"W3005614006","doi":"10.4324/9780203409978-19","title":"The evaluation of assessment: post-EIS research and process development B.SADLER","year":2013,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Process (computing); Materials science; Process management; Engineering ethics; Psychology; Computer science; Business; Engineering","score_opus":0.6368306974563738,"score_gpt":0.621106100466391,"score_spread":0.015724596989982742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3005614006","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009782366,0.00052580726,0.000091060865,0.0018089353,0.00023207864,0.0014408202,0.0000062010095,0.000013156725,0.9860996],"genre_scores_gemma":[0.17925264,0.00029283672,0.00083970535,0.00011351946,0.00007461445,0.00020667052,0.000027280259,0.000024807678,0.8191679],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9856092,0.00032005963,0.0012182278,0.0005861948,0.011970728,0.00029558878],"domain_scores_gemma":[0.98211145,0.0019538396,0.0005480449,0.0007476647,0.014525389,0.00011359898],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.03934098,0.00022887693,0.00033405374,0.00047978456,0.000627482,0.0005120152,0.00080337765,0.00020790212,0.020880673],"category_scores_gemma":[0.00085307664,0.00012099297,0.00005683115,0.00018385312,0.00036180505,0.00037052884,0.00028068997,0.00045288625,0.0010132404],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020520947,0.00004072234,0.000502435,0.00003330699,0.00008435844,2.480074e-7,0.0010901617,0.000034057473,0.00002677781,0.18925293,0.011902954,0.79701155],"study_design_scores_gemma":[0.00084564515,0.00034872134,0.029807417,0.00021688864,0.00006058458,0.0000047371936,0.0028568066,0.0136163235,0.0003173529,0.37950307,0.57197195,0.00045048379],"about_ca_topic_score_codex":0.000014575346,"about_ca_topic_score_gemma":0.00024116112,"teacher_disagreement_score":0.79656106,"about_ca_system_score_codex":0.00020096241,"about_ca_system_score_gemma":0.0032121057,"threshold_uncertainty_score":0.99976456},"labels":[],"label_agreement":null},{"id":"W300774755","doi":"10.3138/cjpe.23.007","title":"Bureaucratic Competence as an Essential Factor in Cross-Cultural/Multicultural Program Evaluations","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Bureaucracy; Multiculturalism; Competence (human resources); Equity (law); Affirmative action; Public relations; Social psychology; Political science; Cultural diversity; Sociology; Psychology; Law","score_opus":0.3771933823224479,"score_gpt":0.5862658034914479,"score_spread":0.20907242116899993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W300774755","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9945583,0.00019803066,0.00008534468,0.0009954217,0.00087271293,0.0021789982,0.000011282918,0.000027334278,0.0010725855],"genre_scores_gemma":[0.9929322,0.000017188464,0.006149189,0.00013418359,0.00025695065,0.00023451603,0.00006587774,0.000013793145,0.00019612719],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99265766,0.0010453827,0.0016408833,0.00040048157,0.0037461678,0.00050943776],"domain_scores_gemma":[0.98987716,0.0002350305,0.0008945939,0.00041194874,0.0077772494,0.00080400746],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0070461854,0.00024405567,0.0003973906,0.0007787645,0.0005883127,0.0010989958,0.00079567166,0.00014818159,0.003436092],"category_scores_gemma":[0.005345708,0.00017533042,0.0001940205,0.0014256849,0.0004226934,0.0032585477,0.000018401368,0.00040576974,0.00021043487],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000641251,0.0005481958,0.27398023,0.000009828437,0.000052757947,0.00007214364,0.015050718,0.01665554,0.00063055387,0.0004711248,0.0008486017,0.6916162],"study_design_scores_gemma":[0.0022523978,0.0013585372,0.82542735,0.00006243756,0.00006213352,0.0003515336,0.0025946004,0.15825309,0.0002782136,0.0028937403,0.006136364,0.0003296135],"about_ca_topic_score_codex":0.0020875402,"about_ca_topic_score_gemma":0.048617553,"teacher_disagreement_score":0.69128656,"about_ca_system_score_codex":0.0006613167,"about_ca_system_score_gemma":0.0066077597,"threshold_uncertainty_score":0.99993795},"labels":[],"label_agreement":null},{"id":"W3009054679","doi":"10.3138/cjpe.69006","title":"Section 35 Legal Framework: Implications for Evaluation","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Carleton University","funders":"","keywords":"Indigenous; Government (linguistics); General partnership; Duty; Political science; Public administration; Indigenous rights; Law; Work (physics); Sociology; Human rights; Engineering","score_opus":0.5534072977341611,"score_gpt":0.5909154903539823,"score_spread":0.03750819261982119,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009054679","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44655108,0.0017130167,0.35658816,0.16698115,0.0064507634,0.012559269,0.00012521794,0.000081430284,0.008949903],"genre_scores_gemma":[0.98389304,0.0000076041497,0.013195954,0.0011748625,0.001186455,0.00042606756,0.00005258479,0.00001574349,0.000047679892],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99554497,0.0005734653,0.0011464745,0.00030726852,0.0021245296,0.00030328188],"domain_scores_gemma":[0.99009866,0.0004836185,0.0009429463,0.00029695357,0.007489684,0.0006881476],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016546195,0.00014254224,0.00025357067,0.0004883128,0.0004020646,0.0006439135,0.00049959036,0.00014386415,0.00201134],"category_scores_gemma":[0.013675429,0.00012145561,0.00021728204,0.0011678138,0.00006476268,0.0010487306,0.000010697622,0.0002742028,0.000052580595],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037730053,0.000033093736,0.009371821,0.000005935498,0.000036026493,3.362799e-7,0.0010871249,0.00981047,0.00014167008,0.0046389718,0.015298781,0.95953804],"study_design_scores_gemma":[0.0023751727,0.0013637771,0.11855814,0.00005084904,0.00038103506,0.00003625012,0.0013582102,0.4505213,0.00017204584,0.0799541,0.34494758,0.00028155756],"about_ca_topic_score_codex":0.00012660725,"about_ca_topic_score_gemma":0.0033389695,"teacher_disagreement_score":0.9592565,"about_ca_system_score_codex":0.0005514292,"about_ca_system_score_gemma":0.007864307,"threshold_uncertainty_score":0.99890095},"labels":[],"label_agreement":null},{"id":"W3009478627","doi":"10.3138/cjpe.68831","title":"Indigenous Health Service Evaluation: Principles and Guidelines from a Provincial “Three Ribbon” Expert Panel","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Toronto Metropolitan University; Public Health Ontario","funders":"","keywords":"Indigenous; Service (business); Public relations; Sociology; Set (abstract data type); Political science; Business; Computer science; Marketing","score_opus":0.7302785118808507,"score_gpt":0.5552141874564791,"score_spread":0.1750643244243716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009478627","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89072096,0.009654939,0.0027791688,0.091490515,0.0009891173,0.0038093426,0.000067793415,0.000028141872,0.00046000566],"genre_scores_gemma":[0.9669251,0.00010678961,0.019760048,0.011229036,0.001634093,0.0001948338,0.00009552366,0.000026661823,0.000027934084],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99258554,0.000867268,0.001775779,0.00040346239,0.003998872,0.0003690956],"domain_scores_gemma":[0.98908085,0.00020762038,0.0013622433,0.00030560623,0.007908078,0.0011355871],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017671054,0.00020277924,0.00041917295,0.00035514616,0.00043079254,0.0006117627,0.0005757693,0.00010725164,0.0016701567],"category_scores_gemma":[0.006003613,0.00016124475,0.00009748613,0.00088632264,0.00006485543,0.00075220934,0.000038035425,0.00025069574,0.00006562448],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003333134,0.000025569636,0.015670396,0.000007344054,0.000035311186,0.0000035901653,0.013738582,0.002473857,0.000022486112,0.000043837088,0.003788402,0.9641573],"study_design_scores_gemma":[0.0027765213,0.0012867481,0.1605062,0.0001498738,0.00014057558,0.00004254852,0.005972902,0.6925935,0.00004772913,0.00814747,0.12798578,0.00035015057],"about_ca_topic_score_codex":0.006869617,"about_ca_topic_score_gemma":0.1951328,"teacher_disagreement_score":0.96380717,"about_ca_system_score_codex":0.00054132345,"about_ca_system_score_gemma":0.02119541,"threshold_uncertainty_score":0.9997437},"labels":[],"label_agreement":null},{"id":"W3009649701","doi":"10.3138/cjpe.68866","title":"Identifying Key Epistemological Challenges Evaluating in Indigenous Contexts: Achieving <i>Bimaadiziwin</i> through Youth Futures","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Indigenous; Futures contract; Sociology; General partnership; Privilege (computing); Reciprocity (cultural anthropology); Field (mathematics); Agency (philosophy); Accountability; Government (linguistics); Work (physics); Public relations; Epistemology; Political science; Social science; Business; Law","score_opus":0.6425698594806223,"score_gpt":0.5452973114993448,"score_spread":0.09727254798127749,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009649701","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9704447,0.011715303,0.0013109728,0.011262826,0.0009729837,0.0017865726,0.000012532323,0.000025149711,0.0024689834],"genre_scores_gemma":[0.99187154,0.00015113842,0.0063426886,0.0010780026,0.00045947,0.000052595333,0.000013577396,0.000017673,0.000013329947],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99222016,0.0018849988,0.0017925012,0.00044378926,0.0031299416,0.0005286331],"domain_scores_gemma":[0.99553305,0.00046060808,0.001220473,0.00028625963,0.0019202069,0.00057939993],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021124378,0.00023041847,0.0005319702,0.00047919087,0.0003889843,0.00062078383,0.0008330968,0.00016772695,0.0007350711],"category_scores_gemma":[0.007796255,0.00018114444,0.00020406661,0.000985398,0.000116363466,0.00121468,0.000040054485,0.00057881785,0.000072882634],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004969902,0.000047869715,0.027518125,0.000021815207,0.000032156364,0.000033176682,0.092896394,0.0027209271,0.00008399691,0.00034392017,0.00016666365,0.8760853],"study_design_scores_gemma":[0.010369391,0.006811726,0.6213431,0.0011551111,0.0006196181,0.00030315787,0.21807195,0.07200786,0.00036265855,0.04461674,0.022707483,0.0016312342],"about_ca_topic_score_codex":0.0005425654,"about_ca_topic_score_gemma":0.0153312255,"teacher_disagreement_score":0.874454,"about_ca_system_score_codex":0.00050436356,"about_ca_system_score_gemma":0.0038178444,"threshold_uncertainty_score":0.93334085},"labels":[],"label_agreement":null},{"id":"W3009664453","doi":"10.3138/cjpe.69095","title":"Reflections on Evaluating in Indigenous Contexts: Looking to the Future","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Indigenous; Sociology; Psychology; Environmental ethics; Political science; Philosophy; Ecology; Biology","score_opus":0.4296188597017498,"score_gpt":0.5859342152437196,"score_spread":0.1563153555419698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009664453","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8813077,0.0008253325,0.0014002031,0.10671417,0.0020853668,0.0032135693,0.0000093289145,0.000015666059,0.00442867],"genre_scores_gemma":[0.9924153,0.000005764923,0.0015783014,0.005030607,0.00082658365,0.00009089896,0.0000035308904,0.000009652992,0.00003932431],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9951438,0.0009285959,0.00091605267,0.00022481088,0.0024956956,0.0002910798],"domain_scores_gemma":[0.9965827,0.0002866592,0.0005031605,0.0002419806,0.0018856596,0.0004998369],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016687317,0.000116283976,0.00020490993,0.00058846874,0.00038109763,0.00045118504,0.0005917189,0.000065201944,0.00091461954],"category_scores_gemma":[0.004981509,0.00007565875,0.00009651227,0.0018435741,0.00003211284,0.00033333586,0.000013571195,0.0004150244,0.0001979785],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033136243,0.000019470132,0.0067109233,0.000001568052,0.000011359283,0.000004849759,0.01721953,0.03247473,0.000044409633,0.000257227,0.002404424,0.94081837],"study_design_scores_gemma":[0.0030898112,0.006915718,0.29632738,0.00022875678,0.00013996415,0.000072532755,0.029120129,0.08666131,0.00018281494,0.008205314,0.5685603,0.000495959],"about_ca_topic_score_codex":0.000291784,"about_ca_topic_score_gemma":0.06980285,"teacher_disagreement_score":0.9403224,"about_ca_system_score_codex":0.00052790873,"about_ca_system_score_gemma":0.004617613,"threshold_uncertainty_score":0.9999987},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"opus","categories":["sts"],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W3009813686","doi":"10.3138/cjpe.68857","title":"Reflections on Being a Learner: The Value of Relationship-based Community Evaluations in Indigenous Communities","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Western University","funders":"","keywords":"Transformative learning; Indigenous; General partnership; Sociology; Value (mathematics); Power (physics); Work (physics); Process (computing); Traditional knowledge; Epistemology; Pedagogy; Political science; Computer science; Law","score_opus":0.6524773854460769,"score_gpt":0.5870706981648242,"score_spread":0.06540668728125276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009813686","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9787988,0.0001374298,0.0015642487,0.0130535485,0.00025947182,0.001337982,0.000012325649,0.000010594343,0.0048255767],"genre_scores_gemma":[0.997423,0.0000044722397,0.0013081626,0.0010608787,0.00006358239,0.00008429823,0.000024973331,0.000010713787,0.000019907708],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9906331,0.005716719,0.0012372332,0.00010293906,0.0020833218,0.00022672978],"domain_scores_gemma":[0.99339694,0.0027063477,0.00088692526,0.00047630572,0.0022801799,0.00025329957],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02528478,0.000125601,0.0002623462,0.0008652313,0.001002804,0.00022837188,0.00082539726,0.00008716528,0.0004767702],"category_scores_gemma":[0.008371669,0.00009164471,0.00014474177,0.0019903712,0.00021743796,0.0003846402,0.000018737459,0.0010197817,0.000024258798],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000073596,0.00023008125,0.18238169,0.000013768752,0.00004290515,0.0000018634754,0.09603457,0.48141873,0.000048551046,0.008548895,0.000550102,0.23065524],"study_design_scores_gemma":[0.001624266,0.002003457,0.70621216,0.0001618988,0.00013963455,0.00001021236,0.037084613,0.22037613,0.00012853528,0.02580227,0.0062763,0.00018048806],"about_ca_topic_score_codex":0.0053115166,"about_ca_topic_score_gemma":0.11690757,"teacher_disagreement_score":0.5238305,"about_ca_system_score_codex":0.00044441392,"about_ca_system_score_gemma":0.006550034,"threshold_uncertainty_score":0.9999812},"labels":[],"label_agreement":null},{"id":"W3009813774","doi":"","title":"National Collaborative Outreach Programme (Phase 1) Monitoring and Evaluation Report September 2019","year":2019,"lang":"en","type":"article","venue":"NECTAR - Northampton Electronic Collection of Thesis and Research (University of Northampton)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact","funders":"","keywords":"Outreach; Phase (matter); Geography; Political science","score_opus":0.12887866889627883,"score_gpt":0.46005031291493914,"score_spread":0.3311716440186603,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009813774","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9884798,0.00040600024,0.000105815045,0.0009844138,0.00012856345,0.0011703664,0.0000194397,0.000018791572,0.008686821],"genre_scores_gemma":[0.9883243,0.00047992478,0.00034567606,0.0000052436562,0.000043846252,0.000009173826,0.000034610974,0.00001076267,0.010746503],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9935257,0.00078858767,0.00052384235,0.0006705923,0.0040044747,0.00048680528],"domain_scores_gemma":[0.99314094,0.0010652269,0.00055414217,0.00039096412,0.004688503,0.00016020364],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.012565069,0.00018129875,0.00044727023,0.0009776768,0.00058604777,0.00009082055,0.00031677954,0.00014886828,0.0012662633],"category_scores_gemma":[0.0006993659,0.00016936463,0.00012691603,0.0022999141,0.00029967498,0.0006916304,0.00017575137,0.00038964153,0.00002941978],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019405537,0.0012520016,0.820535,0.00009155051,0.0006115888,0.0000107438345,0.007492295,0.0015810817,0.006976081,0.0021395602,0.008145433,0.1492241],"study_design_scores_gemma":[0.013703065,0.0068703042,0.6897158,0.00022575038,0.0002190682,0.00014896711,0.028732931,0.10400955,0.006290751,0.0086526405,0.14046247,0.0009687152],"about_ca_topic_score_codex":0.0005737908,"about_ca_topic_score_gemma":0.0015462496,"teacher_disagreement_score":0.1482554,"about_ca_system_score_codex":0.0004496672,"about_ca_system_score_gemma":0.0025163214,"threshold_uncertainty_score":0.9996467},"labels":[],"label_agreement":null},{"id":"W3010143613","doi":"10.3138/cjpe.68914","title":"EvalIndigenous Origin Story: Effective Practices within Local Contexts to Inform the Field and Practice of Evaluation","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Indigenous; Politics; Sovereignty; Field (mathematics); Traditional knowledge; Work (physics); Political science; Sociology; Environmental ethics; Law; Ecology; Engineering","score_opus":0.32734472912731394,"score_gpt":0.5695930311312456,"score_spread":0.24224830200393166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3010143613","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85992855,0.0018672509,0.008729443,0.11660341,0.0012760576,0.007814335,0.000011972434,0.00001242518,0.0037565602],"genre_scores_gemma":[0.99425024,0.000008897059,0.002043542,0.0033815992,0.00016546197,0.00012117763,0.0000040130994,0.000007844037,0.00001724159],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99245626,0.0025733288,0.00094113016,0.00022826916,0.0035861498,0.00021484584],"domain_scores_gemma":[0.9845653,0.004781647,0.0025803305,0.00024726978,0.007302778,0.00052263675],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.051345635,0.00013437125,0.00027253886,0.0003212947,0.00035194773,0.0003473058,0.00036549827,0.00008543205,0.0005006816],"category_scores_gemma":[0.09824252,0.00008789764,0.00007596283,0.0010242583,0.0001189766,0.0013404123,0.000022957101,0.00036749706,0.00004171483],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028776142,0.00002962938,0.0025682691,0.000009965671,0.000073227435,0.0000034211805,0.024401965,0.009710553,0.000051975312,0.00043556886,0.0029276384,0.9595],"study_design_scores_gemma":[0.004589737,0.012473122,0.08205338,0.0001883021,0.001445532,0.00024757982,0.059299994,0.3801858,0.0012761599,0.0036418464,0.4541048,0.00049372256],"about_ca_topic_score_codex":0.0010170129,"about_ca_topic_score_gemma":0.013314665,"teacher_disagreement_score":0.9590063,"about_ca_system_score_codex":0.0003493222,"about_ca_system_score_gemma":0.006500561,"threshold_uncertainty_score":0.9991317},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"qualitative","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W3010351954","doi":"10.3138/cjpe.68837","title":"Indigenous Evaluation in the Northwest Territories: Opportunities and Challenges","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Indigenous; Service (business); Service delivery framework; Traditional knowledge; Service provider; Culturally appropriate; Economic growth; Political science; Business; Environmental planning; Geography; Medicine; Marketing; Economics; Gerontology","score_opus":0.6396488333319937,"score_gpt":0.4982009790427576,"score_spread":0.14144785428923612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3010351954","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91979605,0.010290704,0.000050874438,0.06516319,0.0005776486,0.0019932468,0.000016132984,0.000006819404,0.002105323],"genre_scores_gemma":[0.997995,0.0006004435,0.00025663676,0.00071907474,0.0002990058,0.0000979168,0.000020861864,0.0000058356404,0.000005192246],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9948937,0.0012267957,0.0007591508,0.00017596825,0.0027389983,0.0002053809],"domain_scores_gemma":[0.9968227,0.00030958414,0.00046562683,0.00018183081,0.0019009131,0.00031930328],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023105726,0.000106611245,0.00018942554,0.0003808051,0.00019120576,0.00043403305,0.00044396255,0.00006256071,0.0004085932],"category_scores_gemma":[0.002749425,0.000070150236,0.00005235402,0.00046031558,0.00009619689,0.000665913,0.000009772127,0.00019547885,0.000008982055],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008717841,0.00001816756,0.02345221,0.0000067338074,0.000009551516,0.000008074901,0.036292862,0.0004733738,0.000001417863,0.00030809877,0.00021937735,0.9392014],"study_design_scores_gemma":[0.0015400398,0.0013818659,0.6056171,0.000056843382,0.00013909019,0.0000843817,0.07781883,0.051145673,0.0000095252835,0.008036376,0.25395826,0.00021201753],"about_ca_topic_score_codex":0.0015881844,"about_ca_topic_score_gemma":0.1533991,"teacher_disagreement_score":0.9389894,"about_ca_system_score_codex":0.0001831499,"about_ca_system_score_gemma":0.0046953037,"threshold_uncertainty_score":0.86204916},"labels":[],"label_agreement":null},{"id":"W3010430962","doi":"10.1016/j.evalprogplan.2020.101817","title":"Does it make a difference? Evaluation of a Canadian poverty reduction initiative","year":2020,"lang":"en","type":"article","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Brock University","funders":"","keywords":"Poverty; Psychology; Public relations; Plan (archaeology); Exploratory research; Control (management); Perception; Medical education; Political science; Applied psychology; Sociology; Medicine; Management; Social science","score_opus":0.44331895806071553,"score_gpt":0.5342344542829909,"score_spread":0.09091549622227535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3010430962","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9236095,0.00041520517,0.00054024457,0.030738465,0.0006986523,0.0027510352,0.000047341913,0.0000706685,0.041128922],"genre_scores_gemma":[0.9970322,0.000025931524,0.00112642,0.0013081337,0.00012063124,0.0001950414,0.00009239176,0.0000074401933,0.00009179757],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9943,0.000993531,0.0006574026,0.00043161467,0.0034023668,0.00021507264],"domain_scores_gemma":[0.99690264,0.00022703626,0.0003906871,0.00020412753,0.002013582,0.00026191268],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010812117,0.00014616582,0.00023625669,0.0005547728,0.00022629875,0.00022187195,0.00018451044,0.00008946048,0.002286171],"category_scores_gemma":[0.0031826156,0.00009072826,0.000055119297,0.0013575968,0.00006798043,0.00033037734,0.00003477718,0.00015358365,0.00003707082],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000063831976,0.0000452777,0.023379121,0.000012969806,0.00003750003,5.1888685e-7,0.023111666,0.0024617752,0.00033230762,0.00037374007,0.0026001984,0.9475811],"study_design_scores_gemma":[0.0014743498,0.00038154057,0.1732958,0.00008190527,0.0001597286,0.0000039030942,0.015033202,0.77493346,0.00044625113,0.006354243,0.02761203,0.00022360688],"about_ca_topic_score_codex":0.00072904653,"about_ca_topic_score_gemma":0.0039587254,"teacher_disagreement_score":0.9473575,"about_ca_system_score_codex":0.00010692075,"about_ca_system_score_gemma":0.0012206263,"threshold_uncertainty_score":0.9986259},"labels":[],"label_agreement":null},{"id":"W3010495354","doi":"10.3138/cjpe.69010","title":"Evaluation in Indigenous Contexts: An Introduction to Practice","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Indigenous; Sociology; Psychology; Engineering ethics; Engineering; Ecology","score_opus":0.34926966146980354,"score_gpt":0.5540992470149855,"score_spread":0.20482958554518194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3010495354","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84315354,0.0006812068,0.004719151,0.14238529,0.0024902779,0.005166205,0.000008729239,0.000020476362,0.0013751101],"genre_scores_gemma":[0.9902486,0.0000048401807,0.0062493384,0.0022653902,0.0010549932,0.0001235934,0.000021195818,0.000011896358,0.00002014373],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99091893,0.0024892965,0.001243691,0.00036196536,0.004681341,0.00030478154],"domain_scores_gemma":[0.98831254,0.00021670181,0.00076405954,0.00030028555,0.009499016,0.00090739963],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.051512063,0.00013146516,0.0002558008,0.0009070607,0.00015966692,0.0005227878,0.00048204866,0.000086033135,0.0021655636],"category_scores_gemma":[0.03342957,0.00011453134,0.00006704102,0.0018458207,0.000039242124,0.0022637988,0.000011757835,0.00029345634,0.00017803098],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006636264,0.00006706417,0.004245333,0.0000017800385,0.000016270527,0.0000052840564,0.01262439,0.029319735,0.00010181698,0.00012938968,0.0037860628,0.9496365],"study_design_scores_gemma":[0.003563789,0.005398589,0.102948755,0.000041327734,0.00037034802,0.000112905975,0.013690037,0.22158216,0.00026316184,0.0063542826,0.6452383,0.0004363784],"about_ca_topic_score_codex":0.00068151386,"about_ca_topic_score_gemma":0.032439716,"teacher_disagreement_score":0.94920015,"about_ca_system_score_codex":0.0010616806,"about_ca_system_score_gemma":0.009450715,"threshold_uncertainty_score":0.9987466},"labels":[],"label_agreement":null},{"id":"W301099006","doi":"","title":"Impacts of the Canadian Evaluation Society's Evaluation Competitions for Students: Guest Editors' Introduction.","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Psychology; Sociology","score_opus":0.24853880815214335,"score_gpt":0.5377223463397195,"score_spread":0.28918353818757614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W301099006","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84002084,0.0022584307,0.0020296304,0.04579933,0.07929932,0.024100538,0.0002445575,0.000028753737,0.0062186196],"genre_scores_gemma":[0.99269277,0.000008747716,0.002345321,0.00023176115,0.00409263,0.00044596117,0.00008535042,0.000019040308,0.00007839857],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9882254,0.002079307,0.0015623869,0.0003478333,0.007310762,0.0004743019],"domain_scores_gemma":[0.9759462,0.00037160478,0.0015456983,0.00062382483,0.020848611,0.0006640707],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06580941,0.00020892154,0.00033610818,0.0007488673,0.0010249864,0.00060726865,0.00081641617,0.00018142421,0.0031228694],"category_scores_gemma":[0.018468855,0.00015440721,0.0004050302,0.0015616355,0.00022911547,0.000925958,0.000013217442,0.00030327376,0.000027418182],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004631585,0.00044486782,0.1639483,0.000046442296,0.00047851563,6.505608e-7,0.0066594807,0.04518969,0.00041546114,0.0052741705,0.53971344,0.23778266],"study_design_scores_gemma":[0.005851022,0.0009816992,0.20896375,0.00016863442,0.0015873831,0.00006127154,0.005440706,0.10948841,0.0010776299,0.028345883,0.6375509,0.0004827059],"about_ca_topic_score_codex":0.014352034,"about_ca_topic_score_gemma":0.69269085,"teacher_disagreement_score":0.6783388,"about_ca_system_score_codex":0.0032694072,"about_ca_system_score_gemma":0.0356213,"threshold_uncertainty_score":0.9977884},"labels":[],"label_agreement":null},{"id":"W3011407335","doi":"10.1111/capa.12360","title":"Public administration in the cross‐hairs of evidence‐based policy and authentic engagement: School closures in Ontario","year":2020,"lang":"en","type":"article","venue":"Canadian Public Administration","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Demographics; Administration (probate law); Politics; Public administration; Stakeholder engagement; Political science; Closure (psychology); Public policy; Stakeholder; Public relations; Public engagement; Sociology; Law","score_opus":0.5358163952108805,"score_gpt":0.4797274421385246,"score_spread":0.05608895307235595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011407335","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75644374,0.000047463236,0.0001998056,0.23965749,0.00008289789,0.0005557307,0.000018441368,0.000009865132,0.0029845827],"genre_scores_gemma":[0.9954633,0.0000072208722,0.00013217502,0.003917781,0.000082737635,0.00006553402,0.000055572564,0.0000070399283,0.0002686274],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99627054,0.0006792157,0.0009879688,0.00044237735,0.0012464449,0.00037346987],"domain_scores_gemma":[0.99771005,0.0006821528,0.0003195163,0.00040579273,0.00035203193,0.0005304643],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006006897,0.00016091403,0.00021598976,0.00084303756,0.00021101585,0.001237011,0.00062726013,0.00011639929,0.0015229785],"category_scores_gemma":[0.009602439,0.000117721036,0.00005566667,0.0017077825,0.00015268748,0.0018005543,0.000026294256,0.00035632917,0.000038729682],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005491489,0.00007546823,0.91871625,0.000020824395,0.0000072678895,0.000016605924,0.0019640103,0.000029591209,0.0000447752,0.071264915,0.0011080565,0.006697335],"study_design_scores_gemma":[0.00071556267,0.0004903745,0.9287014,0.000036785394,0.000006624836,0.000005728357,0.0017312106,0.0079172775,0.000086047745,0.0023017558,0.057820726,0.00018647824],"about_ca_topic_score_codex":0.024993967,"about_ca_topic_score_gemma":0.9673025,"teacher_disagreement_score":0.94230855,"about_ca_system_score_codex":0.0005343691,"about_ca_system_score_gemma":0.025042964,"threshold_uncertainty_score":0.9997998},"labels":[],"label_agreement":null},{"id":"W3011548789","doi":"10.1002/ev.20398","title":"Finding the Impact: Methods for Assessing the Contribution of Collective Impact to Systems and Population Change in a Multi‐Site Study","year":2020,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact","funders":"","keywords":"Scale (ratio); Context (archaeology); Interim; Population; Work (physics); SPARK (programming language); Management science; Computer science; Political science; Sociology; Engineering","score_opus":0.5624400587745525,"score_gpt":0.6718887697007279,"score_spread":0.10944871092617536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011548789","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77961814,0.00023250777,0.20941041,0.00176398,0.0003291203,0.008569719,0.000030907977,0.000015616508,0.000029599043],"genre_scores_gemma":[0.995693,0.0000040954865,0.002425569,0.00007293177,0.00013399834,0.001577101,0.00003713378,0.000009356584,0.000046765384],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967269,0.0014154185,0.0006408828,0.00032235586,0.0007215775,0.00017288922],"domain_scores_gemma":[0.9949687,0.0031578713,0.00043921004,0.00021399057,0.0011433341,0.00007689281],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01809795,0.00012658749,0.00027751413,0.00029140335,0.0005374275,0.00034344377,0.00014670867,0.000052246614,0.000035973422],"category_scores_gemma":[0.009708745,0.000069077396,0.000115324605,0.0017297111,0.000016356826,0.0005876988,0.000034897246,0.000085463136,0.0000022493002],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034007124,0.00019812894,0.5428273,0.00000989335,0.00010754883,3.0553412e-8,0.047929373,0.07795132,0.002071462,0.00016078605,0.00075978594,0.3276443],"study_design_scores_gemma":[0.001155353,0.00028007413,0.487921,0.000012244456,0.000057616973,5.09522e-7,0.0026199582,0.5073546,0.000052683212,0.00036689668,0.0001332614,0.000045796776],"about_ca_topic_score_codex":0.0023466907,"about_ca_topic_score_gemma":0.0012720851,"teacher_disagreement_score":0.4294033,"about_ca_system_score_codex":0.0005032026,"about_ca_system_score_gemma":0.00036571897,"threshold_uncertainty_score":0.9986329},"labels":[],"label_agreement":null},{"id":"W3011833521","doi":"","title":"Research Guides: CNST 1130: Work in Canadian Society: Tips for CNST Research","year":2018,"lang":"en","type":"libguides","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Work (physics); Political science; Engineering; Mechanical engineering","score_opus":0.7463698719017722,"score_gpt":0.6652410405142203,"score_spread":0.08112883138755189,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011833521","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036366684,0.0012957101,0.0002360268,0.047879014,0.0040961416,0.0041817464,0.000464508,0.0000763394,0.93813384],"genre_scores_gemma":[0.020121483,0.0012818931,0.009830714,0.003535478,0.0043549063,0.0011435568,0.00051587174,0.00013497916,0.9590811],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9800456,0.0019638087,0.002057836,0.0018413384,0.011058213,0.0030331628],"domain_scores_gemma":[0.9759188,0.011596699,0.00026133825,0.0022934482,0.008915765,0.0010138974],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.14659788,0.00043157974,0.00084142963,0.0042257714,0.0018163655,0.0022101381,0.0043778825,0.0011301239,0.023540752],"category_scores_gemma":[0.0128498925,0.00032462314,0.00041666624,0.007923777,0.0012101486,0.00058887975,0.0006991289,0.0023880054,0.007540068],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044322624,0.000038662503,0.004229817,0.000039112256,0.000027449849,0.0000045504853,0.0012280459,0.000015224331,0.0000017488655,0.0018532057,0.97036207,0.022155816],"study_design_scores_gemma":[0.00050127035,0.00024555254,0.002308044,0.00030878463,0.000005392188,0.000002207248,0.0081122415,0.002431078,0.000027727145,0.013980004,0.971694,0.00038370572],"about_ca_topic_score_codex":0.2672258,"about_ca_topic_score_gemma":0.8631863,"teacher_disagreement_score":0.5959605,"about_ca_system_score_codex":0.002527182,"about_ca_system_score_gemma":0.021757198,"threshold_uncertainty_score":0.9999206},"labels":[],"label_agreement":null},{"id":"W3013809716","doi":"10.18438/eblip29638","title":"Gathering Evidence for Sustainable Development Goals: An Alignment Perspective","year":2020,"lang":"en","type":"article","venue":"Evidence Based Library and Information Practice","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Perspective (graphical); Computer science; Development (topology); Data science; Sustainable development; Political science; Artificial intelligence","score_opus":0.18815398408352207,"score_gpt":0.45359523234421917,"score_spread":0.2654412482606971,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3013809716","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04337636,0.0025412957,0.29690582,0.63585967,0.0002888803,0.00338435,0.000013874946,0.00039083158,0.017238917],"genre_scores_gemma":[0.7809483,0.0006658211,0.053809848,0.16312543,0.00019295898,0.00029865312,0.000025394056,0.000016351234,0.00091726315],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970137,0.0003855552,0.0008159313,0.0003474818,0.0011664688,0.00027087866],"domain_scores_gemma":[0.99275994,0.0053321756,0.0006002321,0.00031764322,0.00069540506,0.00029457457],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.004364045,0.00016750858,0.00018720167,0.00018668885,0.00046835854,0.0015968374,0.0004957166,0.000059740938,0.0009684904],"category_scores_gemma":[0.01817106,0.00013552817,0.000048322832,0.0007227053,0.00004793365,0.33793435,0.00016815946,0.00014311723,0.00017048066],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003887879,0.00015884427,0.0031165103,0.0003812753,0.000059750415,0.00001011975,0.029689563,0.00975313,0.00026486762,0.8394518,0.012053978,0.10117229],"study_design_scores_gemma":[0.0005246702,0.00059378264,0.0047997115,0.00016239882,0.00002347316,0.0000041073727,0.07035214,0.07002524,0.004169741,0.0009910951,0.8480899,0.00026375992],"about_ca_topic_score_codex":0.0000051235947,"about_ca_topic_score_gemma":7.498474e-8,"teacher_disagreement_score":0.8384607,"about_ca_system_score_codex":0.00006723244,"about_ca_system_score_gemma":0.0011168751,"threshold_uncertainty_score":0.99994475},"labels":[],"label_agreement":null},{"id":"W3013834841","doi":"10.4324/9780429336256-3","title":"Utilizing Evaluation in Organizations: The Balancing Act","year":2020,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Business; Function (biology); Supply and demand; Knowledge management; Process management; Computer science; Economics","score_opus":0.27507149441982065,"score_gpt":0.4739975960714458,"score_spread":0.19892610165162516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3013834841","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013744929,0.00022039216,0.0010181677,0.0073444033,0.0004138697,0.00063319766,0.0000046618266,0.000036525125,0.99019134],"genre_scores_gemma":[0.54191965,0.00020343193,0.0005543477,0.0048819133,0.00036839052,0.00003558517,0.000090938825,0.000050297283,0.45189542],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99508405,0.00016177492,0.0008687394,0.00046699404,0.0032815868,0.00013688281],"domain_scores_gemma":[0.9970697,0.0009013839,0.0003687787,0.000578829,0.0010248151,0.000056470344],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0070151063,0.00019414086,0.00027643688,0.00026880295,0.00016702877,0.0003008466,0.0006347501,0.00014400759,0.03977974],"category_scores_gemma":[0.0027627854,0.00011316979,0.00007197732,0.00045468277,0.0000424647,0.00028962683,0.00014699978,0.00034684496,0.0034227127],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001725032,0.000021100812,0.005540625,0.0000122130195,0.000047764275,0.000004430331,0.0028004576,0.0033020114,0.000058840244,0.6653584,0.046132937,0.27670395],"study_design_scores_gemma":[0.00060111267,0.000054489035,0.007927969,0.00012235719,0.00007294899,0.0000052667783,0.0016065286,0.22267051,0.000050673858,0.19885853,0.56759876,0.0004308756],"about_ca_topic_score_codex":0.000011762774,"about_ca_topic_score_gemma":0.00042066386,"teacher_disagreement_score":0.5417822,"about_ca_system_score_codex":0.00019388307,"about_ca_system_score_gemma":0.000972724,"threshold_uncertainty_score":0.99735326},"labels":[],"label_agreement":null},{"id":"W3014556897","doi":"10.46743/2160-3715/2020.4176","title":"Outcome Mapping: Documenting Process in the Métis Settlements Life Skills Journey Project","year":2020,"lang":"en","type":"article","venue":"The Qualitative Report","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia; University of Alberta","funders":"University of Alberta; Nova Southeastern University; Alberta Health Services","keywords":"Outcome (game theory); Settlement (finance); Project team; Process (computing); Identification (biology); Human settlement; Psychology; Process management; Sociology; Knowledge management; Engineering; Geography; Computer science; Archaeology","score_opus":0.6136070965587114,"score_gpt":0.6642015430775936,"score_spread":0.05059444651888223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3014556897","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.904217,0.00005242442,0.0028619335,0.071225725,0.00022250222,0.0011346191,0.0000119204215,0.00003382142,0.020240048],"genre_scores_gemma":[0.9908332,0.000006897684,0.00043044938,0.007047173,0.00012002356,0.000120037614,0.000010616666,0.000009528871,0.0014220591],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99181056,0.0024484312,0.0018205073,0.00043854772,0.0031454659,0.00033647634],"domain_scores_gemma":[0.99549186,0.0023662348,0.0010844095,0.00052033534,0.0004563681,0.00008076597],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04131869,0.00016900977,0.0003235346,0.00013378874,0.00032758125,0.00036108648,0.0009576242,0.000036160258,0.0005618381],"category_scores_gemma":[0.013507964,0.0000780154,0.00011606863,0.0015734098,0.00011087765,0.0004968477,0.00013307239,0.00033009448,0.00026553453],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031253243,0.00011102772,0.16322389,0.000028976072,0.000058697275,0.00006475246,0.8176437,0.00023476608,0.000033484073,0.0018462712,0.014541933,0.0021812613],"study_design_scores_gemma":[0.0008199282,0.00017287482,0.086082436,0.0000460963,0.000024704364,0.00006222273,0.8305113,0.002044779,0.0000889189,0.016720606,0.06312655,0.00029959218],"about_ca_topic_score_codex":0.00004218476,"about_ca_topic_score_gemma":0.000017764309,"teacher_disagreement_score":0.08661621,"about_ca_system_score_codex":0.000052031377,"about_ca_system_score_gemma":0.0005084198,"threshold_uncertainty_score":0.9948017},"labels":[],"label_agreement":null},{"id":"W3014593810","doi":"","title":"How Hip is The Partnership: The Value of a Generalist Journal in a Niche World","year":2016,"lang":"en","type":"article","venue":"Scholarship@Western (Western University)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Generalist and specialist species; Niche; General partnership; Value (mathematics); Business; Ecology; Biology; Computer science","score_opus":0.35838784450054606,"score_gpt":0.44965953019594856,"score_spread":0.0912716856954025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3014593810","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9603619,0.00011394182,0.0007525308,0.037612587,0.00028724942,0.0002552917,0.000011300977,0.000015911717,0.0005892732],"genre_scores_gemma":[0.94187754,0.00008014993,0.00002425962,0.0016792221,0.0001285651,0.0000016831644,7.136559e-7,0.00001387079,0.056194007],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.994975,0.0016535006,0.0005546079,0.0004366475,0.001943786,0.00043651112],"domain_scores_gemma":[0.9962765,0.0013790565,0.0006488046,0.0010349597,0.0004881076,0.00017258398],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0065958067,0.00023274281,0.0003232016,0.000717525,0.0003936785,0.00089338736,0.002621441,0.000099645535,0.00026359546],"category_scores_gemma":[0.00052507024,0.00010844304,0.0002458268,0.0016758599,0.00042720293,0.002160258,0.00039019267,0.0005626162,0.00015210573],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007698538,0.000043832926,0.99241114,0.000003563997,0.000030566163,0.000024984558,0.0011884077,0.000030972296,0.00056589243,0.0012458625,0.000068573936,0.004309199],"study_design_scores_gemma":[0.0013015425,0.00008323522,0.9364526,0.00012799188,0.000041052117,0.000032286018,0.001703923,0.0000056364015,0.0024227968,0.0032590013,0.05436672,0.00020317202],"about_ca_topic_score_codex":0.000003949963,"about_ca_topic_score_gemma":0.0032304935,"teacher_disagreement_score":0.055958517,"about_ca_system_score_codex":0.00021167638,"about_ca_system_score_gemma":0.0003560833,"threshold_uncertainty_score":0.8614955},"labels":[],"label_agreement":null},{"id":"W3014806869","doi":"","title":"Élaboration et premiers pas de validation de questionnaires pour évaluer la fidélité du modèle de réponse à l’intervention en littératie dans les écoles primaires francophones québécoises","year":2020,"lang":"fr","type":"article","venue":"Canadian Journal of Education / Revue canadienne de l éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Laurentian University; Université du Québec en Outaouais","funders":"","keywords":"Fidelity; Psychology; Context (archaeology); Response to intervention; Literacy; Humanities; Pedagogy; Medical education; Special education; Computer science; Medicine","score_opus":0.11436176593894774,"score_gpt":0.3690426547594119,"score_spread":0.25468088882046414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3014806869","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80348194,0.0017464198,0.040789563,0.14914691,0.0038093012,0.0003607362,0.00008568664,0.00001737856,0.00056205207],"genre_scores_gemma":[0.9842946,0.00057622103,0.007268972,0.0034207415,0.0017631346,0.00008124772,0.000108916385,0.000047898506,0.0024383015],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9931443,0.0038965496,0.0013867884,0.00043825226,0.00037813172,0.00075601134],"domain_scores_gemma":[0.99307066,0.0010794734,0.0013430415,0.00036731025,0.0021258472,0.0020136463],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00940117,0.00032244364,0.0003912704,0.0006842542,0.0006251791,0.0008455524,0.0006352452,0.00036775396,0.0010901733],"category_scores_gemma":[0.015467885,0.00038335405,0.00024811327,0.0010734313,0.00019755823,0.0016461867,0.00001823082,0.0006475602,0.000040596216],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000114815426,0.00039698192,0.3703311,0.00045159587,0.00013304042,0.00003346994,0.3895488,0.048887994,0.0029736308,0.013429672,0.058694027,0.115004845],"study_design_scores_gemma":[0.0008057552,0.00045856388,0.6627055,0.0017551942,0.00034722668,0.00079842913,0.15025517,0.039949242,0.0020521283,0.014242255,0.12598743,0.0006431413],"about_ca_topic_score_codex":0.19927521,"about_ca_topic_score_gemma":0.83659446,"teacher_disagreement_score":0.63731927,"about_ca_system_score_codex":0.009411598,"about_ca_system_score_gemma":0.067405224,"threshold_uncertainty_score":0.99986184},"labels":[],"label_agreement":null},{"id":"W3015081587","doi":"10.5539/jsd.v13n2p132","title":"Local Knowledge on Development The Missing Link in the Research-Policy Nexus of Sustainable Development","year":2020,"lang":"en","type":"article","venue":"Journal of Sustainable Development","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Nexus (standard); Grassroots; Function (biology); Politics; Transformational leadership; Blueprint; Political science; Psychological intervention; Sustainable development; Pledge; Knowledge management; Process management; Public relations; Business; Computer science; Medicine; Engineering","score_opus":0.26253128373167733,"score_gpt":0.48628350349513666,"score_spread":0.22375221976345933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3015081587","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7381576,0.00219025,0.01919573,0.19000989,0.00045423207,0.003229644,0.000001023575,0.00003472142,0.046726953],"genre_scores_gemma":[0.9881133,0.000033255514,0.0036338938,0.0020673263,0.00023777015,0.00006559749,0.0000022908234,0.000024033683,0.005822525],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9882089,0.0015324308,0.0030024515,0.0004570996,0.005546262,0.0012528702],"domain_scores_gemma":[0.989711,0.0024836669,0.0011034488,0.00052505214,0.005819248,0.00035762467],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.043308675,0.0003377662,0.00063104666,0.0016112095,0.001250178,0.0005595533,0.0025387593,0.00013693052,0.00023833886],"category_scores_gemma":[0.0063659903,0.00018015706,0.00013188994,0.0049851993,0.00030099225,0.0006422438,0.0006827608,0.0011850853,0.00014180168],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008902332,0.0010002716,0.0029119055,0.0003799844,0.00019712532,0.0011065854,0.47352132,0.011308002,0.000087670946,0.058310937,0.028815307,0.42147067],"study_design_scores_gemma":[0.000968453,0.0002740884,0.036706913,0.00013362734,0.000006583116,0.000025358306,0.288224,0.00053249486,0.003897289,0.0041058385,0.6649095,0.00021585124],"about_ca_topic_score_codex":0.000023752082,"about_ca_topic_score_gemma":0.00003008023,"teacher_disagreement_score":0.63609415,"about_ca_system_score_codex":0.0025279676,"about_ca_system_score_gemma":0.026185913,"threshold_uncertainty_score":0.98511505},"labels":[],"label_agreement":null},{"id":"W3015620140","doi":"10.22230/ijepl.2020v16n6a949","title":"How a Networked Approach to Building Capacity in Knowledge Mobilization Supports Research Impact","year":2020,"lang":"en","type":"article","venue":"International Journal of Education Policy and Leadership","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"York University; Queen's University","funders":"","keywords":"Networked learning; Work (physics); Knowledge management; Capacity building; Perception; Sociology; Computer science; Psychology; Political science; Pedagogy; Engineering; Educational technology","score_opus":0.7833021679620529,"score_gpt":0.6036816553006714,"score_spread":0.17962051266138146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3015620140","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8416639,0.00037069767,0.013282332,0.13770227,0.0008681287,0.00029917795,0.000005598182,0.000007359913,0.0058005233],"genre_scores_gemma":[0.99392205,0.000024778814,0.001809295,0.0018392245,0.0017158604,0.000009599725,0.000004079279,0.000007041121,0.00066804513],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9969656,0.0005301979,0.0005827384,0.00022331644,0.0014768133,0.00022132923],"domain_scores_gemma":[0.9965955,0.0006615516,0.0003002447,0.000116791096,0.002008543,0.0003173839],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0052593006,0.00009843091,0.00018402515,0.0013293988,0.00007060318,0.00056391564,0.0005835634,0.00006233756,0.00009440182],"category_scores_gemma":[0.007133716,0.00007533843,0.00007647748,0.0014088915,0.00007230938,0.0008321063,0.0000567472,0.0003425743,0.00001509846],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010282621,0.0021784494,0.24973401,0.000087936016,0.00020487957,0.0000072606754,0.2082182,0.04572944,0.004313702,0.06936682,0.14036901,0.278762],"study_design_scores_gemma":[0.0032927897,0.0013500099,0.46949005,0.0005381493,0.000028963528,0.00034808184,0.13948338,0.07679901,0.0014981473,0.03946553,0.26692533,0.000780524],"about_ca_topic_score_codex":0.000066944005,"about_ca_topic_score_gemma":0.000025460462,"teacher_disagreement_score":0.2779815,"about_ca_system_score_codex":0.00032394688,"about_ca_system_score_gemma":0.0016611915,"threshold_uncertainty_score":0.85402393},"labels":[],"label_agreement":null},{"id":"W3016011794","doi":"","title":"Actionable knowledge and the art of engagement","year":2019,"lang":"en","type":"article","venue":"AGU Fall Meeting Abstracts","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science","score_opus":0.11470771171054184,"score_gpt":0.4197222890543502,"score_spread":0.3050145773438084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3016011794","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6776951,0.00012169898,0.000011479584,0.0008850555,0.0002694474,0.00016250084,7.4546386e-7,0.000009204564,0.32084477],"genre_scores_gemma":[0.98751366,0.000047004614,0.00036433648,0.00016976592,0.00004409717,0.000009012078,0.0000015117398,0.0000043577234,0.011846276],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99816185,0.0002225681,0.0004951605,0.00020756875,0.0007761182,0.00013672681],"domain_scores_gemma":[0.99659723,0.002477921,0.00030588807,0.00032537576,0.00025079466,0.00004278075],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010415872,0.00007735948,0.00017353497,0.00008031565,0.00012324585,0.00009249194,0.00025152732,0.000033800738,0.00018192238],"category_scores_gemma":[0.0012133297,0.000043891683,0.00004977664,0.00018992274,0.00007419986,0.00019829119,0.00009224093,0.00013746382,0.0014943978],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035050948,0.0004266834,0.7691245,0.00012541706,0.00014491602,0.0000022496179,0.012481335,0.0322666,0.004278248,0.02208,0.06773298,0.09098654],"study_design_scores_gemma":[0.0022599648,0.000091483504,0.51976573,0.000097893724,0.000025275673,0.0000047654025,0.0030658382,0.011054185,0.0020658919,0.0049431263,0.45644748,0.00017838119],"about_ca_topic_score_codex":0.00018456543,"about_ca_topic_score_gemma":0.0002951218,"teacher_disagreement_score":0.3887145,"about_ca_system_score_codex":0.000016295353,"about_ca_system_score_gemma":0.000083678184,"threshold_uncertainty_score":0.9992831},"labels":[],"label_agreement":null},{"id":"W3017631649","doi":"","title":"A Comparison of Quality Assurance Systems in International Students’ Education: Australia, Canada, the Netherlands’s Cases","year":2014,"lang":"en","type":"article","venue":"Korean Journal of Comparative Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quality assurance; Political science; Quality (philosophy); Business; Marketing","score_opus":0.334820014415581,"score_gpt":0.5916591837435246,"score_spread":0.25683916932794354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3017631649","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98871547,0.0003482093,0.0008342856,0.0027451112,0.0039677396,0.00019363394,0.00000570837,0.0000013634351,0.0031884804],"genre_scores_gemma":[0.99791205,0.0000076231345,0.00019181159,0.00014186998,0.00041957965,0.000012943022,0.0000075683524,0.0000029933115,0.0013035642],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.994875,0.001178521,0.0016028488,0.00014223954,0.0020932113,0.00010817713],"domain_scores_gemma":[0.9936784,0.0018944715,0.0019970092,0.00028257788,0.002066387,0.00008117179],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0056437757,0.000111095986,0.00042820178,0.0002212822,0.00007566643,0.00016049329,0.0009053398,0.000028667531,0.00024406759],"category_scores_gemma":[0.0008708972,0.00006960668,0.00006389586,0.00041196664,0.000072627045,0.00034735465,0.000025656278,0.00020930111,0.000010366813],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000064688335,0.0005347849,0.9222787,0.000008483579,0.00003097871,1.5231919e-7,0.006199925,0.0063646543,0.00005584987,0.004144591,0.055816874,0.004500333],"study_design_scores_gemma":[0.00032869427,0.00011432081,0.927024,0.0001210704,0.000011562791,0.00001951255,0.031070309,0.0012695829,0.00026226288,0.0011677917,0.038526293,0.00008460263],"about_ca_topic_score_codex":0.034146845,"about_ca_topic_score_gemma":0.14938058,"teacher_disagreement_score":0.11523373,"about_ca_system_score_codex":0.0002543502,"about_ca_system_score_gemma":0.0034994658,"threshold_uncertainty_score":0.97228485},"labels":[],"label_agreement":null},{"id":"W301898455","doi":"10.55016/ojs/jet.v19i1.44156","title":"Implementing Theory and Practice: The Right Blend","year":2018,"lang":"en","type":"article","venue":"Journal of educational thought.","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Psychology; Pedagogy; Mathematics education; Sociology; Epistemology; Social psychology; Philosophy","score_opus":0.13792143162005277,"score_gpt":0.5609009394241523,"score_spread":0.42297950780409954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W301898455","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4385313,0.0016140655,0.004248639,0.2732762,0.0040071714,0.00023425772,0.0000072304997,0.000004532754,0.2780766],"genre_scores_gemma":[0.97266686,0.00006754007,0.011934479,0.0030263064,0.0030751615,0.000002886653,7.999707e-7,0.0000051222714,0.009220872],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99715066,0.000767909,0.0006218789,0.0001076288,0.0012079561,0.00014395708],"domain_scores_gemma":[0.98574364,0.011508593,0.0008575854,0.00019269335,0.0016274792,0.00006999247],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.027973134,0.000063936175,0.00010759168,0.00013370374,0.0004591095,0.0002580959,0.0003659697,0.00001677718,0.008870309],"category_scores_gemma":[0.009914801,0.000031389685,0.000054632466,0.0003243868,0.00015511438,0.0008386105,0.000069364476,0.00013795319,0.00014853831],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001289381,0.00009916352,0.006183322,0.0000013405023,0.000053276726,6.574496e-7,0.002176594,0.000009172618,0.00033523884,0.89144325,0.07000977,0.029559247],"study_design_scores_gemma":[0.00023895326,0.00008360429,0.026355695,0.000010170145,0.000027628199,0.000267405,0.0038319284,0.00007319035,0.00026684615,0.22080697,0.74799204,0.00004559014],"about_ca_topic_score_codex":0.0000016138096,"about_ca_topic_score_gemma":0.000013883452,"teacher_disagreement_score":0.6779823,"about_ca_system_score_codex":0.000031855114,"about_ca_system_score_gemma":0.00062942505,"threshold_uncertainty_score":0.9984251},"labels":[],"label_agreement":null},{"id":"W3020197475","doi":"10.1177/1356389020911060","title":"Evaluators in the Anthropocene","year":2020,"lang":"en","type":"article","venue":"Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria; Université de Sherbrooke","funders":"","keywords":"Anthropocene; Biosphere; Environmental ethics; Action (physics); State (computer science); Natural (archaeology); Call to action; Earth system science; Work (physics); Non-human; Environmental planning; Environmental resource management; Political science; Ecology; History; Geography; Archaeology; Environmental science; Business; Law; Computer science; Biology; Engineering","score_opus":0.4706248224375595,"score_gpt":0.5890246793657072,"score_spread":0.11839985692814775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3020197475","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86963075,0.00021198446,0.0021305499,0.077694185,0.0004110751,0.00093008863,0.0000029298742,0.00002579192,0.048962638],"genre_scores_gemma":[0.9939139,0.000010993906,0.00021109692,0.0056004,0.00015977872,0.000057573816,0.000010209631,0.000004281208,0.000031793596],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.992666,0.001463494,0.00053505384,0.00031193008,0.004875513,0.00014800612],"domain_scores_gemma":[0.99841696,0.0005746899,0.00015630231,0.00034349237,0.00045728445,0.000051275198],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.022130672,0.000083176004,0.0001222252,0.000104978906,0.00011860603,0.00016696916,0.0005318873,0.000036730922,0.008981529],"category_scores_gemma":[0.0050010183,0.000047837697,0.00005152376,0.0012963549,0.000044363584,0.00038888564,0.000034640423,0.00012642698,0.001813462],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007130217,0.00014928132,0.15976445,0.0000054643765,0.000011594583,0.0000027001577,0.019898431,0.023159439,0.0004392241,0.0050968975,0.06141278,0.72998846],"study_design_scores_gemma":[0.0008116145,0.00012036655,0.34387082,0.0000043045447,0.000017072876,0.0000013464153,0.0031195544,0.6204537,0.00019345488,0.015438916,0.015872426,0.00009642368],"about_ca_topic_score_codex":0.000007869057,"about_ca_topic_score_gemma":0.00002358612,"teacher_disagreement_score":0.729892,"about_ca_system_score_codex":0.000059039667,"about_ca_system_score_gemma":0.00031491774,"threshold_uncertainty_score":0.9989637},"labels":[],"label_agreement":null},{"id":"W302023808","doi":"10.3138/jcs.48.2.224","title":"Activists, Policy Sedimentation, and Policy Change: The Case of Early Childhood Education in Ontario","year":2014,"lang":"en","type":"article","venue":"Journal of Canadian Studies","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Legislation; Early childhood education; Government (linguistics); Public administration; Early childhood; Education policy; Child care; Political science; Sociology; Economic growth; Law; Pedagogy; Higher education; Economics; Psychology; Medicine","score_opus":0.16159048880894,"score_gpt":0.48192102434475476,"score_spread":0.32033053553581475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W302023808","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9740178,0.00046670315,0.0000035598828,0.022831457,0.00018474935,0.000101335245,0.0000018004031,5.442525e-7,0.0023920564],"genre_scores_gemma":[0.9976103,0.00019546425,0.00009947924,0.0014028997,0.00030526402,0.0000043789805,2.0155585e-7,0.0000026811995,0.0003793761],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9988671,0.00014211693,0.0004423587,0.00007423521,0.00035662326,0.00011758787],"domain_scores_gemma":[0.9985381,0.00027923757,0.00040456562,0.00011974284,0.00053830724,0.00012007601],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021218879,0.00006381047,0.00018653263,0.0015626055,0.00013225489,0.000055106924,0.00013264254,0.000019759576,0.000031047322],"category_scores_gemma":[0.00093704934,0.000038367558,0.00003330568,0.0007324924,0.000070614224,0.00033450537,0.000019268111,0.00012146593,0.0000028516047],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014597693,0.000055530807,0.29871514,0.0000052761493,0.00008379412,0.000012424493,0.14689215,0.00003095459,0.000010417526,0.008783359,0.0057966667,0.53959966],"study_design_scores_gemma":[0.0002673423,0.0001246137,0.96185386,0.000027705519,0.0000111609215,0.00016547156,0.0170452,0.00000934542,0.000014756336,0.0057512233,0.014689895,0.000039402486],"about_ca_topic_score_codex":0.77961725,"about_ca_topic_score_gemma":0.98074764,"teacher_disagreement_score":0.66313875,"about_ca_system_score_codex":0.0003748772,"about_ca_system_score_gemma":0.005455703,"threshold_uncertainty_score":0.9678183},"labels":[],"label_agreement":null},{"id":"W3021032006","doi":"10.1007/s11266-020-00223-8","title":"Seeing Through the Logical Framework","year":2020,"lang":"en","type":"article","venue":"VOLUNTAS International Journal of Voluntary and Nonprofit Organizations","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Inscribed figure; Logical framework; Reading (process); Sociology; Conceptual framework; Political science; Engineering ethics; Management science; Epistemology; Knowledge management; Computer science; Social science; Engineering; Law","score_opus":0.12202821821252864,"score_gpt":0.44098229351427826,"score_spread":0.31895407530174963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3021032006","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39459005,0.00088330737,0.3682757,0.23021008,0.0028520313,0.0002494393,0.000059830585,0.00003747789,0.002842086],"genre_scores_gemma":[0.9781607,0.0002681212,0.008039584,0.012087258,0.0012260416,0.0000016139528,0.000010482911,0.000011852456,0.00019438879],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968656,0.00018789431,0.0008712637,0.00021205234,0.0017273856,0.00013585988],"domain_scores_gemma":[0.9960149,0.0009139429,0.00053513655,0.0001754224,0.0022275522,0.00013303944],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001095888,0.00012904452,0.00021365784,0.00010483461,0.00028732713,0.0003352084,0.0011040082,0.00007133983,0.004241441],"category_scores_gemma":[0.0040787826,0.0000760697,0.000086443346,0.0009478016,0.00013592125,0.00091965444,0.00022305727,0.0004045115,0.00016214872],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029712165,0.00022449173,0.7625239,0.00000913388,0.0005159733,0.00008948781,0.024074677,0.0056883073,0.0010032393,0.115725935,0.07117426,0.018673483],"study_design_scores_gemma":[0.0020485616,0.00089262443,0.29418528,0.0001446882,0.0002257998,0.0007925641,0.016466945,0.027881404,0.001909358,0.12394357,0.53088313,0.0006260675],"about_ca_topic_score_codex":0.000014179712,"about_ca_topic_score_gemma":0.000008508949,"teacher_disagreement_score":0.5835706,"about_ca_system_score_codex":0.00004509665,"about_ca_system_score_gemma":0.0002309572,"threshold_uncertainty_score":0.9966688},"labels":[],"label_agreement":null},{"id":"W3022015682","doi":"10.7202/1069651ar","title":"The Impact of Quality Assurance Policies on Curriculum Development in Ontario Postsecondary Education","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Higher Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Quality assurance; Accountability; Curriculum; Context (archaeology); Higher education; Quality (philosophy); Quality management; Political science; Public relations; Business; Marketing; Service (business)","score_opus":0.14146963313147348,"score_gpt":0.4828812715166655,"score_spread":0.341411638385192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3022015682","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9804754,0.0005670982,0.0000060130965,0.01190132,0.0012006126,0.000111308225,0.0000023955504,0.0000010120416,0.005734793],"genre_scores_gemma":[0.9956692,0.0000057466764,0.00016684298,0.0013330957,0.00013235575,0.0000050036606,0.0000041202998,0.0000040400314,0.0026796337],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9980612,0.00020994268,0.0008777717,0.00011323285,0.0005746025,0.00016326661],"domain_scores_gemma":[0.99766845,0.000235653,0.000692849,0.00017552215,0.0008890965,0.00033843794],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017456891,0.000088949244,0.00017900161,0.00028844737,0.0001342647,0.0001340406,0.0004098674,0.000036962952,0.0014421599],"category_scores_gemma":[0.00051409786,0.00005494645,0.000086374996,0.00047392037,0.00004551487,0.00031627223,0.0000064602127,0.00022379457,0.00003995847],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016647537,0.00007380355,0.9189948,0.000002894945,0.000012610391,2.3628724e-7,0.0063092615,0.00038791768,0.000039500956,0.0012891338,0.052971065,0.019902172],"study_design_scores_gemma":[0.000109444496,0.000092901,0.8601407,0.00003598566,0.0000022334918,0.0000024908159,0.001284646,0.0000067376063,0.00006537725,0.0010640937,0.1371391,0.000056315483],"about_ca_topic_score_codex":0.13506307,"about_ca_topic_score_gemma":0.5197259,"teacher_disagreement_score":0.38466284,"about_ca_system_score_codex":0.001129511,"about_ca_system_score_gemma":0.052276254,"threshold_uncertainty_score":0.99947065},"labels":[],"label_agreement":null},{"id":"W3022711913","doi":"","title":"Mapping Positive Change in Manitoba, Chihuahua, Mexico","year":2016,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Geography; Regional science; Archaeology","score_opus":0.6686579710476815,"score_gpt":0.6616068560562918,"score_spread":0.007051114991389773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3022711913","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97166306,0.0030375256,0.0011437502,0.0030022173,0.0010789441,0.0008043458,0.00005998315,0.000024855213,0.019185314],"genre_scores_gemma":[0.9932941,0.003871164,0.00022220348,0.0014153902,0.00025998772,0.000092738854,0.0000040316654,0.000026793527,0.00081355195],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9939992,0.00071774784,0.0015896338,0.0006368615,0.002568572,0.00048800424],"domain_scores_gemma":[0.995619,0.001428961,0.0012582093,0.00070769084,0.00071880425,0.00026732957],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008643961,0.00029821423,0.00078440155,0.0021071474,0.00024469759,0.0015085053,0.0039669876,0.000113499125,0.037109874],"category_scores_gemma":[0.0011533952,0.00018960089,0.00019360287,0.0022308978,0.00013948273,0.00630468,0.001113675,0.00028645256,0.00044273256],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007594864,0.00012828855,0.7817897,0.00000641849,0.000035444533,0.000019440777,0.000643174,0.00001485117,0.015274459,0.00018401617,0.009539886,0.19228832],"study_design_scores_gemma":[0.000750064,0.00001302893,0.9635946,0.0005174141,0.0000095820715,0.000008834433,0.00048344294,0.00023049329,0.008136625,0.013992171,0.011956915,0.0003067919],"about_ca_topic_score_codex":0.0011263767,"about_ca_topic_score_gemma":0.00116577,"teacher_disagreement_score":0.19198154,"about_ca_system_score_codex":0.00024872588,"about_ca_system_score_gemma":0.00023225819,"threshold_uncertainty_score":0.99952805},"labels":[],"label_agreement":null},{"id":"W3023199880","doi":"10.1002/jcop.22372","title":"What sets the conditions for success in community‐partnered evaluation work? Multiple perspectives on a small‐scale research‐practice partnership evaluation","year":2020,"lang":"en","type":"article","venue":"Journal of Community Psychology","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact","funders":"Wake Forest Clinical and Translational Science Institute, Wake Forest School of Medicine; National Institutes of Health; National Center for Advancing Translational Sciences; Kate B. Reynolds Charitable Trust","keywords":"General partnership; Scale (ratio); Foundation (evidence); Work (physics); Public relations; Best practice; Knowledge management; Psychology; Medical education; Engineering ethics; Political science; Medicine; Computer science; Engineering","score_opus":0.8013742476961554,"score_gpt":0.6811201698389863,"score_spread":0.12025407785716913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3023199880","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86795145,0.00044712125,0.0004978505,0.124834076,0.000515036,0.0011594715,0.000006881277,0.000008629317,0.0045794905],"genre_scores_gemma":[0.992614,0.0002327374,0.0003570597,0.006378657,0.00017899867,0.00015859613,0.000029248478,0.000014173621,0.000036543388],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9383917,0.05635963,0.0013598843,0.00020369179,0.0033176185,0.0003675056],"domain_scores_gemma":[0.9536135,0.036598682,0.0010818504,0.0011346482,0.00740174,0.00016957523],"candidate_categories":["metaresearch","sts","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13479683,0.0001684972,0.00040520425,0.00062190654,0.0014535312,0.0005640794,0.002041601,0.0001580066,0.0005636864],"category_scores_gemma":[0.04779881,0.000117410396,0.00018252642,0.0017588997,0.00044014485,0.0015860852,0.00016015171,0.0033300258,0.00007216133],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008680337,0.0058329403,0.017525045,0.000030865685,0.000276532,0.0000042596544,0.6828923,0.030169707,0.0010267938,0.0021706554,0.09564109,0.15574948],"study_design_scores_gemma":[0.007883642,0.003171345,0.23236145,0.00017815117,0.00013538283,0.000034818942,0.65854377,0.031604853,0.00009518167,0.041797906,0.023974717,0.00021879286],"about_ca_topic_score_codex":0.00005279713,"about_ca_topic_score_gemma":0.0013663375,"teacher_disagreement_score":0.2148364,"about_ca_system_score_codex":0.00037189625,"about_ca_system_score_gemma":0.0006986859,"threshold_uncertainty_score":0.99984646},"labels":[],"label_agreement":null},{"id":"W3024258853","doi":"10.1007/978-3-030-43597-4_8","title":"Evaluating Learning-Centred Leadership","year":2020,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Rubric; Accountability; Order (exchange); Computer science; Institution; Knowledge management; Political science; Management science; Engineering ethics; Sociology; Mathematics education; Psychology; Engineering; Business; Social science","score_opus":0.8060100564351427,"score_gpt":0.5434709869061345,"score_spread":0.2625390695290082,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3024258853","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002169781,0.00036716924,0.0006474445,0.008137866,0.00045954494,0.00029657836,0.000004510505,0.0001352256,0.98993],"genre_scores_gemma":[0.017799105,0.00003995005,0.0012199961,0.0028070414,0.00031280916,0.0000062938216,0.000041822423,0.00004030708,0.97773266],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9932461,0.00016708385,0.0010110575,0.00081419764,0.0044886954,0.00027286378],"domain_scores_gemma":[0.9969047,0.0010763564,0.00064248877,0.0005474013,0.00061451865,0.00021458828],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0029722669,0.0003297689,0.0005149868,0.00025444556,0.00020702173,0.0003753466,0.0007585944,0.000261172,0.122543104],"category_scores_gemma":[0.0021071252,0.00024347618,0.00028277267,0.00011994704,0.000083980005,0.00021598487,0.00018739121,0.00076611014,0.032589916],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007965408,0.000021475631,0.00043149834,0.000036336503,0.00012090094,0.000017293945,0.0021357345,0.0019787306,0.000093746814,0.32908154,0.12390322,0.5420999],"study_design_scores_gemma":[0.0004503771,0.00028688097,0.00009142393,0.00006385934,0.000049259525,0.0000036484887,0.0012870713,0.039986107,0.00002863411,0.04341593,0.91391283,0.00042397506],"about_ca_topic_score_codex":0.0000027020255,"about_ca_topic_score_gemma":0.000016906644,"teacher_disagreement_score":0.7900096,"about_ca_system_score_codex":0.000089997106,"about_ca_system_score_gemma":0.000520365,"threshold_uncertainty_score":0.99286705},"labels":[],"label_agreement":null},{"id":"W3024420656","doi":"10.3138/cpp.2018-048","title":"The Leadership Legacy of Commission Chairs: Building on and Extending a Comparative Study of Ten Canadian Commissions of Inquiry","year":2020,"lang":"en","type":"article","venue":"Canadian Public Policy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Fiduciary; Commission; Public administration; Law; Management; Sociology; Political science; Economics","score_opus":0.6546103291880176,"score_gpt":0.5246975933465341,"score_spread":0.12991273584148355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3024420656","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91387707,0.00014398506,0.000022235878,0.070094265,0.00010721677,0.00047498912,0.000059344464,0.0000071937816,0.015213721],"genre_scores_gemma":[0.9986894,0.00000725883,0.000035478686,0.0009768248,0.00007875684,0.000009122176,0.0000029960129,0.0000073055467,0.00019284316],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9975433,0.00039988465,0.00065965665,0.00024347044,0.00076139893,0.00039233745],"domain_scores_gemma":[0.9967593,0.0008059989,0.00034925298,0.0004418224,0.00037180836,0.0012718393],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018834056,0.0001325615,0.0003567302,0.0010185678,0.0004965199,0.00015149066,0.00074678805,0.000058722046,0.00016324985],"category_scores_gemma":[0.0022960322,0.000089564455,0.000050617793,0.0015924292,0.00028990596,0.00034007625,0.000065269895,0.00019573752,0.0000060052425],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001220822,0.0003241373,0.25848204,0.000079317004,0.00024907308,0.000011163586,0.20898007,0.0007393631,0.0006708244,0.27086514,0.078910716,0.18056607],"study_design_scores_gemma":[0.0017989717,0.0014486522,0.4584222,0.00015601295,0.000028267064,0.0000051999114,0.3600095,0.012368112,0.00054522883,0.0014579081,0.1634045,0.0003554394],"about_ca_topic_score_codex":0.46457425,"about_ca_topic_score_gemma":0.80646944,"teacher_disagreement_score":0.34189516,"about_ca_system_score_codex":0.00020574749,"about_ca_system_score_gemma":0.005034104,"threshold_uncertainty_score":0.89302844},"labels":[],"label_agreement":null},{"id":"W3025305511","doi":"","title":"Translating Research into Practice: Establishing a Network of Climate Change Practitioners in Ontario, Canada","year":2017,"lang":"en","type":"article","venue":"AGUFM","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Climate change; Environmental resource management; Environmental science; Oceanography; Geology","score_opus":0.4481536271303522,"score_gpt":0.5642988665971949,"score_spread":0.11614523946684269,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3025305511","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7677256,0.00013536662,0.000065720866,0.036382873,0.0009236935,0.0005175324,0.000005028271,0.000008906308,0.1942353],"genre_scores_gemma":[0.9962168,0.00006049535,0.0029285776,0.00034708437,0.00011619979,0.000037844162,0.0000045962006,0.00000600474,0.00028239636],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99612707,0.0004312551,0.0005374731,0.00027812595,0.0022570714,0.00036900255],"domain_scores_gemma":[0.99609816,0.0019478037,0.0005324634,0.0006489024,0.0006942331,0.00007843129],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017419657,0.000076105774,0.00018629844,0.00011530819,0.0007081818,0.00047470658,0.00064348243,0.000051739913,0.0006877581],"category_scores_gemma":[0.0060082837,0.00006383394,0.000028800821,0.00035872313,0.000073741554,0.0028529349,0.00013895806,0.00044742724,0.00002052152],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020752585,0.00012231579,0.6761757,0.00003093822,0.000022663824,0.00006573547,0.03291515,0.006364404,0.00010797675,0.008969933,0.0070986445,0.267919],"study_design_scores_gemma":[0.0010489252,0.00014495052,0.6439382,0.00032096298,0.000014249414,0.0000080551545,0.018373441,0.023032537,0.00006597273,0.008618811,0.30416253,0.00027139386],"about_ca_topic_score_codex":0.9875398,"about_ca_topic_score_gemma":0.9995227,"teacher_disagreement_score":0.2970639,"about_ca_system_score_codex":0.00044252863,"about_ca_system_score_gemma":0.0022571713,"threshold_uncertainty_score":0.75304693},"labels":[],"label_agreement":null},{"id":"W3026166820","doi":"","title":"La qualité de l'audit : histoire d'un concept et de son utilisation dans la recherche académique (ou l'histoire de la naissance d'une chimère)","year":2016,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.16702657808962737,"score_gpt":0.4264912603093091,"score_spread":0.2594646822196818,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3026166820","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17469852,0.0013290269,0.50133014,0.039975848,0.0004157862,0.0006482037,0.00015429521,0.0003654608,0.28108272],"genre_scores_gemma":[0.9189357,0.0011228935,0.05287033,0.00071785547,0.00006600232,0.00025290044,0.00023481164,0.00008224217,0.025717238],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9104188,0.08412098,0.0014841357,0.0014273355,0.001808943,0.00073978904],"domain_scores_gemma":[0.96481085,0.028031118,0.0016024797,0.0029983805,0.0021330856,0.00042411295],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.09855621,0.00057420426,0.00068406353,0.00037173895,0.0009790293,0.0009633534,0.002979899,0.0014448388,0.0007431488],"category_scores_gemma":[0.024151389,0.000516315,0.00040446417,0.0008169811,0.001464933,0.00050266663,0.0011124556,0.002355151,0.000095172894],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000082815655,0.0008605605,0.019876804,0.00013955813,0.000118493575,0.000022284734,0.12994504,0.0006861586,0.015567033,0.32975742,0.011112507,0.49183133],"study_design_scores_gemma":[0.0026526398,0.000005557029,0.16959226,0.004064619,0.00016308788,0.00017758238,0.0051248027,0.038525663,0.07619624,0.31670916,0.3849059,0.00188247],"about_ca_topic_score_codex":0.0018452054,"about_ca_topic_score_gemma":0.0025332924,"teacher_disagreement_score":0.74423724,"about_ca_system_score_codex":0.0022800197,"about_ca_system_score_gemma":0.004268637,"threshold_uncertainty_score":0.9999465},"labels":[],"label_agreement":null},{"id":"W3027127350","doi":"10.36834/cmej.70331","title":"A plea for program evaluation in a pandemic","year":2020,"lang":"en","type":"article","venue":"Canadian Medical Education Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Plea; Pandemic; Computer science; Coronavirus disease 2019 (COVID-19); Data science; Medicine; Political science; Law; Pathology","score_opus":0.31903570275946885,"score_gpt":0.5713732575257328,"score_spread":0.2523375547662639,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3027127350","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2670227,0.0007288897,0.0023272613,0.7121484,0.0034590007,0.0029630917,0.000011379181,0.000033587326,0.011305641],"genre_scores_gemma":[0.93666995,0.000040083716,0.0018799114,0.059305508,0.0014074198,0.00041595649,0.00001938897,0.00000852167,0.0002532871],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9963831,0.0002648925,0.00063110853,0.00020597961,0.0022591606,0.00025581536],"domain_scores_gemma":[0.99403703,0.0002290253,0.00016160056,0.000118829055,0.0009997413,0.0044537913],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009215527,0.000072838055,0.00013883735,0.00034510263,0.00014661519,0.00022359972,0.00042769828,0.0001023216,0.04797296],"category_scores_gemma":[0.07388241,0.000057131485,0.0000620871,0.00068090245,0.00003972339,0.00026519693,0.000008441825,0.0003477753,0.00016134203],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008317287,0.000027877373,0.010011202,0.0000022394443,0.0000028589877,9.0438886e-7,0.0013165667,0.00006348262,0.0000016065018,0.000269255,0.09524372,0.893052],"study_design_scores_gemma":[0.00081968,0.000119986435,0.019306138,0.000030447234,0.000008008869,0.000043050448,0.0027455257,0.14791512,0.0000013605827,0.0047333753,0.824191,0.0000863156],"about_ca_topic_score_codex":0.00052007945,"about_ca_topic_score_gemma":0.03595916,"teacher_disagreement_score":0.8929657,"about_ca_system_score_codex":0.0003970208,"about_ca_system_score_gemma":0.0929211,"threshold_uncertainty_score":0.98163205},"labels":[],"label_agreement":null},{"id":"W3027644949","doi":"10.11124/jbies-20-00134","title":"Exploring the world “out there”: the use of scoping reviews in education research","year":2020,"lang":"en","type":"editorial","venue":"JBI Evidence Synthesis","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Excellence in Mining Innovation; Queen's University","funders":"","keywords":"Engineering ethics; Data science; Political science; Engineering; Computer science","score_opus":0.7179115675509535,"score_gpt":0.5932629600633694,"score_spread":0.1246486074875841,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3027644949","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003291865,0.018306917,0.00010052973,0.04525144,0.9233068,0.005736907,0.000029252085,0.000043193682,0.003933092],"genre_scores_gemma":[0.023185011,0.1283163,0.0017905916,0.00109321,0.8080261,0.010328333,0.0000135945,0.00014224031,0.027104635],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98207784,0.007728126,0.0019635072,0.0008238635,0.0069796587,0.00042700663],"domain_scores_gemma":[0.8034039,0.19018614,0.0014457395,0.0028645643,0.001972131,0.00012750909],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.048814524,0.0002802843,0.0008000413,0.00072498893,0.00041293897,0.0008731684,0.0030556691,0.00014576684,0.0009251402],"category_scores_gemma":[0.23881358,0.00013493824,0.0002619634,0.0031247719,0.0003104939,0.0018547991,0.00048661412,0.0014827544,0.00096085336],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031845597,0.000025245306,0.00047205965,0.00015976,0.0000082727165,4.909009e-7,0.0017397618,0.000044971686,0.000023580164,0.00005777528,0.8238468,0.17358944],"study_design_scores_gemma":[0.000029969402,0.000027422157,0.0012385818,0.016084373,0.000032082116,1.4286654e-7,0.0013451724,0.00022836102,0.00023845135,0.00031524544,0.9803058,0.00015441295],"about_ca_topic_score_codex":0.00050269725,"about_ca_topic_score_gemma":0.0050243787,"teacher_disagreement_score":0.18999906,"about_ca_system_score_codex":0.00030871434,"about_ca_system_score_gemma":0.0033576118,"threshold_uncertainty_score":0.99998814},"labels":[],"label_agreement":null},{"id":"W3027908324","doi":"10.1016/b978-0-7295-4299-9.00010-8","title":"10.1016/b978-0-7295-4299-9.00010-8","year":2000,"lang":"en","type":"book-chapter","venue":"Time to knit","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Reading (process); History; Linguistics; Philosophy","score_opus":0.08553090200001398,"score_gpt":0.34527458690360485,"score_spread":0.2597436849035909,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3027908324","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000016985698,0.00015023688,0.0000045969973,0.0008177073,0.000019943755,0.00047168625,0.000107158136,0.00011226503,0.9983147],"genre_scores_gemma":[0.0000045779657,0.0000016720605,0.00015805452,0.00029859968,0.00046739605,0.000026967797,0.00007834868,0.00006551513,0.99889886],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99459714,0.00007785217,0.0010522319,0.0008560535,0.0030226456,0.00039410056],"domain_scores_gemma":[0.99698967,0.0004893772,0.0003689194,0.001338911,0.0004712723,0.00034183808],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0021355634,0.0004677493,0.00066572294,0.0006502663,0.0001973598,0.00037331006,0.0012656715,0.00035554546,0.9998473],"category_scores_gemma":[0.00018961959,0.00037914974,0.0003024392,0.00019934459,0.00009716791,0.00028142083,0.00020801506,0.00042541316,0.9995538],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039325536,0.000012756982,4.5307505e-8,0.0000018611969,0.000019106188,0.000004557495,0.000016623551,0.00007093392,9.856096e-7,0.00018399223,0.40294287,0.5967069],"study_design_scores_gemma":[0.00024654955,0.00020441612,0.000010274798,0.00006461251,0.00003883903,0.000009826953,0.0000016962163,0.00040976796,0.0000058675596,0.0039822855,0.99454033,0.00048551953],"about_ca_topic_score_codex":0.0000074004506,"about_ca_topic_score_gemma":0.0000015605674,"teacher_disagreement_score":0.59622145,"about_ca_system_score_codex":0.00013075018,"about_ca_system_score_gemma":0.0003825825,"threshold_uncertainty_score":0.99986607},"labels":[],"label_agreement":null},{"id":"W3028275031","doi":"10.1093/oso/9780190939717.003.0003","title":"Improving the Design and Interpretation of Sample Surveys in the Workplace","year":2020,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Sample (material); Stakeholder; Census; Quarter (Canadian coin); Population; Interpretation (philosophy); Survey sampling; Sample size determination; Statistics; Psychology; Geography; Computer science; Public relations; Demography; Political science; Mathematics; Sociology","score_opus":0.22683728133266165,"score_gpt":0.4225129491463852,"score_spread":0.19567566781372356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3028275031","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001776123,0.00017204782,0.77387136,0.0028956092,0.00013855098,0.00065277173,0.000009525068,0.000008491363,0.22207402],"genre_scores_gemma":[0.93476987,0.00010440499,0.0051657883,0.001637107,0.000060218033,0.000021237278,0.00001222543,0.000015009138,0.05821415],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99723333,0.0008765887,0.00053937134,0.00024290649,0.0010345731,0.00007324249],"domain_scores_gemma":[0.99066806,0.008521037,0.00032310784,0.00032561403,0.00014251494,0.000019663325],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01942835,0.00011194886,0.00019791715,0.00009767139,0.000060264585,0.00015712442,0.0004983329,0.000068941634,0.0012049394],"category_scores_gemma":[0.0011677431,0.000048530295,0.00004986852,0.000105246145,0.000080204634,0.0001283567,0.00008704656,0.0002085875,0.00004620592],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043594806,0.000009430434,0.001281284,0.000015052203,0.000020303392,9.3035237e-7,0.0057841726,0.0012839496,0.00001922485,0.083634906,0.0037881413,0.904119],"study_design_scores_gemma":[0.00057083165,0.00037017616,0.012390466,0.0001353944,0.00005400927,0.0000050922986,0.004365792,0.73802847,0.00007413166,0.21806023,0.025562746,0.00038268144],"about_ca_topic_score_codex":0.00006714439,"about_ca_topic_score_gemma":0.0002871785,"teacher_disagreement_score":0.93459225,"about_ca_system_score_codex":0.00001637268,"about_ca_system_score_gemma":0.0001327323,"threshold_uncertainty_score":0.9997081},"labels":[],"label_agreement":null},{"id":"W3028612984","doi":"10.3138/cjpe.61841","title":"Predicting Credentialed Evaluator Status: Characteristics, Comparisons, and Implications for the CE Program","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Victoria; University of Saskatchewan","funders":"","keywords":"Scope (computer science); Sustainability; Order (exchange); Accounting; Political science; Actuarial science; Sociology; Public economics; Business; Economics; Computer science; Finance","score_opus":0.4209077424068388,"score_gpt":0.5372251137668627,"score_spread":0.11631737136002385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3028612984","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8664732,0.004367845,0.030133888,0.082273774,0.0019376079,0.013718896,0.00029748798,0.00007871394,0.0007186214],"genre_scores_gemma":[0.9901622,0.000053613116,0.008222036,0.0005213452,0.00046726022,0.0004969058,0.000041104642,0.0000136880035,0.000021881862],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9966795,0.0003925508,0.001099409,0.00025462292,0.0012295794,0.00034435015],"domain_scores_gemma":[0.9936703,0.00077994436,0.0009936683,0.00025810557,0.0035665457,0.0007314287],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009374411,0.00013554555,0.0002728821,0.00019377764,0.00061480753,0.0010362909,0.000472483,0.000064709326,0.00046095822],"category_scores_gemma":[0.008119296,0.000092448994,0.00012371225,0.0005406236,0.00014400398,0.0004892527,0.000022779162,0.00021358799,0.000012759049],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028100872,0.00003086979,0.22060452,0.000008293332,0.000048612732,2.5202615e-7,0.0011805607,0.00021846846,0.0000309982,0.0002503714,0.006717866,0.7708811],"study_design_scores_gemma":[0.00092362874,0.00066474243,0.5238436,0.000020973639,0.00024960094,0.000010938259,0.0018674121,0.32515803,0.000012149773,0.00091746694,0.1462282,0.000103281374],"about_ca_topic_score_codex":0.0001556882,"about_ca_topic_score_gemma":0.003321597,"teacher_disagreement_score":0.7707778,"about_ca_system_score_codex":0.00016536018,"about_ca_system_score_gemma":0.0041843103,"threshold_uncertainty_score":0.9992976},"labels":[],"label_agreement":null},{"id":"W3029887321","doi":"10.3138/cjpe.61270","title":"A Rapid Review of Evaluation Capacity-Building Strategies for Chronic Disease Prevention","year":2020,"lang":"en","type":"review","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Impact; University of Waterloo","funders":"","keywords":"CLARITY; Context (archaeology); Capacity building; Grey literature; Medicine; Political science; Public relations; Psychology; Business; MEDLINE; Biology","score_opus":0.6926985361281605,"score_gpt":0.6014460517410005,"score_spread":0.09125248438715994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3029887321","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000020472615,0.9845556,0.0031098344,0.0006435616,0.0009905531,0.010271683,0.00010119213,0.000008464499,0.00029866325],"genre_scores_gemma":[0.0004967671,0.9935335,0.0034513634,0.00008267113,0.000621253,0.0014681706,0.0002847773,0.000036179244,0.000025323041],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9881361,0.0029641236,0.0035386595,0.0004810693,0.004511487,0.00036856145],"domain_scores_gemma":[0.9845138,0.0006176855,0.0054684123,0.00055017805,0.008098514,0.00075141387],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.041885644,0.00038473768,0.001776932,0.0010992808,0.00020355567,0.0004248145,0.0007797296,0.00018702711,0.0026366143],"category_scores_gemma":[0.011071915,0.00029382392,0.0013189891,0.0015533676,0.00011926923,0.0010467762,0.000021853397,0.00039858563,0.000028827246],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000071317227,0.000030236552,0.0000034580203,0.016836375,0.00012720644,0.0000014491815,0.00010278455,0.0001524076,2.9020524e-7,0.0005258355,0.002577225,0.9796356],"study_design_scores_gemma":[0.0005918743,0.000767686,0.00003236463,0.059179787,0.0045991703,0.00002259059,0.00010472386,0.014274045,6.297901e-7,0.0100628575,0.9101128,0.0002514677],"about_ca_topic_score_codex":0.000043287517,"about_ca_topic_score_gemma":0.0011036523,"teacher_disagreement_score":0.9793841,"about_ca_system_score_codex":0.0018964339,"about_ca_system_score_gemma":0.080941595,"threshold_uncertainty_score":0.99995136},"labels":[],"label_agreement":null},{"id":"W3031036335","doi":"10.3138/cjpe.61624","title":"Evaluation in the Provinces and Territories: A Cross-Canada Snapshot and Call to Action","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Prince Edward Island; University of Victoria; Université Laval; Dalhousie University","funders":"","keywords":"Snapshot (computer storage); Government (linguistics); Public administration; Political science; State (computer science); Action (physics); Regional science; Public relations; Geography; Computer science","score_opus":0.4273514882657697,"score_gpt":0.5421958438593792,"score_spread":0.11484435559360956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3031036335","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9739662,0.00040697056,0.00008848599,0.022966756,0.0004173494,0.001498191,0.000007812656,0.0000021011424,0.00064613257],"genre_scores_gemma":[0.99785733,0.000007943819,0.0004521502,0.0013414884,0.00022712896,0.00009305065,0.000008911477,0.0000042609245,0.000007739226],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9950007,0.0008113966,0.0006576784,0.00021962263,0.0031216752,0.00018892932],"domain_scores_gemma":[0.99687696,0.00028095525,0.0003256682,0.00013491616,0.0019774141,0.00040411792],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018768318,0.00010061355,0.00016289369,0.00022607928,0.00019460155,0.00074834574,0.00028534824,0.00004704018,0.00032963883],"category_scores_gemma":[0.0064143785,0.00006705979,0.000025749649,0.00065639993,0.00006897769,0.0006411579,0.000012589803,0.00018228496,0.0000025414586],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027556813,0.000011466481,0.10977822,0.0000070778865,0.000011134509,0.000004017509,0.0062019904,0.0020795176,0.000033787317,0.00007475714,0.0033232195,0.87844723],"study_design_scores_gemma":[0.001131879,0.0008097955,0.74557894,0.000037175574,0.00008816783,0.00003826668,0.007100509,0.14606667,0.000050244707,0.0021127698,0.09683095,0.00015465372],"about_ca_topic_score_codex":0.09195006,"about_ca_topic_score_gemma":0.94499004,"teacher_disagreement_score":0.8782926,"about_ca_system_score_codex":0.00046496475,"about_ca_system_score_gemma":0.008853809,"threshold_uncertainty_score":0.9967651},"labels":[],"label_agreement":null},{"id":"W3031535673","doi":"10.3138/cjpe.61660","title":"A Transdisciplinary Model of Program Outcomes for Enhanced Evaluation Practice","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychological intervention; Taxonomy (biology); Management science; Context (archaeology); Psychology; Program evaluation; Cognition; Computer science; Knowledge management; Process management; Political science; Ecology; Business; Engineering","score_opus":0.6071453782410605,"score_gpt":0.6059684492511166,"score_spread":0.0011769289899439261,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3031535673","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7731614,0.00089898065,0.1348249,0.0658646,0.0013137662,0.017281484,0.000103000835,0.00005265678,0.006499202],"genre_scores_gemma":[0.9364724,0.00000849848,0.062105753,0.000577876,0.0001291014,0.0006191282,0.00003251037,0.000016760645,0.00003792903],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9931051,0.00071531394,0.0016600806,0.00032286556,0.0038766414,0.00032001224],"domain_scores_gemma":[0.98621047,0.0006718162,0.0016157718,0.00029348666,0.010623391,0.0005850527],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021927936,0.00018204197,0.00045643927,0.00044809058,0.00020346706,0.00024649285,0.0005685971,0.00011592322,0.00059628434],"category_scores_gemma":[0.013926356,0.00014202688,0.00031794567,0.00086551136,0.00010358208,0.0013410931,0.000012989241,0.00021055536,0.000016246235],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001721246,0.0001750773,0.00065671373,0.000025826708,0.00008635393,6.70479e-7,0.010795212,0.09600993,0.00053590175,0.00029180964,0.0013935665,0.8898568],"study_design_scores_gemma":[0.0025944225,0.002137423,0.0031941812,0.000041627383,0.00050853414,0.000005687465,0.005649282,0.9694816,0.00075795903,0.009220995,0.0062376033,0.00017072202],"about_ca_topic_score_codex":0.00003765104,"about_ca_topic_score_gemma":0.0014601893,"teacher_disagreement_score":0.8896861,"about_ca_system_score_codex":0.0003075083,"about_ca_system_score_gemma":0.009650147,"threshold_uncertainty_score":0.9959642},"labels":[],"label_agreement":null},{"id":"W3031765893","doi":"10.3138/cjpe.56949","title":"Reflections on Inter-University Collaboration to Deliver a Graduate Certificate in Evaluation to Government of the Northwest Territories Employees","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Government of Northwest Territories; Carleton University; University of Victoria","funders":"","keywords":"Credential; Negotiation; Government (linguistics); Certificate; Public relations; Higher education; Process (computing); sort; Political science; Sociology; Medical education; Business; Computer science; Medicine","score_opus":0.596189237013459,"score_gpt":0.5212415559789882,"score_spread":0.0749476810344708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3031765893","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9713792,0.000010998118,0.00077692984,0.024779137,0.0007096737,0.0016938751,0.000053832176,0.000004389304,0.0005919391],"genre_scores_gemma":[0.99843675,0.0000022763425,0.0008979903,0.0004977463,0.00009248853,0.00003281315,0.0000063723614,0.0000061623364,0.000027413742],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99462956,0.0008391772,0.0007048129,0.00022398864,0.0034249085,0.00017753118],"domain_scores_gemma":[0.99557906,0.0001229563,0.00048826332,0.00024814744,0.003197532,0.00036403688],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006448949,0.00010516255,0.00018289484,0.00036153238,0.00019675579,0.00016449769,0.0004680901,0.000045587818,0.0002527598],"category_scores_gemma":[0.0038280317,0.00007991156,0.00008196738,0.0022787962,0.000044025393,0.00048566228,0.000028819113,0.00015932642,0.00002168186],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030780677,0.00013904415,0.08329698,0.0000070290334,0.00003427497,0.000002743056,0.027245285,0.0934075,0.000830339,0.00039551212,0.0032378538,0.7910956],"study_design_scores_gemma":[0.0012094956,0.0021262784,0.9046745,0.00014816773,0.00012862576,0.0000028424347,0.01664973,0.036879472,0.0015685492,0.001029724,0.035385873,0.00019675095],"about_ca_topic_score_codex":0.0018672079,"about_ca_topic_score_gemma":0.308831,"teacher_disagreement_score":0.8213775,"about_ca_system_score_codex":0.0013332188,"about_ca_system_score_gemma":0.0021979646,"threshold_uncertainty_score":0.703781},"labels":[],"label_agreement":null},{"id":"W3032011752","doi":"10.1080/0907676x.2020.1766168","title":"It is time to rethink the book review","year":2020,"lang":"en","type":"article","venue":"Perspectives","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science","score_opus":0.2181051707554214,"score_gpt":0.5087505395654653,"score_spread":0.29064536881004394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3032011752","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010123904,0.027787682,0.00024451638,0.82464343,0.00003999582,0.00032702,0.000005786514,0.000028901437,0.14682144],"genre_scores_gemma":[0.00671534,0.0057406244,0.00040664952,0.92494863,0.00026156835,0.00003992458,9.670692e-7,0.000009807662,0.061876513],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.997828,0.00019929,0.00028862245,0.00035581342,0.00119949,0.00012877701],"domain_scores_gemma":[0.99863243,0.00037829106,0.00009050503,0.00041449082,0.00036436933,0.000119927194],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0020037203,0.0000897824,0.0001841143,0.000034664135,0.00016393028,0.00012793587,0.0006147659,0.0000206556,0.12054489],"category_scores_gemma":[0.0023633146,0.000048122136,0.00009996503,0.00063348596,0.00005570625,0.00024843996,0.00011466913,0.00012951622,0.03799797],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005901382,0.0000078013645,0.000031158284,0.0000053675344,0.0000071325703,3.928731e-7,0.02493857,0.000006887373,0.00004875817,0.00022579692,0.97073835,0.0039838958],"study_design_scores_gemma":[0.00006399682,0.00006947587,0.0008386617,0.000049480375,0.000010039427,0.0000010888225,0.003751317,0.0011145951,0.00006839822,0.0004997414,0.9934558,0.0000773903],"about_ca_topic_score_codex":0.0000017566483,"about_ca_topic_score_gemma":0.0000012593313,"teacher_disagreement_score":0.10030519,"about_ca_system_score_codex":0.00003727329,"about_ca_system_score_gemma":0.000109929206,"threshold_uncertainty_score":0.96275103},"labels":[],"label_agreement":null},{"id":"W3032165765","doi":"10.3138/cjpe.56898","title":"Scope Creep and Purposeful Pivots in Developmental Evaluation","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Scope (computer science); Stakeholder; Set (abstract data type); Session (web analytics); Psychology; Knowledge management; Engineering ethics; Plenary session; Process management; Pedagogy; Public relations; Business; Political science; Computer science; Engineering; World Wide Web; Library science","score_opus":0.5926935965616887,"score_gpt":0.5368839960960672,"score_spread":0.055809600465621556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3032165765","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98544574,0.0012897893,0.00037335407,0.00688785,0.00035673205,0.0016624707,0.000003820924,0.0000065259924,0.003973745],"genre_scores_gemma":[0.994355,0.000022535525,0.004783292,0.0006097408,0.00012441778,0.000066492335,0.000011121617,0.000008250393,0.000019150388],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99493706,0.0007133594,0.0010264624,0.00025693263,0.0028167001,0.00024949227],"domain_scores_gemma":[0.9964918,0.000152528,0.00049663434,0.00011443268,0.002129491,0.00061510067],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0176788,0.00012463312,0.00024220053,0.0005970921,0.00013759386,0.00041325914,0.00032171898,0.000074262025,0.0028606656],"category_scores_gemma":[0.0054082414,0.00010407021,0.00005573801,0.0010182856,0.000075287746,0.0008916627,0.00001915441,0.00021327351,0.00008777385],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021863862,0.000018454064,0.07771953,0.0000038823086,0.000011049327,0.000005652514,0.0027110144,0.0015088392,0.00008957023,0.00007871567,0.0013270733,0.9165044],"study_design_scores_gemma":[0.0034426353,0.0007915074,0.60869676,0.00009285744,0.00009378631,0.00007198458,0.0050374456,0.33856526,0.00024600243,0.005414617,0.037270658,0.00027652952],"about_ca_topic_score_codex":0.0002498645,"about_ca_topic_score_gemma":0.01895737,"teacher_disagreement_score":0.9162278,"about_ca_system_score_codex":0.0005846668,"about_ca_system_score_gemma":0.008260373,"threshold_uncertainty_score":0.9989441},"labels":[],"label_agreement":null},{"id":"W3032988029","doi":"10.17269/s41997-020-00317-2","title":"Chronic disease prevention evaluation in Ontario’s public health system: a qualitative needs assessment","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Public Health","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa; University of Waterloo; Impact","funders":"Ontario Ministry of Health and Long-Term Care","keywords":"Thematic analysis; Public health; Context (archaeology); Capacity building; Public relations; Focus group; Work (physics); Qualitative research; Qualitative property; Medicine; Knowledge management; Political science; Sociology; Business; Nursing; Engineering; Computer science; Marketing; Geography; Social science","score_opus":0.6139334125471698,"score_gpt":0.5627080866659068,"score_spread":0.05122532588126305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3032988029","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31620526,0.002243762,0.03492944,0.6412684,0.0013289746,0.0014892148,0.00004734326,0.0000174708,0.0024701743],"genre_scores_gemma":[0.9939185,0.000025308736,0.00068910955,0.004762823,0.00026598136,0.000034660326,0.000046003897,0.000013510493,0.00024412556],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.984883,0.007492786,0.0027351694,0.00036987013,0.0035108866,0.0010082528],"domain_scores_gemma":[0.98964846,0.0003593615,0.0019024857,0.00034145408,0.0018078889,0.005940348],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.074681774,0.00018747078,0.0006089442,0.0018021661,0.00037545853,0.0006879614,0.00068122766,0.0000617909,0.0027060686],"category_scores_gemma":[0.003625714,0.00015857513,0.00016920836,0.0021616747,0.00007441162,0.0017153256,0.000026673906,0.00062831066,0.000062494764],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000019266157,0.00015108871,0.27745605,0.00022998646,0.00009375718,0.000025163892,0.20073879,0.0021313836,0.0000015922772,0.03666586,0.023715891,0.45877117],"study_design_scores_gemma":[0.0025448604,0.001645126,0.6342418,0.00026998247,0.000013025147,0.000019600266,0.111361004,0.03074992,1.4028411e-7,0.0017125284,0.21718962,0.00025238332],"about_ca_topic_score_codex":0.0886357,"about_ca_topic_score_gemma":0.87133044,"teacher_disagreement_score":0.78269476,"about_ca_system_score_codex":0.021420248,"about_ca_system_score_gemma":0.3228175,"threshold_uncertainty_score":0.9982056},"labels":[],"label_agreement":null},{"id":"W3033421757","doi":"10.3138/cpp.2019-002","title":"Candidate–Evaluator Similarity, Favouritism, Informational Advantage, and Committee Dynamics","year":2020,"lang":"en","type":"article","venue":"Canadian Public Policy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université du Québec en Outaouais","funders":"","keywords":"Multidisciplinary approach; Scholarship; Similarity (geometry); Psychology; Discipline; Political science; Computer science; Sociology; Artificial intelligence; Social science; Law","score_opus":0.1123114543756424,"score_gpt":0.4266436279274972,"score_spread":0.31433217355185483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3033421757","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17913318,0.0001161554,0.00094747083,0.6716199,0.00030869327,0.000481349,0.0016226447,0.00008240959,0.1456882],"genre_scores_gemma":[0.9510388,0.000036565663,0.00025563448,0.047458995,0.00026732218,0.0000149611005,0.00017770774,0.000011076253,0.00073896075],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.997365,0.00013563408,0.000543182,0.00028555782,0.0011677828,0.00050282833],"domain_scores_gemma":[0.99716187,0.00020946804,0.00015002089,0.00033434315,0.0004169995,0.0017272758],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015475904,0.00015734397,0.00022127111,0.00070309674,0.00042489416,0.0008803929,0.0006481579,0.000099634104,0.0024862944],"category_scores_gemma":[0.0028365287,0.00014366045,0.000052631563,0.0011777105,0.00013860117,0.0013131925,0.00013749379,0.00022857913,0.0005016291],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000081932685,0.000016462216,0.11213392,0.000018021465,0.000034072003,0.000011818701,0.0021350312,0.000068796784,0.000004697232,0.4478534,0.23744063,0.20027497],"study_design_scores_gemma":[0.00064588117,0.000054435808,0.061818395,0.0000048237666,0.000006005816,0.000025686431,0.001269805,0.13614397,0.0000036957256,0.0097722765,0.78999776,0.00025726037],"about_ca_topic_score_codex":0.017781964,"about_ca_topic_score_gemma":0.3408067,"teacher_disagreement_score":0.7719056,"about_ca_system_score_codex":0.00047578,"about_ca_system_score_gemma":0.00836014,"threshold_uncertainty_score":0.99842554},"labels":[],"label_agreement":null},{"id":"W3033723693","doi":"","title":"Integrating the consolidated framework for implementation research into a culturally responsive evaluation approach: Examples from mixed-methods evaluations of diabetes prevention and management programs reaching underserved populations","year":2020,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Workplace Health, Safety and Compensation Commission","funders":"","keywords":"Medicine; Health services research; Health informatics; Health administration; Public health; Implementation research; Nursing; Medical education; Psychological intervention","score_opus":0.6667949059385525,"score_gpt":0.6448667056210342,"score_spread":0.021928200317518298,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3033723693","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5226193,0.000114951115,0.46734592,0.005563167,0.00010300477,0.0037957004,0.000017706272,0.00003426115,0.00040597044],"genre_scores_gemma":[0.5730179,0.000011956024,0.42577463,0.00012722083,0.00003980559,0.0006010283,0.0003904235,0.000008572615,0.000028478176],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98981464,0.0057121734,0.0011799908,0.0006440721,0.0023691396,0.0002799814],"domain_scores_gemma":[0.99231124,0.0042858003,0.0005813716,0.0004556259,0.0022668417,0.00009910289],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02744325,0.00017302105,0.00028043136,0.0002596649,0.00087176444,0.0005373122,0.0004498418,0.00009120783,0.000292926],"category_scores_gemma":[0.0058712587,0.000109515706,0.00011230449,0.0014173904,0.00017500727,0.00063124247,0.00022271996,0.0002054684,0.000005959687],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008074377,0.00009633067,0.009073969,0.00005107027,0.00015754452,3.3493404e-8,0.037743784,0.0005778782,0.0037403193,0.12814914,0.00076509645,0.8195641],"study_design_scores_gemma":[0.0008223221,0.0003282096,0.059516348,0.00008432509,0.00018111944,1.361814e-7,0.24231261,0.29965204,0.0011058858,0.3953905,0.0004599943,0.00014649205],"about_ca_topic_score_codex":0.00017767376,"about_ca_topic_score_gemma":0.00081455975,"teacher_disagreement_score":0.8194176,"about_ca_system_score_codex":0.0001308361,"about_ca_system_score_gemma":0.00023463024,"threshold_uncertainty_score":0.9511337},"labels":[],"label_agreement":null},{"id":"W3034035587","doi":"10.31045/jes.3.2.7","title":"A Thirty State Analysis of Teacher Supervision and Evaluation Systems in the ESSA Era","year":2020,"lang":"en","type":"article","venue":"Journal of Educational Supervision","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Toronto; University of Minnesota; Princeton University","keywords":"Formative assessment; Accountability; Summative assessment; Public administration; Legislation; Policy analysis; Politics; State (computer science); Political science; Psychology; Law; Pedagogy; Computer science","score_opus":0.17399231894091108,"score_gpt":0.4769084655628433,"score_spread":0.3029161466219322,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3034035587","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97261226,0.0017032292,0.00017799997,0.024406323,0.0002433206,0.00021858195,0.000009049795,0.0000011143825,0.00062812684],"genre_scores_gemma":[0.9987528,0.00019446689,0.0003277376,0.0005050346,0.0001464935,0.0000063902917,0.000015014109,0.0000044088424,0.000047680955],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9936272,0.0011210006,0.0013873952,0.00021576113,0.0035318895,0.00011679062],"domain_scores_gemma":[0.99558413,0.0017727955,0.00065531296,0.00024498603,0.0016346374,0.00010815423],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.013794687,0.000111316585,0.000398558,0.000686288,0.00009206853,0.00018638778,0.0005171828,0.000051135758,0.0020056635],"category_scores_gemma":[0.002363423,0.00006132821,0.00016380892,0.0022112734,0.00004686413,0.0007428056,0.00005014347,0.0002511623,0.000015506193],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027036775,0.00067248615,0.7803757,0.00003671369,0.000325216,0.0000017744117,0.04626544,0.07935133,0.0017318233,0.002414897,0.009046923,0.07950731],"study_design_scores_gemma":[0.00050664914,0.00018141809,0.73086786,0.00003729722,0.00019650285,0.000007059778,0.007652014,0.2566926,0.00001515667,0.001886859,0.0018877641,0.00006882809],"about_ca_topic_score_codex":0.00008073195,"about_ca_topic_score_gemma":0.00005424644,"teacher_disagreement_score":0.17734127,"about_ca_system_score_codex":0.00006950712,"about_ca_system_score_gemma":0.00061414385,"threshold_uncertainty_score":0.9989066},"labels":[],"label_agreement":null},{"id":"W3034139149","doi":"10.33524/cjar.v20i2.473","title":"Action Researchers to the Rescue","year":2019,"lang":"en","type":"article","venue":"The Canadian Journal of Action Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"McGill University","funders":"","keywords":"Action research; Action (physics); Engineering ethics; Psychology; Mathematics education; Engineering","score_opus":0.8423953390990969,"score_gpt":0.6769942386013318,"score_spread":0.16540110049776513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3034139149","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7903362,0.000076934855,0.00011114003,0.18935044,0.0012884641,0.00043555783,0.0000032312305,0.000002568734,0.018395485],"genre_scores_gemma":[0.97310853,0.00003294815,0.000041955063,0.00067268097,0.0003848158,0.0000062389145,3.5887354e-7,0.000006971389,0.025745505],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.992826,0.0019704537,0.00044902053,0.00015130293,0.0041614054,0.0004418476],"domain_scores_gemma":[0.9942019,0.0015579176,0.00013321998,0.0006377636,0.0029069972,0.00056221645],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.052171275,0.000061838735,0.00012192377,0.0010453787,0.0010978057,0.0008763624,0.0015032933,0.00005663877,0.0070883236],"category_scores_gemma":[0.0045307875,0.000029003812,0.000085354186,0.0020122593,0.00016505421,0.00047714304,0.00005111449,0.001184441,0.0041962746],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003851959,0.000023140996,0.018005248,0.0000071686623,0.00006211935,0.0000150848555,0.006986139,0.017581439,0.0025756503,0.0040966254,0.6761177,0.27414444],"study_design_scores_gemma":[0.00020505373,0.00029237196,0.07424772,0.000018421559,0.0000027232893,0.00004289521,0.013399886,0.0014883318,0.0007555853,0.0028589629,0.906638,0.000050004524],"about_ca_topic_score_codex":0.013381934,"about_ca_topic_score_gemma":0.33145723,"teacher_disagreement_score":0.3180753,"about_ca_system_score_codex":0.0006937105,"about_ca_system_score_gemma":0.005035384,"threshold_uncertainty_score":0.99657905},"labels":[],"label_agreement":null},{"id":"W3034165477","doi":"10.33524/cjar.v20i2.475","title":"Cancellation of 2020 Conference: The Canadian Association of Action Research in Education","year":2019,"lang":"en","type":"article","venue":"The Canadian Journal of Action Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"McGill University","funders":"","keywords":"Action (physics); Political science; Library science; Executive director; Action research; Association (psychology); Public relations; Management; Media studies; Public administration; Psychology; Sociology; Pedagogy","score_opus":0.6386429341247034,"score_gpt":0.6327070125644678,"score_spread":0.005935921560235591,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3034165477","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93147504,0.00011433477,0.0000061904634,0.043070152,0.0010968602,0.0004916338,0.000010138711,8.668068e-7,0.02373478],"genre_scores_gemma":[0.99308354,0.00015430874,0.000019462825,0.00007023982,0.00019233978,0.000008459063,0.000003581905,0.0000060789175,0.0064619943],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9918871,0.0028327578,0.00081006024,0.00015463322,0.003902286,0.00041315463],"domain_scores_gemma":[0.9887496,0.0018638617,0.00066496053,0.0004031774,0.008022258,0.00029611838],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.05069467,0.00006918188,0.00019823649,0.0019619148,0.00061172945,0.0002990839,0.00079832145,0.0001412713,0.0026301069],"category_scores_gemma":[0.0026724148,0.000043552856,0.00006761226,0.002771154,0.00021036326,0.00051858556,0.00002067508,0.001210416,0.0001298888],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023630715,0.00008691292,0.6287048,0.000058509748,0.00007553413,0.0000028376023,0.012205586,0.011136508,0.005436417,0.008586314,0.093939036,0.23953128],"study_design_scores_gemma":[0.00065186055,0.0003892479,0.7680883,0.0001887142,0.000011631693,0.000013732276,0.0342178,0.007498477,0.003340913,0.01749126,0.16799168,0.00011639093],"about_ca_topic_score_codex":0.56174386,"about_ca_topic_score_gemma":0.9885733,"teacher_disagreement_score":0.4268295,"about_ca_system_score_codex":0.0036643133,"about_ca_system_score_gemma":0.036098994,"threshold_uncertainty_score":0.9982816},"labels":[],"label_agreement":null},{"id":"W3034877270","doi":"","title":"A program implementation fidelity assessment of a Housing First program in Ontario","year":2020,"lang":"en","type":"article","venue":"Scholars Commons (Wilfrid Laurier University)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Business","score_opus":0.14653954263686317,"score_gpt":0.43315573994825296,"score_spread":0.28661619731138976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3034877270","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9813427,0.000010657216,0.00075934856,0.0028675648,0.00010699961,0.0012329469,0.000025236306,0.00009982627,0.013554768],"genre_scores_gemma":[0.98553854,0.000006927264,0.0139425695,0.00019844879,0.000014396429,0.000013173823,0.00004029849,0.000009712441,0.00023593525],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9967055,0.00041745786,0.0006987634,0.0005118235,0.001337542,0.00032892867],"domain_scores_gemma":[0.9982487,0.00020724045,0.0004068657,0.00048490133,0.0004318496,0.00022045264],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0019141941,0.0001856014,0.00036819564,0.0005372281,0.0002832672,0.0002587171,0.0007907603,0.00008400039,0.0015163837],"category_scores_gemma":[0.00015261113,0.00018228126,0.00015594593,0.002281023,0.00011328124,0.0013649103,0.00033328385,0.0005480287,0.000023752205],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006289644,0.00038297183,0.93931407,0.000010941771,0.000028439776,0.000021204187,0.0016140784,0.0005944438,0.00004896582,0.0017821917,0.00063257955,0.05550723],"study_design_scores_gemma":[0.0016492043,0.00051041006,0.69057345,0.000029013107,0.00003325083,7.3567554e-7,0.0040408834,0.0058037243,0.00010546787,0.0002772989,0.29677197,0.00020460514],"about_ca_topic_score_codex":0.006334174,"about_ca_topic_score_gemma":0.40451604,"teacher_disagreement_score":0.3981819,"about_ca_system_score_codex":0.0005444573,"about_ca_system_score_gemma":0.0012572873,"threshold_uncertainty_score":0.9993964},"labels":[],"label_agreement":null},{"id":"W3035076565","doi":"10.1177/1098214020908211","title":"The Role of Intuition in Evaluative Judgment and Decision","year":2020,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Intuition; Psychology; Epistemology; Social psychology; Management science; Cognitive science","score_opus":0.117224265564639,"score_gpt":0.4903323073651327,"score_spread":0.37310804180049373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035076565","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9895865,0.0006045569,0.005347468,0.0034064255,0.00010905882,0.00022522177,0.0000013720303,0.0000014408243,0.00071796356],"genre_scores_gemma":[0.9975567,0.00022027636,0.0019050192,0.00024877334,0.000056629186,0.00000615874,7.153767e-7,0.0000036588071,0.0000020723571],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99465907,0.0008213959,0.001103019,0.00014682273,0.003168671,0.0001010189],"domain_scores_gemma":[0.9948945,0.0018401344,0.0014139205,0.00014526462,0.0016216435,0.00008451859],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017182862,0.00007543248,0.00025517697,0.00019015084,0.00007531082,0.00006790161,0.00022471823,0.000017360966,0.00021832598],"category_scores_gemma":[0.004969893,0.000044119635,0.000062386716,0.0008267024,0.00016568601,0.0003705403,0.0000460855,0.00013735265,0.000012833995],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024849098,0.000023171644,0.013352024,5.5664515e-7,0.0000107484375,2.4589627e-7,0.0028819425,0.0041808784,0.0012110658,0.00043584962,0.00011694158,0.9775381],"study_design_scores_gemma":[0.001935175,0.0029676268,0.28627208,0.00007812794,0.00007302203,0.000013945601,0.03204533,0.5063393,0.0021438664,0.16524488,0.0027605975,0.00012604451],"about_ca_topic_score_codex":0.000010767681,"about_ca_topic_score_gemma":0.00002768371,"teacher_disagreement_score":0.97741205,"about_ca_system_score_codex":0.00009049195,"about_ca_system_score_gemma":0.00038825124,"threshold_uncertainty_score":0.5955272},"labels":[],"label_agreement":null},{"id":"W3035260022","doi":"10.5130/ijcre.v13i1.7110","title":"Injustices épistémiques et recherche participative: un agenda de recherche à la croisée de l’université et des communautés","year":2020,"lang":"fr","type":"article","venue":"Gateways International Journal of Community Research and Engagement","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université du Québec à Rimouski; Université Laval; Université de Montréal","funders":"","keywords":"Humanities; Sociology; Political science; Philosophy","score_opus":0.9307859812820833,"score_gpt":0.6900613775980631,"score_spread":0.24072460368402027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035260022","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80251515,0.0032537295,0.027742662,0.13681185,0.000226114,0.00018140173,0.000048753685,0.000018450459,0.029201912],"genre_scores_gemma":[0.9088563,0.0436924,0.042307608,0.003947431,0.00012530776,0.000007863095,0.00001137706,0.000017022323,0.001034708],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.873787,0.12233672,0.0008778618,0.0001621434,0.0022996638,0.0005366213],"domain_scores_gemma":[0.96459275,0.030769097,0.00042096552,0.00032604038,0.0033676461,0.0005234745],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.20075853,0.00019748339,0.0003193257,0.00036794916,0.0010578246,0.0009775277,0.0022772148,0.00026625034,0.0025538756],"category_scores_gemma":[0.029930498,0.00017472294,0.0001333443,0.00064530806,0.0008579867,0.0011355975,0.0013745343,0.0094023375,0.000044470347],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012207092,0.0015147317,0.013444554,0.00015475648,0.00075036444,0.00015134425,0.43876305,0.0022733873,0.0025292963,0.017049367,0.022662494,0.49948594],"study_design_scores_gemma":[0.0033705642,0.0036436447,0.08853576,0.0010596197,0.00012637627,0.00021113433,0.26949096,0.011936178,0.009202377,0.36331433,0.24870531,0.0004037652],"about_ca_topic_score_codex":0.0009518874,"about_ca_topic_score_gemma":0.00053572544,"teacher_disagreement_score":0.49908218,"about_ca_system_score_codex":0.0013028674,"about_ca_system_score_gemma":0.001989049,"threshold_uncertainty_score":0.99835795},"labels":[{"model":"gemma","categories":["sts"],"domain":null,"study_design":"theoretical_or_conceptual","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch","sts"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W3035271094","doi":"10.1177/1098214019899164","title":"Talking Circles: A Culturally Responsive Evaluation Practice","year":2020,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":64,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Stollery Children's Hospital","funders":"","keywords":"Privilege (computing); Indigenous; Invisibility; Sociology; Power (physics); Stakeholder; Culturally appropriate; Power structure; Psychology; Pedagogy; Social psychology; Public relations; Computer science; Ethnography; Political science; Medicine; Computer security; Artificial intelligence","score_opus":0.22132405977411476,"score_gpt":0.5437861279564394,"score_spread":0.3224620681823247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035271094","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90099776,0.0003314499,0.011353708,0.07834337,0.0006390774,0.0007078856,0.000003856951,0.00001746488,0.007605411],"genre_scores_gemma":[0.9849212,0.00005047859,0.008025411,0.006504564,0.00043968868,0.000014222038,0.000006130718,0.000010836416,0.000027451466],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9848098,0.0040964973,0.0014770775,0.00032121682,0.009099884,0.00019548845],"domain_scores_gemma":[0.9803633,0.0022893916,0.0034564643,0.00028398054,0.013378401,0.0002284458],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.038181048,0.00014796545,0.00038671505,0.0003095923,0.00016546244,0.0002918189,0.0004399312,0.000036146146,0.001908107],"category_scores_gemma":[0.0607248,0.00010905984,0.0001774028,0.0017139709,0.00013011711,0.0021489752,0.000050400457,0.0002899696,0.00026714616],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000684661,0.00006716159,0.0010840201,0.0000020564248,0.000087109125,0.000006539016,0.0133393975,0.02047441,0.004021595,0.00017788357,0.006290049,0.9537651],"study_design_scores_gemma":[0.0053762817,0.006109191,0.11051746,0.00013709613,0.0012465992,0.000427697,0.13663293,0.6473782,0.00122866,0.008371631,0.08194409,0.00063015585],"about_ca_topic_score_codex":0.0000105194795,"about_ca_topic_score_gemma":0.0000060557268,"teacher_disagreement_score":0.95313495,"about_ca_system_score_codex":0.0003153653,"about_ca_system_score_gemma":0.001976588,"threshold_uncertainty_score":0.9990043},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"qualitative","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W3035948670","doi":"10.4000/ries.9447","title":"La fiabilité : une voie vers l’équité ?","year":2020,"lang":"fr","type":"article","venue":"Revue internationale d éducation de Sèvres","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Musée de la Civilisation","funders":"","keywords":"Humanities; Political science; Art","score_opus":0.2657528420640797,"score_gpt":0.4848087645293551,"score_spread":0.21905592246527544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035948670","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26669088,0.0028391788,0.011300362,0.52618295,0.0048363428,0.0004935337,0.000106026295,0.000096281976,0.18745445],"genre_scores_gemma":[0.8895758,0.0009851513,0.0024525593,0.0049232133,0.0016285381,0.00007436151,0.00007596905,0.00002802238,0.100256436],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99647844,0.0006243881,0.0008704909,0.0005883669,0.0011296318,0.00030867275],"domain_scores_gemma":[0.9956647,0.0024184128,0.00041315527,0.0004030826,0.00079569314,0.00030491597],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0024056719,0.00022354675,0.00026411028,0.00021546573,0.00015864646,0.00040386527,0.00088404457,0.00018024842,0.018576978],"category_scores_gemma":[0.0050709816,0.0002344847,0.00020585189,0.0009419949,0.00021138028,0.00082228356,0.00012228545,0.00036561157,0.0050366535],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011465192,0.0005931386,0.05300921,0.0002751259,0.00017632399,0.000020625092,0.04238608,0.009922553,0.00070356694,0.21975957,0.1139893,0.55904984],"study_design_scores_gemma":[0.00045100687,0.00010438239,0.042934176,0.00016256374,0.00003580484,0.00003290456,0.0036566043,0.05953472,0.00034076962,0.012171181,0.880333,0.00024285931],"about_ca_topic_score_codex":0.0003419919,"about_ca_topic_score_gemma":0.0003655965,"teacher_disagreement_score":0.7663437,"about_ca_system_score_codex":0.0006187291,"about_ca_system_score_gemma":0.0014245956,"threshold_uncertainty_score":0.995738},"labels":[],"label_agreement":null},{"id":"W3036150174","doi":"","title":"DEC's New Recommended Practices: The Context for Change","year":2000,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Education and Early Childhood Development","funders":"","keywords":"Context (archaeology); Computer science; Geography","score_opus":0.7289340169908687,"score_gpt":0.6079763311447699,"score_spread":0.12095768584609878,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3036150174","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0522848,0.0003481782,0.006446666,0.49321088,0.0011666975,0.00236174,0.000013954535,0.00010873757,0.44405833],"genre_scores_gemma":[0.60921776,0.00022573846,0.0045954543,0.054369863,0.000638832,0.00021998693,0.000007566027,0.000010512374,0.3307143],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.998465,0.00013068302,0.00033237317,0.00021554006,0.00069504173,0.00016138732],"domain_scores_gemma":[0.9968696,0.0022135053,0.00024750907,0.00042306236,0.00016809035,0.00007822533],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0037744094,0.00007391228,0.0001109663,0.000043900713,0.00021288973,0.00028316982,0.00048491487,0.000033800603,0.07363182],"category_scores_gemma":[0.0009971664,0.000035384575,0.000071149334,0.00020268955,0.000017941295,0.00065635773,0.0000213101,0.000054663076,0.0019918834],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002824249,0.000015723728,0.0006628911,4.0131934e-7,0.0000046623004,5.9123277e-8,0.0011229643,0.0000024246694,0.000002766204,0.002007322,0.28248817,0.71366435],"study_design_scores_gemma":[0.0004963512,0.00008252117,0.0030148453,0.0000028590505,0.000007078353,0.0000021329213,0.002474069,0.0050589032,0.0000802857,0.006775128,0.9819423,0.000063526146],"about_ca_topic_score_codex":0.00020122273,"about_ca_topic_score_gemma":0.0023641682,"teacher_disagreement_score":0.7136009,"about_ca_system_score_codex":0.000019158035,"about_ca_system_score_gemma":0.00014350016,"threshold_uncertainty_score":0.9987852},"labels":[],"label_agreement":null},{"id":"W3036747120","doi":"10.1111/medu.14281","title":"Useful to whom? Evaluation utilisation theory and boundaries for programme evaluation scope","year":2020,"lang":"en","type":"review","venue":"Medical Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Global Health Research; University of Toronto","funders":"","keywords":"Scope (computer science); Stakeholder; Theory of change; Context (archaeology); Scholarship; Process (computing); Engineering ethics; Management science; Monitoring and evaluation; Diversity (politics); Program evaluation; Participatory evaluation; Psychology; Sociology; Public relations; Political science; Computer science; Social science; Engineering","score_opus":0.392409528471173,"score_gpt":0.6146912310302682,"score_spread":0.22228170255909524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3036747120","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014111913,0.96897334,0.008139509,0.008810191,0.0033138592,0.009424381,0.00002604367,0.000055839184,0.0011157097],"genre_scores_gemma":[0.001086182,0.9726617,0.0027398674,0.0046407213,0.0020279144,0.013534076,0.002178969,0.00008372192,0.0010468574],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9860811,0.0033629227,0.0017348235,0.0010969805,0.007357761,0.00036641757],"domain_scores_gemma":[0.99270743,0.0026259532,0.00085802237,0.00063909934,0.0026938436,0.0004756745],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.057532698,0.0003867272,0.0010423724,0.00056914805,0.00061755656,0.001711733,0.0006445749,0.0004115168,0.004293663],"category_scores_gemma":[0.10379386,0.0002806334,0.00023571818,0.0012826779,0.00027540565,0.0005313687,0.00012660131,0.000326013,0.0004563992],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024983967,0.000099221004,0.000020866073,0.0006259426,0.000031635187,5.627416e-8,0.0013893255,0.0000018460867,6.325124e-8,0.0038610573,0.025139676,0.9688053],"study_design_scores_gemma":[0.00040615248,0.00017845117,0.00015926399,0.0018904997,0.00076553377,0.000007458452,0.00076711696,0.007128935,6.277769e-7,0.016847363,0.97156143,0.00028718525],"about_ca_topic_score_codex":0.000016263271,"about_ca_topic_score_gemma":0.000110451445,"teacher_disagreement_score":0.96851814,"about_ca_system_score_codex":0.0006889648,"about_ca_system_score_gemma":0.042851582,"threshold_uncertainty_score":0.9999646},"labels":[],"label_agreement":null},{"id":"W3038125260","doi":"10.22230/ijepl.2020v16n11a1021","title":"Wordplay or Paradigm Shift: The Meaning of “Research Impact”","year":2020,"lang":"en","type":"article","venue":"International Journal of Education Policy and Leadership","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"William T. Grant Foundation","keywords":"Framing (construction); Paradigm shift; Meaning (existential); Political science; Engineering ethics; Sociology; Context (archaeology); Epistemology; Engineering; History","score_opus":0.7288837399782909,"score_gpt":0.6310501086515562,"score_spread":0.09783363132673473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3038125260","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29642642,0.0006387186,0.0012908374,0.69502014,0.000934377,0.00014608356,0.000008991393,0.000004769099,0.0055296337],"genre_scores_gemma":[0.99224365,0.000064513006,0.00018264922,0.005478887,0.0014384954,0.0000024082965,0.0000012638952,0.0000045066486,0.00058365194],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9966553,0.0003832701,0.0006607785,0.00011266933,0.0020478177,0.0001401868],"domain_scores_gemma":[0.99594164,0.0023059712,0.0005272119,0.00012199146,0.0009455165,0.00015765413],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0043629226,0.00007130014,0.00014667826,0.0005014757,0.00009326538,0.00023773067,0.0008286198,0.000036912446,0.0012205703],"category_scores_gemma":[0.006343981,0.00003676829,0.00009322989,0.0007010733,0.00017567539,0.00048547026,0.000046479294,0.00030677594,0.000033536275],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019480861,0.0005393726,0.081880726,0.000044586286,0.00046132426,0.00000934961,0.2129486,0.0021346442,0.0005744943,0.38542047,0.09804395,0.21599439],"study_design_scores_gemma":[0.0021087222,0.0014139237,0.35278428,0.0004063584,0.000047439727,0.00035400136,0.11875829,0.0041598864,0.0017992207,0.2631103,0.25472793,0.000329638],"about_ca_topic_score_codex":0.00006735471,"about_ca_topic_score_gemma":0.000022026645,"teacher_disagreement_score":0.6958172,"about_ca_system_score_codex":0.00008412813,"about_ca_system_score_gemma":0.0023697277,"threshold_uncertainty_score":0.99969244},"labels":[],"label_agreement":null},{"id":"W3039363111","doi":"10.1080/1360144x.2020.1786694","title":"Comprehensive assessment for teaching and learning centres: a field-tested planning model","year":2020,"lang":"en","type":"article","venue":"The International Journal for Academic Development","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Field (mathematics); Work (physics); Knowledge management; Computer science; Management science; Engineering ethics; Process management; Engineering management; Engineering","score_opus":0.2892621726134628,"score_gpt":0.531291375115197,"score_spread":0.24202920250173415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3039363111","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32110828,0.00022085875,0.62754804,0.04868097,0.0008344915,0.000500563,0.000008210968,0.000029574048,0.0010690191],"genre_scores_gemma":[0.91908276,0.00006441173,0.0683413,0.009835488,0.0004840698,0.00006682613,0.000015103151,0.000015192969,0.0020948232],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972803,0.00015052794,0.00073289406,0.00023606514,0.0013847864,0.00021540886],"domain_scores_gemma":[0.9957482,0.0030232733,0.00042067806,0.00006070342,0.00061171886,0.00013540432],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044667474,0.00012986541,0.00017619059,0.000114254944,0.0008716949,0.00032294,0.0008431921,0.00006371537,0.00005450823],"category_scores_gemma":[0.0023003612,0.0000825658,0.000077769466,0.00006526183,0.00002606398,0.0003169363,0.00019469568,0.0010341918,0.000007472994],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008862789,0.000052410636,0.013877965,0.000030700314,0.0005499081,0.00000762585,0.07818795,0.3019258,0.0055374242,0.007658855,0.09227658,0.4990085],"study_design_scores_gemma":[0.00093965285,0.00007904748,0.0016859614,0.000061021514,0.000012624443,0.00003171009,0.0059921816,0.6248674,0.00027991575,0.005968064,0.35996246,0.000119953525],"about_ca_topic_score_codex":0.0000010210777,"about_ca_topic_score_gemma":5.2985206e-7,"teacher_disagreement_score":0.5979745,"about_ca_system_score_codex":0.00012794508,"about_ca_system_score_gemma":0.00041986714,"threshold_uncertainty_score":0.67044604},"labels":[],"label_agreement":null},{"id":"W3041340937","doi":"10.11575/prism/37984","title":"Exploring the leadership of multidisciplinary collaboration in child maltreatment service organizations: A case study of the Southern Alberta Children Advocacy Centre","year":2020,"lang":"en","type":"dissertation","venue":"Open MIND","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Multidisciplinary approach; Political science; Service (business); Public relations; Pedagogy; Sociology; Business; Law","score_opus":0.2723672407280586,"score_gpt":0.4473413824712621,"score_spread":0.17497414174320347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3041340937","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9919302,0.000043199947,7.653898e-7,0.0028182566,0.00022742365,0.0031681417,0.00005094523,9.2358954e-7,0.0017601595],"genre_scores_gemma":[0.9966139,0.000009137424,0.00008559547,0.00003508613,0.000033589688,0.00009771674,0.00022587176,0.000021879066,0.0028771888],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9965354,0.0006294599,0.0010428252,0.0004950785,0.001149131,0.00014806945],"domain_scores_gemma":[0.99692667,0.00045462768,0.000995509,0.0007901027,0.00078619376,0.000046910543],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011511913,0.00022894787,0.00039454023,0.0001531993,0.00032966686,0.0002127429,0.001268431,0.00007227758,0.0011849207],"category_scores_gemma":[0.0005835578,0.00012870495,0.00005434728,0.003107015,0.000024409885,0.00044822544,0.000255308,0.00022601782,0.0001436941],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019705245,0.00097579457,0.11286461,0.000023802435,0.00011616757,0.000014946898,0.8671152,0.0037585837,0.000043746302,0.000007948184,0.00003629631,0.014845826],"study_design_scores_gemma":[0.0011802717,0.0001213012,0.08607788,0.00019617584,0.00012353453,0.000015867936,0.91004056,0.0010642996,0.00095116487,0.000011588777,0.00007758913,0.00013975303],"about_ca_topic_score_codex":0.0063289134,"about_ca_topic_score_gemma":0.2708406,"teacher_disagreement_score":0.26451167,"about_ca_system_score_codex":0.00007023212,"about_ca_system_score_gemma":0.0008052886,"threshold_uncertainty_score":0.99972814},"labels":[],"label_agreement":null},{"id":"W3043139730","doi":"","title":"Revisiting a Qualitative Study Experience","year":2011,"lang":"en","type":"article","venue":"Early childhood education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Qualitative research; Psychology; Sociology; Social science","score_opus":0.2296063055849556,"score_gpt":0.5201824305728961,"score_spread":0.29057612498794055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3043139730","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9621532,0.00004909598,0.0003501457,0.00024752424,0.0005921524,0.00040478722,0.000001119846,0.00003612244,0.036165874],"genre_scores_gemma":[0.99638915,0.000002374502,0.0015620282,0.00029867896,0.00021210355,0.000114128576,0.0000029022544,0.0000077877385,0.001410857],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9972114,0.0005700509,0.0005608943,0.00039176978,0.0010983581,0.00016752916],"domain_scores_gemma":[0.99842197,0.00023341527,0.0002963242,0.0005176402,0.00043211627,0.000098514865],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003605412,0.00011004227,0.00015066852,0.0002097198,0.00022460654,0.0001831985,0.0004358204,0.000028712173,0.0030485438],"category_scores_gemma":[0.0010939077,0.000085479514,0.000050729304,0.0006983326,0.000036720914,0.00088740163,0.0000520637,0.000113609516,0.0012230282],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000026923162,0.00039332907,0.05540207,3.0529768e-7,0.000005458682,1.4285153e-7,0.8749891,5.250954e-7,0.000010120778,0.0010564388,0.00027319542,0.06786663],"study_design_scores_gemma":[0.0001067753,0.000095943295,0.61095315,0.000008874791,0.00000418166,9.3693836e-7,0.38390815,0.000004508971,0.000066925655,0.004503757,0.00027242996,0.00007437569],"about_ca_topic_score_codex":0.00021441026,"about_ca_topic_score_gemma":0.000013640682,"teacher_disagreement_score":0.55555105,"about_ca_system_score_codex":0.00004319476,"about_ca_system_score_gemma":0.0005343759,"threshold_uncertainty_score":0.99955463},"labels":[],"label_agreement":null},{"id":"W3043263376","doi":"","title":"The Professional Learning Community to Implement the Results-Based Management Approach (RBM) in Québec.","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Educational Administration and Policy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université Laval","funders":"","keywords":"Accountability; Context (archaeology); Principal (computer security); Prioritization; Work (physics); Professional development; Professional learning community; Knowledge management; Psychology; Public relations; Process management; Computer science; Pedagogy; Business; Political science; Engineering; Computer security","score_opus":0.2088063627807884,"score_gpt":0.5033304639407774,"score_spread":0.294524101159989,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3043263376","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17764856,0.00008558954,0.00014500326,0.809028,0.00019107184,0.00026874745,0.00001908684,0.0000012873962,0.012612607],"genre_scores_gemma":[0.98891556,0.000009210827,0.00032690255,0.008672672,0.00026179772,0.000018568571,0.00001419643,0.000003360637,0.0017777439],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99790096,0.0005921278,0.0006655196,0.00009927827,0.0005780825,0.00016404652],"domain_scores_gemma":[0.99756455,0.0012284247,0.00029312103,0.00015294105,0.00030804254,0.00045289926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004180666,0.00007740192,0.00009586701,0.00021932198,0.00096169335,0.00030002405,0.0004741191,0.000022015573,0.00024002956],"category_scores_gemma":[0.0025309871,0.00004333142,0.00004071006,0.00058817846,0.00007379891,0.00011672724,0.000021516575,0.00034366176,0.000022307686],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007289965,0.00031152443,0.14324836,0.000039298597,0.0000836894,0.0000071868362,0.05601925,0.013868722,0.000026514552,0.3722205,0.31855363,0.09489234],"study_design_scores_gemma":[0.00053016533,0.00028360466,0.3415939,0.000022066506,0.0000064769324,0.00001528194,0.019056408,0.0016066034,0.000011734107,0.0025444138,0.6342452,0.0000841107],"about_ca_topic_score_codex":0.0067832884,"about_ca_topic_score_gemma":0.14774983,"teacher_disagreement_score":0.81126696,"about_ca_system_score_codex":0.00017565684,"about_ca_system_score_gemma":0.011960058,"threshold_uncertainty_score":0.9998306},"labels":[],"label_agreement":null},{"id":"W3045181370","doi":"10.1016/j.heliyon.2020.e04519","title":"Evidence-based policy making: determining what is evidence","year":2020,"lang":"en","type":"article","venue":"Heliyon","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria; University of Saskatchewan","funders":"","keywords":"Management science; Data science; Computer science; Engineering ethics; Economics; Engineering","score_opus":0.5804620414742484,"score_gpt":0.552244302045557,"score_spread":0.028217739428691435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3045181370","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4766493,0.029426036,0.021909978,0.46515992,0.0013361973,0.0008309777,0.000007936123,0.00028151117,0.004398146],"genre_scores_gemma":[0.92930025,0.0037460886,0.0015567105,0.064561926,0.00040634035,0.000020235426,5.83515e-7,0.000011678609,0.00039618622],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99596846,0.00028453412,0.0006262492,0.0005658062,0.0022517242,0.0003032038],"domain_scores_gemma":[0.9966876,0.0018573402,0.00028715562,0.00056607666,0.00039949128,0.00020236777],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002471678,0.00016321699,0.00024317764,0.00023169887,0.00018936413,0.0011151547,0.00081101054,0.00007214364,0.004473334],"category_scores_gemma":[0.0061660158,0.00012528777,0.00012851486,0.0013086846,0.00006188867,0.0033262644,0.00014778075,0.00016430048,0.0034756905],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018941595,0.000038841754,0.08723733,0.00019729279,0.000012691765,0.000022968145,0.008203164,0.0018885023,0.006605555,0.00054017093,0.0067988047,0.88826525],"study_design_scores_gemma":[0.0019859537,0.0022875946,0.15554011,0.025728785,0.00009227477,0.000025711239,0.010280918,0.38853547,0.06830948,0.0025577531,0.3428242,0.0018317599],"about_ca_topic_score_codex":0.000004754008,"about_ca_topic_score_gemma":0.0000080797,"teacher_disagreement_score":0.8864335,"about_ca_system_score_codex":0.000085626714,"about_ca_system_score_gemma":0.00080767827,"threshold_uncertainty_score":0.9999218},"labels":[],"label_agreement":null},{"id":"W3046954090","doi":"10.1177/0305829820935177","title":"Who Practises Practice Theory (and How)? (Meta-)theorists, Scholar-practitioners, (Bourdieusian) Researchers, and Social Prestige in Academia","year":2020,"lang":"en","type":"article","venue":"Millennium Journal of International Studies","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Prestige; Reflexivity; Sociology; Epistemology; Practice theory; Social theory; Social practice; Social science; Philosophy; Art history","score_opus":0.428790862080372,"score_gpt":0.5574437164906976,"score_spread":0.1286528544103256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3046954090","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14438234,0.13261837,0.00079982646,0.7167508,0.0006044445,0.00026832026,0.000034362332,0.0000134159645,0.0045281383],"genre_scores_gemma":[0.8683198,0.121370494,0.0027245474,0.005799509,0.0007816223,0.000015794662,0.0000020426257,0.000015084844,0.000971072],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9948159,0.0016729407,0.000731577,0.0002984614,0.0022896994,0.0001914634],"domain_scores_gemma":[0.99079716,0.006107428,0.001052154,0.000087529595,0.001821753,0.00013400087],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017378638,0.00016986407,0.0004970285,0.0003316023,0.00033296118,0.00044358795,0.00045846752,0.00015562556,0.00027768058],"category_scores_gemma":[0.043381758,0.00011520955,0.00012323643,0.00030802988,0.00028584525,0.0027565695,0.00033390988,0.0017501883,0.000014463987],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00619467,0.00032929363,0.046052363,0.00009780979,0.00825621,0.00030382816,0.06590506,0.00033238315,0.0012046274,0.07139655,0.73284745,0.06707978],"study_design_scores_gemma":[0.0012055549,0.0002459742,0.030980837,0.000044805023,0.00022330898,0.00012323471,0.060021058,0.0001510722,0.00014673725,0.002941549,0.90375316,0.00016269182],"about_ca_topic_score_codex":0.0000071535515,"about_ca_topic_score_gemma":0.000012914369,"teacher_disagreement_score":0.7239375,"about_ca_system_score_codex":0.00012351209,"about_ca_system_score_gemma":0.00018357865,"threshold_uncertainty_score":0.96467626},"labels":[],"label_agreement":null},{"id":"W304700293","doi":"10.3138/cjpe.0025.007","title":"Program Evaluation without a Client: The Case of the Disappearing Intended Users","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Scope (computer science); Negotiation; Meaning (existential); Business; Knowledge management; Process management; Public relations; Computer science; Psychology; Sociology; Political science","score_opus":0.5459869971696891,"score_gpt":0.541121227098997,"score_spread":0.00486577007069211,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W304700293","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98685867,0.00024956593,0.00028325166,0.0013104124,0.0012845367,0.004485179,0.0000051393563,0.000010758688,0.0055125128],"genre_scores_gemma":[0.9974064,0.0000041191956,0.0019745934,0.00011356086,0.00009987418,0.00031556372,0.0000032481641,0.000012315653,0.00007027721],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9939367,0.0016206357,0.0012595516,0.00023233287,0.002629548,0.0003212037],"domain_scores_gemma":[0.99243283,0.00018537161,0.0014944772,0.0006563702,0.0049312636,0.00029968438],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.030844795,0.00015668097,0.00024807875,0.00039228125,0.00045261014,0.00028690163,0.00088864483,0.00008385684,0.0014410826],"category_scores_gemma":[0.0045776744,0.00008147099,0.0002461696,0.0012042788,0.00033847528,0.00061010214,0.000041316573,0.0003371756,0.000023262173],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026860904,0.00008473519,0.05782231,0.0000046426617,0.000049162976,0.0000073553238,0.0072370055,0.00078131526,0.000014808085,0.0006124868,0.0003905117,0.9329688],"study_design_scores_gemma":[0.0028931757,0.0014746679,0.43494707,0.00024299831,0.0009517064,0.0011508828,0.026392564,0.49136388,0.00058262947,0.026480231,0.013171706,0.00034847893],"about_ca_topic_score_codex":0.0020402046,"about_ca_topic_score_gemma":0.0654992,"teacher_disagreement_score":0.93262035,"about_ca_system_score_codex":0.0003972367,"about_ca_system_score_gemma":0.00456622,"threshold_uncertainty_score":0.9994717},"labels":[],"label_agreement":null},{"id":"W3047902130","doi":"","title":"L’efficacité des conseils d’administration. Quelques pistes d’amélioration","year":2018,"lang":"fr","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"","keywords":"Political science; Computer science; Medicine","score_opus":0.07691819297910053,"score_gpt":0.3685677567256891,"score_spread":0.29164956374658857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3047902130","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3273174,0.0021648593,0.31239697,0.044215087,0.0015214559,0.0014141124,0.00024181145,0.0003851175,0.3103432],"genre_scores_gemma":[0.79831463,0.0017232529,0.09061163,0.000527453,0.0001727116,0.00018659378,0.0006926457,0.00007082054,0.10770025],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9764352,0.01615292,0.0022938051,0.0018317109,0.0024946656,0.0007917195],"domain_scores_gemma":[0.97329205,0.006848897,0.0019221734,0.0036566816,0.013732333,0.0005478906],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.030908126,0.00078075577,0.0008528709,0.0005345294,0.0017707513,0.0030587474,0.0026407582,0.0007071365,0.0062575852],"category_scores_gemma":[0.010416461,0.00077098433,0.00048612093,0.0014474303,0.0023388627,0.0011047891,0.0011956922,0.0008805512,0.002429014],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000117818156,0.0022430487,0.025670202,0.00031017847,0.00024090958,0.000014014948,0.027403131,0.00036361112,0.0028613084,0.5610117,0.012957754,0.36680633],"study_design_scores_gemma":[0.0023950895,0.000018050096,0.06544919,0.0064889933,0.00031676664,0.00011201206,0.0027929668,0.14459354,0.13321899,0.19160257,0.45050114,0.0025106862],"about_ca_topic_score_codex":0.0012142324,"about_ca_topic_score_gemma":0.0077008093,"teacher_disagreement_score":0.47099727,"about_ca_system_score_codex":0.00052664906,"about_ca_system_score_gemma":0.003536976,"threshold_uncertainty_score":0.9995288},"labels":[],"label_agreement":null},{"id":"W3073019040","doi":"10.21428/88de04a1.fd3fc79b","title":"Book Review | Qualitative Research in Action: A Canadian Primer","year":2013,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Primer (cosmetics); Action (physics); Political science; Sociology; Psychology; Chemistry; Physics","score_opus":0.787055114695318,"score_gpt":0.7254820645441046,"score_spread":0.06157305015121339,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3073019040","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0055869655,0.035398833,0.00009738445,0.3081321,0.00025643094,0.0015890647,0.0000027087146,0.000019013649,0.6489175],"genre_scores_gemma":[0.1644132,0.015617255,0.0012275559,0.17242496,0.00012289308,0.00071908726,0.000010179183,0.000014302598,0.6454506],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961972,0.0012365016,0.00043430692,0.00024105585,0.0016160895,0.00027483283],"domain_scores_gemma":[0.99748236,0.001043501,0.000049171602,0.00036163477,0.0008632652,0.00020004352],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.015276953,0.000055474055,0.00014168984,0.00048108047,0.00011670795,0.0001310137,0.0003174873,0.00003380627,0.20007795],"category_scores_gemma":[0.00096598506,0.000035810343,0.000030063478,0.0013152558,0.0000585547,0.00073914905,0.000033650686,0.00019472711,0.022138879],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.70657e-7,0.000008115895,0.0005637656,0.000009270613,0.000001104165,4.574672e-7,0.0010559432,0.0000013349126,0.000004726138,0.0012644331,0.9732752,0.023814982],"study_design_scores_gemma":[0.00008625735,0.000026758318,0.011343812,0.000097591976,6.5020424e-7,8.579508e-7,0.004369568,0.0004076545,0.00002503514,0.003801885,0.97978246,0.000057439665],"about_ca_topic_score_codex":0.110606834,"about_ca_topic_score_gemma":0.1570763,"teacher_disagreement_score":0.17793907,"about_ca_system_score_codex":0.00019634387,"about_ca_system_score_gemma":0.0009615414,"threshold_uncertainty_score":0.9786225},"labels":[],"label_agreement":null},{"id":"W307743687","doi":"","title":"Ontario Pins Hopes on Practices, Not Testing, to Achieve.","year":2007,"lang":"en","type":"article","venue":"Education week","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Mathematics education; Pedagogy; Public administration; Sociology; Psychology","score_opus":0.4740482752024762,"score_gpt":0.5585496077338987,"score_spread":0.0845013325314225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W307743687","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7373997,0.000010312826,0.001742715,0.029641237,0.002082867,0.00033241723,0.0000020363896,0.00003634683,0.22875239],"genre_scores_gemma":[0.8721305,0.0000016104223,0.01303642,0.020365873,0.00046551562,0.00002955291,0.0000093685585,0.000008784859,0.093952365],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99740005,0.00009650537,0.0005002126,0.00038038482,0.0013990253,0.00022381607],"domain_scores_gemma":[0.99651545,0.0015840303,0.00052905467,0.00051459164,0.00064374064,0.00021314225],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0055519943,0.000112591035,0.00012154067,0.00035939732,0.00022266044,0.00028474728,0.00040680307,0.000044521195,0.004174827],"category_scores_gemma":[0.006306648,0.00008916682,0.000036396534,0.00082027033,0.00002081384,0.0004559718,0.000041995092,0.00018663025,0.008057143],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001411684,0.0009565845,0.069365315,0.000002764342,0.000007916544,9.25412e-7,0.0071021845,0.00024940804,0.00058631424,0.0037159084,0.25567585,0.6621957],"study_design_scores_gemma":[0.00008063792,0.00026388216,0.42522675,0.000011328797,0.0000035564542,0.0000025014963,0.00075625477,0.000042195083,0.0003239306,0.00064313464,0.5725629,0.000082959334],"about_ca_topic_score_codex":0.008275081,"about_ca_topic_score_gemma":0.04276382,"teacher_disagreement_score":0.6621127,"about_ca_system_score_codex":0.0002939485,"about_ca_system_score_gemma":0.0022357882,"threshold_uncertainty_score":0.9983289},"labels":[],"label_agreement":null},{"id":"W3083387357","doi":"10.1016/j.envsci.2020.08.021","title":"The CEEDER database of evidence reviews: An open-access evidence service for researchers and decision-makers","year":2020,"lang":"en","type":"article","venue":"Environmental Science & Policy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":25,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Economic and Social Research Council","keywords":"Incentive; Transparency (behavior); Systematic review; Evidence-based practice; Reliability (semiconductor); Evidence-based policy; Resource (disambiguation); Service (business); Grey literature; Computer science; Knowledge management; Business; Management science; Political science; MEDLINE; Marketing; Economics; Medicine","score_opus":0.7866679771554409,"score_gpt":0.65409991774004,"score_spread":0.13256805941540095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3083387357","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9207129,0.003232516,0.0027097275,0.06980178,0.00016211807,0.0027895572,0.00007068205,0.000014711783,0.0005060042],"genre_scores_gemma":[0.98032874,0.0070118215,0.005003073,0.0072645145,0.000103255916,0.0001207245,0.000002476958,0.00001013038,0.00015523937],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99488926,0.000291356,0.0007302685,0.00085985905,0.0027746172,0.00045466077],"domain_scores_gemma":[0.9944701,0.003457659,0.00039055638,0.0009900174,0.00011697536,0.0005746893],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.017295133,0.0001601748,0.00025853867,0.00014610612,0.0010856052,0.0018729965,0.0065640863,0.000030681444,0.00047430015],"category_scores_gemma":[0.015851272,0.00008732482,0.000045013978,0.002140913,0.0013177556,0.009561157,0.003358028,0.00013717095,0.00013329429],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00052390393,0.000116425435,0.021347336,0.00004629233,0.000007267496,0.000001257369,0.005316049,0.00047915426,0.080944456,0.0019221733,0.006761223,0.88253444],"study_design_scores_gemma":[0.0023022403,0.0028977592,0.42269924,0.001548367,0.00006223824,0.000020635276,0.023364972,0.15345071,0.018092463,0.02158205,0.35270137,0.0012779392],"about_ca_topic_score_codex":0.0004293739,"about_ca_topic_score_gemma":0.00018683828,"teacher_disagreement_score":0.8812565,"about_ca_system_score_codex":0.0001708664,"about_ca_system_score_gemma":0.0007385147,"threshold_uncertainty_score":0.99916315},"labels":[],"label_agreement":null},{"id":"W3087003154","doi":"10.69554/gfln6937","title":"From pipeline audit to e-survey: A case study in research-driven prospect prioritisation and qualification","year":2020,"lang":"en","type":"article","venue":"Journal of education advancement & marketing.","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Audit; Survey research; Pipeline (software); Business; Engineering; Accounting; Business administration; Mechanical engineering","score_opus":0.4807729698410548,"score_gpt":0.6027245240111753,"score_spread":0.12195155417012049,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3087003154","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9770587,0.00017998848,0.0021680845,0.019042296,0.0004730573,0.0008543823,0.000008649136,0.000005220324,0.00020958555],"genre_scores_gemma":[0.9943094,0.00009730973,0.0042993613,0.00054343784,0.0004472543,0.00004055987,0.0000084077155,0.0000089557125,0.00024530164],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9931066,0.0027887563,0.0014932277,0.00039527382,0.0020339522,0.00018218317],"domain_scores_gemma":[0.9941889,0.0022601923,0.00079636154,0.00026345026,0.0022444513,0.00024661282],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.026829906,0.00011199925,0.00027566392,0.00051737303,0.00014398395,0.00026101072,0.00029377436,0.00003119633,0.00070792116],"category_scores_gemma":[0.019025495,0.000094245544,0.000032343367,0.0013579417,0.000031237036,0.0006462812,0.0000892205,0.00027995842,0.00004480329],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007595503,0.0009895719,0.6506098,0.000012480575,0.000014753612,0.000033168417,0.021566264,0.0007560206,0.0007602911,0.000023754972,0.015451599,0.30902272],"study_design_scores_gemma":[0.0014185221,0.00079685566,0.8540253,0.000114107184,0.000014405177,0.00004184922,0.11117313,0.0053292564,0.000048050846,0.0005115086,0.026360715,0.00016630269],"about_ca_topic_score_codex":0.00024219818,"about_ca_topic_score_gemma":0.00082497,"teacher_disagreement_score":0.30885643,"about_ca_system_score_codex":0.00026275712,"about_ca_system_score_gemma":0.00089086103,"threshold_uncertainty_score":0.98923767},"labels":[],"label_agreement":null},{"id":"W3088124318","doi":"10.1093/reseval/rvaa017","title":"The program and policy change framework: A new tool to measure research use in low- and middle-income countries","year":2020,"lang":"en","type":"article","venue":"Research Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Global Challenges Research Fund; UK Research and Innovation; National Academies of Sciences, Engineering, and Medicine; Federation for the Humanities and Social Sciences; United States Agency for International Development","keywords":"Agency (philosophy); Conceptual framework; International development; Tracking (education); Low and middle income countries; Inclusion (mineral); Research program; Policy development; Program evaluation; Theory of change; Process management; Political science; Economic growth; Developing country; Business; Economics; Sociology; Public administration; Management","score_opus":0.8269559494441125,"score_gpt":0.6651916119829281,"score_spread":0.16176433746118446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3088124318","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8246776,0.0009663664,0.00015782124,0.1689789,0.000064107255,0.0046784896,0.000008751952,0.000027584574,0.00044037806],"genre_scores_gemma":[0.9954824,0.0007099579,0.00116566,0.00080205256,0.00050167926,0.0009016979,0.0000039664606,0.000013794463,0.00041883314],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9823352,0.003965064,0.00060203247,0.0006767152,0.011620462,0.00080054556],"domain_scores_gemma":[0.9888256,0.0065176343,0.000074014395,0.0005400486,0.0035924825,0.00045022604],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.075180605,0.00012156334,0.0001907853,0.0008187682,0.0007765813,0.0023816768,0.000540005,0.00012214026,0.00022972669],"category_scores_gemma":[0.07909382,0.0000791803,0.000025939737,0.004289315,0.0002975173,0.000966164,0.0004831767,0.00074047776,0.0003119594],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005793633,0.00006178048,0.07049276,0.00007399791,0.0000148510435,0.0000034128939,0.022717193,0.00009135117,0.00006148239,0.016993718,0.0030118744,0.88589823],"study_design_scores_gemma":[0.0013545686,0.0011894136,0.7148746,0.00069475744,0.000006558426,0.0000027655628,0.0044374606,0.1487891,0.00009389381,0.056492858,0.07183165,0.0002323677],"about_ca_topic_score_codex":0.0005709722,"about_ca_topic_score_gemma":0.0016006458,"teacher_disagreement_score":0.88566583,"about_ca_system_score_codex":0.0002977117,"about_ca_system_score_gemma":0.0019540943,"threshold_uncertainty_score":0.99865395},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"evaluation","study_design":"theoretical_or_conceptual","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W3088160480","doi":"10.13140/rg.2.2.13032.60164","title":"Travailler dans des contextes complexes : une exploration des profils d'intelligence culturelle de gestionnaires du Nunavik","year":2018,"lang":"fr","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Humanities; Political science; Art","score_opus":0.23181566682567886,"score_gpt":0.45589101540863014,"score_spread":0.22407534858295128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3088160480","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40410835,0.0025623469,0.54201454,0.011084345,0.0011662001,0.0006235715,0.000023793893,0.00012816791,0.038288713],"genre_scores_gemma":[0.9254741,0.0018998006,0.025469974,0.00068585196,0.00052628294,0.00007684083,0.000016500917,0.00002157793,0.045829076],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99595565,0.0006256277,0.0009755057,0.0006172162,0.0012007846,0.00062521535],"domain_scores_gemma":[0.9964032,0.00064118044,0.00028359253,0.00048148262,0.001895746,0.0002947911],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["sts","insufficient_payload"],"category_scores_codex":[0.0032680482,0.00034623875,0.00034520144,0.00017117952,0.0014909942,0.0007075509,0.0006557707,0.0001897873,0.017203618],"category_scores_gemma":[0.0011864714,0.000257066,0.00014685428,0.0012020095,0.0030985896,0.0024054819,0.00010791868,0.0001891143,0.004601435],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012342146,0.00056280737,0.061423294,0.00007192223,0.000067179055,0.000005985128,0.11941766,0.002637979,0.007821423,0.066683955,0.035072856,0.7061115],"study_design_scores_gemma":[0.0007638153,0.0015554073,0.17835942,0.00067580177,0.00010494291,0.000093052775,0.094297074,0.20365445,0.11444988,0.318987,0.08616442,0.0008947228],"about_ca_topic_score_codex":0.0036530453,"about_ca_topic_score_gemma":0.022412023,"teacher_disagreement_score":0.70521677,"about_ca_system_score_codex":0.00031336467,"about_ca_system_score_gemma":0.0005338868,"threshold_uncertainty_score":0.99998814},"labels":[],"label_agreement":null},{"id":"W3088466851","doi":"10.1093/reseval/rvaa024","title":"Understanding and evaluating the impact of integrated problem-oriented research programmes: Concepts and considerations","year":2020,"lang":"en","type":"article","venue":"Research Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Roads University","funders":"Social Sciences and Humanities Research Council of Canada; Canada Research Chairs","keywords":"Context (archaeology); Counterfactual thinking; Scale (ratio); Theory of change; Management science; Discipline; Computer science; Field (mathematics); Impact evaluation; Ex-ante; Impact assessment; Research program; Political science; Economics; Sociology; Psychology; Management; Social science","score_opus":0.9197335360181665,"score_gpt":0.7290685971858931,"score_spread":0.19066493883227342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3088466851","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97551626,0.00053138327,0.0029842514,0.01386427,0.00003493584,0.0033017036,0.000020278572,0.00002302378,0.0037238977],"genre_scores_gemma":[0.9984961,0.00007651995,0.001024131,0.00004691432,0.00005419824,0.00020435119,0.00002189422,0.000010457853,0.00006544671],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98054963,0.008999654,0.0008301128,0.00060681056,0.008506783,0.00050698937],"domain_scores_gemma":[0.9819466,0.009232275,0.00022433163,0.00039518115,0.00794959,0.00025202535],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.100608334,0.00012829337,0.00024345166,0.0004838284,0.0011477366,0.0006790437,0.00025166362,0.000080971775,0.0014478116],"category_scores_gemma":[0.045438215,0.00007328518,0.000056534805,0.002831275,0.0010408588,0.0005508438,0.00025080144,0.00066996913,0.000032010972],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00139013,0.0005108977,0.18284057,0.00019041004,0.00045969823,0.0000055250775,0.13420843,0.021485223,0.06514219,0.1622057,0.043781143,0.3877801],"study_design_scores_gemma":[0.001164549,0.0020400588,0.017406294,0.00006401355,0.000016677195,0.0000050912063,0.032128163,0.84128827,0.00033146748,0.10525874,0.00020341118,0.00009326704],"about_ca_topic_score_codex":0.00025309325,"about_ca_topic_score_gemma":0.0000953998,"teacher_disagreement_score":0.81980306,"about_ca_system_score_codex":0.00045829063,"about_ca_system_score_gemma":0.002916306,"threshold_uncertainty_score":0.999465},"labels":[],"label_agreement":null},{"id":"W3088611382","doi":"10.31372/20200502.1086","title":"Development of a Culturally Specific Leadership Curriculum through Community-Based Participatory Research and Popular Education","year":2020,"lang":"en","type":"article","venue":"Asian/Pacific Island Nursing Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Northwest Health Foundation","keywords":"Curriculum; Citizen journalism; Sociology; Participatory action research; Pedagogy; Community-based participatory research; Engineering ethics; Political science; Psychology; Engineering; Anthropology","score_opus":0.6485136311256229,"score_gpt":0.5283103784669586,"score_spread":0.12020325265866427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3088611382","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9419315,0.0010833346,0.0073822397,0.031812515,0.00085315097,0.00033290178,0.0000054954535,0.000024066998,0.016574826],"genre_scores_gemma":[0.98762316,0.000037735797,0.0116005,0.00024308662,0.00025390377,0.0000072272665,0.000016404363,0.000010902901,0.0002070605],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9952688,0.0012921302,0.00086212566,0.00024291954,0.0019594813,0.000374503],"domain_scores_gemma":[0.99798495,0.00019961018,0.00035154322,0.00028980616,0.0009316456,0.0002424717],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0067138206,0.00014922657,0.00027856237,0.0002358073,0.0012173619,0.00042833984,0.00047483304,0.00008176614,0.0002797462],"category_scores_gemma":[0.00032803667,0.00010728355,0.00006651186,0.0008349522,0.00032555542,0.0005065553,0.000032726533,0.00092236296,0.00007202654],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032949742,0.0013123753,0.039617516,0.00011061157,0.00005586614,0.0000084024105,0.3956136,0.00009651347,0.0038222687,0.0033254563,0.11733679,0.4383711],"study_design_scores_gemma":[0.0016982426,0.0008008142,0.026101707,0.0010474204,0.00002875665,0.000089871544,0.6315335,0.0017314685,0.0032598297,0.012336484,0.32094067,0.00043125238],"about_ca_topic_score_codex":0.0000032875332,"about_ca_topic_score_gemma":0.0000123847185,"teacher_disagreement_score":0.43793982,"about_ca_system_score_codex":0.00015139475,"about_ca_system_score_gemma":0.0009972192,"threshold_uncertainty_score":0.9363087},"labels":[],"label_agreement":null},{"id":"W3090487419","doi":"","title":"Évaluation de l’efficacité des systèmes d’assurance qualité des collèges québécois : bilan des résultats de l’an 3 du premier cycle d’audit 2016-2017","year":2018,"lang":"fr","type":"article","venue":"Bibliothèque et Archives nationales du Québec (Québec government)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.06342425872075907,"score_gpt":0.3511209873570006,"score_spread":0.2876967286362415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3090487419","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9245128,0.010108983,0.021420956,0.009635908,0.00041602744,0.0007884193,0.0002997789,0.00017466118,0.032642476],"genre_scores_gemma":[0.94604945,0.0054849647,0.016454134,0.0015338447,0.0010880174,0.000327713,0.000028831953,0.00010410916,0.028928919],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9893596,0.0026620696,0.0017224286,0.0012962788,0.003699672,0.0012599308],"domain_scores_gemma":[0.975182,0.020769745,0.0011977619,0.0010047016,0.0010593194,0.0007864823],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["sts","insufficient_payload"],"category_scores_codex":[0.007932947,0.0007907569,0.00074872415,0.0012477703,0.002161826,0.0017700504,0.0019029429,0.00024209179,0.007417597],"category_scores_gemma":[0.02210092,0.00072884606,0.00041009337,0.002349257,0.0036091343,0.0037615208,0.00043735118,0.00044491087,0.0012990686],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00086198474,0.0018041775,0.6878986,0.0004669801,0.0004372894,0.000026878564,0.13732283,0.010522595,0.0061259447,0.010606581,0.039397236,0.10452893],"study_design_scores_gemma":[0.0018012124,0.0007586265,0.8441171,0.0008781446,0.00016988497,0.00016243193,0.004057352,0.059709147,0.0029597937,0.023168972,0.06133349,0.0008838254],"about_ca_topic_score_codex":0.29016587,"about_ca_topic_score_gemma":0.97922564,"teacher_disagreement_score":0.68905973,"about_ca_system_score_codex":0.012730978,"about_ca_system_score_gemma":0.09827358,"threshold_uncertainty_score":0.99951625},"labels":[],"label_agreement":null},{"id":"W3091989186","doi":"10.1108/qrj-07-2020-0085","title":"Exodus at home: a narrative introspection on what matters","year":2020,"lang":"en","type":"article","venue":"Qualitative Research Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Introspection; Narrative; Originality; Value (mathematics); Gestalt psychology; Sociology; Narrative inquiry; Epistemology; Empiricism; Psychology; Social psychology; Social science; Linguistics; Qualitative research; Computer science; Philosophy","score_opus":0.6847026402421811,"score_gpt":0.6916016732250665,"score_spread":0.006899032982885411,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3091989186","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5893651,0.00022101363,0.0028187975,0.40341976,0.00061987876,0.00032591406,0.000009060616,0.000022055256,0.0031983743],"genre_scores_gemma":[0.9856895,0.00050416274,0.00063138985,0.006587537,0.0008963403,0.000031236577,0.000004695738,0.000018200193,0.0056369323],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9840817,0.0075601656,0.00075702963,0.00045663517,0.0066524628,0.0004919934],"domain_scores_gemma":[0.9916187,0.0049928343,0.00032154712,0.00025453427,0.002266628,0.0005457587],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.030349799,0.00014882891,0.00029057555,0.0005522021,0.0012319115,0.0016824398,0.0006346579,0.000059123213,0.012666728],"category_scores_gemma":[0.0063342745,0.00009914173,0.00013948555,0.0015966352,0.000343049,0.0018730523,0.0001717729,0.0011706351,0.004985388],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009976611,0.00008485781,0.0005194321,0.000008027505,0.00007149411,0.000040629162,0.60944766,0.00038733205,0.0026105493,0.0075802295,0.32930925,0.048942875],"study_design_scores_gemma":[0.0014410202,0.0026183506,0.003815038,0.00009834485,0.0000038310227,0.000041885993,0.834273,0.002845083,0.0014313842,0.05439658,0.09880596,0.0002295408],"about_ca_topic_score_codex":0.00000529954,"about_ca_topic_score_gemma":0.000015727446,"teacher_disagreement_score":0.39683223,"about_ca_system_score_codex":0.0006520928,"about_ca_system_score_gemma":0.0003654701,"threshold_uncertainty_score":0.9993539},"labels":[],"label_agreement":null},{"id":"W3092260212","doi":"10.1093/eurpub/ckaa166.1169","title":"Using theory of change to assess impact of knowledge translation initiatives","year":2020,"lang":"en","type":"article","venue":"European Journal of Public Health","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Competence (human resources); Theory of change; Knowledge translation; Knowledge management; Workforce; Quality (philosophy); Process management; Medical education; Management science; Public relations; Psychology; Business; Computer science; Medicine; Political science; Engineering; Sociology","score_opus":0.935269314419008,"score_gpt":0.6324294077576736,"score_spread":0.3028399066613343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092260212","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6826939,0.00051542505,0.2991604,0.00801549,0.00022189597,0.00020394682,0.00002305345,0.0000058595747,0.009160064],"genre_scores_gemma":[0.99502176,0.00005348046,0.004037072,0.000628461,0.0002405135,2.3227317e-7,0.0000010236369,0.000010361084,0.0000070993633],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98784643,0.008859946,0.0017341753,0.0001521993,0.0011798266,0.00022743962],"domain_scores_gemma":[0.9962985,0.0006344314,0.0013674062,0.00014591056,0.0011119335,0.0004418163],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.040678866,0.000087569984,0.00037054534,0.00043690018,0.000058460093,0.000055751494,0.00043563813,0.000012218225,0.0005637633],"category_scores_gemma":[0.002095793,0.00005806046,0.00016780342,0.0010269841,0.000043318014,0.00093433727,0.000040164065,0.00015549976,0.000024216615],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006138457,0.00017887134,0.025291339,0.000048747002,0.000060184706,0.0000035962676,0.08480124,0.00059113745,0.0014466644,0.0011805637,0.0005831928,0.8857531],"study_design_scores_gemma":[0.0011543247,0.0034623956,0.97416794,0.00015089496,0.000011573986,0.000015153761,0.006894812,0.006476826,0.00019183688,0.00029248075,0.007053083,0.00012864644],"about_ca_topic_score_codex":0.000003257045,"about_ca_topic_score_gemma":0.0000022410895,"teacher_disagreement_score":0.9488766,"about_ca_system_score_codex":0.00007245891,"about_ca_system_score_gemma":0.0014285501,"threshold_uncertainty_score":0.987823},"labels":[],"label_agreement":null},{"id":"W3093541286","doi":"10.1177/0886109920965287","title":"Still We Resist: Reflections on Our Tenure as Editors-in-Chief","year":2020,"lang":"en","type":"article","venue":"Affilia","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Resist; Business; Media studies; Sociology; Nanotechnology; Materials science","score_opus":0.2828664371524465,"score_gpt":0.5228298088973709,"score_spread":0.23996337174492433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3093541286","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30638346,0.00013797046,0.00027886167,0.43559188,0.011122586,0.0006395024,0.000042178774,0.00022816936,0.24557538],"genre_scores_gemma":[0.98468816,0.000035546964,0.00037299897,0.00385373,0.0021480608,0.00001844646,0.0000045128654,0.000009592909,0.008868958],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99760354,0.000165252,0.00041342032,0.00041810432,0.0011965514,0.00020312546],"domain_scores_gemma":[0.9989128,0.00026292977,0.000117360454,0.00038099312,0.0001677179,0.00015820524],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0010386427,0.00011896247,0.00017845204,0.00017565669,0.00010164072,0.00012655584,0.00033069996,0.00007908386,0.0014938028],"category_scores_gemma":[0.0016959917,0.000087943474,0.000076980636,0.0010350831,0.000020266763,0.00022755927,0.000057296453,0.00025670748,0.007544078],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014623921,0.0001392597,0.004655468,0.0000059740737,0.000011710188,0.000016660246,0.004257017,0.0018051412,0.0011485593,0.0032551314,0.972064,0.012494815],"study_design_scores_gemma":[0.00041807754,0.0003464336,0.019957757,0.000022196517,0.0000060415846,0.000002104482,0.0034563213,0.0019124033,0.0005128531,0.0031717157,0.9700526,0.00014151937],"about_ca_topic_score_codex":0.000024923922,"about_ca_topic_score_gemma":0.00022367934,"teacher_disagreement_score":0.6783047,"about_ca_system_score_codex":0.000055777895,"about_ca_system_score_gemma":0.00020265732,"threshold_uncertainty_score":0.999419},"labels":[],"label_agreement":null},{"id":"W3093596797","doi":"10.29173/assert12","title":"Q &amp; A with Terence Beck on “Identity, Discourse, and Safety in Controversial Issue Discussions\"","year":2020,"lang":"en","type":"article","venue":"Annals of Social Studies Education Research for Teachers","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Identity (music); Sociology; Philosophy; Aesthetics","score_opus":0.6862930207642991,"score_gpt":0.6860346294419947,"score_spread":0.00025839132230442985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3093596797","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6398322,0.0003346471,0.00011773396,0.3552938,0.00012755285,0.0008051905,0.000032026495,0.000007564742,0.003449298],"genre_scores_gemma":[0.99531454,0.00037722485,0.0001767566,0.0011632082,0.0002175904,0.00011857077,0.000009551169,0.000006357163,0.00261619],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.9970802,0.00040501897,0.0003819924,0.00032282324,0.0015504452,0.00025953393],"domain_scores_gemma":[0.9973787,0.0011594526,0.00016478461,0.00013119799,0.0010497328,0.00011611815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00501256,0.000094549694,0.0002735969,0.00019482132,0.0004963819,0.00010510371,0.00030383497,0.00004150871,0.00016861287],"category_scores_gemma":[0.0048269155,0.00006120372,0.00005601356,0.0007539179,0.00053152343,0.00043112173,0.00011743007,0.00021110359,0.000028370985],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012080637,0.0006303035,0.05618,0.000077158955,0.00015935337,3.689202e-7,0.22481646,0.000053621112,0.00010359758,0.02831366,0.49034414,0.19811328],"study_design_scores_gemma":[0.0013362942,0.0008841508,0.17088376,0.000106672516,0.00001344203,1.7918603e-7,0.504774,0.00007950858,0.00008915974,0.012129193,0.30950436,0.00019932466],"about_ca_topic_score_codex":0.00011868661,"about_ca_topic_score_gemma":0.00082774315,"teacher_disagreement_score":0.35548237,"about_ca_system_score_codex":0.00006468859,"about_ca_system_score_gemma":0.0004631896,"threshold_uncertainty_score":0.5778617},"labels":[],"label_agreement":null},{"id":"W3094330052","doi":"10.56645/jmde.v16i36.623","title":"Evaluation Policy and Organizational Evaluation Capacity Building: Application of an Ecological Framework across Cultural Contexts","year":2020,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Ottawa; Saudi Arabian Cultural Bureau; National Science Foundation","keywords":"Context (archaeology); Focus group; Conceptual framework; Capacity building; Situated; Government (linguistics); Public relations; Political science; Sociology; Psychology; Environmental resource management; Geography; Business; Social science; Marketing; Economics","score_opus":0.3125964842906351,"score_gpt":0.5461170546069485,"score_spread":0.2335205703163134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3094330052","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97057176,0.00024513644,0.021497244,0.0057881763,0.00032418332,0.0013550973,0.000024912666,0.0000155491,0.00017792713],"genre_scores_gemma":[0.98770034,0.00003241248,0.011099973,0.00023361319,0.00079757016,0.000053778775,0.00006103752,0.000016239104,0.000005018666],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9842613,0.0030630566,0.002098303,0.00055337703,0.009757684,0.00026631713],"domain_scores_gemma":[0.9788213,0.0011756654,0.002711902,0.00037844942,0.016588299,0.0003244281],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.047018927,0.0002522032,0.0005321215,0.00031270148,0.00041432978,0.00022015806,0.0005761835,0.0002551547,0.0007623515],"category_scores_gemma":[0.03256073,0.00018759759,0.00015006556,0.001444777,0.0002169879,0.0021026304,0.0001751958,0.00038169755,0.000024807308],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00071621506,0.0013536186,0.06529303,0.000045809094,0.00019532074,0.0000014924934,0.035586108,0.25231382,0.042152144,0.008398825,0.00022634421,0.5937173],"study_design_scores_gemma":[0.0019142635,0.0006469739,0.31865388,0.000026903703,0.00020471061,0.000023431603,0.0025482415,0.6175789,0.0013458222,0.056852903,0.00006047452,0.00014349892],"about_ca_topic_score_codex":0.000011885293,"about_ca_topic_score_gemma":0.00003619131,"teacher_disagreement_score":0.59357375,"about_ca_system_score_codex":0.00064685463,"about_ca_system_score_gemma":0.0017520146,"threshold_uncertainty_score":0.9812946},"labels":[],"label_agreement":null},{"id":"W3095653627","doi":"10.4000/ree.1473","title":"L’implantation de programmes d’insertion professionnelle dans l’enseignement : qu’en pensent les enseignants débutants ?","year":2020,"lang":"fr","type":"article","venue":"Recherches en éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université du Québec en Abitibi-Témiscamingue; Université de Montréal; Université de Sherbrooke","funders":"","keywords":"Humanities; Political science; Art","score_opus":0.4635354929028782,"score_gpt":0.5109266625052749,"score_spread":0.04739116960239664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3095653627","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87809193,0.0016784818,0.026918706,0.0841,0.0019946266,0.0016437444,0.000033969867,0.00020561091,0.005332924],"genre_scores_gemma":[0.9755815,0.0019714294,0.0127122905,0.0011624146,0.0006728538,0.0002378558,0.000119045864,0.00005913976,0.0074834395],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9907649,0.0049536293,0.0011989933,0.00085188035,0.001557118,0.00067349285],"domain_scores_gemma":[0.99606615,0.0018484896,0.00062269927,0.0004616399,0.00059888157,0.00040214078],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.009141316,0.00040112223,0.00040981913,0.00020141208,0.00057860377,0.00032968106,0.0005729025,0.00056137383,0.001930102],"category_scores_gemma":[0.0037371614,0.00036197703,0.00017332977,0.0010332996,0.0001231091,0.0008260778,0.00013631367,0.00066952436,0.0018415812],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017538093,0.0007126572,0.013621199,0.0002712349,0.000067835615,0.000007742236,0.34739706,0.00065833266,0.020383263,0.0012004712,0.010778252,0.60472655],"study_design_scores_gemma":[0.0023496815,0.0014399169,0.373848,0.0010882438,0.00036055598,0.00010845228,0.37663138,0.13796021,0.03832356,0.012398177,0.054161157,0.0013306874],"about_ca_topic_score_codex":0.0007359389,"about_ca_topic_score_gemma":0.00060084113,"teacher_disagreement_score":0.6033959,"about_ca_system_score_codex":0.0028513726,"about_ca_system_score_gemma":0.0036024007,"threshold_uncertainty_score":0.99988323},"labels":[],"label_agreement":null},{"id":"W3095898194","doi":"10.1515/9780228003106-014","title":"International Education Policy in Ontario: A Swinging Pendulum?","year":2020,"lang":"en","type":"book-chapter","venue":"McGill-Queen's University Press eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Pendulum; Political science; Engineering; Mechanical engineering","score_opus":0.0944924197541477,"score_gpt":0.3535988598197596,"score_spread":0.2591064400656119,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3095898194","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000069039896,6.3684087e-7,0.00008632883,0.0018165212,0.00078637723,0.0003636821,0.00008690055,0.00005796611,0.99673253],"genre_scores_gemma":[0.020085024,0.000029675151,0.00044968416,0.0007101655,0.00016409409,0.0000025013492,0.000073963325,0.000026221467,0.97845864],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99675727,0.00009574032,0.00055412325,0.00075295765,0.0015958558,0.00024404399],"domain_scores_gemma":[0.99807775,0.00017825923,0.00051386043,0.0005360778,0.00049556664,0.00019849968],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005802074,0.00032831452,0.0004144265,0.0011569783,0.000229464,0.00016384765,0.0011798592,0.00026279155,0.0013909895],"category_scores_gemma":[0.00015273514,0.0003481843,0.00021780469,0.000057312463,0.0000774067,0.00041984205,0.00061219785,0.0007229126,0.00016740913],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000077938865,0.000029896675,0.00041640594,0.000009880113,0.000057583016,0.000038646056,0.0006273441,0.000116039766,0.000004847665,0.97687453,0.005011377,0.016735524],"study_design_scores_gemma":[0.00049460767,0.000036642487,0.0009308026,0.000120305376,0.00003084582,0.000002411416,0.00023633768,0.00021866032,0.000021012896,0.005646095,0.9919278,0.00033448212],"about_ca_topic_score_codex":0.040632624,"about_ca_topic_score_gemma":0.00092350104,"teacher_disagreement_score":0.9869164,"about_ca_system_score_codex":0.0016849124,"about_ca_system_score_gemma":0.0013933303,"threshold_uncertainty_score":0.999897},"labels":[],"label_agreement":null},{"id":"W3096927313","doi":"10.7202/1071517ar","title":"Élaboration du Gabarit d’évaluation de l’environnement des programmes : le cas d’une unité universitaire de formation continue au Québec","year":2020,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Political science; Valuation (finance); Humanities; Economics; Art","score_opus":0.15462594917698577,"score_gpt":0.418505429817297,"score_spread":0.2638794806403112,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3096927313","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60151815,0.0004607914,0.17329247,0.21999696,0.0006082709,0.0011570689,0.000027048274,0.00009959749,0.002839638],"genre_scores_gemma":[0.9846423,0.0005385838,0.009777639,0.0016620691,0.0005447429,0.0001592031,0.0007531045,0.00004345063,0.00187889],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.98723733,0.007829158,0.001358556,0.0007258262,0.0021986263,0.00065052736],"domain_scores_gemma":[0.9952805,0.0010805854,0.0009933878,0.0004782802,0.0018108173,0.0003563986],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.030174442,0.0004274026,0.00041075484,0.00034131075,0.001243475,0.0005870706,0.00048913655,0.0003516533,0.00126413],"category_scores_gemma":[0.0048974934,0.0004617627,0.00018641054,0.0018273578,0.00025780674,0.004051483,0.00010104934,0.0004174616,0.00059199816],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00010407427,0.00046892723,0.11078943,0.00015933861,0.000073435855,0.0000029879388,0.47927496,0.032566804,0.0015687967,0.0067447796,0.0068818717,0.3613646],"study_design_scores_gemma":[0.0016046766,0.00049689034,0.551799,0.00014708655,0.00029221192,0.00002245306,0.056450535,0.34581652,0.0024803665,0.0040451316,0.036364876,0.00048026672],"about_ca_topic_score_codex":0.027723134,"about_ca_topic_score_gemma":0.111749105,"teacher_disagreement_score":0.44100955,"about_ca_system_score_codex":0.0056771366,"about_ca_system_score_gemma":0.0202319,"threshold_uncertainty_score":0.9997834},"labels":[],"label_agreement":null},{"id":"W3097050441","doi":"10.5206/cjsotl-rcacea.2020.2.10730","title":"Book Review: Outcome Harvesting: Principles, Steps, and Evaluation Applications","year":2020,"lang":"en","type":"article","venue":"The Canadian Journal for the Scholarship of Teaching and Learning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Outcome (game theory); Computer science; Sociology; Mathematics; Mathematical economics","score_opus":0.38151024493093544,"score_gpt":0.49565639649626864,"score_spread":0.1141461515653332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3097050441","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09374906,0.47775432,0.018755922,0.40048075,0.0004908683,0.003403518,0.0000223084,0.00003884055,0.0053044213],"genre_scores_gemma":[0.97517174,0.0009976926,0.000922266,0.017411122,0.00020894781,0.000046347184,0.0000040303426,0.000013624368,0.0052241962],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968694,0.001543318,0.0005269626,0.00015967514,0.000730646,0.00016998878],"domain_scores_gemma":[0.99682456,0.0018651137,0.00046104097,0.00019021198,0.00036088558,0.0002981716],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.044469167,0.00008719193,0.00016733828,0.00007737351,0.00392709,0.00060495915,0.00046132345,0.000032872205,0.00024034875],"category_scores_gemma":[0.017792186,0.000046638408,0.000065738204,0.00012632388,0.00009857119,0.00039565258,0.000032499553,0.0014640176,0.000008399847],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026647122,0.000007860244,0.101718105,0.00017383299,0.00008903841,8.278368e-7,0.00912167,0.012971512,0.00007888708,0.004907595,0.026590561,0.84431344],"study_design_scores_gemma":[0.00022364913,0.000060544844,0.022923298,0.00013154784,0.00009618126,0.000031975578,0.0010029938,0.021617156,0.000002754523,0.0008192793,0.9530195,0.00007113857],"about_ca_topic_score_codex":0.00028816817,"about_ca_topic_score_gemma":0.0010509456,"teacher_disagreement_score":0.9264289,"about_ca_system_score_codex":0.00004900865,"about_ca_system_score_gemma":0.00048169206,"threshold_uncertainty_score":0.99736965},"labels":[],"label_agreement":null},{"id":"W3099471317","doi":"10.3138/cjpe.70004","title":"Sustainability Analysis of Intervention Benefits: A Theory of Change Approach","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sustainability; Intervention (counseling); Spell; Sustainability organizations; Work (physics); Environmental economics; Business; Environmental resource management; Economics; Psychology; Engineering; Sociology; Ecology","score_opus":0.6214875283452821,"score_gpt":0.5413536083546764,"score_spread":0.0801339199906057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3099471317","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98255146,0.0010922652,0.011808764,0.002313226,0.00016530626,0.0012737425,0.000034112167,0.0000047861386,0.0007563237],"genre_scores_gemma":[0.99839,0.0000059218273,0.0013700711,0.000090294794,0.000059766506,0.000043418157,0.000024719511,0.0000044368203,0.000011323392],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99562496,0.0010028692,0.0012988154,0.00017837128,0.0017391881,0.0001557717],"domain_scores_gemma":[0.99189144,0.00020184646,0.0014336187,0.00024655458,0.0059143566,0.00031217796],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.019280892,0.00008898947,0.00041678766,0.0010742384,0.00005517175,0.0000713291,0.00042073455,0.00006246421,0.0014010329],"category_scores_gemma":[0.0052697198,0.000069008885,0.00039992196,0.002886235,0.0001155159,0.0005020531,0.000016918622,0.00012208727,0.0000022864515],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005865338,0.00009999217,0.06936284,0.00003405463,0.00027119258,5.039697e-7,0.0066078305,0.00864966,0.000007777219,0.0030077226,0.000102567785,0.9117972],"study_design_scores_gemma":[0.0010083291,0.0012537453,0.6038186,0.000041698324,0.0017153384,0.000002748413,0.01683423,0.36118963,0.00012940465,0.012241746,0.0016357858,0.0001287778],"about_ca_topic_score_codex":0.0004851808,"about_ca_topic_score_gemma":0.0032415525,"teacher_disagreement_score":0.9116684,"about_ca_system_score_codex":0.00023722743,"about_ca_system_score_gemma":0.0017338933,"threshold_uncertainty_score":0.99951184},"labels":[],"label_agreement":null},{"id":"W3099626247","doi":"10.22215/etd/2020-14177","title":"The Government of Canada’s Second Language Evaluation, Test of Written Expression: Exploring Validity","year":2020,"lang":"en","type":"dissertation","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Carleton University","funders":"","keywords":"Government (linguistics); Test (biology); Context (archaeology); Expression (computer science); Stakeholder; Psychology; Ecological validity; Language assessment; Political science; Public relations; Mathematics education; Linguistics; Computer science; History","score_opus":0.2446088050734773,"score_gpt":0.43881182330005536,"score_spread":0.19420301822657807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3099626247","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70670813,0.0004204375,0.0000514911,0.00124438,0.0018109969,0.0007664027,0.00016641269,0.000013192306,0.28881857],"genre_scores_gemma":[0.96973115,0.00005827221,0.00016969933,0.00008767796,0.00009027217,0.00009669719,0.00007968532,0.000012548315,0.029674],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.98875964,0.00028706147,0.0012320167,0.0003500879,0.009200361,0.00017085606],"domain_scores_gemma":[0.9946132,0.002391354,0.0011383882,0.0006569733,0.0011045086,0.000095581854],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0053543155,0.00018275857,0.00037772395,0.000044392174,0.00019831888,0.00006979714,0.0007879935,0.00007403253,0.010302358],"category_scores_gemma":[0.0047182394,0.00010755284,0.00011171874,0.0003206233,0.000027829748,0.00020911434,0.00006936869,0.00018020331,0.000010056406],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005420909,0.00040511918,0.0363937,0.00060473947,0.00023261769,0.000008453879,0.04350125,0.0008513215,0.083035946,0.0027811984,0.54813224,0.2835113],"study_design_scores_gemma":[0.0008421874,0.00019479118,0.17858239,0.0002432154,0.00011219401,8.4044086e-7,0.18481916,0.008301605,0.5455796,0.0010580834,0.07983455,0.0004313528],"about_ca_topic_score_codex":0.0033571508,"about_ca_topic_score_gemma":0.36019248,"teacher_disagreement_score":0.4682977,"about_ca_system_score_codex":0.00020605096,"about_ca_system_score_gemma":0.0033691,"threshold_uncertainty_score":0.9906024},"labels":[],"label_agreement":null},{"id":"W3099638507","doi":"10.1177/1558689820970692","title":"Strange Bedfellows: Exploring Methodological Intersections Between Realist Inquiry and Structural Equation Modeling","year":2020,"lang":"en","type":"article","venue":"Journal of Mixed Methods Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Structural equation modeling; Epistemology; Field (mathematics); Critical realism (philosophy of perception); Sociology; Multimethodology; Latent variable; Realism; Management science; Computer science; Social science; Mathematics; Philosophy; Artificial intelligence; Engineering","score_opus":0.9738115710504699,"score_gpt":0.7338355106388782,"score_spread":0.2399760604115917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3099638507","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46067742,0.00015369235,0.5357634,0.0028633138,0.00029942772,0.00008519774,0.0000023140997,0.0000052466776,0.00015001332],"genre_scores_gemma":[0.6675997,0.00016982986,0.33141857,0.0000563938,0.00072071666,0.000005436633,0.000001266317,0.0000073523383,0.000020762629],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9857966,0.009641895,0.0012530426,0.00031992907,0.0026804062,0.00030812877],"domain_scores_gemma":[0.987438,0.009949175,0.0003522986,0.0002166307,0.001656523,0.00038733028],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.072575726,0.000118253956,0.0004721036,0.0006217152,0.0003305081,0.00031355632,0.00056960626,0.00009867565,0.00032490553],"category_scores_gemma":[0.024847284,0.000078864105,0.00014757068,0.001094094,0.00016967805,0.0010135692,0.00024363538,0.0011101402,0.000010957926],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034782116,0.000022948192,0.010589395,0.00003300115,0.0001079442,0.00001363658,0.021769,0.01881765,0.01996863,0.0010079003,0.00082847656,0.9264936],"study_design_scores_gemma":[0.0013398988,0.001732688,0.03140718,0.0000945173,0.000069582864,0.0000563633,0.079480916,0.7826157,0.007549561,0.09193454,0.0034278077,0.0002912037],"about_ca_topic_score_codex":0.000027869804,"about_ca_topic_score_gemma":0.00000882227,"teacher_disagreement_score":0.9262024,"about_ca_system_score_codex":0.00010075796,"about_ca_system_score_gemma":0.00021105884,"threshold_uncertainty_score":0.98336685},"labels":[],"label_agreement":null},{"id":"W309965191","doi":"","title":"Alternative Strategies for Large Scale Student Assessment in Canada: Is Value-Added Assessment One Possible Answer","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Educational Administration and Policy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Accountability; Scale (ratio); Popularity; Value (mathematics); Educational assessment; Student achievement; Public relations; Academic achievement; Political science; Psychology; Pedagogy; Computer science; Geography; Social psychology","score_opus":0.10309039879760774,"score_gpt":0.4976632851093496,"score_spread":0.39457288631174187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W309965191","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79360914,0.0001528049,0.001454403,0.18973298,0.00063963875,0.00041533387,0.00031201067,0.000001463035,0.013682218],"genre_scores_gemma":[0.9881157,0.000028159599,0.004467573,0.0052152034,0.00079724594,0.000028108549,0.000029343977,0.000007859873,0.0013107832],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99726516,0.0001432893,0.0009986304,0.00022931177,0.0010375095,0.00032609113],"domain_scores_gemma":[0.99733895,0.00048589046,0.0005303138,0.00017060195,0.0008721894,0.00060207106],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0019079706,0.00014905975,0.00026947426,0.00063278276,0.00025442068,0.00047442582,0.00034542935,0.00004666285,0.0023920648],"category_scores_gemma":[0.0001980515,0.00013144944,0.00006836406,0.00040699117,0.00004585379,0.00075591635,0.0000119856195,0.00021059594,0.000006664972],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004413803,0.0004564645,0.32839358,0.000019055307,0.00009760114,0.0000041713092,0.0076505714,0.003027669,0.000055918023,0.6166084,0.035755206,0.007887216],"study_design_scores_gemma":[0.0012133839,0.00029515012,0.8926193,0.0000438826,0.0000194258,0.00002991461,0.011477728,0.0055173947,0.0000794597,0.032409366,0.056093346,0.00020165322],"about_ca_topic_score_codex":0.28239346,"about_ca_topic_score_gemma":0.9757282,"teacher_disagreement_score":0.69333476,"about_ca_system_score_codex":0.0018185369,"about_ca_system_score_gemma":0.1294992,"threshold_uncertainty_score":0.9985199},"labels":[],"label_agreement":null},{"id":"W3101505332","doi":"10.3138/cjpe.69796","title":"Application of an Evaluation Framework for Extra-Organizational Communities of Practice: Assessment and Refinement","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université du Québec à Montréal; University of Toronto","funders":"","keywords":"Knowledge management; Community of practice; Reflection (computer programming); Work (physics); Content analysis; Value (mathematics); Qualitative research; Psychology; Sociology; Computer science; Pedagogy","score_opus":0.39468624739554886,"score_gpt":0.5735482175325376,"score_spread":0.17886197013698873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3101505332","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5844133,0.0007600186,0.39189678,0.01631832,0.00043101294,0.0050588483,0.000085355554,0.000011601284,0.001024785],"genre_scores_gemma":[0.8624265,0.000016459508,0.13693596,0.00027078882,0.00010800297,0.0001303033,0.000100089586,0.000009485617,0.0000023656787],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99495184,0.00090320036,0.0012512258,0.00016051382,0.0025945976,0.00013861185],"domain_scores_gemma":[0.98655564,0.00088383025,0.0018417946,0.00026981652,0.010152747,0.00029620464],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017980173,0.0001093446,0.00027657417,0.00033130933,0.00017017053,0.0001381568,0.0003518717,0.00008813043,0.0006926258],"category_scores_gemma":[0.005154195,0.00009546447,0.00006631176,0.00064104603,0.00011910054,0.0007936285,0.000015747682,0.00016239511,0.0000016386068],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000077104865,0.00015807421,0.0233405,0.00003696322,0.00007181567,1.894008e-7,0.007891189,0.0116040055,0.00036827454,0.020631703,0.00021968823,0.9356005],"study_design_scores_gemma":[0.0017278092,0.0022523266,0.096228786,0.00007029239,0.00040701116,0.0000114715585,0.0151813775,0.824194,0.0004683102,0.049169097,0.010135074,0.00015443032],"about_ca_topic_score_codex":0.00024647475,"about_ca_topic_score_gemma":0.0016281464,"teacher_disagreement_score":0.9354461,"about_ca_system_score_codex":0.0002292271,"about_ca_system_score_gemma":0.0046716174,"threshold_uncertainty_score":0.8287249},"labels":[],"label_agreement":null},{"id":"W3102015017","doi":"10.3138/cjpe.61723","title":"Anticipating and Addressing Stakeholders’ Stereotypes of Evaluation","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Perception; Process (computing); Psychology; Focus (optics); Applied psychology; Knowledge management; Social psychology; Public relations; Computer science; Political science","score_opus":0.8194598612454987,"score_gpt":0.5817553033009218,"score_spread":0.2377045579445769,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3102015017","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9912761,0.0009585619,0.0016633159,0.0034825956,0.00028807123,0.0008615734,0.0000061900237,0.0000049241703,0.001458669],"genre_scores_gemma":[0.99582136,0.0000069455523,0.0037990683,0.00021384751,0.00012184085,0.000015586342,0.000006443446,0.0000073186993,0.0000075817175],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952951,0.00073061587,0.0010128025,0.00018090005,0.0025988796,0.0001817008],"domain_scores_gemma":[0.99427783,0.00024023325,0.0010761688,0.0001459437,0.0038474703,0.00041233253],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.015764358,0.0000977372,0.0002550548,0.00037221113,0.00014379494,0.00027916458,0.0001999865,0.000055773733,0.0015061442],"category_scores_gemma":[0.0055506895,0.00007835988,0.0000702759,0.0006264579,0.0000986505,0.0006800175,0.000013502483,0.00014955524,0.000009215393],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016615553,0.000013826747,0.037047863,0.000013681823,0.000022824495,0.0000017448846,0.004993834,0.0031406991,0.0002853249,0.000077829434,0.00052192225,0.95386386],"study_design_scores_gemma":[0.0017748896,0.00091749954,0.16140446,0.00015852704,0.0002596739,0.000021547177,0.00713078,0.82040095,0.0006078466,0.0031361787,0.0040228735,0.00016474577],"about_ca_topic_score_codex":0.0001763856,"about_ca_topic_score_gemma":0.00209044,"teacher_disagreement_score":0.9536991,"about_ca_system_score_codex":0.0001154148,"about_ca_system_score_gemma":0.0034779427,"threshold_uncertainty_score":0.99940664},"labels":[],"label_agreement":null},{"id":"W3103082364","doi":"10.3138/cjpe.69230","title":"The Use and Benefits of Evaluation Framework Modules at the Canadian Foundation for Healthcare Improvement: Engaged Capacity Building and Collaborative Program Evaluation Planning","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Toronto Public Health; Canadian Foundation for Healthcare Improvement","funders":"","keywords":"Foundation (evidence); Participatory evaluation; Citizen journalism; Health care; Process management; Computer science; Knowledge management; Program evaluation; Capacity building; Engineering management; Management science; Business; Engineering; Sociology; Political science; World Wide Web","score_opus":0.5503134362738925,"score_gpt":0.515309111644216,"score_spread":0.03500432462967651,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3103082364","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9678161,0.0028790396,0.0012219856,0.017584652,0.0004907303,0.00990196,0.00006343205,0.00000871249,0.000033402237],"genre_scores_gemma":[0.9888532,0.00005531249,0.009348217,0.00041698103,0.00019597888,0.0010461829,0.0000619748,0.000016343718,0.000005813844],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99214256,0.0028073683,0.0011822381,0.00038068378,0.0030803496,0.00040678892],"domain_scores_gemma":[0.982356,0.0023703766,0.0014307993,0.00029195956,0.012907173,0.0006436524],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04529775,0.00020359039,0.00029539163,0.0003389568,0.0030119496,0.0013480929,0.00029174917,0.00015551418,0.00009006776],"category_scores_gemma":[0.03141608,0.00013468767,0.000075816366,0.0010914024,0.00028506338,0.0009911429,0.00002724756,0.0004821217,0.0000016703282],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007137342,0.0000122515885,0.011973148,0.00002140684,0.00006252884,2.4240018e-7,0.009899853,0.019746631,0.00005535333,0.001096052,0.0002839925,0.95677716],"study_design_scores_gemma":[0.0018194274,0.0016995125,0.14034507,0.00019703427,0.00041685477,0.000012646784,0.0075124595,0.81800234,0.0003349686,0.013119352,0.016313853,0.00022647728],"about_ca_topic_score_codex":0.0095621245,"about_ca_topic_score_gemma":0.54916793,"teacher_disagreement_score":0.9565507,"about_ca_system_score_codex":0.0012247888,"about_ca_system_score_gemma":0.0075859954,"threshold_uncertainty_score":0.9996886},"labels":[],"label_agreement":null},{"id":"W3103472363","doi":"10.9745/ghsp-d-20-00126","title":"Lessons Learned From Implementing Prospective, Multicountry Mixed-Methods Evaluations for Gavi and the Global Fund","year":2020,"lang":"en","type":"article","venue":"Global Health Science and Practice","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Université Cheikh Anta Diop de Dakar; International Development Research Centre; Institute for Health Metrics and Evaluation; Innovation, Science and Economic Development Canada; University of Washington; Global Fund to Fight AIDS, Tuberculosis and Malaria; GAVI Alliance","keywords":"Process management; Psychological intervention; Program evaluation; Computer science; Identification (biology); Management science; Business; Knowledge management; Political science; Medicine; Engineering; Nursing; Public administration","score_opus":0.5138434656549402,"score_gpt":0.6895332523121247,"score_spread":0.1756897866571845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3103472363","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04946048,0.0027993433,0.13834576,0.78681135,0.001095431,0.002837137,0.0005349772,0.00007163041,0.01804386],"genre_scores_gemma":[0.8631292,0.0005131566,0.10789695,0.02811624,0.00019899686,0.00010116476,0.000008337456,0.0000045947895,0.00003138096],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9947432,0.0009974182,0.0006928203,0.00084012095,0.002173906,0.00055250566],"domain_scores_gemma":[0.991299,0.0057534077,0.00067316473,0.00036601312,0.0014858113,0.00042265345],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.046426177,0.00014916579,0.00029236256,0.000035545374,0.0023843837,0.0011533052,0.00055721786,0.00004273838,0.000091971764],"category_scores_gemma":[0.02802441,0.00009559941,0.000043739383,0.0017941771,0.0007477765,0.0017923028,0.00035349993,0.00015242642,0.00003258433],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00051587727,0.000042967407,0.016315872,0.000013728142,0.000017363825,3.2529186e-7,0.002374079,0.00006978023,0.000028260327,0.08461293,0.0035129066,0.89249593],"study_design_scores_gemma":[0.00443895,0.00039108781,0.2576575,0.000022508317,0.00010092692,0.000029464669,0.03200181,0.19213212,0.000026751462,0.13250266,0.38042706,0.00026918482],"about_ca_topic_score_codex":0.00073594524,"about_ca_topic_score_gemma":0.00042626917,"teacher_disagreement_score":0.89222676,"about_ca_system_score_codex":0.0002778743,"about_ca_system_score_gemma":0.0026250337,"threshold_uncertainty_score":0.9998836},"labels":[],"label_agreement":null},{"id":"W3103842672","doi":"10.3138/cjpe.68127","title":"Comparing and Contrasting a Program versus System Approach to Evaluation: The Example of a Cardiac Care System","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Scope (computer science); Perspective (graphical); Set (abstract data type); Systems theory; Management science; Computer science; Systems thinking; Risk analysis (engineering); Medicine; Artificial intelligence; Engineering; Programming language","score_opus":0.5917953680574175,"score_gpt":0.4872887842568676,"score_spread":0.10450658380054989,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3103842672","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97356254,0.0024872741,0.0016924606,0.0010664184,0.001252901,0.007667538,0.000019416138,0.000040985928,0.012210451],"genre_scores_gemma":[0.99457914,0.0000012915149,0.004719719,0.00003948381,0.00022140559,0.00041061998,0.000013963922,0.000011820786,0.0000025627974],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99373543,0.0012830779,0.001152212,0.00030762205,0.0032354833,0.00028618527],"domain_scores_gemma":[0.9926455,0.000419087,0.0008512164,0.00030889036,0.0051465444,0.0006287539],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016202027,0.00016330808,0.0004986289,0.00027894526,0.00033956757,0.00049654447,0.0004887957,0.00006659338,0.000029494186],"category_scores_gemma":[0.002375698,0.0001093098,0.00014725719,0.0010073942,0.00008817219,0.00031108342,0.000032516407,0.00019963314,0.00001013486],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010823102,0.000029904368,0.040696498,0.00016371868,0.00016865646,0.0000012028114,0.01986929,0.016226813,0.000027057305,0.001931404,0.00046486518,0.92031235],"study_design_scores_gemma":[0.0022163135,0.0012021216,0.078981206,0.0002205522,0.0006141992,0.000019689833,0.09186068,0.8151121,0.000046386507,0.000024727682,0.009508091,0.00019394209],"about_ca_topic_score_codex":0.0011575806,"about_ca_topic_score_gemma":0.0016035581,"teacher_disagreement_score":0.9201184,"about_ca_system_score_codex":0.00064672384,"about_ca_system_score_gemma":0.003296984,"threshold_uncertainty_score":0.5848708},"labels":[],"label_agreement":null},{"id":"W3104561082","doi":"10.22215/etd/2020-14203","title":"An Examination of the Desistance and Risk Paradigms in Correctional Service Canada Policies","year":2020,"lang":"en","type":"dissertation","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Thematic analysis; Constructivist grounded theory; Service (business); Criminology; Public administration; Sociology; Grounded theory; Psychology; Political science; Social science; Qualitative research; Business","score_opus":0.08230053768493555,"score_gpt":0.41856319189509983,"score_spread":0.33626265421016427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3104561082","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9793607,0.00006004415,0.000046456607,0.00044882658,0.0006793336,0.00018041606,0.00003318455,0.0000048282586,0.019186232],"genre_scores_gemma":[0.9963777,0.000070404196,0.00008467984,0.00035669567,0.000027005362,0.000021151915,0.0000667107,0.0000052741907,0.0029903522],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9975003,0.0003063099,0.00047796097,0.0002463468,0.0013835585,0.00008552729],"domain_scores_gemma":[0.9984519,0.00041305818,0.00045498434,0.00023369439,0.00040031993,0.000046079855],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001151547,0.000107651795,0.00018633486,0.00010303407,0.00011027512,0.00006856879,0.00034560944,0.00006741392,0.00037560542],"category_scores_gemma":[0.00037598575,0.00006868493,0.000022139744,0.00081335206,0.000017676848,0.00018850467,0.000013965175,0.00015869882,0.0000030935626],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022194434,0.00015239372,0.7651816,0.00015745591,0.000058566,0.0000013337046,0.033479586,0.008059955,0.00046355047,0.013977976,0.009340741,0.16890492],"study_design_scores_gemma":[0.00012142033,0.00001889742,0.96149594,0.000023265613,0.000010130553,4.7273497e-7,0.012628951,0.021760726,0.00050631264,0.00046991147,0.0028830902,0.000080865175],"about_ca_topic_score_codex":0.28643316,"about_ca_topic_score_gemma":0.99011946,"teacher_disagreement_score":0.7036863,"about_ca_system_score_codex":0.00009373418,"about_ca_system_score_gemma":0.0012465528,"threshold_uncertainty_score":0.7183185},"labels":[],"label_agreement":null},{"id":"W3105492687","doi":"10.3138/cjpe.69535","title":"Toward Learning from Change Pathways: Reviewing Theory of Change and Its Discontents","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Underpinning; Vagueness; Theory of change; Context (archaeology); Stakeholder; Process (computing); Stakeholder engagement; Epistemology; Management science; Knowledge management; Sociology; Computer science; Political science; Public relations; Economics; Engineering; Artificial intelligence","score_opus":0.918735116591738,"score_gpt":0.5122009043033375,"score_spread":0.4065342122884005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3105492687","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97238964,0.018003825,0.00045675572,0.006803091,0.00048648426,0.0014744519,0.000016269696,0.000008239178,0.00036121858],"genre_scores_gemma":[0.9982341,0.00026243457,0.00037701966,0.0006695898,0.00036322346,0.000062485946,0.0000119636225,0.000008143978,0.000011054998],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9967198,0.00085095933,0.00075575995,0.00018200437,0.0013165972,0.00017490466],"domain_scores_gemma":[0.99706817,0.00022081891,0.0008225329,0.00010439384,0.0013323546,0.00045174247],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008744089,0.00010391631,0.00030417967,0.00022715415,0.000107031025,0.0001526376,0.0002821319,0.000053033265,0.0010590168],"category_scores_gemma":[0.0043763984,0.000077629826,0.00009439585,0.00041896195,0.000042015996,0.0009068071,0.00002240047,0.00020059934,0.000025901212],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017488468,0.000009742632,0.023970192,0.000016942678,0.00002328758,0.0000041396956,0.017120501,0.000030458998,0.00010318835,0.00030707257,0.00006208722,0.9583349],"study_design_scores_gemma":[0.004172196,0.003367363,0.65621674,0.0015609455,0.00064144173,0.000034286437,0.032176528,0.223127,0.0007680103,0.019987805,0.057268564,0.0006791361],"about_ca_topic_score_codex":0.00025435392,"about_ca_topic_score_gemma":0.00076927635,"teacher_disagreement_score":0.9576558,"about_ca_system_score_codex":0.00008091484,"about_ca_system_score_gemma":0.00066466996,"threshold_uncertainty_score":0.99985415},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":["metaresearch"],"domain":"methods","study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W3107879023","doi":"10.3917/rffp.151.0063","title":"Le programme de péréquation canadien : principes, formule et application","year":2020,"lang":"fr","type":"article","venue":"Revue française de finances publiques.","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Humanities; Physics; Philosophy","score_opus":0.10334406942862455,"score_gpt":0.40151516021447764,"score_spread":0.2981710907858531,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3107879023","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.082172275,0.009820702,0.27740866,0.5630236,0.0012013727,0.0025722312,0.00017258081,0.00031384398,0.06331471],"genre_scores_gemma":[0.95211387,0.0019763191,0.019936841,0.011109425,0.0010279859,0.00083958765,0.00015513366,0.00005724412,0.012783608],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9955014,0.0004973338,0.0010827926,0.0008701158,0.00094106264,0.0011072881],"domain_scores_gemma":[0.99668115,0.00033483212,0.0007243516,0.0006552674,0.0009161605,0.0006882085],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.005608796,0.00034189087,0.0005057346,0.00020380387,0.0004180941,0.0007001157,0.0009786673,0.00035956252,0.00047358146],"category_scores_gemma":[0.0024126086,0.0003639362,0.00021210407,0.0016802797,0.00017083091,0.0023415803,0.00014156858,0.00045193438,0.0004250552],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000758286,0.00025471207,0.01724779,0.0003159652,0.000031288488,0.0000181136,0.0095978035,0.0048228838,0.0001430045,0.42990944,0.020340974,0.5172422],"study_design_scores_gemma":[0.0006151861,0.0002570311,0.020429024,0.00011628865,0.000022175185,0.000024906103,0.00036241763,0.21124367,0.0003701803,0.011287522,0.7549355,0.00033609095],"about_ca_topic_score_codex":0.0041022734,"about_ca_topic_score_gemma":0.008459229,"teacher_disagreement_score":0.8699416,"about_ca_system_score_codex":0.0006381541,"about_ca_system_score_gemma":0.008335587,"threshold_uncertainty_score":0.99988127},"labels":[],"label_agreement":null},{"id":"W3109000035","doi":"10.3386/w25460","title":"Addressing Cross-National Generalizability in Educational Impact Evaluation","year":2019,"lang":"en","type":"preprint","venue":"National Bureau of Economic Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Generalizability theory; Variety (cybernetics); Cross country; External validity; Quarter (Canadian coin); Political science; Cross-cultural; Econometrics; Psychology; Regional science; Computer science; Economics; Geography; Demographic economics; Artificial intelligence; Social psychology","score_opus":0.8923654787697515,"score_gpt":0.7649700817209754,"score_spread":0.12739539704877612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3109000035","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7562391,0.0004168865,0.000056153993,0.0057260096,0.001402573,0.0018373501,0.00036244767,0.0000093168455,0.23395014],"genre_scores_gemma":[0.99508476,0.00004624608,0.00052898255,0.00007798984,0.00064959144,0.00032674792,0.0012079176,0.000019516227,0.0020582627],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9825823,0.0021162196,0.002189011,0.001246367,0.011398372,0.00046775362],"domain_scores_gemma":[0.97976017,0.006020819,0.0008906073,0.0007489418,0.012444554,0.00013488249],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.08301709,0.0002667002,0.0005671273,0.0025574837,0.00017934077,0.0006906352,0.0015067877,0.0004315306,0.017728062],"category_scores_gemma":[0.013996593,0.00023746376,0.00032543056,0.0006596534,0.00035959337,0.000828013,0.00074195734,0.0010253519,0.0011175001],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000082471044,0.00018899339,0.21410333,0.00003330895,0.000042553744,7.993774e-8,0.00016652924,0.7007563,0.000070292226,0.06618258,0.016632654,0.0017408882],"study_design_scores_gemma":[0.00047890906,0.000024014213,0.2664239,0.00003625747,0.0000023779867,9.930576e-7,0.00002886823,0.26536492,0.000043870827,0.46723384,0.00024793192,0.00011409174],"about_ca_topic_score_codex":0.0007338489,"about_ca_topic_score_gemma":0.00034821147,"teacher_disagreement_score":0.4353914,"about_ca_system_score_codex":0.0067459764,"about_ca_system_score_gemma":0.029651264,"threshold_uncertainty_score":0.99966025},"labels":[],"label_agreement":null},{"id":"W3109011900","doi":"10.1177/1356389020969721","title":"How to normalize reflexive evaluation? Navigating between legitimacy and integrity","year":2020,"lang":"en","type":"article","venue":"Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athena Sustainable Materials Institute","funders":"","keywords":"Reflexivity; Normalization (sociology); Legitimacy; Epistemology; Process management; Political science; Sociology; Computer science; Knowledge management; Business; Social science; Politics","score_opus":0.4709169939777773,"score_gpt":0.5835940233142233,"score_spread":0.11267702933644597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3109011900","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87594014,0.00012315765,0.01538944,0.09956587,0.00027194584,0.0017560774,0.000024250947,0.000062961015,0.0068661342],"genre_scores_gemma":[0.9910709,0.00000512286,0.0054757413,0.00252878,0.000520779,0.00016720436,0.00007833718,0.0000127523235,0.00014035469],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99123955,0.0013454193,0.0007007883,0.0007060523,0.005751748,0.00025646584],"domain_scores_gemma":[0.9953752,0.00083984074,0.0003654601,0.00039804343,0.0026971472,0.0003242723],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.021389624,0.0001893298,0.00030038232,0.0001226058,0.0003133693,0.0008232196,0.0003897599,0.00008834487,0.0018289536],"category_scores_gemma":[0.015351594,0.00015441205,0.0000683358,0.0010590411,0.000055660596,0.0013333109,0.00017090337,0.00035467767,0.00048671014],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035866626,0.000017364478,0.0557517,0.000008186939,0.000024232175,3.7058626e-7,0.007895164,0.0016599097,0.00082665664,0.0006424487,0.0048118946,0.9283262],"study_design_scores_gemma":[0.0019677796,0.0004507978,0.29791245,0.00006506221,0.00018860192,0.000002531093,0.0058112303,0.6530857,0.0019115765,0.019898057,0.01827625,0.0004299731],"about_ca_topic_score_codex":0.000023655692,"about_ca_topic_score_gemma":0.000034373235,"teacher_disagreement_score":0.92789626,"about_ca_system_score_codex":0.00018705009,"about_ca_system_score_gemma":0.00052497035,"threshold_uncertainty_score":0.9990835},"labels":[],"label_agreement":null},{"id":"W310937889","doi":"10.3138/cjpe.0014.008","title":"Building Capacity for School Improvement through Evaluation: Experiences of the Manitoba School Improvement Program Inc.","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Empowerment; Context (archaeology); Capacity building; Perspective (graphical); Program evaluation; Sociology; Pedagogy; Medical education; Political science; Medicine; Public administration; Computer science; Geography","score_opus":0.28399040238513046,"score_gpt":0.49536869734142874,"score_spread":0.21137829495629828,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W310937889","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9859704,0.0004154865,0.00092825486,0.0014612571,0.0015956064,0.008289523,0.000019519988,0.000015620444,0.0013043372],"genre_scores_gemma":[0.9683853,0.000014383563,0.0278922,0.000407945,0.00043867808,0.0027056711,0.0000111647505,0.000018012817,0.00012667438],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9913845,0.0006382205,0.0020010653,0.00043036873,0.005011192,0.00053467514],"domain_scores_gemma":[0.9908492,0.00021446917,0.0015456002,0.0006777025,0.0061623575,0.000550681],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.020459356,0.00026205578,0.00040580065,0.00034204967,0.00063757825,0.0006353807,0.0011850046,0.00013459493,0.009022727],"category_scores_gemma":[0.0036907396,0.0001744118,0.00032547401,0.0010480263,0.00026667974,0.0013138187,0.00003199249,0.00031553442,0.000034315995],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039081384,0.00014180942,0.0024906327,0.00001383314,0.000061144245,3.2681857e-7,0.003229478,0.0016927881,0.00041104498,0.00017420613,0.0023313903,0.9894143],"study_design_scores_gemma":[0.013594025,0.013666087,0.11362757,0.0007060917,0.0014584586,0.00007802564,0.07137163,0.30638275,0.023023315,0.08422739,0.37036663,0.0014980285],"about_ca_topic_score_codex":0.0010672663,"about_ca_topic_score_gemma":0.008927734,"teacher_disagreement_score":0.98791623,"about_ca_system_score_codex":0.0013338315,"about_ca_system_score_gemma":0.008725105,"threshold_uncertainty_score":0.9968945},"labels":[],"label_agreement":null},{"id":"W3110959118","doi":"10.1093/jeea/jvaa019","title":"How Much Can We Generalize From Impact Evaluations?","year":2020,"lang":"en","type":"article","venue":"Journal of the European Economic Association","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":232,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Exploit; Set (abstract data type); Sample (material); Government (linguistics); Sample size determination; Econometrics; Computer science; Treatment effect; Economics; Statistics; Mathematics; Computer security","score_opus":0.18303211893111443,"score_gpt":0.4270938186999413,"score_spread":0.24406169976882686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3110959118","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8437785,0.00009874553,0.000679066,0.14961176,0.0012499114,0.00010024514,0.000056498287,0.000007750177,0.0044175466],"genre_scores_gemma":[0.9944611,0.00007317227,0.00028838625,0.0014631306,0.00156545,4.4685012e-7,0.000003498725,0.000012583332,0.0021321909],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9962759,0.0016963993,0.0007943034,0.00015611865,0.00094177685,0.0001354861],"domain_scores_gemma":[0.99613374,0.0005010912,0.0026303595,0.00023934364,0.00037068906,0.000124764],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0073204213,0.00010398999,0.00024468257,0.000075746575,0.00015312238,0.0005864402,0.0007784068,0.000032126874,0.00084227364],"category_scores_gemma":[0.0028024055,0.000062289255,0.00032637388,0.00016643257,0.0000135555865,0.0006021761,0.000091732334,0.00021916378,0.00041351057],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058049525,0.00004741075,0.47460762,0.0000016613349,0.00039652552,0.0000027740773,0.0064703617,0.03717791,0.0031452165,0.00015112896,0.3823286,0.09561273],"study_design_scores_gemma":[0.0016400773,0.00015719513,0.86631036,0.000019372892,0.00011614547,0.0000051239904,0.0015181123,0.03936847,0.00076573127,0.00882196,0.08107654,0.00020089457],"about_ca_topic_score_codex":0.000015550751,"about_ca_topic_score_gemma":0.000041789957,"teacher_disagreement_score":0.39170274,"about_ca_system_score_codex":0.0009323934,"about_ca_system_score_gemma":0.00039075018,"threshold_uncertainty_score":0.9222306},"labels":[],"label_agreement":null},{"id":"W3110971321","doi":"10.1016/j.tree.2020.11.001","title":"Evaluating Impact Using Time-Series Data","year":2020,"lang":"en","type":"review","venue":"Trends in Ecology & Evolution","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":171,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Cambridge Trust; European Commission; Leverhulme Trust; Natural Environment Research Council; Cambridge Philosophical Society; Arcadia Fund; Bird Studies Canada; Villum Fonden","keywords":"Series (stratigraphy); Time series; Computer science; Statistics; Mathematics; Geology","score_opus":0.6901198173060419,"score_gpt":0.6637457293661183,"score_spread":0.026374087939923574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3110971321","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00045148152,0.9948406,0.00027295452,0.00024147253,0.0010420585,0.00044209388,0.00026434983,0.00006169127,0.0023832547],"genre_scores_gemma":[0.0009094991,0.9885375,0.005368002,0.00005180127,0.00057012745,0.00005186789,0.0015859029,0.000056952937,0.0028683443],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9932717,0.00202337,0.0018264889,0.0011433939,0.0012622325,0.00047281673],"domain_scores_gemma":[0.9958365,0.0011094986,0.0012249885,0.0015289173,0.00018498566,0.00011513912],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008976687,0.00041493497,0.0018193115,0.0013579156,0.00018911327,0.0001414946,0.0017989124,0.000431807,0.008711573],"category_scores_gemma":[0.002709501,0.00030290714,0.00031745434,0.0028187025,0.00013545474,0.0010374689,0.00083141885,0.0005828172,0.0023771143],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011818641,0.00003724811,0.0015034344,0.000078735,0.000050802068,0.000004656102,0.00005612045,0.00079279667,8.0867346e-7,0.00004499443,0.0035718028,0.9938468],"study_design_scores_gemma":[0.00037973237,0.00036109218,0.009845714,0.00063304685,0.0004698985,0.000094202194,0.000060216196,0.25039095,7.274658e-8,0.0008726754,0.7364437,0.00044870487],"about_ca_topic_score_codex":0.000042213826,"about_ca_topic_score_gemma":0.0003939004,"teacher_disagreement_score":0.9933981,"about_ca_system_score_codex":0.0013481007,"about_ca_system_score_gemma":0.002148521,"threshold_uncertainty_score":0.9999423},"labels":[],"label_agreement":null},{"id":"W3110995281","doi":"10.14428/qpes.v1i4.62393","title":"Mesure et évaluation de la qualité des pratiques de développement des compétences informationnelles au sein du réseau de l'Université du Québec","year":2021,"lang":"fr","type":"article","venue":"Les Annales de QPES","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université du Québec; Université du Québec à Rimouski","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.13811547993019668,"score_gpt":0.4498436650498429,"score_spread":0.31172818511964623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3110995281","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85241556,0.005722666,0.09090412,0.04709364,0.00012836597,0.00018094086,0.0000337306,0.00006576208,0.003455241],"genre_scores_gemma":[0.91773665,0.012989906,0.06571639,0.0020691096,0.00019837699,0.00003014103,0.000052061543,0.00001873625,0.0011886375],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9928684,0.0041053244,0.00084088056,0.0003685603,0.001142542,0.0006742426],"domain_scores_gemma":[0.99534625,0.0025431288,0.00044754698,0.00031885217,0.0010550601,0.00028917438],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.013713599,0.00032442584,0.00036200372,0.0002310875,0.0011676442,0.0009202049,0.00055971806,0.00026330398,0.0025938817],"category_scores_gemma":[0.0023707186,0.0003012088,0.00021455801,0.0006278122,0.0007724218,0.0013921794,0.0002063388,0.0003151812,0.00013435626],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005844538,0.00020039036,0.56251615,0.00016689283,0.00010508128,0.00003053607,0.22765991,0.021194644,0.00048183522,0.0096383225,0.00819351,0.16975428],"study_design_scores_gemma":[0.0005900387,0.00017505269,0.7332697,0.00041512994,0.00009854989,0.00015601299,0.09834902,0.07541214,0.0036511,0.02778081,0.059752215,0.00035023468],"about_ca_topic_score_codex":0.026365925,"about_ca_topic_score_gemma":0.199052,"teacher_disagreement_score":0.17268609,"about_ca_system_score_codex":0.0018380218,"about_ca_system_score_gemma":0.014690565,"threshold_uncertainty_score":0.99994403},"labels":[],"label_agreement":null},{"id":"W3111116449","doi":"10.47678/cjhe.vi0.188799","title":"L’influence perçue des instruments d’action publique fédéraux et provinciaux sur la production de recherche universitaire au Canada","year":2020,"lang":"fr","type":"article","venue":"Canadian Journal of Higher Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Toronto; Université de Montréal","funders":"","keywords":"Humanities; Psychology; Art","score_opus":0.2777329783157342,"score_gpt":0.45583621400987656,"score_spread":0.17810323569414238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3111116449","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82896054,0.0011310459,0.00007026052,0.16097419,0.0035158934,0.00017852223,0.000015859046,0.000004676134,0.0051490352],"genre_scores_gemma":[0.9685478,0.00020462765,0.0010331927,0.005226728,0.0007362483,0.0000045079996,0.000009410002,0.000015768734,0.02422169],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.996423,0.0015794161,0.00059609406,0.00027001585,0.00073692045,0.0003945387],"domain_scores_gemma":[0.9955805,0.00027631002,0.0006266499,0.00019723242,0.0021146974,0.0012046366],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0036651269,0.00017731481,0.0002084341,0.000303633,0.00036822798,0.00030241258,0.00046572956,0.00022100571,0.000917199],"category_scores_gemma":[0.0026802474,0.00017840516,0.000072214054,0.0010408568,0.00016750667,0.0030653272,0.000016004495,0.0007866556,0.000023322005],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000053640517,0.00010448003,0.5408724,0.00013219153,0.0000714819,0.000025966352,0.012008409,0.008883142,0.0002412784,0.003943565,0.21890192,0.21476156],"study_design_scores_gemma":[0.00020813476,0.00014946682,0.40071917,0.0002058934,0.000050557603,0.00012650651,0.005761457,0.00015779094,0.00022780224,0.0021204033,0.5901096,0.00016323451],"about_ca_topic_score_codex":0.7917611,"about_ca_topic_score_gemma":0.9527641,"teacher_disagreement_score":0.37120768,"about_ca_system_score_codex":0.012333497,"about_ca_system_score_gemma":0.32064897,"threshold_uncertainty_score":0.9999961},"labels":[],"label_agreement":null},{"id":"W3112518056","doi":"10.1163/15718069-bja10031","title":"Best Practices in the Measurement and Evaluation of Track Two Dialogues: Towards a “Reflective Practice Model”","year":2020,"lang":"en","type":"article","venue":"International Negotiation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Snapshot (computer storage); Computer science; Measure (data warehouse); Best practice; Field (mathematics); Negotiation; Political science; Data mining; Law; Mathematics","score_opus":0.7031697532543458,"score_gpt":0.5923994374193863,"score_spread":0.11077031583495955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3112518056","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73166764,0.00030890424,0.017659077,0.119378015,0.0006135904,0.0013675063,0.000029988256,0.00002093343,0.12895437],"genre_scores_gemma":[0.99605983,0.00005535167,0.0015552305,0.0021015424,0.00013545582,0.000059355654,0.000013909642,0.00000433403,0.000014990134],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99239886,0.00081672147,0.0006290571,0.00031551567,0.005749764,0.00009007915],"domain_scores_gemma":[0.994592,0.0008765567,0.0010578985,0.00016188978,0.003274734,0.000036884274],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0148853315,0.00009243181,0.00012716626,0.0001567709,0.000058690443,0.00019193608,0.00039255663,0.000036578756,0.00015181764],"category_scores_gemma":[0.021179559,0.000063781714,0.000040334373,0.0004350581,0.000036865345,0.0016779312,0.00004599543,0.00014404609,0.000042163992],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009938993,0.0009840453,0.013482739,0.000019691359,0.0001849372,0.0000025624718,0.11111404,0.44519082,0.00473414,0.02380865,0.0022392105,0.39724526],"study_design_scores_gemma":[0.0011068742,0.00012520446,0.017635405,0.000016527769,0.00006574772,0.0000032355042,0.007112138,0.956804,0.00042394147,0.014258381,0.0023720793,0.00007645807],"about_ca_topic_score_codex":0.00019016021,"about_ca_topic_score_gemma":0.0005098746,"teacher_disagreement_score":0.5116132,"about_ca_system_score_codex":0.0001686724,"about_ca_system_score_gemma":0.00045851356,"threshold_uncertainty_score":0.98706543},"labels":[],"label_agreement":null},{"id":"W3112866667","doi":"10.20381/ruor-25133","title":"The use of the PARIHS framework in implementation research and practice—a citation analysis of the literature","year":2020,"lang":"en","type":"article","venue":"QUT ePrints (Queensland University of Technology)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; Uppsala Universitet; Forskningsrådet om Hälsa, Arbetsliv och Välfärd","keywords":"Computer science; Data science; Medicine","score_opus":0.28955436282790553,"score_gpt":0.48427857075124314,"score_spread":0.1947242079233376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3112866667","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9547596,0.000036481648,0.0004356476,0.044306092,0.000024959409,0.00020394292,0.000017764312,0.000004229543,0.00021131002],"genre_scores_gemma":[0.99835324,0.00018249523,0.0013127764,0.00006611374,0.0000024216743,4.0442052e-7,0.0000014639145,0.0000012219533,0.00007983411],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99839175,0.0004128198,0.0002449103,0.00016986698,0.00069176144,0.00008890746],"domain_scores_gemma":[0.9968739,0.0016540762,0.00035014068,0.00043186868,0.00067363447,0.000016361562],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021197635,0.00004470504,0.00013879487,0.00036994225,0.00019909196,0.00003340386,0.000571568,0.0000996561,0.00006835855],"category_scores_gemma":[0.003271452,0.000024270315,0.000058016638,0.0047009974,0.00041403619,0.00020931724,0.00033619071,0.00029898557,0.0000016858697],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012768686,0.00003687333,0.94508636,0.0000071244963,0.00012065308,7.6399687e-7,0.007000394,0.000384414,0.00046364169,0.02399137,0.00064453494,0.022136161],"study_design_scores_gemma":[0.00024345134,0.00005317117,0.95002997,0.00003184115,0.00006642698,3.8393569e-7,0.023806531,0.0018917853,0.00072857965,0.010610205,0.012505182,0.00003248941],"about_ca_topic_score_codex":0.00014408067,"about_ca_topic_score_gemma":0.0008752978,"teacher_disagreement_score":0.04423998,"about_ca_system_score_codex":0.000023333374,"about_ca_system_score_gemma":0.000083886174,"threshold_uncertainty_score":0.39164698},"labels":[],"label_agreement":null},{"id":"W3115113532","doi":"10.18162/fp.2020.559","title":"Évaluation des enseignants permanents du secondaire au Québec : quelle démarche préconiser selon des enseignants et des directeurs d’école ?","year":2020,"lang":"fr","type":"article","venue":"Formation et profession","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Political science; Humanities; Philosophy","score_opus":0.2530906363410558,"score_gpt":0.4203834868275277,"score_spread":0.1672928504864719,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3115113532","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9533247,0.0014248264,0.01822286,0.015038636,0.0014219148,0.0014744198,0.000094594434,0.00018149982,0.0088166],"genre_scores_gemma":[0.9693501,0.0014862997,0.003775678,0.004163845,0.00022120583,0.00018085128,0.00031176148,0.00006202952,0.020448228],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9901076,0.00405735,0.001763303,0.0007734046,0.0024028474,0.00089548744],"domain_scores_gemma":[0.9953171,0.001024408,0.0009982723,0.0005086604,0.0015994023,0.000552136],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008336642,0.00057722774,0.0006026208,0.00034675375,0.0028348751,0.0005310258,0.0006717043,0.00039636358,0.004483476],"category_scores_gemma":[0.0029236749,0.00047509515,0.00024979425,0.0012252328,0.000589776,0.0073816865,0.00041718633,0.0006869407,0.0025543894],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022489959,0.0003196179,0.050182674,0.00059754966,0.00003738322,0.000006410238,0.41778556,0.0033272835,0.0017700826,0.00025578693,0.0033808362,0.52211195],"study_design_scores_gemma":[0.0037789328,0.0009977452,0.35196513,0.0030856798,0.0001581679,0.000053394673,0.10201586,0.45982686,0.01148414,0.007024088,0.058472045,0.0011379496],"about_ca_topic_score_codex":0.0031555048,"about_ca_topic_score_gemma":0.020459656,"teacher_disagreement_score":0.520974,"about_ca_system_score_codex":0.0012179961,"about_ca_system_score_gemma":0.0043356493,"threshold_uncertainty_score":0.99977005},"labels":[],"label_agreement":null},{"id":"W3116677346","doi":"10.29379/jedem.v12i2.598","title":"Improving Monitoring and Evaluation in the Civic Tech Ecosystem","year":2020,"lang":"en","type":"article","venue":"JeDEM - eJournal of eDemocracy and Open Government","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Western University","funders":"","keywords":"Sophistication; Sustainability; Monitoring and evaluation; Resource (disambiguation); Knowledge management; Business; Computer science; Political science; Sociology","score_opus":0.19997569517397656,"score_gpt":0.4570129682412581,"score_spread":0.2570372730672815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3116677346","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97547936,0.00037459604,0.0002925747,0.015215677,0.00020282128,0.00073935045,0.0000074636614,0.0000023457396,0.007685828],"genre_scores_gemma":[0.9985519,0.00015422759,0.00044239435,0.0006315652,0.00011385884,0.000019362536,3.716638e-7,0.0000047400017,0.00008156569],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99552315,0.00038871617,0.0007527612,0.0002772333,0.002914427,0.00014370863],"domain_scores_gemma":[0.99836445,0.00066301244,0.00056624075,0.0001993388,0.00012291143,0.00008402044],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011036989,0.00010907789,0.00026480344,0.00003685758,0.00016809792,0.00056682876,0.00062425336,0.00003871249,0.00022156435],"category_scores_gemma":[0.00059938023,0.000065353146,0.00003753619,0.0002758275,0.000018549172,0.00089257135,0.00030879423,0.00018840979,0.000012439044],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022231122,0.00010693574,0.3404376,0.00005521388,0.0000351289,0.0000071867116,0.0063878517,0.0012985811,0.004442611,0.00056931225,0.0013240874,0.64511317],"study_design_scores_gemma":[0.003850775,0.0007986282,0.63970035,0.0003089861,0.00009769869,0.000051651215,0.056990173,0.26978505,0.0034273805,0.0033639197,0.021270888,0.0003544962],"about_ca_topic_score_codex":0.000020309111,"about_ca_topic_score_gemma":0.000029125476,"teacher_disagreement_score":0.6447587,"about_ca_system_score_codex":0.00010482439,"about_ca_system_score_gemma":0.00012749141,"threshold_uncertainty_score":0.54659426},"labels":[],"label_agreement":null},{"id":"W3118341547","doi":"10.1007/s11077-020-09413-z","title":"Public policy schools in the global south: a mapping and analysis of the emerging landscape","year":2021,"lang":"en","type":"article","venue":"Policy Sciences","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Internationalization; Public policy; Corporate governance; Public administration; Political science; Sample (material); Policy analysis; Education policy; Policy studies; Economic growth; Higher education; Economics; Management","score_opus":0.32408646987922995,"score_gpt":0.5117668025573616,"score_spread":0.18768033267813167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3118341547","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8875763,0.00018931222,0.00015261436,0.088755146,0.00006496097,0.00007378559,0.000019514368,0.0000050741464,0.023163332],"genre_scores_gemma":[0.9970958,0.000028846105,0.00020183931,0.0024629007,0.00007401306,0.000005773407,9.096109e-7,0.0000010021264,0.00012887259],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99672365,0.0005063732,0.00044043778,0.0003092958,0.0017436729,0.0002765759],"domain_scores_gemma":[0.9986322,0.00044818126,0.00023083715,0.0004274825,0.00020295125,0.000058327147],"candidate_categories":["bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.006634943,0.000081090184,0.00019958512,0.0008226124,0.00040580632,0.00064655195,0.0010621145,0.000027460681,0.00016815054],"category_scores_gemma":[0.0055179726,0.00003843972,0.000115481234,0.023232523,0.0002827905,0.00039982467,0.00024542966,0.00009362116,0.000011015283],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.5807516e-7,0.00001188023,0.94476545,0.0000010813732,0.000016815125,2.878664e-7,0.002988239,0.00057668594,0.000022465467,0.043707944,0.000107778156,0.0078008366],"study_design_scores_gemma":[0.00010086161,0.000008660324,0.94219524,0.0000072941557,0.000016813678,0.0000037503821,0.015215818,0.022001872,0.00001557024,0.018532785,0.0018468533,0.00005449059],"about_ca_topic_score_codex":0.000690757,"about_ca_topic_score_gemma":0.00180207,"teacher_disagreement_score":0.10951958,"about_ca_system_score_codex":0.000039298815,"about_ca_system_score_gemma":0.0015324327,"threshold_uncertainty_score":0.99752915},"labels":[],"label_agreement":null},{"id":"W3121316204","doi":"10.2139/ssrn.2819390","title":"Viewpoint: Estimating the Causal Effects of Policies and Programs","year":2016,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; McMaster University Medical Centre","funders":"","keywords":"Credibility; Interpretation (philosophy); Causal inference; Identification (biology); Context (archaeology); Positive economics; Internal validity; Inference; Estimation; Economics; Epistemology; Econometrics; Computer science","score_opus":0.05473092629401031,"score_gpt":0.42318548486359686,"score_spread":0.36845455856958653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3121316204","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9428694,0.0016466888,0.03653118,0.017854275,0.00029660226,0.000207721,4.3395215e-7,0.000011305104,0.0005823587],"genre_scores_gemma":[0.99767536,0.0006703161,0.0003503198,0.00016115316,0.00018523527,0.0000064754795,9.9312174e-8,0.0000053244007,0.00094573107],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976534,0.00022422736,0.0003988734,0.00012338937,0.0008505954,0.000749517],"domain_scores_gemma":[0.9984393,0.0008168987,0.00032056487,0.00018493821,0.00018934192,0.0000489255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007905659,0.00008310674,0.00015114206,0.00008813772,0.00021910373,0.00010155246,0.0003297344,0.000027356917,0.000039502498],"category_scores_gemma":[0.0010032293,0.000032394448,0.00005913898,0.00023043151,0.00012854132,0.0002560556,0.000055436947,0.00033577209,0.000026827507],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009845356,0.000015595846,0.00916735,0.0000040696586,0.000028738505,3.0255686e-7,0.00052029814,0.0000109942075,0.0009548715,0.08414584,0.00005997353,0.9050821],"study_design_scores_gemma":[0.0010565616,0.00092946074,0.02198952,0.00014211374,0.000035778423,0.00033262445,0.0017514264,0.002038768,0.0011289333,0.9668922,0.0035635512,0.0001390717],"about_ca_topic_score_codex":0.000019673234,"about_ca_topic_score_gemma":0.00022695278,"teacher_disagreement_score":0.90494305,"about_ca_system_score_codex":0.000117705524,"about_ca_system_score_gemma":0.0008526384,"threshold_uncertainty_score":0.27399597},"labels":[],"label_agreement":null},{"id":"W3121783325","doi":"","title":"Policy Analysis and Policy Work in Federal Systems: Policy Advice and Its Contribution to Evidence-Based Policy Making in Multi-Level Governance Systems","year":2010,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Work (physics); Corporate governance; Policy analysis; Political science; Public administration; Order (exchange); Policy studies; Scale (ratio); Public policy; Public economics; Business; Public relations; Economics; Finance; Geography","score_opus":0.09698557393801663,"score_gpt":0.45810527080031577,"score_spread":0.36111969686229917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3121783325","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95554733,0.0054423152,0.008732011,0.029024681,0.000243456,0.00078346534,0.000035745048,0.000030793,0.00016017255],"genre_scores_gemma":[0.9947951,0.0021360847,0.00013359413,0.00078427116,0.0010755917,0.000051306833,0.000002810103,0.000019818983,0.0010014118],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99339074,0.0007885485,0.0013836798,0.00062137627,0.0015837739,0.0022318934],"domain_scores_gemma":[0.9970396,0.0007495418,0.00083649915,0.00040887864,0.000642241,0.00032322772],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.013093268,0.00033388953,0.0007216085,0.0039226157,0.00039249068,0.0010521876,0.000640826,0.00021052046,0.000012966741],"category_scores_gemma":[0.008992457,0.0002747808,0.00012913696,0.008826329,0.00006463327,0.0011211141,0.00013173031,0.001644282,0.000029758467],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006330077,0.00017674963,0.5413013,0.000049463655,0.0002534726,0.000013049985,0.001574817,0.03427439,0.0015452317,0.35459182,0.00004917962,0.065537505],"study_design_scores_gemma":[0.0031559784,0.0002814252,0.87237424,0.0006045155,0.000050772556,0.00019622628,0.0012436477,0.114049174,0.000036653182,0.006269446,0.001188037,0.0005498787],"about_ca_topic_score_codex":0.01343847,"about_ca_topic_score_gemma":0.050543785,"teacher_disagreement_score":0.3483224,"about_ca_system_score_codex":0.003265662,"about_ca_system_score_gemma":0.012715023,"threshold_uncertainty_score":0.9999848},"labels":[],"label_agreement":null},{"id":"W3121828879","doi":"","title":"Evaluation par les nouveaux immigrants de leur vie au Canada","year":2010,"lang":"fr","type":"article","venue":"Direction des etudes analytiques : documents de recherche","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Humanities; Political science; Art","score_opus":0.3125568166052898,"score_gpt":0.5266722308909082,"score_spread":0.21411541428561842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3121828879","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90343785,0.0026382618,0.0040002256,0.0055854935,0.00328002,0.0007756214,0.000043531167,0.00011374678,0.080125235],"genre_scores_gemma":[0.9473665,0.0044649052,0.01067519,0.0009859572,0.0006659122,0.00017196781,0.000033848803,0.000056611847,0.03557913],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9858067,0.007344062,0.0012927981,0.00093184394,0.003508855,0.0011157456],"domain_scores_gemma":[0.993608,0.0018336809,0.00065547257,0.00082670426,0.0024904362,0.00058571016],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05130689,0.0005294264,0.00056988816,0.00041628076,0.00095770834,0.00076011784,0.0008653728,0.0009275606,0.013016668],"category_scores_gemma":[0.009116641,0.0004980259,0.00030708974,0.0016170884,0.00036475863,0.0013838762,0.00014340122,0.0019174344,0.00016911066],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000044370496,0.0002769757,0.19626743,0.00006112713,0.0003229099,0.000009273405,0.002587394,0.0020509686,0.0027537385,0.00075089466,0.0077559687,0.787119],"study_design_scores_gemma":[0.0013886037,0.00027147686,0.32467958,0.0003826543,0.00092098524,0.0001073664,0.0038396711,0.16649777,0.011610469,0.02468412,0.46456462,0.0010526507],"about_ca_topic_score_codex":0.84613085,"about_ca_topic_score_gemma":0.9813118,"teacher_disagreement_score":0.7860663,"about_ca_system_score_codex":0.011219868,"about_ca_system_score_gemma":0.018288262,"threshold_uncertainty_score":0.99974716},"labels":[],"label_agreement":null},{"id":"W3122379543","doi":"10.1596/1813-9450-7243","title":"Program Evaluation and Spillover Effects","year":2015,"lang":"en","type":"book","venue":"World Bank, Washington, DC eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact","funders":"","keywords":"Spillover effect; Measure (data warehouse); Affect (linguistics); Field (mathematics); Computer science; Risk analysis (engineering); Econometrics; Management science; Economics; Psychology; Business; Microeconomics; Mathematics; Data mining","score_opus":0.14415819707347233,"score_gpt":0.45550159841048077,"score_spread":0.31134340133700844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3122379543","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035995753,0.0009725091,0.000039299048,0.00038627832,0.0020053242,0.0042865593,0.00001931838,0.00021695011,0.9884742],"genre_scores_gemma":[0.014662333,0.00001853956,0.0013170148,0.0008163717,0.00087478536,0.0005857388,0.00013313653,0.000090894675,0.98150116],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98906004,0.0007051677,0.0013220098,0.0013068554,0.0070281643,0.0005777312],"domain_scores_gemma":[0.9939691,0.0013097406,0.0010358972,0.0013736443,0.0019107561,0.000400905],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0153369205,0.00066966866,0.00092825695,0.0010883713,0.00031914722,0.0011825039,0.0009896888,0.0003932036,0.0014647606],"category_scores_gemma":[0.0014559272,0.0005170837,0.00024794936,0.00029948147,0.00029973965,0.00043584246,0.00041125197,0.00083726225,0.0012698111],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037331854,0.000045366975,0.00037375366,0.000066582914,0.00006492418,0.0000070120122,0.00068405306,0.000026496686,0.000017507176,0.0070563084,0.30125982,0.69036084],"study_design_scores_gemma":[0.0012254369,0.00023990957,0.001896615,0.00032134415,0.00022197106,0.0000080527225,0.000034967547,0.0034696024,0.00009150198,0.09035165,0.90153784,0.00060114096],"about_ca_topic_score_codex":0.00001618548,"about_ca_topic_score_gemma":0.00071905355,"teacher_disagreement_score":0.68975973,"about_ca_system_score_codex":0.00070059585,"about_ca_system_score_gemma":0.0027437306,"threshold_uncertainty_score":0.9998544},"labels":[],"label_agreement":null},{"id":"W3122679125","doi":"","title":"Scientific Advice to Public Policy-Making","year":2004,"lang":"en","type":"preprint","venue":"Econstor (Econstor)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Universitat Autònoma de Barcelona; Università di Cagliari; Abdus Salam International Centre for Theoretical Physics; University College London","keywords":"Advice (programming); Context (archaeology); Set (abstract data type); Process (computing); Political science; Public policy; Science policy; Public relations; Policy making; Commission; European commission; Discipline; Management science; Public administration; Business; Computer science; Economics; European union; Law","score_opus":0.1261950932722345,"score_gpt":0.44077542039009837,"score_spread":0.3145803271178639,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3122679125","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8050431,0.0005889677,0.0025106717,0.014886237,0.015475974,0.0013206659,0.00030024786,0.00042620453,0.15944794],"genre_scores_gemma":[0.9744603,0.000023212702,0.004645708,0.0036149905,0.0014071788,0.00024435626,0.000070548995,0.000068012196,0.015465678],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.989408,0.0005440923,0.0024022774,0.00264375,0.003734388,0.0012674665],"domain_scores_gemma":[0.9912345,0.00097224175,0.0014379183,0.0035120228,0.0019609497,0.00088237826],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.011023328,0.0007863504,0.0011696883,0.0041896044,0.0011543104,0.0048451535,0.003754083,0.0005952138,0.014498617],"category_scores_gemma":[0.0059177945,0.0007230641,0.00063616654,0.0025167435,0.000778378,0.0011818962,0.002516475,0.0012368878,0.01706124],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004699796,0.00041463817,0.7842629,0.00011434713,0.00020131047,0.000032687272,0.00423911,0.011290265,0.0001590377,0.0388879,0.12730297,0.033047855],"study_design_scores_gemma":[0.0012226185,0.00015384813,0.16762401,0.0006044977,0.00007259671,0.00010405996,0.001382374,0.0047196294,0.00020111502,0.045166723,0.7766682,0.0020803055],"about_ca_topic_score_codex":0.00023054332,"about_ca_topic_score_gemma":0.0019383531,"teacher_disagreement_score":0.64936525,"about_ca_system_score_codex":0.0023437191,"about_ca_system_score_gemma":0.017148277,"threshold_uncertainty_score":0.99952203},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"grok","categories":["sts"],"domain":null,"study_design":"theoretical_or_conceptual","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"opus","categories":["sts"],"domain":null,"study_design":"theoretical_or_conceptual","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W3122873909","doi":"","title":"Defining and Using Performance Indicators and Targets in Government M and E Systems","year":2011,"lang":"en","type":"preprint","venue":"RePEc: Research Papers in Economics","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Scope (computer science); Pace; Performance indicator; Government (linguistics); Business; Work (physics); Quality (philosophy); Performance measurement; Environmental resource management; Environmental economics; Computer science; Economics; Marketing; Geography; Engineering","score_opus":0.16373406482602285,"score_gpt":0.440072411767851,"score_spread":0.27633834694182813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3122873909","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97806823,0.0011870911,0.000004000731,0.00005788904,0.00023849837,0.0004908645,0.000022503711,0.0000058614187,0.019925058],"genre_scores_gemma":[0.98405045,0.014963518,0.0005323075,0.000029640327,0.000033211425,0.000068147616,0.0000033618267,0.000017856933,0.00030151202],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9964895,0.00038576583,0.0008835025,0.00088382734,0.00089695666,0.00046039626],"domain_scores_gemma":[0.9980956,0.0007988123,0.00033431413,0.0005197918,0.000064964464,0.00018656555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011327449,0.00021728656,0.00049516326,0.0007040447,0.00017677456,0.00041722844,0.00036923168,0.00025029763,0.000051129322],"category_scores_gemma":[0.0006134877,0.00019469424,0.000028074624,0.00019047568,0.0003063761,0.0002915898,0.0014061732,0.00087492575,0.0000039668503],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045378732,0.000029748091,0.7427886,0.000111758905,0.000015903213,0.0000048403354,0.0015712649,0.0035179744,0.00001700839,0.0005233678,0.0000069749526,0.25136718],"study_design_scores_gemma":[0.0007195794,0.000110952875,0.6227548,0.0004165571,0.0000060247344,0.00002010971,0.0047109616,0.36702037,0.00005546604,0.0009097914,0.002906039,0.00036932708],"about_ca_topic_score_codex":0.00013739616,"about_ca_topic_score_gemma":0.00025136577,"teacher_disagreement_score":0.36350238,"about_ca_system_score_codex":0.0005419988,"about_ca_system_score_gemma":0.00041185148,"threshold_uncertainty_score":0.79394},"labels":[],"label_agreement":null},{"id":"W3122908871","doi":"","title":"How Can Explanations Be Used to Foster Organizational Justice","year":2005,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":59,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Organizational justice; Economic Justice; Psychology; Social psychology; Knowledge management; Business; Organizational commitment; Computer science; Political science; Law","score_opus":0.30777983169935547,"score_gpt":0.4819731327673813,"score_spread":0.17419330106802583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3122908871","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09750541,0.000006467795,0.076411426,0.7615632,0.00045696204,0.000287403,0.000036515146,0.00007378943,0.06365886],"genre_scores_gemma":[0.9075271,0.0000011820856,0.009655639,0.02351607,0.00021756365,0.000013173152,0.000021989512,0.000006009914,0.059041295],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978283,0.000055894696,0.00024615956,0.00022629189,0.0015062032,0.00013711693],"domain_scores_gemma":[0.99850935,0.00038195075,0.00006023406,0.00027485678,0.00064240163,0.00013123416],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00090803695,0.000072981085,0.00008840411,0.00021179822,0.00018258243,0.00043837866,0.00031001508,0.000029937371,0.013441931],"category_scores_gemma":[0.0010348262,0.00005173279,0.000024745545,0.0007848813,0.000013987261,0.00045630013,0.00006123008,0.000045581484,0.0011805564],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008869787,0.00011235321,0.019275634,0.0000024032154,0.0000151597105,8.4181147e-7,0.00632047,0.004703207,0.0015103609,0.06472791,0.87369025,0.029632542],"study_design_scores_gemma":[0.00043741398,0.000047386162,0.01855699,0.0000027768133,0.000018819383,0.0000040938735,0.005449506,0.014442742,0.0032870357,0.001418564,0.9561448,0.00018984749],"about_ca_topic_score_codex":0.0000037956027,"about_ca_topic_score_gemma":0.0019163584,"teacher_disagreement_score":0.81002164,"about_ca_system_score_codex":0.000060695787,"about_ca_system_score_gemma":0.00018947409,"threshold_uncertainty_score":0.99959713},"labels":[],"label_agreement":null},{"id":"W3122968069","doi":"","title":"Measurement of S&T Performance in the Government of Canada: From Outputs to Outcomes","year":2000,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Innovation, Science and Economic Development Canada","funders":"","keywords":"Incentive; Perspective (graphical); Government (linguistics); Process (computing); Performance measurement; Performance management; Organizational culture; Business; Public relations; Knowledge management; Process management; Operations management; Marketing; Political science; Computer science; Economics; Microeconomics","score_opus":0.06451300862409651,"score_gpt":0.3530523083459796,"score_spread":0.2885392997218831,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3122968069","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9881898,0.00033258513,0.00048262888,0.0052168197,0.00011045916,0.00013518678,0.000005761591,0.0000011675528,0.005525582],"genre_scores_gemma":[0.9984414,0.00032173996,0.000043573866,0.00035461475,0.000036795554,0.0000045293295,2.0247141e-7,0.0000035431858,0.0007935997],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9923816,0.00019901936,0.00076085614,0.00014037511,0.005823132,0.00069505913],"domain_scores_gemma":[0.99906576,0.00014707718,0.0002438102,0.00029520693,0.00019986746,0.000048298883],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012386278,0.00009325651,0.00022927792,0.000056290326,0.000077754215,0.000024923369,0.0007372798,0.000021244898,0.0006111488],"category_scores_gemma":[0.00024165513,0.000051876443,0.00006300338,0.00032943967,0.000017215514,0.00013342171,0.000020707059,0.00041104385,0.000011028642],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017064936,0.00013314733,0.5158139,0.0000028991449,0.00007641623,9.627078e-7,0.001723989,0.0049932646,0.00025691924,0.005981001,0.0005627325,0.47028413],"study_design_scores_gemma":[0.00071165815,0.00029869733,0.9671079,0.00003614232,0.000013408793,0.0000072351754,0.005526608,0.00056278537,0.00076044287,0.008555655,0.016314728,0.00010476972],"about_ca_topic_score_codex":0.009127114,"about_ca_topic_score_gemma":0.45394728,"teacher_disagreement_score":0.47017935,"about_ca_system_score_codex":0.0012754545,"about_ca_system_score_gemma":0.005021076,"threshold_uncertainty_score":0.9974712},"labels":[],"label_agreement":null},{"id":"W3124100376","doi":"10.2139/ssrn.2643383","title":"Assessment Practices in the Policy and Politics Cycles: A Contribution to Reflexive Governance for Sustainable Development?","year":2014,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Reflexivity; Politics; Corporate governance; Political science; Sustainable development; Public administration; Accounting; Business; Sociology; Social science; Finance; Law","score_opus":0.06703741705746742,"score_gpt":0.4938317517392399,"score_spread":0.42679433468177247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3124100376","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8400942,0.00039591914,0.10670912,0.045036886,0.00010417274,0.00092956563,0.0000031262537,0.000012024595,0.006714982],"genre_scores_gemma":[0.9940802,0.00030298403,0.0011195617,0.0015372421,0.0003673936,0.0000570457,0.000002389228,0.0000065320883,0.0025266744],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9962445,0.00042269385,0.00052726496,0.00023972504,0.0010591742,0.0015066373],"domain_scores_gemma":[0.9969912,0.0013778148,0.0006737895,0.00020836083,0.0006620259,0.000086816086],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027637046,0.000115409726,0.00017777036,0.00019953492,0.00053595915,0.00050442206,0.00048847,0.000046442194,0.000012871518],"category_scores_gemma":[0.007944122,0.00007233269,0.000039986422,0.0005432467,0.000027373939,0.0006627294,0.00005991431,0.0005742899,0.000013089938],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003138953,0.000032048993,0.0049242205,0.0000031243449,0.000013477941,5.176453e-7,0.0006666934,0.000089867244,0.000018513902,0.96823263,0.00015902857,0.025828488],"study_design_scores_gemma":[0.0010016845,0.00047415556,0.08010067,0.000015005112,0.000010136789,0.00006268703,0.014163806,0.0015229284,0.00003581605,0.61099076,0.29149374,0.00012857476],"about_ca_topic_score_codex":0.000088466004,"about_ca_topic_score_gemma":0.0012385414,"teacher_disagreement_score":0.35724184,"about_ca_system_score_codex":0.0017996832,"about_ca_system_score_gemma":0.006583405,"threshold_uncertainty_score":0.99904835},"labels":[],"label_agreement":null},{"id":"W3125659080","doi":"10.22215/etd/2015-10847","title":"Why Get Involved in Program Evaluations?: Toward a Model of Stakeholder Involvement Motives","year":2015,"lang":"en","type":"dissertation","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"CLARITY; Stakeholder; Stakeholder analysis; Thematic analysis; Relevance (law); Psychology; Process (computing); Value (mathematics); Public relations; Medical education; Medicine; Political science; Qualitative research; Computer science; Sociology","score_opus":0.5569159270801035,"score_gpt":0.5430457789554698,"score_spread":0.013870148124633719,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3125659080","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9272547,0.0007686022,0.0020456265,0.0011902478,0.0008443659,0.0038179434,0.00008742811,0.00010470261,0.06388642],"genre_scores_gemma":[0.9534625,0.00023278977,0.017942855,0.0009102623,0.00006708414,0.0012194115,0.0018405503,0.0000529034,0.024271691],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99117416,0.00040882183,0.0019292767,0.0007493095,0.00540247,0.00033595384],"domain_scores_gemma":[0.9945524,0.00026892297,0.00093688886,0.0007848584,0.003298503,0.00015847017],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008223252,0.00036552455,0.0007345317,0.0011815368,0.00006140308,0.00021154013,0.0008530159,0.00029401373,0.0019271186],"category_scores_gemma":[0.0011202472,0.00027311884,0.00017948533,0.0012181465,0.00006674453,0.0006419421,0.00007732079,0.00031993748,0.000096191616],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000608276,0.0038650136,0.024255447,0.00042404616,0.00023462233,0.0000020959733,0.069920436,0.10787879,0.0013082329,0.0064101764,0.12430546,0.6607874],"study_design_scores_gemma":[0.0025764462,0.000666709,0.027762419,0.0003679835,0.00010171584,2.0562045e-7,0.07208824,0.782986,0.0015208732,0.10365057,0.007501307,0.00077753],"about_ca_topic_score_codex":0.00026172886,"about_ca_topic_score_gemma":0.0125422105,"teacher_disagreement_score":0.67510724,"about_ca_system_score_codex":0.00025590512,"about_ca_system_score_gemma":0.0021514257,"threshold_uncertainty_score":0.9999721},"labels":[],"label_agreement":null},{"id":"W3128096052","doi":"10.56645/jmde.v17i38.673","title":"Evaluation in Our New Normal Environment: Navigating the Challenges with Data Collection","year":2021,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Data collection; Credibility; Best practice; Data quality; Computer science; Quality (philosophy); Public relations; Data science; Risk analysis (engineering); Process management; Business; Political science; Marketing; Sociology","score_opus":0.36889537975502795,"score_gpt":0.5129477895526718,"score_spread":0.1440524097976439,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3128096052","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9375741,0.005121533,0.0048239315,0.048995648,0.0008673664,0.0008753542,0.0000052607397,0.0000074477734,0.0017293703],"genre_scores_gemma":[0.9935388,0.0006560086,0.005102351,0.00005124969,0.0003981951,0.000019123794,0.00003513123,0.000012378691,0.00018676711],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9872029,0.0027331607,0.001297559,0.0004312875,0.008126257,0.00020883516],"domain_scores_gemma":[0.99495703,0.00065728516,0.0013196028,0.00089585636,0.0020692672,0.00010098754],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.056888513,0.00016192821,0.00028346005,0.00021002864,0.00031744965,0.0001856446,0.00073520443,0.00007972737,0.0006514844],"category_scores_gemma":[0.0033782145,0.00009697505,0.0000729303,0.00079061254,0.000031737225,0.00187518,0.00027491344,0.00051157025,0.00005369027],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002504083,0.0003263514,0.019247243,0.000007095569,0.00007899556,0.000014474197,0.010331347,0.23575391,0.0009699123,0.0000644438,0.0013649157,0.7315909],"study_design_scores_gemma":[0.002972607,0.00030622905,0.2702905,0.00015269528,0.00020530191,0.00015950589,0.022236917,0.6982861,0.00039358574,0.0044022496,0.0004629114,0.00013135554],"about_ca_topic_score_codex":0.000016087688,"about_ca_topic_score_gemma":0.0007146276,"teacher_disagreement_score":0.73145956,"about_ca_system_score_codex":0.0004788222,"about_ca_system_score_gemma":0.0033633339,"threshold_uncertainty_score":0.97113174},"labels":[],"label_agreement":null},{"id":"W3128457202","doi":"","title":"Handbook on Measuring Equity in Education (2018). Montréal: UNESCO Institute for Statistics, 142 pp. [RECENSIÓN]","year":2020,"lang":"es","type":"article","venue":"Estudios sobre Educación","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Equity (law); Library science; Statistics; Sociology; Mathematics education; Political science; Regional science; Mathematics; Computer science; Law","score_opus":0.20830247379671057,"score_gpt":0.45723019177431085,"score_spread":0.24892771797760027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3128457202","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43870446,0.05893325,0.071191974,0.29591262,0.08612528,0.018702373,0.0029838101,0.00068502617,0.026761211],"genre_scores_gemma":[0.96763366,0.008126043,0.012354462,0.006593004,0.002814565,0.0005271843,0.0002116374,0.00008973214,0.0016497305],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9943422,0.00031274062,0.0013888378,0.0011687714,0.0020569365,0.00073051726],"domain_scores_gemma":[0.9964234,0.0008637426,0.00058617216,0.00067451276,0.00095573557,0.0004964287],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00263196,0.00053043675,0.000793896,0.00031631472,0.0005332247,0.00058625214,0.00080953335,0.00020422808,0.00035094298],"category_scores_gemma":[0.0038633884,0.00047870306,0.00018032429,0.0010098014,0.00020309587,0.00080890214,0.00031494355,0.0005055526,0.0013701047],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048400462,0.0013205524,0.020686835,0.0003195548,0.00012513826,0.000009018656,0.005069379,0.0035520142,0.00027741387,0.020799777,0.4114482,0.5359081],"study_design_scores_gemma":[0.0034111561,0.001329172,0.06441954,0.0012419211,0.00021528504,0.000007872375,0.0059827087,0.012200792,0.0015712677,0.0049667833,0.903433,0.0012204595],"about_ca_topic_score_codex":0.0004238952,"about_ca_topic_score_gemma":0.001106849,"teacher_disagreement_score":0.53468764,"about_ca_system_score_codex":0.0006184303,"about_ca_system_score_gemma":0.00426207,"threshold_uncertainty_score":0.99976647},"labels":[],"label_agreement":null},{"id":"W3129339433","doi":"10.1037/cbs0000251","title":"On the quest for quality self-report data: HEXACO and indicators of careless responding.","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Behavioural Science/Revue canadienne des sciences du comportement","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Quality (philosophy); Social psychology; Epistemology","score_opus":0.43362449037945533,"score_gpt":0.4599925323206153,"score_spread":0.026368041941159992,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3129339433","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9921458,0.0001919059,0.00018585358,0.004891964,0.0012783029,0.000281157,0.00013106098,0.000003771162,0.0008902243],"genre_scores_gemma":[0.9977851,0.000016223532,0.001635747,0.00031221958,0.000073794574,0.0000072531257,0.00000852079,0.000006041335,0.00015511445],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9952816,0.00029089086,0.0015785143,0.00068524596,0.0014464841,0.00071728433],"domain_scores_gemma":[0.99315464,0.001010418,0.0015150202,0.00087327266,0.0021667865,0.0012798375],"candidate_categories":["metaresearch","sts"],"consensus_categories":["sts"],"category_scores_codex":[0.038230605,0.0001856105,0.0004423078,0.0014380993,0.0019854712,0.00066521205,0.002847002,0.000049754366,0.0003124464],"category_scores_gemma":[0.00467127,0.00012109183,0.00011350887,0.003690596,0.0033737426,0.0011176105,0.00017295333,0.00020269003,0.0000017236276],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014005174,0.00006765311,0.9286154,0.000014716128,0.000024719542,0.0002387606,0.0044991206,0.00026709939,0.00039023973,0.05752652,0.0013520166,0.006989726],"study_design_scores_gemma":[0.0007071819,0.00093784765,0.94771844,0.00020566177,0.00009957931,0.001072076,0.018594613,0.002589789,0.0014153827,0.009884547,0.01635507,0.0004197885],"about_ca_topic_score_codex":0.011771045,"about_ca_topic_score_gemma":0.34373492,"teacher_disagreement_score":0.33196387,"about_ca_system_score_codex":0.0008899008,"about_ca_system_score_gemma":0.011789391,"threshold_uncertainty_score":0.9993385},"labels":[],"label_agreement":null},{"id":"W3130034484","doi":"10.1177/0539018421993021","title":"Evaluating science: Opening a debate","year":2021,"lang":"en","type":"article","venue":"Social Science Information","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Judgement; Knowledge production; Epistemology; Production (economics); Sociology; Political science; Positive economics; Knowledge management; Economics; Computer science; Microeconomics; Philosophy","score_opus":0.3455408685169892,"score_gpt":0.6034309286713302,"score_spread":0.257890060154341,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3130034484","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6929836,0.000007538674,0.004037376,0.0020260718,0.0009824205,0.00018102367,0.0000034801244,0.000049238144,0.29972923],"genre_scores_gemma":[0.9946569,0.000002410312,0.0035499835,0.0012646008,0.000098417106,0.0000144104015,0.0000053383833,0.0000020588539,0.00040584613],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99107254,0.000103005426,0.0007629288,0.00031681225,0.007268461,0.00047624536],"domain_scores_gemma":[0.9947478,0.00016634191,0.00041300713,0.00032476292,0.0041997456,0.00014834235],"candidate_categories":["metaresearch","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["scholarly_communication","insufficient_payload"],"category_scores_codex":[0.028184928,0.00009615907,0.000144999,0.0005685062,0.0033171063,0.0032580153,0.0011638216,0.00004037096,0.0012594726],"category_scores_gemma":[0.009315941,0.000077083176,0.000059825084,0.008199125,0.0009542067,0.015358683,0.0004239021,0.00014314684,0.0011473523],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000076155643,0.000016821265,0.00292559,0.0000033208426,0.0000018212672,7.157167e-7,0.018536082,0.0007837291,0.017113585,0.05174592,0.0005217984,0.908343],"study_design_scores_gemma":[0.0016157549,0.0001836625,0.2625612,0.000044815086,0.000021226553,0.000047561276,0.068723045,0.50129104,0.059664905,0.049574994,0.05545902,0.0008127711],"about_ca_topic_score_codex":0.00001358954,"about_ca_topic_score_gemma":0.0000075459056,"teacher_disagreement_score":0.90753025,"about_ca_system_score_codex":0.00036818034,"about_ca_system_score_gemma":0.0053791925,"threshold_uncertainty_score":0.9996535},"labels":[],"label_agreement":null},{"id":"W3132537658","doi":"10.2139/ssrn.3715451","title":"Mutually Compatible, Yet Different: A Theoretical Framework for Reconciling Different Impact Monetization Methodologies and Frameworks","year":2020,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact","funders":"","keywords":"Monetization; Computer science; Business; Economics; Macroeconomics","score_opus":0.18161353305789216,"score_gpt":0.48967057657931423,"score_spread":0.30805704352142205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3132537658","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41924936,0.0006266084,0.573438,0.006204234,0.00017047206,0.00021056834,0.0000063731395,0.00002461425,0.000069800386],"genre_scores_gemma":[0.984327,0.00203214,0.012369732,0.0008057297,0.0003813646,0.000017541648,0.000008376793,0.000020612368,0.000037477574],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9957849,0.000706711,0.00078204565,0.00042323314,0.0010328947,0.0012702271],"domain_scores_gemma":[0.99347484,0.0052619134,0.0004301465,0.00023619802,0.00034952213,0.00024738244],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.006039305,0.00025956772,0.000515749,0.00015401695,0.00036121198,0.00048418043,0.00051861233,0.00028473474,0.00058322557],"category_scores_gemma":[0.008527605,0.00015536929,0.00022374235,0.00033433898,0.00014573941,0.00028374387,0.00010268821,0.0024967794,0.000013228823],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045188438,0.00003538179,0.019696172,0.000007891724,0.00014151545,5.037194e-7,0.0018498952,0.0013907814,0.00019734501,0.8001072,0.00014088502,0.17598054],"study_design_scores_gemma":[0.0006259113,0.0011287334,0.01102485,0.00003445792,0.00004495047,0.000026273023,0.003574775,0.07671701,0.00014694763,0.90639627,0.00009461115,0.00018520391],"about_ca_topic_score_codex":0.0000022552092,"about_ca_topic_score_gemma":0.000033124412,"teacher_disagreement_score":0.56507766,"about_ca_system_score_codex":0.00032882145,"about_ca_system_score_gemma":0.00072425004,"threshold_uncertainty_score":0.999824},"labels":[],"label_agreement":null},{"id":"W3132909419","doi":"","title":"Enduring Issues / Changing Perspectives 3","year":2019,"lang":"en","type":"article","venue":"Pacific Affairs","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Political science; Epistemology; Philosophy","score_opus":0.08160248287341722,"score_gpt":0.4207523995860814,"score_spread":0.3391499167126642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3132909419","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1137401,0.00043431114,0.0005466564,0.0010988913,0.00069380406,0.0001967593,0.0000030089116,0.00007713081,0.88320935],"genre_scores_gemma":[0.94449407,0.000047744434,0.0005505562,0.000010811205,0.00013871747,0.000010013657,0.0000016911479,0.000008796894,0.054737616],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9977608,0.00009594166,0.000281455,0.0003929039,0.0011877742,0.00028117944],"domain_scores_gemma":[0.9989098,0.00022562574,0.00011691782,0.0004883725,0.00019119239,0.00006812906],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0023052248,0.000110086556,0.0001810367,0.00036220637,0.00013823631,0.00020447728,0.00033042478,0.000040219365,0.0131687755],"category_scores_gemma":[0.00022317425,0.000081454215,0.00008615985,0.0006303525,0.000040022012,0.00045946686,0.00008831027,0.000103270664,0.009461652],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014061185,0.00036590366,0.1883281,0.000054613494,0.00013954489,0.000025228823,0.44866082,0.0028268627,0.008022828,0.1927995,0.020458799,0.1381772],"study_design_scores_gemma":[0.00022438719,0.000041226664,0.0068096197,0.000016321344,0.0000032238465,0.000003415499,0.95349294,0.006701538,0.00086076115,0.0021481083,0.029539473,0.00015898929],"about_ca_topic_score_codex":0.0000033196468,"about_ca_topic_score_gemma":0.0000031824702,"teacher_disagreement_score":0.830754,"about_ca_system_score_codex":0.000057357018,"about_ca_system_score_gemma":0.000052920397,"threshold_uncertainty_score":0.9913096},"labels":[],"label_agreement":null},{"id":"W3133660863","doi":"10.3917/dbu.desja.2017.01.0083","title":"Comment changent les formations d’enseignants ?","year":2017,"lang":"fr","type":"book-chapter","venue":"Perspectives en éducation et formation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Political science","score_opus":0.33798715645453464,"score_gpt":0.49210942227522914,"score_spread":0.1541222658206945,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3133660863","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003888755,0.0012354719,0.03975772,0.14958774,0.003304026,0.0021427553,0.00038215527,0.00013270893,0.79956865],"genre_scores_gemma":[0.82530403,0.0077444282,0.003451426,0.0017546996,0.0007666675,0.00034094712,0.0011341636,0.000086888336,0.15941674],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.993885,0.00071553234,0.0016613321,0.00076242804,0.0024636444,0.0005120605],"domain_scores_gemma":[0.9923749,0.0009936986,0.0025494108,0.0015188457,0.002295517,0.00026765504],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.006648589,0.00068134256,0.00065452215,0.0010074723,0.0023327526,0.0011305567,0.0011146967,0.0004856566,0.013888687],"category_scores_gemma":[0.0013679361,0.00063023664,0.00040920495,0.00012294884,0.00040971398,0.005401552,0.00027870797,0.00074384623,0.0061335666],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028435525,0.00023396748,0.00008064666,0.000084392515,0.0000987953,8.6620486e-7,0.17391548,0.00027784018,0.000025760639,0.7108051,0.00834961,0.106099084],"study_design_scores_gemma":[0.0008612581,0.0002525456,0.0070459414,0.000548418,0.00017173997,0.000043875385,0.08454934,0.021218458,0.00014576277,0.03896088,0.8453654,0.00083638425],"about_ca_topic_score_codex":0.0001685143,"about_ca_topic_score_gemma":0.00073103665,"teacher_disagreement_score":0.8370158,"about_ca_system_score_codex":0.0028713816,"about_ca_system_score_gemma":0.0011353819,"threshold_uncertainty_score":0.99990636},"labels":[],"label_agreement":null},{"id":"W3135128798","doi":"10.18848/2327-7955/cgp/v28i01/97-111","title":"Responding to the Findings of Canada’s Truth and Reconciliation Commission: A Case Study of Barriers and Drivers for Change at a Small Undergraduate Institution","year":2021,"lang":"en","type":"article","venue":"The International Journal of Learning in Higher Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Institution; Commission; Political science; Psychology; Law; Sociology","score_opus":0.2179887541939017,"score_gpt":0.45250020319621326,"score_spread":0.23451144900231155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3135128798","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9724265,0.000078451965,0.00006625709,0.02609224,0.0010180164,0.00016400055,0.0000021405776,8.102021e-7,0.00015158973],"genre_scores_gemma":[0.9978991,0.000021440377,0.0001510979,0.00017006941,0.00008569661,0.000008420802,0.0000012935594,0.0000026559644,0.0016601841],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.998449,0.0002707798,0.00046596918,0.00009902183,0.000658704,0.000056489534],"domain_scores_gemma":[0.9975221,0.00095577084,0.00048331107,0.000084922445,0.00090524444,0.000048659633],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029866782,0.000051238276,0.000113924834,0.0002937512,0.0001454416,0.000052969695,0.00018665407,0.00001838072,0.000064128995],"category_scores_gemma":[0.0015943589,0.000031902284,0.000021635273,0.0003147038,0.000025581876,0.0001666909,0.00006145914,0.000108175096,1.8706181e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00070011726,0.00018111806,0.8794189,0.00002131294,0.00013031135,0.000031801337,0.06662388,0.01416204,0.0010625633,0.0066782334,0.0022787706,0.028710917],"study_design_scores_gemma":[0.002260625,0.00062771275,0.7897076,0.00031686478,0.000072391296,0.0006205285,0.14958793,0.0049765427,0.00095689355,0.0017684458,0.048958078,0.0001463913],"about_ca_topic_score_codex":0.003293556,"about_ca_topic_score_gemma":0.036599636,"teacher_disagreement_score":0.08971133,"about_ca_system_score_codex":0.00026562545,"about_ca_system_score_gemma":0.0011177931,"threshold_uncertainty_score":0.9809799},"labels":[],"label_agreement":null},{"id":"W3135702957","doi":"10.1080/1360144x.2021.1887876","title":"‘Complexifying’ our approach to evaluating educational development outcomes: bridging theoretical innovations with frontline practice","year":2021,"lang":"en","type":"article","venue":"The International Journal for Academic Development","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Bridging (networking); Transferability; Reductionism; Computer science; Process (computing); Management science; Knowledge management; Benchmarking; Quality (philosophy); Engineering ethics; Process management; Sociology; Psychology; Management; Epistemology","score_opus":0.33864891270080044,"score_gpt":0.5742633131341004,"score_spread":0.23561440043329995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3135702957","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2265327,0.000100016725,0.56292284,0.19865198,0.0031096588,0.00079511764,0.000015290549,0.000035589965,0.007836791],"genre_scores_gemma":[0.49367246,0.0000117801965,0.483102,0.014274604,0.0007696208,0.00026216626,0.00009572767,0.000027941029,0.007783697],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9921669,0.00026477393,0.0016567834,0.000484529,0.005035554,0.00039147792],"domain_scores_gemma":[0.990979,0.0017922341,0.00073437375,0.00028148683,0.006008974,0.00020390407],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0143465735,0.00024627472,0.0002854344,0.00039294263,0.00094887905,0.00068924116,0.0016735788,0.00007949835,0.000392907],"category_scores_gemma":[0.009885717,0.00014642354,0.00008704021,0.0006821654,0.00005191244,0.00063344714,0.00037084604,0.00072900584,0.0002056995],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010285041,0.0011964936,0.03525397,0.0000218804,0.0020720598,0.000019090383,0.031184029,0.0479954,0.0011822745,0.51874363,0.08334577,0.2779569],"study_design_scores_gemma":[0.004141409,0.0001483859,0.12539113,0.00037426563,0.00012213242,0.0027269782,0.033180453,0.028041236,0.0036752904,0.06453159,0.736536,0.0011310994],"about_ca_topic_score_codex":0.0000016503806,"about_ca_topic_score_gemma":0.000007088387,"teacher_disagreement_score":0.65319026,"about_ca_system_score_codex":0.00075241365,"about_ca_system_score_gemma":0.005332161,"threshold_uncertainty_score":0.99845445},"labels":[],"label_agreement":null},{"id":"W3136354237","doi":"10.3138/cjpe.69703","title":"UEval: Bringing Community-Based Experiential Learning to the Evaluation Classroom","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Canadian Patient Safety Institute; University of Alberta","funders":"","keywords":"Experiential learning; Curriculum; Citizen journalism; Pedagogy; Psychology; Experiential education; Participatory action research; Engineering ethics; Medical education; Sociology; Political science; Engineering; Medicine","score_opus":0.4370275756617095,"score_gpt":0.5432201279952923,"score_spread":0.10619255233358277,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3136354237","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9688201,0.00051509315,0.011173976,0.011887356,0.0022284742,0.0014488269,0.0000044460853,0.000018819826,0.003902938],"genre_scores_gemma":[0.9950172,0.0000023059583,0.0032568593,0.001017068,0.00029784013,0.00013343267,0.00004640814,0.000015037538,0.00021389793],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98832387,0.0056635574,0.001010481,0.00021894088,0.004428613,0.0003545698],"domain_scores_gemma":[0.98915535,0.0006719451,0.00063830294,0.0005464165,0.008511859,0.0004761083],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.052164398,0.00014454313,0.00023264553,0.00061154255,0.0011698308,0.0010817653,0.00068064773,0.00007730879,0.004186662],"category_scores_gemma":[0.012679966,0.00010743241,0.00018526759,0.0015583376,0.00007104506,0.00048960425,0.000035393594,0.0006728011,0.00014687581],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015659594,0.000045953086,0.007763531,0.000003515436,0.000024459194,0.0000043074174,0.006367557,0.15349004,0.00018395057,0.00007005888,0.0034826875,0.8285483],"study_design_scores_gemma":[0.0015060583,0.00052142545,0.04616685,0.000104743376,0.00019270368,0.00005097486,0.018792639,0.58845913,0.0010190508,0.0018092564,0.34115764,0.00021951836],"about_ca_topic_score_codex":0.0005040291,"about_ca_topic_score_gemma":0.031057104,"teacher_disagreement_score":0.8283288,"about_ca_system_score_codex":0.0007104546,"about_ca_system_score_gemma":0.010812149,"threshold_uncertainty_score":0.99995524},"labels":[],"label_agreement":null},{"id":"W3136555995","doi":"10.3138/cjpe.69601","title":"In Their Own Words: Student Key Learning Experiences in an Introductory Evaluation Course","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Key (lock); Psychology; Taxonomy (biology); Mathematics education; Grounded theory; Pedagogy; Reflective practice; Medical education; Computer science; Qualitative research; Sociology; Medicine","score_opus":0.3004856471172792,"score_gpt":0.5460008305135504,"score_spread":0.2455151833962712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3136555995","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99300796,0.0016568552,0.00008310242,0.0022634363,0.0014282252,0.00081683794,0.0000010699605,0.0000051600978,0.0007373744],"genre_scores_gemma":[0.99847054,0.000022764376,0.00070397736,0.00017905862,0.00030095642,0.00021005464,0.000019492238,0.000010024898,0.00008310154],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9912131,0.0032249668,0.0013261394,0.00038616871,0.0034850477,0.00036457786],"domain_scores_gemma":[0.9943844,0.0002517065,0.00067496643,0.0003482431,0.0039712554,0.00036943896],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.037638105,0.00015615427,0.000320679,0.000947509,0.00016578793,0.0006072193,0.00050196215,0.00009474828,0.0060878736],"category_scores_gemma":[0.004405719,0.00012683732,0.00008587003,0.0016421422,0.00009816337,0.0017482262,0.000020376066,0.00044364439,0.000029893452],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016359138,0.00019076728,0.23499136,0.0000021768212,0.000011685599,0.000023838396,0.06911349,0.034797367,0.000117337484,0.00007544222,0.0002681127,0.66039205],"study_design_scores_gemma":[0.0020874536,0.0006361747,0.5431609,0.000093060946,0.00005104526,0.000044819295,0.24312393,0.19424066,0.0002939992,0.003568417,0.012444334,0.00025517397],"about_ca_topic_score_codex":0.00029876406,"about_ca_topic_score_gemma":0.11728419,"teacher_disagreement_score":0.6601369,"about_ca_system_score_codex":0.0009943933,"about_ca_system_score_gemma":0.010381027,"threshold_uncertainty_score":0.9952292},"labels":[],"label_agreement":null},{"id":"W3136672375","doi":"10.3138/cjpe.69698","title":"Praxis Makes Perfect? Transcending Textbooks to Learning Evaluation Experientially and in Cultural Contexts","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Praxis; Transformative learning; Experiential learning; Value (mathematics); White privilege; Sociology; Professional development; Harm; Pedagogy; Psychology; Privilege (computing); Epistemology; Engineering ethics; Racism; Social psychology; Law; Computer science","score_opus":0.3037025959764343,"score_gpt":0.5365116728649787,"score_spread":0.2328090768885444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3136672375","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99158823,0.0013201667,0.00054956175,0.0022528376,0.0005995813,0.0010366024,0.0000021013186,0.000006373819,0.0026445303],"genre_scores_gemma":[0.99741626,0.000015727064,0.0018924413,0.00017109017,0.00011342184,0.000104894214,0.0000143299485,0.000009402418,0.000262416],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99472946,0.0013778318,0.00092193275,0.00030650647,0.0023646797,0.00029958354],"domain_scores_gemma":[0.9947652,0.00020604926,0.0003664052,0.00016514148,0.0040458683,0.00045133146],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01655265,0.00013689997,0.00026693146,0.00069394195,0.0002802042,0.00075062463,0.00020029914,0.00008034825,0.0025730862],"category_scores_gemma":[0.005984348,0.000115309,0.000092158974,0.0007854334,0.00006053195,0.0007780063,0.000012251125,0.00027129133,0.000027521535],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029481116,0.000026180973,0.040971465,0.0000046481046,0.000016026612,0.00001302594,0.01477202,0.007228677,0.0013972193,0.00009025961,0.00029399444,0.935157],"study_design_scores_gemma":[0.0062453393,0.0015431658,0.6091605,0.0005116861,0.0002710367,0.00035444566,0.05367481,0.2280794,0.0031268944,0.003949814,0.09238772,0.00069523155],"about_ca_topic_score_codex":0.00022673253,"about_ca_topic_score_gemma":0.04398987,"teacher_disagreement_score":0.9344618,"about_ca_system_score_codex":0.00049598416,"about_ca_system_score_gemma":0.004210208,"threshold_uncertainty_score":0.9983387},"labels":[],"label_agreement":null},{"id":"W3137000688","doi":"10.3138/cjpe.69691","title":"Collaborative Evaluation Designs as an Authentic Course Assessment","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta; Queen's University","funders":"","keywords":"Authentic assessment; Computer science; Evaluation methods; Graduate students; Authentic learning; Instructional design; Knowledge management; Psychology; Mathematics education; Pedagogy; Curriculum; Multimedia; Engineering","score_opus":0.36482317151236154,"score_gpt":0.5893866504709884,"score_spread":0.22456347895862683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3137000688","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9690569,0.0014604473,0.004543146,0.006147327,0.0034469704,0.0026499897,0.000025084368,0.000020764817,0.012649379],"genre_scores_gemma":[0.988532,0.000015814729,0.010323825,0.000296206,0.00026118965,0.00016722358,0.00009164624,0.000016409249,0.00029568854],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9884252,0.0036153018,0.0012884726,0.0003946455,0.005902145,0.0003742486],"domain_scores_gemma":[0.9753858,0.00043398014,0.0010967017,0.00055171206,0.021676373,0.00085541967],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.036915123,0.00019126628,0.00034612845,0.00057251874,0.0004316792,0.001171792,0.00050394144,0.00012514103,0.015462528],"category_scores_gemma":[0.006553598,0.00016136793,0.00014794982,0.0018355697,0.000118694115,0.001539735,0.000016010054,0.0002956272,0.00017102678],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016477741,0.00026987356,0.01649594,0.0000037693662,0.000095709234,0.000035865054,0.0032991555,0.0077280686,0.0002514436,0.002511824,0.0034264436,0.96586543],"study_design_scores_gemma":[0.004017423,0.0023502673,0.26874328,0.00012397548,0.0010483796,0.00025746968,0.024794089,0.5616567,0.0010181216,0.08269292,0.05276803,0.0005293419],"about_ca_topic_score_codex":0.00020467104,"about_ca_topic_score_gemma":0.02224159,"teacher_disagreement_score":0.9653361,"about_ca_system_score_codex":0.001115312,"about_ca_system_score_gemma":0.059748795,"threshold_uncertainty_score":0.9998651},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W3137617126","doi":"10.3138/cjpe.69753","title":"The Role of Evaluative Thinking in the Teaching of Evaluation","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Salient; Psychology; Pedagogy; Balance (ability); Professional development; Medical education; Engineering ethics; Mathematics education; Political science; Medicine; Engineering","score_opus":0.2792685004296206,"score_gpt":0.5495539625772053,"score_spread":0.27028546214758475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3137617126","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9739891,0.0050819498,0.00034637508,0.0047093863,0.0006528764,0.0016329167,0.0000057637108,0.000002461161,0.013579152],"genre_scores_gemma":[0.9981844,0.000022932856,0.0015000071,0.00009511161,0.00009105185,0.00006534847,0.000008596547,0.0000060905672,0.000026500107],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9855009,0.005973899,0.0016548142,0.00019148132,0.0064227404,0.0002561956],"domain_scores_gemma":[0.98870754,0.0018873108,0.0015428147,0.000457453,0.0072968006,0.000108106695],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11268065,0.000108724416,0.00026213707,0.00042197443,0.00040886374,0.00028921125,0.0007104042,0.00006774315,0.00049660535],"category_scores_gemma":[0.018781073,0.00006147524,0.00016592629,0.001069772,0.00014804835,0.00050109735,0.000021826516,0.00038560215,0.00000641969],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015667412,0.000057153182,0.025405893,0.0000030687595,0.000031967473,0.0000017104029,0.0152725,0.0069030575,0.00021852083,0.0053015063,0.00024390464,0.94654506],"study_design_scores_gemma":[0.0016695907,0.00057163794,0.25522164,0.00021128445,0.00029883755,0.0000669618,0.07973544,0.3315874,0.0016153846,0.3102633,0.018600918,0.00015758014],"about_ca_topic_score_codex":0.000536356,"about_ca_topic_score_gemma":0.022764822,"teacher_disagreement_score":0.94638747,"about_ca_system_score_codex":0.00034010297,"about_ca_system_score_gemma":0.0098233465,"threshold_uncertainty_score":0.99579006},"labels":[],"label_agreement":null},{"id":"W3137749100","doi":"10.7202/1075508ar","title":"Comment exercer une gestion rationnelle axée sur les résultats ? Exemple de la mesure de l’effet d’un programme orthopédagogique sur le rendement des élèves","year":2021,"lang":"fr","type":"article","venue":"Enfance en difficulté","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université TÉLUQ","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.08466992941031855,"score_gpt":0.41116524045222297,"score_spread":0.32649531104190443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3137749100","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8836235,0.005014734,0.040144037,0.0674417,0.0006517013,0.0007208694,0.00007627672,0.00014705028,0.002180148],"genre_scores_gemma":[0.95795757,0.005517262,0.02051432,0.001242051,0.00030804114,0.0003267979,0.00024435332,0.000049275703,0.013840331],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9915259,0.003957421,0.0011038649,0.0008893779,0.0015523846,0.00097103807],"domain_scores_gemma":[0.9943333,0.0031061813,0.00043704285,0.0006995743,0.0010492431,0.00037463102],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009219486,0.00047984868,0.00055992877,0.00012884803,0.0009030459,0.00072162406,0.0005483565,0.00046633312,0.0028871242],"category_scores_gemma":[0.003389271,0.0004285207,0.00027463914,0.0011377014,0.00040959375,0.00081159425,0.00023764362,0.0006788495,0.00018913024],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016571955,0.003938187,0.11595006,0.0002930544,0.0002525258,0.00016890686,0.08845541,0.04216551,0.009929198,0.014736651,0.09665055,0.62729424],"study_design_scores_gemma":[0.0031892606,0.00024056298,0.53478605,0.0006014914,0.00012127849,0.00010496364,0.020879986,0.032690965,0.019884676,0.0074645085,0.37932307,0.0007132237],"about_ca_topic_score_codex":0.001270906,"about_ca_topic_score_gemma":0.0037308899,"teacher_disagreement_score":0.626581,"about_ca_system_score_codex":0.0007007455,"about_ca_system_score_gemma":0.0019443365,"threshold_uncertainty_score":0.99981666},"labels":[],"label_agreement":null},{"id":"W3137926421","doi":"10.3138/cjpe.71156","title":"Establishing and Developing Professional Evaluator Dispositions","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Professional development; Order (exchange); Engineering ethics; Pedagogy; Medical education; Medicine","score_opus":0.36322189242453295,"score_gpt":0.5554788230819199,"score_spread":0.19225693065738692,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3137926421","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96704614,0.0018843308,0.005285447,0.01879032,0.002610283,0.0008227226,0.000013909806,0.000011613924,0.0035352043],"genre_scores_gemma":[0.97631264,0.000017895081,0.022482185,0.0004950491,0.00022488326,0.000046499168,0.000025047984,0.000008594936,0.00038718566],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99555826,0.0009885748,0.00079687673,0.00021317758,0.002206206,0.0002368876],"domain_scores_gemma":[0.99287,0.0006633142,0.00045997763,0.0001998035,0.0053597367,0.00044718749],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016522573,0.00010072309,0.000197057,0.00045050305,0.0004350578,0.00081989914,0.0002407655,0.00007155799,0.0020280923],"category_scores_gemma":[0.01047772,0.00007957473,0.00007561288,0.00087453047,0.000079025274,0.001119025,0.00002613432,0.00020554477,0.000027699929],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010574214,0.000034629353,0.032439306,0.000007526275,0.000030879717,0.0000218283,0.001687429,0.00045402843,0.00027085087,0.0038104558,0.004487643,0.95674485],"study_design_scores_gemma":[0.0022139468,0.00033055907,0.69249564,0.00042679827,0.000242665,0.000828733,0.009525881,0.06382074,0.0006879315,0.0712019,0.15778068,0.0004445138],"about_ca_topic_score_codex":0.00007727207,"about_ca_topic_score_gemma":0.008813517,"teacher_disagreement_score":0.9563003,"about_ca_system_score_codex":0.00034499384,"about_ca_system_score_gemma":0.015797568,"threshold_uncertainty_score":0.9988842},"labels":[],"label_agreement":null},{"id":"W3138644234","doi":"10.3138/cjpe.69751","title":"Offering Graduate Evaluation Degrees Online: Comparing Student Engagement in Two Canadian Programs","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Carleton University; University of Victoria","funders":"","keywords":"Certificate; Set (abstract data type); Graduate students; Online learning; Medical education; Tone (literature); Psychology; Mathematics education; Pedagogy; Computer science; Multimedia; Medicine","score_opus":0.7266241610460255,"score_gpt":0.6005049424468304,"score_spread":0.12611921859919506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3138644234","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9895706,0.0007940456,0.00020292273,0.0025174737,0.0014346341,0.0019523867,0.0000066418006,0.000010979849,0.0035103115],"genre_scores_gemma":[0.99489045,0.000022271744,0.004315734,0.00016148934,0.00022805038,0.00017521076,0.00012326174,0.00001877174,0.00006473485],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9900941,0.0021119146,0.0017107845,0.00043295563,0.004994947,0.0006552452],"domain_scores_gemma":[0.9909709,0.00019387256,0.0007200874,0.00047052768,0.0066582947,0.0009863353],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.034219045,0.000231422,0.00044336336,0.0015359933,0.00035333738,0.0010186881,0.00065764127,0.00007291124,0.0015055762],"category_scores_gemma":[0.003187007,0.00020906335,0.00016950218,0.0018170357,0.00007547331,0.00080234365,0.00003833986,0.0005541185,0.00005573633],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007130722,0.00013815839,0.27582768,0.000004804293,0.000036964746,0.000041229876,0.0023514593,0.036925707,0.000013769956,0.00015629025,0.0002146492,0.6842822],"study_design_scores_gemma":[0.0023278897,0.00025672693,0.5973503,0.00018973755,0.00014618953,0.000048840528,0.0073814243,0.37949428,0.000055306573,0.0024317296,0.0100598615,0.0002577075],"about_ca_topic_score_codex":0.05136699,"about_ca_topic_score_gemma":0.97369856,"teacher_disagreement_score":0.9223316,"about_ca_system_score_codex":0.0028765395,"about_ca_system_score_gemma":0.02137033,"threshold_uncertainty_score":0.9994072},"labels":[],"label_agreement":null},{"id":"W3138688726","doi":"10.3138/cjpe.69697","title":"Pinpointing Where to Start: A Reflective Analysis on the Introductory Evaluation Course","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Course (navigation); Reflective practice; Mathematics education; Process (computing); Psychology; Graduate students; Computer science; Course evaluation; Learning theory; Pedagogy; Higher education; Engineering","score_opus":0.33797496032700913,"score_gpt":0.5470026099765712,"score_spread":0.2090276496495621,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3138688726","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93397015,0.0009903025,0.0021289825,0.05197724,0.0014775429,0.0019543,0.000013414508,0.0000111337995,0.007476907],"genre_scores_gemma":[0.99611807,0.0000063584134,0.0019807105,0.0011162749,0.00038359792,0.00012187791,0.000017141363,0.000010310101,0.00024563383],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9910305,0.0025853186,0.0010029208,0.00037506304,0.004685971,0.00032024083],"domain_scores_gemma":[0.9849547,0.0006497936,0.00076073565,0.0006342299,0.012549805,0.00045071368],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04227577,0.00015170996,0.00031847376,0.00095986674,0.0004537653,0.00071028504,0.0004704127,0.00006883236,0.009441528],"category_scores_gemma":[0.013813416,0.00010272705,0.00026382878,0.004166788,0.00006717819,0.00043827953,0.000019926587,0.00032188857,0.00018383902],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031877953,0.00008974557,0.019523783,0.000002302498,0.00042228855,0.00000811473,0.0040179607,0.07032957,0.0001596682,0.0008994016,0.016453918,0.88806134],"study_design_scores_gemma":[0.0015448086,0.0012792561,0.4732085,0.00013095864,0.0031557588,0.000042269363,0.016951598,0.38992432,0.0010521838,0.017841253,0.094408214,0.00046089952],"about_ca_topic_score_codex":0.00025254494,"about_ca_topic_score_gemma":0.08043789,"teacher_disagreement_score":0.8876005,"about_ca_system_score_codex":0.000988707,"about_ca_system_score_gemma":0.010367366,"threshold_uncertainty_score":0.99524295},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"qualitative","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W3138870977","doi":"10.3138/cjpe.69577","title":"Competency-Based Evaluation Education: Four Essential Things to Know and Do","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Queen's University; University of Alberta","funders":"","keywords":"Pace; Lifelong learning; Perspective (graphical); Context (archaeology); Psychology; Knowledge management; Pedagogy; Computer science; Medical education; Medicine","score_opus":0.1726522912841817,"score_gpt":0.5158863399418671,"score_spread":0.34323404865768536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3138870977","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91070044,0.004596017,0.007503259,0.05248715,0.005382741,0.003292026,0.000013955,0.000023096758,0.016001299],"genre_scores_gemma":[0.97141993,0.000011173821,0.026324736,0.001512276,0.00035304305,0.00011908737,0.000031599637,0.0000115379235,0.00021661833],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99401236,0.0010441015,0.000925693,0.00032911,0.0034293197,0.00025944228],"domain_scores_gemma":[0.9866195,0.00025408593,0.00056290824,0.00036159361,0.01148398,0.00071798783],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017445194,0.00014393199,0.00024973377,0.0007667732,0.00031421264,0.0009984743,0.00032929404,0.0000851383,0.005250778],"category_scores_gemma":[0.0058904397,0.00012527473,0.000111484755,0.0011818744,0.00006627875,0.000829813,0.000018684208,0.00019503957,0.00009218212],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013120047,0.000065714856,0.00981653,0.000006657208,0.000017775568,0.000004635895,0.00094621745,0.0032645303,0.00018395785,0.0013297439,0.0072101066,0.977141],"study_design_scores_gemma":[0.0041212244,0.0012099538,0.22613129,0.0005254904,0.00069628493,0.00036834306,0.0075978045,0.33287865,0.0015933291,0.07103066,0.35310367,0.0007432946],"about_ca_topic_score_codex":0.00018378547,"about_ca_topic_score_gemma":0.008656777,"teacher_disagreement_score":0.9763977,"about_ca_system_score_codex":0.00048110346,"about_ca_system_score_gemma":0.04616685,"threshold_uncertainty_score":0.9956586},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W3138951062","doi":"10.3138/cjpe.71277","title":"Why a Special Issue of Practice Notes about How to Teach Evaluation?: Introducing This Special Issue of The <i>Canadian Journal of Program Evaluation</i>","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Special education; Engineering ethics; Medical education; Psychology; Management science; Library science; Computer science; Mathematics education; Medicine; Engineering","score_opus":0.17232126878233858,"score_gpt":0.4894143158310076,"score_spread":0.31709304704866903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3138951062","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4349505,0.0068995506,0.0020358597,0.41360897,0.042807557,0.027062906,0.00027697356,0.000032360986,0.07232531],"genre_scores_gemma":[0.93800545,0.000051522853,0.033974253,0.0029507787,0.023924204,0.00027916854,0.000054164644,0.00006410362,0.0006963618],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9798015,0.0050469376,0.0030420162,0.00052543695,0.010924893,0.0006592428],"domain_scores_gemma":[0.94655645,0.0011415437,0.004621824,0.00094479637,0.04565459,0.0010807859],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06987218,0.00035246808,0.0008631083,0.0016663139,0.0007087049,0.0012307347,0.0014567306,0.00026463543,0.029244103],"category_scores_gemma":[0.087878235,0.00027221988,0.0005200518,0.0035758882,0.00039349162,0.0018159377,0.000058971385,0.000825694,0.00005968627],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006844619,0.00020603937,0.0058324276,0.000021064006,0.00017259551,0.000009130698,0.009290119,0.010762363,0.00024295927,0.00015354065,0.17491527,0.7983261],"study_design_scores_gemma":[0.002572744,0.0013692505,0.030265993,0.00036087196,0.0013234676,0.00025964784,0.006819787,0.01830423,0.0030522447,0.0024805677,0.9328463,0.0003448694],"about_ca_topic_score_codex":0.0050358167,"about_ca_topic_score_gemma":0.34417912,"teacher_disagreement_score":0.7979812,"about_ca_system_score_codex":0.0019008227,"about_ca_system_score_gemma":0.059477583,"threshold_uncertainty_score":0.999973},"labels":[],"label_agreement":null},{"id":"W3139167773","doi":"10.1177/1356389020978501","title":"Developing an ethical rationale for collaborative approaches to evaluation","year":2021,"lang":"en","type":"article","venue":"Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; University of Victoria","funders":"","keywords":"Reflexivity; Dialogic; Reciprocity (cultural anthropology); Inclusion (mineral); Sociology; Engineering ethics; Context (archaeology); Politics; Set (abstract data type); Epistemology; Political science; Computer science; Pedagogy; Social science; Engineering; Law","score_opus":0.8319796326770158,"score_gpt":0.5935660075730588,"score_spread":0.23841362510395703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3139167773","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39298645,0.00021336725,0.49785814,0.088489756,0.0013642856,0.0054619038,0.000051786414,0.00006025925,0.013514049],"genre_scores_gemma":[0.8962305,0.0000042983092,0.09628579,0.0036638852,0.0003477308,0.0019804297,0.0007365388,0.000015261294,0.000735526],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9908017,0.002177653,0.0007442344,0.00070348685,0.0053600417,0.00021289944],"domain_scores_gemma":[0.9890243,0.0012880238,0.00024423926,0.0004926798,0.00882321,0.00012758622],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03849379,0.00014313185,0.00021656291,0.00023321777,0.00041523846,0.00045629634,0.00026152912,0.00017043752,0.0027223597],"category_scores_gemma":[0.01617557,0.00012519157,0.00006461582,0.0015033045,0.000029771461,0.0007276449,0.000055702785,0.00014580127,0.0003018478],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014234944,0.00016497994,0.001168629,0.000012098754,0.000047200963,3.4375728e-7,0.013327864,0.12036316,0.00223159,0.2259679,0.0102342125,0.6263397],"study_design_scores_gemma":[0.0013444033,0.0001508736,0.019606424,0.000017027838,0.00006712306,0.0000022470026,0.007813538,0.7781933,0.006716229,0.16035031,0.025492057,0.00024649446],"about_ca_topic_score_codex":0.0000019457038,"about_ca_topic_score_gemma":0.0003546394,"teacher_disagreement_score":0.6578301,"about_ca_system_score_codex":0.00048005217,"about_ca_system_score_gemma":0.0055643823,"threshold_uncertainty_score":0.9981893},"labels":[],"label_agreement":null},{"id":"W3139265698","doi":"10.35502/jcswb.185","title":"Ten years after: Enduring questions and celebrating answers about situation tables and CSWB","year":2021,"lang":"en","type":"article","venue":"Journal of Community Safety and Well-Being","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Canadian Massage Therapy Aliance","funders":"","keywords":"History; Psychology","score_opus":0.03887467977627935,"score_gpt":0.37193858585244666,"score_spread":0.3330639060761673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3139265698","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9902592,0.000944017,0.0030090623,0.0021342414,0.0001207543,0.000044489763,0.0000019795873,0.0000056949466,0.0034806111],"genre_scores_gemma":[0.9949088,0.0023298669,0.0021298693,0.00037635624,0.00006226086,7.876171e-7,0.0000026582798,0.0000051058137,0.00018430088],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99789786,0.0007508452,0.00061185705,0.000084948624,0.00052976946,0.00012472199],"domain_scores_gemma":[0.99784756,0.0011670953,0.00033502228,0.00019570718,0.00034253494,0.000112090005],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005155882,0.00009040279,0.00022816235,0.00016857941,0.0006525141,0.0003541134,0.00014040532,0.000054887914,0.00014507557],"category_scores_gemma":[0.0006929133,0.00007654087,0.000042490963,0.00023479827,0.00008540285,0.000872008,0.0001609133,0.00049089536,0.000002536588],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002639303,0.00017710499,0.43781278,0.0000968711,0.00012611962,0.000054644606,0.07866127,0.0025167724,0.003739083,0.0056032953,0.00027726887,0.47067088],"study_design_scores_gemma":[0.0007889677,0.00011236677,0.9503084,0.00029561206,0.000048000034,0.00021112824,0.02029187,0.003967924,0.00043974447,0.015349016,0.0080410335,0.00014595884],"about_ca_topic_score_codex":0.00004899633,"about_ca_topic_score_gemma":0.00026151055,"teacher_disagreement_score":0.51249564,"about_ca_system_score_codex":0.000028205082,"about_ca_system_score_gemma":0.00011340103,"threshold_uncertainty_score":0.5018677},"labels":[],"label_agreement":null},{"id":"W3139404955","doi":"10.3138/cjpe.71359","title":"Re-Envisioning Evaluation Pedagogy with a Community of Scholar Teachers","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Pedagogy; Sociology; Psychology","score_opus":0.4830094280355481,"score_gpt":0.5808736776311207,"score_spread":0.09786424959557266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3139404955","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9871038,0.001158081,0.001820396,0.0022656322,0.00047953398,0.000729851,0.000007968247,0.0000065527447,0.0064281635],"genre_scores_gemma":[0.9891923,0.000010037468,0.0104125235,0.00015234012,0.00007789606,0.00003480575,0.000027372822,0.000011714994,0.00008098659],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9892265,0.0048483093,0.0011538008,0.00019542669,0.0043196366,0.0002563244],"domain_scores_gemma":[0.98471016,0.00074576505,0.0011975296,0.00058616936,0.012363056,0.00039735084],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06028845,0.00013626923,0.00032739507,0.0006522639,0.00056799833,0.00039129678,0.0004975359,0.00009949244,0.004504783],"category_scores_gemma":[0.017450782,0.000104354585,0.00012973612,0.0012922498,0.0001604897,0.001100686,0.000023141152,0.00073024706,0.000024415172],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025188745,0.000093227194,0.039268084,0.000008311757,0.00005092723,0.0000059867507,0.0090071745,0.010733493,0.00018535621,0.00011866768,0.00049552927,0.94000804],"study_design_scores_gemma":[0.006494834,0.0036557515,0.62329996,0.0008667283,0.0010888187,0.00025280094,0.141557,0.14814982,0.003413462,0.020270122,0.05032657,0.00062412425],"about_ca_topic_score_codex":0.0008491144,"about_ca_topic_score_gemma":0.059673004,"teacher_disagreement_score":0.9393839,"about_ca_system_score_codex":0.00052431866,"about_ca_system_score_gemma":0.01780586,"threshold_uncertainty_score":0.99640524},"labels":[],"label_agreement":null},{"id":"W3139438442","doi":"10.3138/cjpe.69696","title":"Teaching Africa-Rooted Evaluation: Using a “Model Client” Innovation to Help Shift the Locus of Knowledge Production","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Economic shortage; Space (punctuation); Sociology; Vulnerability (computing); Knowledge management; Pedagogy; Computer science; Public relations; Psychology; Political science","score_opus":0.5584913811322083,"score_gpt":0.5574010113067539,"score_spread":0.001090369825454407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3139438442","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96564645,0.0007533433,0.019718863,0.0077952896,0.001552085,0.0018856776,0.000006020072,0.000009251716,0.002633011],"genre_scores_gemma":[0.99142563,0.0000022940621,0.007729404,0.000115726165,0.000355585,0.000071705836,0.00001699527,0.000013525213,0.0002691236],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9924194,0.0017993109,0.001661536,0.0003398037,0.0034762132,0.00030373601],"domain_scores_gemma":[0.984128,0.00022143142,0.0012278974,0.00052554486,0.013657614,0.00023951032],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.044269573,0.00015952745,0.0002946802,0.0011705606,0.0005057216,0.00032811836,0.0004643265,0.000093017385,0.00059179554],"category_scores_gemma":[0.013003292,0.00011630211,0.00012663784,0.0033498975,0.00008847314,0.0007795881,0.000035524947,0.00034696324,0.000027231064],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027485581,0.00013427665,0.0041642,0.000012215932,0.000047808444,0.0000018651332,0.011361034,0.23516737,0.0019876675,0.0015411525,0.0017742713,0.7437807],"study_design_scores_gemma":[0.0008982946,0.00031489396,0.01797185,0.00019114354,0.00025884452,0.00007208741,0.003988757,0.9421484,0.0013524719,0.021420829,0.01116322,0.00021924537],"about_ca_topic_score_codex":0.00024506837,"about_ca_topic_score_gemma":0.008828208,"teacher_disagreement_score":0.7435614,"about_ca_system_score_codex":0.0008580882,"about_ca_system_score_gemma":0.014076194,"threshold_uncertainty_score":0.9953106},"labels":[],"label_agreement":null},{"id":"W3139526458","doi":"10.3138/cjpe.69797","title":"If Building Trust Is Important, How Do We Teach Novice Evaluators to Do It?","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Focus (optics); Work (physics); Knowledge management; Key (lock); Psychology; Computer science; Engineering ethics; Pedagogy; Engineering","score_opus":0.2393113993722523,"score_gpt":0.5137830673082322,"score_spread":0.2744716679359799,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3139526458","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8829754,0.0040656747,0.0026733717,0.1017481,0.00292013,0.0018008135,0.000041477386,0.000021708194,0.0037533287],"genre_scores_gemma":[0.9840023,0.00009548244,0.012814244,0.0016206332,0.0005583201,0.00007380082,0.000009286539,0.000025052697,0.0008009155],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9916103,0.00089282583,0.0014548397,0.0005230023,0.004957507,0.00056156464],"domain_scores_gemma":[0.98953545,0.00031100985,0.0010398101,0.0006649641,0.007184106,0.0012646625],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02561283,0.00024740346,0.0004396426,0.0011130165,0.00042254006,0.0019871357,0.0007833277,0.0001505018,0.010169667],"category_scores_gemma":[0.0072870827,0.00020590557,0.00027032298,0.0024110759,0.00007077864,0.0010171174,0.000041797666,0.00040642053,0.00016764867],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017067225,0.000054584223,0.04965117,0.0000077986415,0.000061951454,0.00003831617,0.004390271,0.0011191483,0.00030160166,0.00047384834,0.050936747,0.8929475],"study_design_scores_gemma":[0.0016819974,0.0006903505,0.03259426,0.0002856553,0.0002732562,0.00024034578,0.014356154,0.038246553,0.0012521141,0.01136781,0.89852035,0.0004911434],"about_ca_topic_score_codex":0.00016248068,"about_ca_topic_score_gemma":0.005597321,"teacher_disagreement_score":0.89245635,"about_ca_system_score_codex":0.0008633043,"about_ca_system_score_gemma":0.01282772,"threshold_uncertainty_score":0.9990489},"labels":[],"label_agreement":null},{"id":"W3142181500","doi":"10.34577/00004463","title":"Policy Brief: Strengthening the Evaluative Mechanism for Ontario’s Strategic Mandate Agreement (SMA) in the Provincial Post- Secondary Education Sector","year":2019,"lang":"en","type":"article","venue":"Institutional Repositories DataBase (IRDB)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mandate; Mechanism (biology); Political science; SMA*; Public administration; Law; Epistemology; Computer science; Philosophy","score_opus":0.09607524683692178,"score_gpt":0.4149452112272451,"score_spread":0.31886996439032333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3142181500","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9606403,0.000054967615,0.001170762,0.004250615,0.0035487614,0.002252043,0.00065416074,0.000020523508,0.027407851],"genre_scores_gemma":[0.99194705,0.000007115752,0.0010955161,0.0019076876,0.0010509401,0.00045950583,0.00076812203,0.000009455261,0.0027545965],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99525905,0.00040027103,0.00087534316,0.00059035554,0.0025447875,0.00033021646],"domain_scores_gemma":[0.99635327,0.0009303609,0.00045254958,0.00088648533,0.0013004927,0.00007681823],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004927954,0.00024289313,0.00023376902,0.00024494322,0.0008614599,0.00068797654,0.00094452716,0.00007563176,0.00080524856],"category_scores_gemma":[0.00107014,0.00013898738,0.00012420042,0.0005707596,0.00015893824,0.0013353424,0.00017533552,0.00038146327,0.00012810658],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002827465,0.00025653598,0.004347167,0.00002984955,0.000044561337,0.000004589945,0.0064635403,0.00053591747,0.0017598497,0.98019975,0.001310848,0.0047646454],"study_design_scores_gemma":[0.008075774,0.0023493215,0.2376418,0.00064669165,0.0002666991,0.0003951629,0.06589602,0.021184985,0.008199933,0.3357734,0.31767103,0.0018991823],"about_ca_topic_score_codex":0.015038382,"about_ca_topic_score_gemma":0.06298885,"teacher_disagreement_score":0.64442635,"about_ca_system_score_codex":0.0007701407,"about_ca_system_score_gemma":0.01653214,"threshold_uncertainty_score":0.9915206},"labels":[],"label_agreement":null},{"id":"W3144371939","doi":"10.11575/prism/28317","title":"The role of accounting in the delivery of health care to Canada’s Aboriginal population","year":2017,"lang":"en","type":"dissertation","venue":"PRISM (University of Calgary)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Health care delivery; Accounting; Population; Health care; Population health; Geography; Medicine; Business; Environmental health; Economic growth; Economics","score_opus":0.0307896906641963,"score_gpt":0.36765126538033277,"score_spread":0.3368615747161365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3144371939","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9808127,0.0006912392,0.0001641223,0.0007936807,0.00024701777,0.00033384713,0.000003885924,0.0000020281354,0.016951473],"genre_scores_gemma":[0.9980164,0.00011168591,0.0004868494,0.000034891036,0.0000074897,4.7032339e-7,0.00008259801,0.000003420617,0.0012561503],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99760884,0.00019858104,0.00038118425,0.00016893496,0.0015170715,0.0001254116],"domain_scores_gemma":[0.997578,0.00026350943,0.0011766294,0.00043942162,0.0005128402,0.00002956144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020282625,0.00008522317,0.00027848664,0.0001868716,0.0004093418,0.000027666496,0.0010466478,0.00006674364,0.000050235587],"category_scores_gemma":[0.000119816155,0.00006281205,0.000071166265,0.00019368723,0.000031981035,0.00015102499,0.000026662514,0.00014650458,0.0000020170496],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008946576,0.000014735136,0.04371235,0.00004077873,0.000012093841,7.688805e-7,0.020726575,0.000020415118,0.00002288996,0.00092903734,0.00094100693,0.93348986],"study_design_scores_gemma":[0.00016135735,0.000043045915,0.91014606,0.000085409985,0.000015249325,1.4731525e-7,0.040653992,0.0018973231,0.000036363053,0.00038337123,0.046508163,0.00006950267],"about_ca_topic_score_codex":0.7474603,"about_ca_topic_score_gemma":0.85863346,"teacher_disagreement_score":0.93342036,"about_ca_system_score_codex":0.00015499449,"about_ca_system_score_gemma":0.002654321,"threshold_uncertainty_score":0.47086516},"labels":[],"label_agreement":null},{"id":"W3149891919","doi":"10.1038/s41593-021-00836-2","title":"Revising evaluation metrics for graduate admissions and faculty advancement to dismantle privilege","year":2021,"lang":"en","type":"review","venue":"Nature Neuroscience","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":39,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Leonard M. Miller School of Medicine; Graduate School, University of Maryland; U.S. Department of Health and Human Services; National Institutes of Health; National Institute of Mental Health; Institute of Education Sciences; Canadian Institute for Advanced Research; University of Miami; U.S. Department of Education","keywords":"Gatekeeping; Privilege (computing); Inequality; Public relations; Sociology; Ethnic group; Political science; Medical education; Psychology; Engineering ethics; Medicine; Law; Engineering","score_opus":0.7227343083036065,"score_gpt":0.674578412149598,"score_spread":0.048155896154008504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3149891919","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003388584,0.9833563,0.008757095,0.0014702092,0.0027915253,0.0030324773,0.00023744238,0.000028981683,0.00029211337],"genre_scores_gemma":[0.00028475307,0.9911617,0.004695025,0.001757345,0.0001669515,0.00037674958,0.000107741114,0.0000270988,0.001422605],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99161214,0.0005636353,0.0010758064,0.0015539794,0.0047694,0.00042503866],"domain_scores_gemma":[0.9949054,0.0016520337,0.000707835,0.00087558525,0.0014039458,0.00045519462],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0092424685,0.00038980434,0.001094121,0.0007613041,0.0005714527,0.0007499506,0.0010370068,0.00027326006,0.00011989911],"category_scores_gemma":[0.042838704,0.00025540357,0.00030665222,0.0045212097,0.00004956286,0.0005202612,0.0004369695,0.0006788673,0.00002710099],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001570087,0.000029805178,0.0000066159305,0.00028381884,0.0000026216808,0.000001265627,0.00004623802,0.000044843804,0.000008260436,0.0006310136,0.0052148495,0.9937291],"study_design_scores_gemma":[0.00014812927,0.00010447,0.000115652496,0.0017315863,0.00017180895,0.000014935316,0.000041900643,0.003930177,0.000011483453,0.0002610358,0.993176,0.00029282778],"about_ca_topic_score_codex":6.0867035e-7,"about_ca_topic_score_gemma":0.00000438262,"teacher_disagreement_score":0.9934363,"about_ca_system_score_codex":0.00019616655,"about_ca_system_score_gemma":0.0016682507,"threshold_uncertainty_score":0.9999898},"labels":[],"label_agreement":null},{"id":"W3151422448","doi":"","title":"Addressing Cross-National Generalizability in Educational Impact Evaluation","year":2019,"lang":"en","type":"article","venue":"National Bureau of Economic Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Generalizability theory; Variety (cybernetics); External validity; Quarter (Canadian coin); Political science; Cross country; Econometrics; Economics; Public economics; Psychology; Computer science; Demographic economics; Geography; Social psychology; Artificial intelligence","score_opus":0.8585016953890621,"score_gpt":0.7567009036037959,"score_spread":0.10180079178526613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3151422448","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79894793,0.00007247813,0.0000086431,0.0025243752,0.00028659432,0.00054125383,0.000034174052,0.0000035687558,0.19758101],"genre_scores_gemma":[0.99692255,0.000008985286,0.00029669268,0.00007556566,0.00022371377,0.00008961486,0.00017813352,0.00000797157,0.002196781],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9905652,0.0009401473,0.0010965274,0.000564624,0.0065292497,0.00030428806],"domain_scores_gemma":[0.98947173,0.0038654504,0.00029748885,0.00032956104,0.0059454273,0.000090337766],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.051819824,0.00011317472,0.00024130319,0.001283601,0.00012699484,0.0002714675,0.00063575443,0.00011089034,0.03178822],"category_scores_gemma":[0.0064504505,0.00009596155,0.00012802673,0.00073691166,0.00018536206,0.0011067573,0.00011398899,0.00026468688,0.0018722876],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007509723,0.00014539874,0.60419816,0.000007102078,0.00001593861,4.0564085e-8,0.00013419673,0.19923875,0.00059314276,0.18623261,0.0071065403,0.0022530071],"study_design_scores_gemma":[0.0005864287,0.00003340724,0.4276436,0.000008198766,6.6398644e-7,0.0000011192442,0.000042958392,0.16078769,0.00011546181,0.41035515,0.00036601335,0.0000593137],"about_ca_topic_score_codex":0.00027091257,"about_ca_topic_score_gemma":0.0001728328,"teacher_disagreement_score":0.22412254,"about_ca_system_score_codex":0.0025993106,"about_ca_system_score_gemma":0.007701947,"threshold_uncertainty_score":0.9989049},"labels":[],"label_agreement":null},{"id":"W3153721404","doi":"10.22541/au.161793004.43334051/v1","title":"Two sides of the same coin? How quality improvement can be used to augment program evaluation in health professions education to promote social accountability","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of Calgary","funders":"","keywords":"Accountability; Quality (philosophy); Context (archaeology); Field (mathematics); Quality management; Social accounting; Computer science; Inclusion (mineral); Process management; Order (exchange); Knowledge management; Public relations; Management science; Political science; Business; Engineering; Psychology; Operations management","score_opus":0.44192105680221294,"score_gpt":0.6210480155932376,"score_spread":0.1791269587910247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3153721404","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8158592,0.00001876851,0.0004259495,0.16660999,0.0014013156,0.015259905,0.000072654126,0.000030904324,0.00032131618],"genre_scores_gemma":[0.9826709,0.0000038600324,0.0062635075,0.0036119756,0.00011634493,0.006384227,0.00013551854,0.000014978342,0.0007987011],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98653656,0.0032612314,0.00222485,0.001238149,0.0062877033,0.0004514774],"domain_scores_gemma":[0.9933266,0.00033503372,0.0014447212,0.0016079732,0.003053003,0.00023265935],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.034181587,0.00033723243,0.0007724185,0.0003427107,0.0003507538,0.0005298479,0.00106551,0.00017348968,0.00087081897],"category_scores_gemma":[0.0029687732,0.00022112935,0.00024546921,0.00146526,0.00007406858,0.00022267182,0.0014484244,0.0005360112,0.0000065566214],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000622524,0.002718017,0.04685764,0.0003095599,0.00003816806,4.1188045e-8,0.05866741,0.0027465639,0.0020597149,0.0006603484,0.0018931426,0.8839871],"study_design_scores_gemma":[0.0010058815,0.0004095388,0.90556127,0.0006058117,0.000038769496,2.4612862e-7,0.07235165,0.005845911,0.004139389,0.006584908,0.0029713106,0.00048534432],"about_ca_topic_score_codex":0.011595235,"about_ca_topic_score_gemma":0.17857748,"teacher_disagreement_score":0.88350177,"about_ca_system_score_codex":0.002581381,"about_ca_system_score_gemma":0.015733916,"threshold_uncertainty_score":0.99498665},"labels":[],"label_agreement":null},{"id":"W3154034046","doi":"10.1177/1035719x211008263","title":"Thinking with complexity in evaluation: A case study review","year":2021,"lang":"en","type":"article","venue":"Evaluation Journal of Australasia","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact","funders":"","keywords":"Context (archaeology); Management science; Social complexity; Computer science; Complexity management; Exploratory research; Knowledge management; Sociology; Social science; Engineering; Management","score_opus":0.5494958181463374,"score_gpt":0.5867373010000473,"score_spread":0.03724148285370987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3154034046","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.986816,0.0023626813,0.00044425696,0.006238922,0.0003958947,0.0010740968,0.0000016689064,0.0000056724425,0.0026607893],"genre_scores_gemma":[0.99647003,0.00012872653,0.0025820786,0.0005141794,0.000114066104,0.000029474224,0.0000045269217,0.000008114734,0.00014878133],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9838009,0.0038527367,0.0019411156,0.0003379382,0.009859649,0.00020766737],"domain_scores_gemma":[0.98900443,0.0005260991,0.0012371781,0.00052397145,0.008572862,0.00013545254],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.07097194,0.0001652614,0.00052028015,0.000373412,0.00016852785,0.00027866373,0.00041409294,0.000044165485,0.013533339],"category_scores_gemma":[0.004135991,0.0001121453,0.00012035682,0.0018157378,0.00005778907,0.0010034977,0.000053949545,0.0003892168,0.000058722962],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019653211,0.0024703469,0.56338626,0.0001319776,0.00030185122,0.0061930716,0.01717302,0.039237913,0.00008147398,0.00054752885,0.014206309,0.35607368],"study_design_scores_gemma":[0.016470566,0.0023773268,0.7433393,0.0030463333,0.0015919012,0.039998394,0.08924558,0.07460197,0.00019332535,0.024561448,0.0038879823,0.0006858894],"about_ca_topic_score_codex":0.000014059578,"about_ca_topic_score_gemma":0.00092943787,"teacher_disagreement_score":0.3553878,"about_ca_system_score_codex":0.00031594088,"about_ca_system_score_gemma":0.0030742483,"threshold_uncertainty_score":0.9873684},"labels":[],"label_agreement":null},{"id":"W3154316024","doi":"10.1016/j.ebr.2021.100448","title":"Thank you to our Reviewers!","year":2021,"lang":"en","type":"article","venue":"Epilepsy & Behavior Reports","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Art history; Art; Theology; Humanities; Philosophy","score_opus":0.21754894189739987,"score_gpt":0.5190839847129013,"score_spread":0.3015350428155014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3154316024","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9669145,0.0004571867,0.0004825283,0.0053717215,0.0047129923,0.0006008143,0.000009681765,0.000082196806,0.021368401],"genre_scores_gemma":[0.95823723,0.000065509594,0.002784175,0.0017980187,0.0002499958,0.00017732859,0.000026620964,0.000018947385,0.036642186],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99447495,0.00023697592,0.0013846315,0.0008382261,0.0027266024,0.0003386246],"domain_scores_gemma":[0.9962779,0.00008316291,0.00046942715,0.0017097204,0.0011378534,0.00032192818],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0054493165,0.0001913045,0.0004274683,0.00018002998,0.00018478194,0.00030433526,0.00031162874,0.00006455733,0.0067463852],"category_scores_gemma":[0.0022351725,0.00014980389,0.00024805387,0.001100008,0.000016222386,0.00035441093,0.00020771613,0.00018153293,0.002192898],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000056170957,0.00017537278,0.76271087,0.000004057845,0.0000062337313,0.0018103009,0.00032034906,0.000030255796,0.0014750671,0.00011301637,0.07671498,0.1566339],"study_design_scores_gemma":[0.0000979868,0.000048232243,0.51277584,0.000038683615,0.000045299807,0.00059832266,0.00087643875,0.00001031012,0.0028302793,0.00038246965,0.48208237,0.00021379991],"about_ca_topic_score_codex":0.000023950328,"about_ca_topic_score_gemma":0.000075698445,"teacher_disagreement_score":0.40536737,"about_ca_system_score_codex":0.000082913226,"about_ca_system_score_gemma":0.00050097343,"threshold_uncertainty_score":0.99858403},"labels":[],"label_agreement":null},{"id":"W31557020","doi":"10.1021/acs.jmedchem.9b00876","title":"Bridging the gap between research and policy making in the Palestinian Territories : a stakeholders' analysis","year":2009,"lang":"en","type":"book","venue":"Journal of Medicinal Chemistry","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Friedrich-Ebert-Stiftung; Deutsche Forschungsgemeinschaft; Islamic Development Bank; Natural Sciences and Engineering Research Council of Canada; European Commission; United Nations Development Programme","keywords":"Bridging (networking); Political science; Regional science; Geography; Computer science; Computer security","score_opus":0.497259121886904,"score_gpt":0.5600538888404673,"score_spread":0.06279476695356323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W31557020","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21953106,0.008058016,0.00069426815,0.1467634,0.00037840992,0.0006725082,0.00006569403,0.000016086662,0.62382054],"genre_scores_gemma":[0.9507062,0.000287081,0.00007818889,0.00058629445,0.0071871835,0.000003025702,0.000011665307,0.00001103455,0.041129354],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99178374,0.00040778812,0.0012813067,0.00025397676,0.0059646284,0.00030853288],"domain_scores_gemma":[0.9940968,0.0033420878,0.0011211026,0.00050451193,0.00082013983,0.000115325245],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.029446729,0.00019014899,0.0006239979,0.000746453,0.00027428128,0.00039073091,0.0014214461,0.0001828091,0.00017397357],"category_scores_gemma":[0.0033707714,0.000090612935,0.00018835958,0.0013980223,0.0004331614,0.00015254132,0.00009042848,0.0021285696,0.0000026278587],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032431778,0.00019625528,0.16149405,0.00035055372,0.0014123317,0.0008591663,0.04283969,0.00037627673,0.00028040088,0.0006597005,0.2253338,0.56587344],"study_design_scores_gemma":[0.002209788,0.00089968997,0.33061877,0.00343697,0.0017597737,0.0010883034,0.040413223,0.0011458603,0.00017177619,0.084151365,0.53341144,0.00069304375],"about_ca_topic_score_codex":0.000030144678,"about_ca_topic_score_gemma":0.000067963425,"teacher_disagreement_score":0.7311751,"about_ca_system_score_codex":0.00029160187,"about_ca_system_score_gemma":0.0020943114,"threshold_uncertainty_score":0.9993888},"labels":[],"label_agreement":null},{"id":"W3157385886","doi":"10.23977/aetp.2021.52002","title":"Comprehensive Analysis of the Health and Sustainability of National Higher Education","year":2021,"lang":"en","type":"article","venue":"Advances in Educational Technology and Psychology","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mainstream; Sustainability; Higher education; Economic growth; Political science; Sustainable development; Construct (python library); Politics; Economics; Computer science","score_opus":0.0855642499749332,"score_gpt":0.5614602043515552,"score_spread":0.475895954376622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3157385886","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8601454,0.016119996,0.00019793242,0.119452104,0.0005802138,0.0001323858,0.000013911548,0.0000037673892,0.0033542917],"genre_scores_gemma":[0.99580675,0.0008843478,0.0007397198,0.001986779,0.0000124081125,0.000024216582,0.000011962798,0.0000013985358,0.00053239946],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99868447,0.00020226435,0.0004626086,0.00026799197,0.00029883638,0.00008380669],"domain_scores_gemma":[0.99761844,0.00065377925,0.00031028775,0.00026879658,0.0011250969,0.000023626757],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006393473,0.00005621142,0.00022750815,0.0007216715,0.00006454268,0.0000046828213,0.00017643237,0.00007499863,0.0003231853],"category_scores_gemma":[0.00067138707,0.000041496543,0.000033840406,0.003111631,0.00052954914,0.00012866083,0.000058617763,0.000109216904,7.008648e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010019784,0.00015600311,0.5949438,0.000011413497,0.000021743681,1.9154626e-8,0.00017999786,0.00009450914,0.000018806908,0.38555205,0.00022301181,0.018788608],"study_design_scores_gemma":[0.00008451183,0.00002252454,0.53853595,0.0000039902834,0.000005635644,0.000003058237,0.0009041512,0.000030357043,0.000012910525,0.43643656,0.02393911,0.00002124128],"about_ca_topic_score_codex":0.00000558883,"about_ca_topic_score_gemma":0.00006928307,"teacher_disagreement_score":0.13566138,"about_ca_system_score_codex":0.000041092586,"about_ca_system_score_gemma":0.0012972062,"threshold_uncertainty_score":0.35386524},"labels":[],"label_agreement":null},{"id":"W3158309514","doi":"10.1590/1984-92302021v28n9609en","title":"The Governance of Public Policy Evaluation Systems: Policy Effectiveness and Accountability","year":2021,"lang":"en","type":"article","venue":"Organizações & Sociedade","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Accountability; Corporate governance; Public administration; Legislature; Government (linguistics); Process (computing); Business; Public policy; Political science; Finance","score_opus":0.11522071643992113,"score_gpt":0.4695267025062341,"score_spread":0.3543059860663129,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3158309514","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9833493,0.0037525382,0.0004186786,0.008492929,0.00036626597,0.00043163527,0.000031246836,0.00002511108,0.0031322753],"genre_scores_gemma":[0.9981708,0.0008084566,0.00004411712,0.00020512269,0.00023193881,0.000032963457,0.000006071175,0.000013071892,0.00048744024],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99457854,0.0016849812,0.00060321926,0.0004129815,0.0024336409,0.00028666577],"domain_scores_gemma":[0.9935729,0.0025685926,0.00043252623,0.0007500284,0.0025782508,0.00009769295],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013908241,0.00014144093,0.00028532417,0.00006675143,0.00048339012,0.00057942787,0.0004741744,0.000092704846,0.00035676992],"category_scores_gemma":[0.0160757,0.00009206719,0.00007317428,0.0022777552,0.00022457325,0.000543233,0.0002408145,0.00013538514,0.000077847944],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033411787,0.00026759354,0.37542668,0.00014480045,0.00016003347,0.0000011565664,0.006494058,0.00043470008,0.014920735,0.19924115,0.002913742,0.39996195],"study_design_scores_gemma":[0.0007122502,0.000041439078,0.9536905,0.000031179232,0.000027316311,0.000014177827,0.00855309,0.0033828972,0.00421877,0.013823523,0.015341355,0.00016349886],"about_ca_topic_score_codex":0.00023102915,"about_ca_topic_score_gemma":0.00018702968,"teacher_disagreement_score":0.5782638,"about_ca_system_score_codex":0.00044137108,"about_ca_system_score_gemma":0.0036543317,"threshold_uncertainty_score":0.9922123},"labels":[],"label_agreement":null},{"id":"W3160199724","doi":"10.7202/1077006ar","title":"Réflexion portant sur une expérience d’adaptation d’un programme en gestion de l’éducation en contexte autochtone offert en ligne","year":2021,"lang":"fr","type":"article","venue":"Éducation et francophonie","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec en Abitibi-Témiscamingue","funders":"","keywords":"Humanities; Political science; Sociology; Art","score_opus":0.10666351377325828,"score_gpt":0.4198804761957247,"score_spread":0.31321696242246644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3160199724","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7136116,0.003868005,0.109451115,0.14823034,0.016539572,0.0015842385,0.00006296715,0.00022321656,0.006428955],"genre_scores_gemma":[0.95777905,0.0021694181,0.010752739,0.0024891612,0.00083552743,0.00047158526,0.0005302772,0.00006220117,0.024910064],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98941964,0.004085672,0.0018688972,0.0012818065,0.0024614206,0.0008825604],"domain_scores_gemma":[0.99120164,0.0036663674,0.0010439198,0.001132975,0.0025065902,0.00044851677],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0140489545,0.00054144644,0.0006206877,0.0003836986,0.0005659383,0.000694822,0.0006593826,0.000664696,0.006257124],"category_scores_gemma":[0.008108661,0.0005609766,0.00025788497,0.0029101693,0.00020793616,0.0024099539,0.0001289063,0.0008199992,0.0018412172],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013141878,0.0019512913,0.0029501212,0.00015925572,0.00009746141,0.000030565756,0.27944162,0.0117408065,0.011535805,0.015256806,0.008057813,0.668647],"study_design_scores_gemma":[0.0033160895,0.000725651,0.34881258,0.0009412897,0.00023961453,0.00033547997,0.09830504,0.24779515,0.0178826,0.03612212,0.24408965,0.0014347188],"about_ca_topic_score_codex":0.0033104515,"about_ca_topic_score_gemma":0.0032893273,"teacher_disagreement_score":0.6672123,"about_ca_system_score_codex":0.0025493673,"about_ca_system_score_gemma":0.01227205,"threshold_uncertainty_score":0.99968415},"labels":[],"label_agreement":null},{"id":"W3164606496","doi":"10.21203/rs.3.rs-386476/v1","title":"Putting the Meaning Into Meaningful Change Research","year":2021,"lang":"en","type":"preprint","venue":"Research Square","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Roche (Canada)","funders":"","keywords":"Meaning (existential); Epistemology; Psychology; Sociology; Philosophy","score_opus":0.7793072584283701,"score_gpt":0.6738752692096676,"score_spread":0.10543198921870256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3164606496","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6549042,0.011173412,0.0013410527,0.12898804,0.004246425,0.008526592,0.000058015103,0.00031837358,0.19044393],"genre_scores_gemma":[0.9890269,0.00082435244,0.0027411554,0.00026373024,0.0018646911,0.0011986382,0.00006959158,0.00005731495,0.0039535966],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9567061,0.013420377,0.0012904347,0.001907776,0.024994146,0.001681129],"domain_scores_gemma":[0.9710875,0.012298939,0.00031729022,0.0034553478,0.012464578,0.00037633523],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.15814051,0.0003387291,0.0005864506,0.0018531345,0.0030707389,0.0054588034,0.004637877,0.00045486915,0.0051699122],"category_scores_gemma":[0.030878907,0.00021334029,0.00034229664,0.0048174085,0.00066861423,0.000649401,0.010836893,0.0068212147,0.0017864916],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006819858,0.00031242703,0.033581957,0.0007318326,0.0001583747,0.00018606336,0.15207353,0.0014548233,0.00091397803,0.02122637,0.04527878,0.74401367],"study_design_scores_gemma":[0.0008404857,0.0005637037,0.077712454,0.0040803207,0.000026710786,0.000024430461,0.21939199,0.079605006,0.0015955942,0.344624,0.27062482,0.0009105018],"about_ca_topic_score_codex":0.0017092037,"about_ca_topic_score_gemma":0.0028157497,"teacher_disagreement_score":0.74310315,"about_ca_system_score_codex":0.0008196224,"about_ca_system_score_gemma":0.002915333,"threshold_uncertainty_score":0.9989907},"labels":[],"label_agreement":null},{"id":"W3169303212","doi":"10.2139/ssrn.3480708","title":"A Journal-Based Replication of 'Being Chosen to Lead'","year":2019,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of British Columbia Hospital","funders":"","keywords":"Replication (statistics); Lead (geology); Computer science; Biology; Virology; Paleontology","score_opus":0.06797222546404733,"score_gpt":0.44936458266663987,"score_spread":0.38139235720259257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3169303212","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94369113,0.00019777394,0.040942207,0.009469995,0.00039774174,0.00020693007,7.0762843e-7,0.00000985317,0.005083646],"genre_scores_gemma":[0.99282664,0.0001751245,0.0006702686,0.0005285671,0.00020255671,0.0000029518228,9.10424e-7,0.000010465831,0.0055824965],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9959862,0.00023039502,0.0008224856,0.00026706723,0.0017471975,0.00094665715],"domain_scores_gemma":[0.99757683,0.0002573826,0.00064164976,0.00060191104,0.00080227986,0.00011994574],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020691719,0.00010461888,0.00023241462,0.00046939077,0.00016853318,0.00018423596,0.00072628673,0.000049441773,0.0007699045],"category_scores_gemma":[0.001024611,0.00007489644,0.00015163164,0.0006917725,0.000017673998,0.00041116064,0.000032536132,0.0009531095,0.0006552531],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030017414,0.00014041671,0.11961387,0.000008164853,0.00011840197,0.0000016940597,0.0014658554,0.011005003,0.027706804,0.07013228,0.002423595,0.76708376],"study_design_scores_gemma":[0.004297064,0.0036233645,0.054753866,0.00018838744,0.000068782785,0.00080407085,0.011336159,0.02399515,0.012114775,0.77497536,0.113170914,0.0006721011],"about_ca_topic_score_codex":0.000009573746,"about_ca_topic_score_gemma":0.00010306335,"teacher_disagreement_score":0.76641166,"about_ca_system_score_codex":0.00060863374,"about_ca_system_score_gemma":0.0041042254,"threshold_uncertainty_score":0.8429915},"labels":[],"label_agreement":null},{"id":"W3171468312","doi":"10.1108/dpm-02-2021-0034","title":"Graduate certificate in local development planning, land use management and disaster risk management: a knowledge, attitude and practice (KAP) evaluation","year":2021,"lang":"en","type":"article","venue":"Disaster Prevention and Management An International Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Certificate; Medical education; Intervention (counseling); Medicine; Index (typography); Composite index; Control (management); Emergency management; Psychology; Family medicine; Computer science; Business; Nursing; Political science; Composite indicator","score_opus":0.3897397605536501,"score_gpt":0.5185664070418124,"score_spread":0.12882664648816233,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3171468312","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89839816,0.0007687475,0.07148776,0.0014672346,0.0011086813,0.00090752036,0.0000083721525,0.00002734882,0.025826154],"genre_scores_gemma":[0.97224253,0.0037188244,0.013886836,0.00042098845,0.00010375355,0.00009521383,0.000092979964,0.000018405402,0.009420452],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99546325,0.0009233214,0.0008895049,0.0006406159,0.001832974,0.00025035936],"domain_scores_gemma":[0.9984424,0.00017470545,0.00043365546,0.00026308213,0.00051434763,0.00017182351],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0059226607,0.00022666054,0.0002064213,0.0006463732,0.00026984906,0.001794703,0.00030455552,0.00004764267,0.00030373357],"category_scores_gemma":[0.00011729757,0.00019444873,0.000053729746,0.00027438637,0.000083768755,0.002455345,0.00054492767,0.0002070658,0.00003836089],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029291224,0.00048257218,0.09072548,0.000055578705,0.0005676013,0.00016518253,0.0063063134,0.00060543395,0.0000027159942,0.0048446585,0.0006466906,0.89530486],"study_design_scores_gemma":[0.0040032705,0.00007217395,0.8569884,0.00034553272,0.00024818364,0.00017869464,0.016506959,0.016694577,0.000007712324,0.008055051,0.09657616,0.0003233173],"about_ca_topic_score_codex":0.0000055371806,"about_ca_topic_score_gemma":0.0001718836,"teacher_disagreement_score":0.89498156,"about_ca_system_score_codex":0.00013869909,"about_ca_system_score_gemma":0.00003966292,"threshold_uncertainty_score":0.99924153},"labels":[],"label_agreement":null},{"id":"W3171752674","doi":"","title":"Diversity Goals For Evaluation And Treatment Of American Indians and Alaska Natives","year":2021,"lang":"en","type":"article","venue":"StatPearls","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Diversity (politics); Geography; Cultural diversity; Immigration; Sociology; Anthropology; Archaeology","score_opus":0.23676463605482392,"score_gpt":0.5197630178713586,"score_spread":0.2829983818165347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3171752674","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9972768,0.00020587051,0.00047899963,0.00076167384,0.000054987486,0.0002701403,0.000066915614,0.000004337579,0.00088027207],"genre_scores_gemma":[0.997699,0.00026414165,0.0011710878,0.000070724214,0.000014803886,0.000017059825,0.000007657568,0.0000024744513,0.0007530332],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99871176,0.00014691497,0.00019642363,0.0002156731,0.0006419373,0.00008730498],"domain_scores_gemma":[0.99854565,0.00061247096,0.00015222361,0.00013614654,0.00050192355,0.000051607145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012076504,0.000060502236,0.00017250486,0.00008226626,0.00023264144,0.000042234882,0.00005189516,0.0000144979085,0.0001661508],"category_scores_gemma":[0.0004384527,0.00004503109,0.00003210661,0.00021235371,0.00012177049,0.00016194566,0.00008954465,0.000014517629,0.0000036060728],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004136953,0.000084686915,0.31133467,0.0000049367727,0.000041225245,7.1812167e-7,0.01851131,0.000051720475,0.0003529696,0.00032563193,0.00026941625,0.6689814],"study_design_scores_gemma":[0.0017749236,0.0008174797,0.9656989,0.000007464657,0.00005135852,0.0000015477588,0.015161341,0.0033105477,0.002743973,0.0054344647,0.0049050124,0.00009296771],"about_ca_topic_score_codex":0.000048719317,"about_ca_topic_score_gemma":0.00023093325,"teacher_disagreement_score":0.6688884,"about_ca_system_score_codex":0.000038847604,"about_ca_system_score_gemma":0.00016235997,"threshold_uncertainty_score":0.18363146},"labels":[],"label_agreement":null},{"id":"W3172069524","doi":"10.1007/978-3-030-70213-7_4","title":"The Importance of Monitoring and Evaluation for Decision-Making","year":2021,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Accountability; Monitoring and evaluation; Computer science; Domain (mathematical analysis); Management science; Risk analysis (engineering); Process management; Engineering; Political science; Business","score_opus":0.2659471567226658,"score_gpt":0.5302739217726826,"score_spread":0.26432676505001684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3172069524","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011164605,0.010050528,0.012548901,0.0010631314,0.0026253227,0.0016960974,0.000030133777,0.000021729344,0.9607996],"genre_scores_gemma":[0.42336953,0.0021417837,0.021758638,0.0001760939,0.0006556394,0.00013485058,0.000012938556,0.000049848833,0.55170065],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9960778,0.000038232454,0.0008891475,0.0003719738,0.0025067762,0.00011607704],"domain_scores_gemma":[0.9892773,0.007564704,0.00064592523,0.0005723749,0.0019049702,0.000034710825],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0089515345,0.00014070513,0.00027340528,0.000111838715,0.0002545923,0.00022064138,0.00031493016,0.000113447364,0.0017360712],"category_scores_gemma":[0.0032072014,0.000081182014,0.00012608604,0.00006357232,0.00006574205,0.00015356146,0.00011665727,0.000102620674,0.000013941843],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025463256,0.000003484195,0.0028076165,0.0000068515383,0.000028518501,2.8586936e-7,0.000084030034,0.00011001364,0.000012045998,0.116908535,0.0022362776,0.87777686],"study_design_scores_gemma":[0.0004061108,0.00009248984,0.0072316956,0.0005980519,0.00010428377,0.0000048395304,0.0008356144,0.024075888,0.00012549898,0.7479343,0.21831776,0.00027349975],"about_ca_topic_score_codex":5.2684203e-7,"about_ca_topic_score_gemma":0.00006216979,"teacher_disagreement_score":0.8775034,"about_ca_system_score_codex":0.00005737491,"about_ca_system_score_gemma":0.00039017881,"threshold_uncertainty_score":0.9991765},"labels":[],"label_agreement":null},{"id":"W3172102900","doi":"10.1007/978-3-030-70213-7_5","title":"Making Monitoring and Evaluation a Part of National and Organizational Culture","year":2021,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Professionalization; Certification; Accountability; Politics; Political science; Organizational culture; Field (mathematics); Public relations; Public administration; Engineering ethics; Engineering; Law","score_opus":0.36915723240263854,"score_gpt":0.5139182263985616,"score_spread":0.14476099399592302,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3172102900","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024870073,0.001830872,0.00031860435,0.00047735852,0.00042553924,0.00024858236,0.000032664513,0.000012465928,0.9941669],"genre_scores_gemma":[0.307639,0.0006349486,0.0036067872,0.0001799705,0.00054251,0.000011249992,0.0001115752,0.000021246964,0.6872527],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.995855,0.00004828598,0.0005049854,0.00033500526,0.0031926255,0.00006413528],"domain_scores_gemma":[0.9962102,0.0002652675,0.00033383223,0.00013628136,0.003016326,0.000038103968],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0024558965,0.00013001161,0.00021357984,0.0001684074,0.00010201276,0.00014895486,0.00009828002,0.00013981626,0.013799248],"category_scores_gemma":[0.00063002633,0.0000993747,0.000033291602,0.00009569725,0.000055617656,0.00020450678,0.00010314595,0.00011121359,0.000032953187],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016959244,0.000030336068,0.017843256,0.000054316708,0.0001500886,0.0000017261925,0.001671475,0.0003833967,0.00033358898,0.8865781,0.018677913,0.074258834],"study_design_scores_gemma":[0.0015054232,0.00013632998,0.0332421,0.00084643165,0.00018978334,0.0000668448,0.0017681225,0.0192426,0.00063302706,0.39410013,0.5474399,0.0008293118],"about_ca_topic_score_codex":5.5649457e-7,"about_ca_topic_score_gemma":0.0000065145614,"teacher_disagreement_score":0.528762,"about_ca_system_score_codex":0.000056234574,"about_ca_system_score_gemma":0.00048299594,"threshold_uncertainty_score":0.98710227},"labels":[],"label_agreement":null},{"id":"W3172583397","doi":"10.7202/1078061ar","title":"Jussi Suikkanen and Antti Kauppinen (Eds.), \"Methodology and Moral Philosophy.\"","year":2021,"lang":"en","type":"article","venue":"Philosophy in Review","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Philosophy; Epistemology","score_opus":0.5784302561472483,"score_gpt":0.541505164222878,"score_spread":0.036925091924370324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3172583397","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038726076,0.7291861,0.00013583031,0.16443083,0.0006262029,0.00089629705,0.000034575987,0.000048146198,0.06591594],"genre_scores_gemma":[0.4785044,0.48583478,0.010407706,0.02373297,0.0005666845,0.00011060945,0.000039187056,0.000030959873,0.0007727017],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9960041,0.0012613343,0.00096518366,0.00068399805,0.00081778486,0.00026758751],"domain_scores_gemma":[0.9975513,0.0011162119,0.00025969968,0.00062471296,0.00028545724,0.000162598],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0056133363,0.00022064247,0.00079782674,0.00019726955,0.000104334,0.000098922945,0.0003157362,0.00008815668,0.0014467132],"category_scores_gemma":[0.0021683914,0.00016530321,0.000096406504,0.0008861914,0.00017008434,0.0003891325,0.00025224008,0.00025602442,0.00019624367],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050011953,0.0002459823,0.121878624,0.002781215,0.00006391285,0.00019066854,0.00050478906,0.000019629215,0.00028171786,0.20051433,0.0067996457,0.6666695],"study_design_scores_gemma":[0.0011344315,0.00016570647,0.07225712,0.0023465182,0.00008373091,0.00025464775,0.00005648517,0.00059476215,0.00006833695,0.7665404,0.15599279,0.00050507963],"about_ca_topic_score_codex":0.000010256728,"about_ca_topic_score_gemma":0.000021400441,"teacher_disagreement_score":0.6661644,"about_ca_system_score_codex":0.000023438486,"about_ca_system_score_gemma":0.00015529606,"threshold_uncertainty_score":0.9994661},"labels":[],"label_agreement":null},{"id":"W3173854273","doi":"10.24908/pceea.vi0.14946","title":"COORDINATING THE INSTRUCTION OF FOUR ONLINE COURSES","year":2021,"lang":"en","type":"article","venue":"Proceedings of the Canadian Engineering Education Association (CEEA)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Okanagan University College; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"","keywords":"Schedule; Medical education; Coronavirus disease 2019 (COVID-19); Class (philosophy); Globe; Health science; Mathematics education; Cohort; Pandemic; Psychology; Medicine; Computer science","score_opus":0.0538288889942165,"score_gpt":0.3579356680443232,"score_spread":0.3041067790501067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3173854273","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9692423,0.00007603171,0.00003073249,0.022794144,0.0020320932,0.00019097974,0.00003241759,0.000017532253,0.0055838204],"genre_scores_gemma":[0.99410605,0.000010851555,0.0009263076,0.0003347869,0.00016747382,0.000014028985,0.00000662794,0.000010161083,0.004423693],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9980526,0.00002476423,0.0005123461,0.00016784978,0.0010688794,0.0001735659],"domain_scores_gemma":[0.99550563,0.00027013666,0.0007869031,0.00016246995,0.0031850897,0.000089749075],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0020443255,0.00009205284,0.00016144989,0.00022507017,0.0002190246,0.000146693,0.00043472523,0.000082229984,0.00016728228],"category_scores_gemma":[0.0086918,0.000066133936,0.000098334116,0.0012594926,0.000024902485,0.00030402117,0.00003928426,0.00018262758,0.0000069609314],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000047031986,0.00016845054,0.81780875,0.00013083624,0.00015156061,9.5261534e-8,0.0039510443,0.007492387,0.008215106,0.04677555,0.075841114,0.039460376],"study_design_scores_gemma":[0.0002866037,0.000017478367,0.89374655,0.00012541065,0.000051943647,0.000009340725,0.0059504104,0.01569797,0.007937873,0.002018225,0.073987454,0.00017075808],"about_ca_topic_score_codex":0.0018335977,"about_ca_topic_score_gemma":0.010484104,"teacher_disagreement_score":0.075937755,"about_ca_system_score_codex":0.00078785565,"about_ca_system_score_gemma":0.0018688093,"threshold_uncertainty_score":0.9996584},"labels":[],"label_agreement":null},{"id":"W3175149188","doi":"10.1080/03057925.2021.1941771","title":"Partnerships to support quality education in Haiti: a case study addressing the Sustainable Development Goals","year":2021,"lang":"en","type":"article","venue":"Compare A Journal of Comparative and International Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Institute for Clinical Evaluative Sciences; Brock University; Wilfrid Laurier University","funders":"","keywords":"General partnership; Sustainable development; Context (archaeology); Government (linguistics); Public relations; Political science; Education for sustainable development; Quality (philosophy); Economic growth; Geography","score_opus":0.7372914340276759,"score_gpt":0.6545411349495829,"score_spread":0.08275029907809306,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3175149188","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9879043,0.00041161117,0.00081523805,0.0041959146,0.0008944042,0.00029839855,0.0000011356545,0.000002540637,0.005476452],"genre_scores_gemma":[0.9913244,0.000007259916,0.0009684557,0.00090798724,0.000173083,0.00003976985,0.000009329507,0.0000034751968,0.0065661934],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9966901,0.0007612304,0.0012028532,0.00022304589,0.0009817069,0.00014106357],"domain_scores_gemma":[0.9935191,0.00063120044,0.0006344345,0.00020097224,0.0048857266,0.00012851],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047226488,0.00011742675,0.00029408842,0.00043156504,0.00023170531,0.000537946,0.00035532966,0.000018879595,0.0005267811],"category_scores_gemma":[0.00090332265,0.00008112159,0.00004902158,0.00058250857,0.00003844344,0.00079037837,0.00010708851,0.00019486071,0.000025456213],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024511723,0.004347747,0.6288091,0.000020965274,0.00013481057,0.00012468504,0.14717862,0.0011809337,0.00012835467,0.012834836,0.062257774,0.14273708],"study_design_scores_gemma":[0.0005235316,0.00013808902,0.33708462,0.0000740393,0.000012953648,0.00068317424,0.5624578,0.00027809216,0.00031965016,0.002940783,0.09536108,0.00012615821],"about_ca_topic_score_codex":0.000062115934,"about_ca_topic_score_gemma":0.001182081,"teacher_disagreement_score":0.4152792,"about_ca_system_score_codex":0.00027381186,"about_ca_system_score_gemma":0.0064616483,"threshold_uncertainty_score":0.9991708},"labels":[],"label_agreement":null},{"id":"W3175834333","doi":"10.4324/9781003021339-9","title":"Interviews and surveys","year":2021,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Energy Regulator; University of Saskatchewan","funders":"Rhodes University; National Research Foundation; Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Arctic Institute of North America","keywords":"Geography; Psychology","score_opus":0.45366326417991065,"score_gpt":0.5128597264294779,"score_spread":0.059196462249567205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3175834333","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005530934,0.00092616136,0.002414663,0.000997287,0.00040548886,0.000091256006,0.00000954925,0.0000141889095,0.9950861],"genre_scores_gemma":[0.0026434502,0.0007535904,0.00034812957,0.00089202053,0.0000774071,0.0000025474856,0.000021368538,0.0000102478125,0.99525124],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976389,0.00016826426,0.0005610398,0.0004015934,0.001142049,0.00008814809],"domain_scores_gemma":[0.9983735,0.0004889434,0.00019091996,0.0005035631,0.00036595843,0.000077097466],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0073919273,0.00015030702,0.00033173308,0.0001548208,0.000052354586,0.00027723715,0.00025944738,0.00012583786,0.11252968],"category_scores_gemma":[0.0001851381,0.000097073724,0.000101094214,0.00004125129,0.00005072102,0.00012761417,0.00021939901,0.0001590656,0.0023052592],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.211698e-7,0.0000046548935,0.0002433439,0.000005349803,0.000018042389,0.0000046758255,0.00012075759,9.2361034e-7,0.0000026570567,0.21843193,0.050488874,0.73067784],"study_design_scores_gemma":[0.000083643594,0.000024423944,0.0012177305,0.00003307862,0.000007353513,0.00000571674,0.00007766498,0.0002338348,0.0000074044924,0.035362497,0.9628123,0.00013436557],"about_ca_topic_score_codex":0.0000070035285,"about_ca_topic_score_gemma":0.00048875075,"teacher_disagreement_score":0.9123234,"about_ca_system_score_codex":0.000019103443,"about_ca_system_score_gemma":0.00014243739,"threshold_uncertainty_score":0.99847156},"labels":[],"label_agreement":null},{"id":"W3177698836","doi":"10.7202/1078492ar","title":"L’approche par compétences dans la programmation pédagogique","year":2021,"lang":"fr","type":"article","venue":"Enjeux et société Approches transdisciplinaires","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Humanities; Political science; Sociology; Philosophy","score_opus":0.12112659921760703,"score_gpt":0.46134995623019703,"score_spread":0.34022335701259,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3177698836","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4633579,0.0156434,0.19355434,0.12192012,0.0038189092,0.0019463241,0.00017668215,0.00051291083,0.19906943],"genre_scores_gemma":[0.9192258,0.0025142194,0.04789473,0.0008078573,0.0005304522,0.00045321265,0.000246982,0.00008278937,0.02824396],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99056673,0.0024841859,0.0016675986,0.0014832695,0.0028178114,0.0009803872],"domain_scores_gemma":[0.9942117,0.0025584828,0.0005651292,0.0010287741,0.0012135878,0.00042236244],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007184363,0.0007149577,0.00090922357,0.00021098653,0.0009725776,0.0014377282,0.0012028828,0.00071996095,0.0024054882],"category_scores_gemma":[0.0010273106,0.0006336139,0.0006904181,0.0017498286,0.0016333107,0.0016199577,0.00029751833,0.0010369538,0.0005306378],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000118697375,0.0019134784,0.0029285548,0.00084383093,0.0003127659,0.00010490313,0.3744369,0.0028748224,0.0027352918,0.13316977,0.0039437427,0.47661725],"study_design_scores_gemma":[0.0031278857,0.00051531283,0.09177966,0.0011591597,0.0004692467,0.00030057543,0.30390057,0.022887295,0.022814443,0.35979554,0.19129199,0.0019583001],"about_ca_topic_score_codex":0.000048035352,"about_ca_topic_score_gemma":0.0013504802,"teacher_disagreement_score":0.47465894,"about_ca_system_score_codex":0.00022898425,"about_ca_system_score_gemma":0.0033652687,"threshold_uncertainty_score":0.9996115},"labels":[],"label_agreement":null},{"id":"W3183879452","doi":"10.1177/10982140211007573","title":"Understanding Evaluation Policy and Organizational Capacity for Evaluation: An Interview Study","year":2021,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Accountability; Context (archaeology); Thematic analysis; Organizational performance; Organizational learning; Capacity building; Conceptual framework; Knowledge management; Management science; Sociology; Psychology; Public relations; Political science; Qualitative research; Computer science; Social science; Economics","score_opus":0.6422351798637937,"score_gpt":0.5788854004605903,"score_spread":0.06334977940320341,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3183879452","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9289254,0.00021879184,0.06434616,0.0037875467,0.0005458596,0.0012783456,0.000012206977,0.000008135012,0.00087753776],"genre_scores_gemma":[0.9942707,0.000030198571,0.0045951298,0.00048678622,0.00046170337,0.00005993485,0.000046733625,0.000016317446,0.000032516156],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9855019,0.0053408956,0.001399178,0.00042684833,0.00713083,0.00020034786],"domain_scores_gemma":[0.98027533,0.0012708709,0.001666459,0.00040592122,0.016198924,0.0001824943],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07109134,0.00017498694,0.00044430798,0.00062928384,0.00032558385,0.00040682437,0.00026237557,0.00004136195,0.002225097],"category_scores_gemma":[0.019001095,0.00014403401,0.000107876156,0.0018955696,0.00013831281,0.0012880213,0.000055840268,0.00015008295,0.000010086316],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013870298,0.00075069687,0.030161984,0.000010130127,0.0002319331,0.0000014179823,0.009007017,0.018402869,0.00082093134,0.005143231,0.0005524355,0.93477863],"study_design_scores_gemma":[0.0076018395,0.0033439617,0.14990686,0.000076334494,0.0011011251,0.00017041886,0.056350306,0.6142021,0.0002460723,0.16563192,0.0010140868,0.0003550002],"about_ca_topic_score_codex":0.00001622955,"about_ca_topic_score_gemma":0.00022119076,"teacher_disagreement_score":0.9344236,"about_ca_system_score_codex":0.0012694029,"about_ca_system_score_gemma":0.0047642333,"threshold_uncertainty_score":0.998687},"labels":[],"label_agreement":null},{"id":"W3184246891","doi":"10.18174/549568","title":"Wageningen Dialogue : Hands-on navigator to explore why, when and how to engage with dialogue in research for more impact in society","year":2021,"lang":"en","type":"report","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact","funders":"","keywords":"Psychology; Sociology","score_opus":0.6981160175261921,"score_gpt":0.603759216783122,"score_spread":0.09435680074307007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3184246891","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9658883,0.00033148925,0.0016537447,0.020132385,0.00049221294,0.0044471426,0.00027547707,0.000039665127,0.0067395857],"genre_scores_gemma":[0.9709815,0.00066232146,0.007969694,0.0020642478,0.00059348077,0.002323922,0.00058231514,0.00010191217,0.014720622],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99057543,0.0007873443,0.0008019125,0.001452542,0.005538296,0.00084445335],"domain_scores_gemma":[0.9928178,0.0033450956,0.00020820992,0.0009936265,0.0021178683,0.000517365],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.029492592,0.00043509292,0.0009934519,0.0010079384,0.0002737994,0.00091192126,0.0007461517,0.00039449765,0.00050994946],"category_scores_gemma":[0.0071650753,0.00027524316,0.00023768254,0.0019384201,0.00011204655,0.00036589644,0.00047645968,0.0010971539,0.00003431271],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004000713,0.00018500925,0.076055944,0.00013241931,0.00009809987,0.0000771724,0.044745393,0.0008180907,0.00018851318,0.00004611615,0.8312861,0.045967087],"study_design_scores_gemma":[0.007166266,0.008360089,0.1997739,0.0030328126,0.000069161506,0.000053975662,0.081572376,0.004940349,0.0018081489,0.002766785,0.68792236,0.0025337655],"about_ca_topic_score_codex":0.0010565082,"about_ca_topic_score_gemma":0.012962125,"teacher_disagreement_score":0.1433637,"about_ca_system_score_codex":0.0009478951,"about_ca_system_score_gemma":0.0041688727,"threshold_uncertainty_score":0.99996996},"labels":[],"label_agreement":null},{"id":"W3185002173","doi":"10.33524/cjar.v21i3.510","title":"Decolonizing Action Research through Two-Eyed Seeing: The Indigenous Quality Assurance Project","year":2021,"lang":"en","type":"article","venue":"The Canadian Journal of Action Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Indigenous; Operationalization; Action research; Traditional knowledge; Quality assurance; Action (physics); Sociology; Participatory action research; Engineering ethics; Political science; Pedagogy; Engineering; Epistemology; Ecology; Anthropology; Operations management","score_opus":0.8864857114242581,"score_gpt":0.7154851070498178,"score_spread":0.1710006043744403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3185002173","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9389037,0.00067051756,0.00036678248,0.046387307,0.0011549091,0.0005189892,0.000008294645,0.0000063423745,0.011983144],"genre_scores_gemma":[0.9928723,0.00027710997,0.00023082599,0.00030963167,0.00057598227,0.00002226849,0.0000019809381,0.000012926236,0.0056969733],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98129314,0.010470851,0.000941617,0.00030294035,0.0061677187,0.00082373933],"domain_scores_gemma":[0.98206836,0.0072582513,0.00045044645,0.00083263725,0.00908754,0.0003027442],"candidate_categories":["metaresearch","sts","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09636966,0.00011162175,0.0002525101,0.00080663513,0.0049117585,0.001737024,0.0014383295,0.00010473821,0.0013228793],"category_scores_gemma":[0.014054795,0.000061800456,0.00015153529,0.004208768,0.000554006,0.0009729386,0.000091613205,0.0025279208,0.00025352754],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009138901,0.00034668652,0.10876383,0.00010714477,0.0005199209,0.0005046982,0.1328733,0.009917669,0.020650746,0.013501966,0.24798915,0.463911],"study_design_scores_gemma":[0.0010151957,0.0004130426,0.20525499,0.00010736361,0.000017316266,0.00052921625,0.09863972,0.0011483936,0.011074501,0.027418569,0.6541636,0.00021810443],"about_ca_topic_score_codex":0.041307632,"about_ca_topic_score_gemma":0.5739088,"teacher_disagreement_score":0.5326011,"about_ca_system_score_codex":0.0014413542,"about_ca_system_score_gemma":0.026123388,"threshold_uncertainty_score":0.99977326},"labels":[],"label_agreement":null},{"id":"W3186334310","doi":"10.1177/15586898211028107","title":"<i>Media Review: 30 Essential Skills for the Qualitative Researcher</i> (2nd ed.)","year":2021,"lang":"en","type":"article","venue":"Journal of Mixed Methods Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; University of Alberta","funders":"","keywords":"Qualitative research; Sociology; Psychology; Mathematics education; Social science","score_opus":0.6305080071023029,"score_gpt":0.7522564133901127,"score_spread":0.12174840628780981,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3186334310","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007291417,0.11302468,0.756183,0.1110391,0.0037244644,0.0015508059,0.00007076113,0.000009489874,0.0071062795],"genre_scores_gemma":[0.009656492,0.14529829,0.8111027,0.002699211,0.0034660737,0.00021525091,0.000014959801,0.000070400354,0.02747662],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9536517,0.033971272,0.0019735782,0.00042942938,0.009276402,0.0006976144],"domain_scores_gemma":[0.77674174,0.19580197,0.0009980536,0.00128533,0.024675632,0.0004972893],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.34245083,0.00013959086,0.00064004003,0.00045678017,0.0005640331,0.0004298051,0.001653174,0.00010094235,0.006840393],"category_scores_gemma":[0.22310592,0.000074626056,0.00047888284,0.002218686,0.00043249386,0.0004563895,0.0003922613,0.0013376672,0.00014877744],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001429839,0.00015634863,0.000026920849,0.00008295831,0.00009506134,0.000016857137,0.004244232,0.000024234765,0.004365292,0.0010692873,0.49359274,0.4961831],"study_design_scores_gemma":[0.0010799966,0.0003966046,0.00091475394,0.0004863136,0.00005056293,0.00006029916,0.029326348,0.0006183225,0.02865326,0.046855927,0.89142376,0.00013384626],"about_ca_topic_score_codex":0.000010760223,"about_ca_topic_score_gemma":0.00002891289,"teacher_disagreement_score":0.49604926,"about_ca_system_score_codex":0.00015589541,"about_ca_system_score_gemma":0.0029895504,"threshold_uncertainty_score":0.9940675},"labels":[],"label_agreement":null},{"id":"W3186957259","doi":"10.1057/s41599-021-00854-2","title":"Conceptualizing the elements of research impact: towards semantic standards","year":2021,"lang":"en","type":"article","venue":"Humanities and Social Sciences Communications","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Golder Associates (Canada); Royal Roads University","funders":"Social Sciences and Humanities Research Council of Canada; Canada Research Chairs; Federation for the Humanities and Social Sciences","keywords":"Accountability; Computer science; Agency (philosophy); Outcome (game theory); Scholarship; Process (computing); Key (lock); Scale (ratio); Focus (optics); Data science; Management science; Knowledge management; Process management; Political science; Sociology; Business; Engineering; Social science; Computer security","score_opus":0.7680403436928166,"score_gpt":0.6533680617342156,"score_spread":0.11467228195860102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3186957259","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71800774,0.0037361614,0.00026304458,0.026430799,0.00020716374,0.00034323992,0.00015313832,0.000024669052,0.25083408],"genre_scores_gemma":[0.9975449,0.0006077397,0.00030827872,0.00039038336,0.000037686674,0.000015343308,0.0000077213235,0.0000024686892,0.0010854958],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.99571294,0.0010883047,0.0004454572,0.00016738405,0.0023742511,0.0002116625],"domain_scores_gemma":[0.99590325,0.0014221963,0.00017213907,0.0005861884,0.0018971068,0.000019106657],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":["sts"],"category_scores_codex":[0.015022068,0.000061278115,0.00015245046,0.00011450092,0.0041747354,0.0006106453,0.001340596,0.000028262144,0.0010476179],"category_scores_gemma":[0.0008765831,0.000037138943,0.000068670335,0.000938638,0.003438456,0.00031181495,0.00077836995,0.0001776188,0.000009543091],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000041265635,0.000076803524,0.012754464,0.000008688855,0.000024773302,3.1787224e-7,0.070756905,0.000018721976,0.00013552044,0.8870331,0.009348268,0.019838333],"study_design_scores_gemma":[0.00034611765,0.00017454111,0.06411811,0.000042649448,0.000018507131,0.0000040190653,0.50191206,0.0056075086,0.00013540554,0.10436958,0.32310995,0.00016153873],"about_ca_topic_score_codex":0.000283833,"about_ca_topic_score_gemma":0.0018156465,"teacher_disagreement_score":0.7826635,"about_ca_system_score_codex":0.000068741254,"about_ca_system_score_gemma":0.0011254274,"threshold_uncertainty_score":0.99986553},"labels":[],"label_agreement":null},{"id":"W3192687436","doi":"10.1097/acm.0000000000004318","title":"Eco-Normalization: Evaluating the Longevity of an Innovation in Context","year":2021,"lang":"en","type":"review","venue":"Academic Medicine","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of Alberta","funders":"","keywords":"Normalization (sociology); Reflexivity; Fidelity; Context (archaeology); Theory of change; Knowledge management; Computer science; Management science; Process management; Sociology; Business; Economics; Social science","score_opus":0.645284918470037,"score_gpt":0.6557072933984428,"score_spread":0.010422374928405809,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3192687436","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014174996,0.99363106,0.0005792423,0.0010740889,0.00067293696,0.0007676425,0.000006649046,0.000010316134,0.0018405396],"genre_scores_gemma":[0.002450924,0.99458295,0.00005261339,0.0009421021,0.00051663566,0.00007817311,0.00023025293,0.00001560963,0.001130725],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.990182,0.0022402217,0.0038989722,0.0005130614,0.0029524546,0.00021328665],"domain_scores_gemma":[0.9923444,0.0032169693,0.0024567638,0.00083662686,0.0010901749,0.000055110453],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.039636977,0.00025506396,0.0016008317,0.00076857244,0.00009409241,0.000023460287,0.0011123016,0.00037693905,0.0033289525],"category_scores_gemma":[0.016141979,0.00013041786,0.00008722504,0.00520764,0.00020348848,0.00038071894,0.00014596626,0.0010403665,0.000053884236],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027065587,0.0000059638014,0.00019940698,0.00038014655,0.000013655985,0.0000010024245,0.0019840994,0.000031033054,0.0000013588395,0.004436769,0.0014989328,0.99144495],"study_design_scores_gemma":[0.00047901095,0.00020083526,0.00021882978,0.010064288,0.00017862718,0.000026992253,0.003508839,0.0038150821,0.000002776981,0.0018821718,0.97944707,0.00017549274],"about_ca_topic_score_codex":0.00003530837,"about_ca_topic_score_gemma":0.000058352107,"teacher_disagreement_score":0.9912694,"about_ca_system_score_codex":0.000118806456,"about_ca_system_score_gemma":0.0012547806,"threshold_uncertainty_score":0.99758214},"labels":[],"label_agreement":null},{"id":"W3192968240","doi":"10.11648/j.cajph.20210704.16","title":"Professionalisation of Program Evaluation in Africa: An Imperative for Effectiveness and Accountability for Public Policy","year":2021,"lang":"en","type":"article","venue":"Central African Journal of Public Health","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Credibility; Accountability; Context (archaeology); Political science; Professionalization; Public relations; Blueprint; Program evaluation; Professional development; Business; Public administration; Medical education; Medicine; Engineering","score_opus":0.4947008381043265,"score_gpt":0.5801040961958369,"score_spread":0.08540325809151039,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3192968240","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9627504,0.00027022327,0.013915829,0.020263195,0.00030704163,0.0023477066,0.000060694994,0.0000055433193,0.00007938221],"genre_scores_gemma":[0.99440956,0.00002919715,0.0049658217,0.00013829573,0.00016229512,0.00024767013,0.0000305666,0.0000071338263,0.000009429755],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9933047,0.003083028,0.0013398562,0.00029840242,0.0014822308,0.0004917809],"domain_scores_gemma":[0.9910306,0.001773286,0.001068063,0.00020719832,0.0055237543,0.00039710413],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04468674,0.000115962415,0.00047195406,0.0004852996,0.00017243429,0.0002165103,0.00024354793,0.000063455846,0.00008070969],"category_scores_gemma":[0.012009143,0.000082519044,0.000108484564,0.001267951,0.00009916307,0.0014990022,0.000034719968,0.00014478625,2.0307874e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015948668,0.0011474589,0.099443875,0.00013172608,0.000029455972,2.2373453e-7,0.012851801,0.00013122335,0.00030479673,0.011189418,0.00018333553,0.8744272],"study_design_scores_gemma":[0.0036361674,0.0019379387,0.91611576,0.0000749762,0.0000128849215,0.000012614883,0.024238339,0.021703014,0.00020785695,0.024016816,0.0079134405,0.00013018436],"about_ca_topic_score_codex":0.000022865068,"about_ca_topic_score_gemma":0.00022948287,"teacher_disagreement_score":0.874297,"about_ca_system_score_codex":0.0007895944,"about_ca_system_score_gemma":0.014323424,"threshold_uncertainty_score":0.9963131},"labels":[],"label_agreement":null},{"id":"W3193724558","doi":"10.1080/14615517.2021.1968264","title":"Book review for impact assessment and project appraisal","year":2021,"lang":"en","type":"article","venue":"Impact Assessment and Project Appraisal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Project appraisal; Impact assessment; Environmental impact assessment; Environmental planning; Political science; Environmental science; Business; Public administration; Law; Finance","score_opus":0.18081582872529664,"score_gpt":0.6164587424993604,"score_spread":0.4356429137740637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3193724558","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4434287,0.3411751,0.05115507,0.049304172,0.008207859,0.024784014,0.0021568332,0.0010425106,0.07874572],"genre_scores_gemma":[0.82101464,0.09190916,0.04826619,0.020193437,0.0024588595,0.0036367942,0.0020027307,0.00036409937,0.0101540955],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99257064,0.0010157932,0.0015332804,0.0013613101,0.0025252057,0.0009937786],"domain_scores_gemma":[0.99181795,0.0049742004,0.0007675573,0.0010415993,0.0010085371,0.000390179],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008168866,0.00074845814,0.0013329748,0.000507472,0.00056948006,0.001452441,0.0005385369,0.00022776885,0.0028127378],"category_scores_gemma":[0.0016291364,0.00050179014,0.0005821497,0.0013580753,0.00020610825,0.0017810105,0.00038489973,0.0005574538,0.000023057299],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019066354,0.00050396007,0.08824608,0.000614227,0.00045017689,0.000025471645,0.00096099847,0.00002493719,0.0006334617,0.0013873372,0.8217948,0.085167855],"study_design_scores_gemma":[0.0040763365,0.002367449,0.22977957,0.00064899406,0.00038290434,0.00031384442,0.0015178815,0.017881142,0.00014076152,0.0005354885,0.7411584,0.001197203],"about_ca_topic_score_codex":0.0001221965,"about_ca_topic_score_gemma":0.000042333628,"teacher_disagreement_score":0.37758592,"about_ca_system_score_codex":0.00028263172,"about_ca_system_score_gemma":0.006688673,"threshold_uncertainty_score":0.9997434},"labels":[],"label_agreement":null},{"id":"W3195637788","doi":"","title":"The Next Generation of Impact Assessment","year":2021,"lang":"en","type":"article","venue":"eYLS (Yale Law School)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Environmental science; Computer science","score_opus":0.2136477971917681,"score_gpt":0.4655096182705991,"score_spread":0.25186182107883104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3195637788","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93611515,0.00079211564,0.0025030111,0.00427238,0.0011189912,0.00021864923,0.000014696234,0.000024424171,0.054940574],"genre_scores_gemma":[0.99220675,0.00013492069,0.0018042919,0.00070526905,0.0002405711,0.000019064415,0.000019190626,0.0000073160777,0.004862624],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9966331,0.0004348806,0.00065976864,0.0002915263,0.0017675323,0.00021315631],"domain_scores_gemma":[0.99731076,0.000637127,0.0002689949,0.00082014553,0.00083355926,0.00012941353],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0038981494,0.000111981484,0.0001972494,0.000045452947,0.00040906845,0.0006726289,0.00042877145,0.000053467156,0.006030681],"category_scores_gemma":[0.000742034,0.000063992535,0.00016471327,0.00052990066,0.00008149403,0.00061274885,0.00010682841,0.00016986807,0.00046816783],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059368747,0.00041823453,0.10929324,0.000014803719,0.00020548853,0.000018149261,0.0007274414,0.01064562,0.1392607,0.44574684,0.13042688,0.16318324],"study_design_scores_gemma":[0.0015929335,0.00037391277,0.2596979,0.000040474566,0.00005088219,0.000027090828,0.00252933,0.09829061,0.043619014,0.030336272,0.56296253,0.00047903846],"about_ca_topic_score_codex":0.00011042197,"about_ca_topic_score_gemma":0.0011837609,"teacher_disagreement_score":0.43253565,"about_ca_system_score_codex":0.000101781385,"about_ca_system_score_gemma":0.0008134247,"threshold_uncertainty_score":0.99487793},"labels":[],"label_agreement":null},{"id":"W3196166069","doi":"10.33774/chemrxiv-2021-7m4tw","title":"Response process validity evidence in chemistry education research","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Process (computing); Cognition; Psychology; Management science; Computer science; Applied psychology; Data science; Engineering; Neuroscience","score_opus":0.7982323329816771,"score_gpt":0.6964298082778361,"score_spread":0.10180252470384099,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196166069","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96800536,0.00038154746,0.0002563233,0.010415444,0.00060934876,0.00045459863,0.0000027262688,0.00002459692,0.019850058],"genre_scores_gemma":[0.97389144,0.00017813854,0.0007605509,0.00027310447,0.00012642938,0.0003234841,0.000017841792,0.000009272641,0.024419714],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9884351,0.003290474,0.0010400892,0.0012022696,0.005683903,0.000348166],"domain_scores_gemma":[0.988593,0.0052399845,0.00026689307,0.0016015444,0.004157294,0.00014130851],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06439434,0.00017579723,0.00032640135,0.00045440087,0.0001360545,0.0010747615,0.0015819208,0.00031179286,0.012605414],"category_scores_gemma":[0.037952002,0.00014162535,0.00009547243,0.0017149455,0.000110910776,0.00053995085,0.0010654689,0.0013017765,0.00032354746],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0036830734,0.0040918803,0.54639524,0.0019783427,0.00005167585,0.00007188646,0.038979996,0.020042412,0.026015535,0.0004613179,0.13259642,0.22563225],"study_design_scores_gemma":[0.0007164823,0.00016680291,0.66903937,0.005915122,0.000021145857,0.000027517404,0.084533006,0.04252534,0.08553249,0.08561985,0.024430351,0.001472538],"about_ca_topic_score_codex":0.00016810629,"about_ca_topic_score_gemma":0.00021225437,"teacher_disagreement_score":0.22415972,"about_ca_system_score_codex":0.0004875115,"about_ca_system_score_gemma":0.018309774,"threshold_uncertainty_score":0.9999622},"labels":[],"label_agreement":null},{"id":"W3196174867","doi":"10.1037/tep0000389","title":"Training practices in routine outcome monitoring among accredited psychology doctoral programs in Canada.","year":2021,"lang":"en","type":"article","venue":"Training and Education in Professional Psychology","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Psychology; Accreditation; Outcome (game theory); Training (meteorology); Medical education; Applied psychology; Clinical psychology; Medicine","score_opus":0.643727520180354,"score_gpt":0.6262306133106151,"score_spread":0.017496906869738815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196174867","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9759076,0.00021420533,0.000013136551,0.011121259,0.0077473903,0.00022480861,0.0000019779889,0.000012740206,0.004756844],"genre_scores_gemma":[0.99533045,0.000039160288,0.0011712561,0.0015542719,0.00024209937,0.00015144476,0.000033836855,0.000011353243,0.0014661489],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99599296,0.00089088426,0.0012699629,0.000710438,0.0006638962,0.00047188683],"domain_scores_gemma":[0.9978648,0.0008630854,0.0006021717,0.0003298977,0.00020579259,0.00013426921],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0045937556,0.00017578114,0.00041190838,0.0005592953,0.000094355455,0.00006876798,0.00031474163,0.00016844671,0.00041460572],"category_scores_gemma":[0.0018426753,0.00015371895,0.000028602106,0.001338592,0.00008822315,0.00046038107,0.00005537254,0.0007225572,0.00000989821],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041759413,0.00021159799,0.813299,0.0000055464234,0.0000035236696,0.000013418206,0.007889846,0.00004505593,0.00004369908,0.00014543268,0.00046566772,0.17783548],"study_design_scores_gemma":[0.0010753339,0.00003561609,0.9354953,0.00014330212,0.0000026436958,0.000031978216,0.05679315,0.00043598012,0.000003520654,0.0027072893,0.003122289,0.00015356245],"about_ca_topic_score_codex":0.027626762,"about_ca_topic_score_gemma":0.39067104,"teacher_disagreement_score":0.3630443,"about_ca_system_score_codex":0.00021205391,"about_ca_system_score_gemma":0.0052426797,"threshold_uncertainty_score":0.97884834},"labels":[],"label_agreement":null},{"id":"W3197231752","doi":"","title":"Program evaluation with multilevel longitudinal data: evidence from simulation study and cluster randomized controlled trial","year":2021,"lang":"en","type":"dissertation","venue":"Mspace (University of Manitoba)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Multilevel model; Cluster (spacecraft); Randomized controlled trial; Longitudinal data; Computer science; Psychology; Data mining; Data science; Medicine; Machine learning; Internal medicine; Operating system","score_opus":0.26804289610136917,"score_gpt":0.461183278106435,"score_spread":0.19314038200506584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3197231752","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9781811,0.00037441094,0.0035875444,0.0002983383,0.0006687678,0.01643811,0.000032179483,0.000031573214,0.00038798],"genre_scores_gemma":[0.99484795,0.000099919846,0.002681504,0.000009050396,0.00012454328,0.000068997266,0.0009028305,0.000014926022,0.0012502675],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9911735,0.0027477134,0.0006685978,0.0010582929,0.004172904,0.0001789735],"domain_scores_gemma":[0.98832196,0.006310988,0.0016888584,0.001096435,0.0024909726,0.000090788926],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.012992659,0.00030963204,0.0017364512,0.00039146197,0.0003358519,0.00032686946,0.000780639,0.00020059626,0.00027536726],"category_scores_gemma":[0.0044558817,0.00024698404,0.00020145494,0.00040482832,0.00012579569,0.0013822183,0.00020871076,0.00026820297,0.000023828987],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.9415955,0.00072213955,0.013100912,0.000026494343,0.00067604333,0.00001114934,0.0027371019,0.005987868,0.0000061487085,0.0000040229725,0.0002720199,0.03486058],"study_design_scores_gemma":[0.45427752,0.00036756464,0.09255015,0.00016186076,0.0014404291,2.4379946e-7,0.034549072,0.41638723,0.0000011775535,0.000048498776,0.000052398962,0.00016383696],"about_ca_topic_score_codex":0.0016640776,"about_ca_topic_score_gemma":0.3621093,"teacher_disagreement_score":0.48731798,"about_ca_system_score_codex":0.00010788412,"about_ca_system_score_gemma":0.0007650232,"threshold_uncertainty_score":0.9999982},"labels":[],"label_agreement":null},{"id":"W3198636920","doi":"10.36939/ir.202109021534","title":"Indigenous Perspectives in Program Evaluation: A scoping literature review exploring wise practices for program evaluation with Indigenous communities in northern Manitoba","year":2021,"lang":"en","type":"dissertation","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Winnipeg","funders":"","keywords":"Indigenous; Perspective (graphical); Work (physics); Traditional knowledge; Program evaluation; Sociology; Political science; Engineering; Public administration; Ecology; Computer science","score_opus":0.46541215548875514,"score_gpt":0.5650113941539214,"score_spread":0.09959923866516629,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3198636920","genre_codex":"empirical","genre_gemma":"protocol","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76484525,0.18304418,0.00001956843,0.00029051615,0.00051015144,0.046522133,0.000018752007,0.00012445712,0.004624981],"genre_scores_gemma":[0.31417567,0.22299214,0.026397474,0.0006163667,0.0007896387,0.4094644,0.022755105,0.00033020385,0.0024790228],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.98799837,0.0025787456,0.0019497897,0.0010946286,0.0057138465,0.0006645992],"domain_scores_gemma":[0.98607546,0.0013227543,0.00261809,0.0011912077,0.008681653,0.00011082179],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.023087578,0.0006330349,0.001122347,0.0013996785,0.0005172659,0.0017766925,0.0009299725,0.0003357902,0.00061820383],"category_scores_gemma":[0.0036752014,0.00048676896,0.00021349332,0.003491199,0.00006767207,0.0025151074,0.00006735519,0.0009818204,0.000026580467],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019599406,0.0010569061,0.017902253,0.0027153192,0.000078008554,0.000011017533,0.15639675,0.00065447617,0.0000016717962,0.000021679845,0.000026299278,0.8209396],"study_design_scores_gemma":[0.0037002645,0.0019160112,0.05634716,0.091610834,0.0006584633,0.000041915227,0.8261324,0.011999839,0.00004719004,0.0007773653,0.0053696143,0.0013989087],"about_ca_topic_score_codex":0.0010402761,"about_ca_topic_score_gemma":0.6542294,"teacher_disagreement_score":0.81954074,"about_ca_system_score_codex":0.0012032476,"about_ca_system_score_gemma":0.006593289,"threshold_uncertainty_score":0.9997584},"labels":[],"label_agreement":null},{"id":"W3198792435","doi":"","title":"Research evidence, policy and practice: reflections on the Ofsted research review on science","year":2021,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Education and Early Childhood Development","funders":"","keywords":"Science education; Pedagogy; Mathematics education; Sociology; Psychology; Engineering ethics; Engineering","score_opus":0.9494133962179323,"score_gpt":0.8112446833350986,"score_spread":0.13816871288283372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3198792435","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040568253,0.0015848697,0.000025185584,0.40091115,0.00012366005,0.00041887976,9.381638e-7,0.000013539958,0.592865],"genre_scores_gemma":[0.8267299,0.045127064,0.0010056115,0.03547875,0.00034761874,0.00017841975,9.0972003e-7,0.000011372203,0.09112037],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.98117745,0.006326433,0.00047639175,0.00073868356,0.010755915,0.0005251513],"domain_scores_gemma":[0.9267411,0.060751166,0.00011060837,0.0017114317,0.010460339,0.00022531152],"candidate_categories":["metaresearch","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.16220519,0.00008632413,0.00015412984,0.0010583991,0.002592783,0.0011836642,0.000969868,0.00004026478,0.0038388467],"category_scores_gemma":[0.31462857,0.00004369392,0.000039054365,0.017006766,0.0010839101,0.0010006992,0.0004944551,0.0008597043,0.0027072958],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059290876,0.00016165164,0.00008322307,0.00002861248,0.000006294568,0.0000074184773,0.0006471067,0.000017518125,0.002310836,0.7195004,0.22430564,0.05287198],"study_design_scores_gemma":[0.00014355131,0.0006237767,0.006435179,0.0015530239,0.0000057334137,0.000043112494,0.0115059735,0.00074340886,0.0023965605,0.02389031,0.9525374,0.000121960176],"about_ca_topic_score_codex":0.00012255288,"about_ca_topic_score_gemma":0.00015873673,"teacher_disagreement_score":0.8226731,"about_ca_system_score_codex":0.00029912108,"about_ca_system_score_gemma":0.0051582283,"threshold_uncertainty_score":0.9998532},"labels":[],"label_agreement":null},{"id":"W3199335739","doi":"10.5430/ijhe.v11n1p187","title":"An Integrative Multi-Dimensional Model of Culturally Relevant Academic Evaluation for the 21st Century","year":2021,"lang":"en","type":"article","venue":"International Journal of Higher Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Multiculturalism; Curriculum; Context (archaeology); Higher education; Process (computing); Engineering ethics; Sociology; Pedagogy; Psychology; Computer science; Engineering; Political science; Geography","score_opus":0.19197057288869032,"score_gpt":0.5462126032347454,"score_spread":0.35424203034605506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3199335739","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89064497,0.0076084896,0.026865205,0.050183844,0.0212146,0.0009567339,0.00012493812,0.000014912363,0.0023863178],"genre_scores_gemma":[0.9839686,0.00038753872,0.012052268,0.0010108561,0.00060295366,0.000027479635,0.000057331483,0.00000770695,0.0018852487],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956026,0.00027874985,0.0010668928,0.00019865834,0.0027553511,0.00009772793],"domain_scores_gemma":[0.98504657,0.0007743648,0.0012069365,0.00022485488,0.012675849,0.000071424205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037003816,0.00011150917,0.00018272188,0.00021918822,0.00009294301,0.00011683802,0.0007734324,0.000073826304,0.00078317814],"category_scores_gemma":[0.0012457723,0.000062662104,0.00017679099,0.00022721087,0.00006015663,0.0009688016,0.000039552782,0.00024634713,0.0000107326805],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00065525074,0.001885277,0.008063804,0.000011147134,0.00052789896,0.0000012048724,0.01066124,0.25962672,0.11372865,0.08534202,0.021062968,0.4984338],"study_design_scores_gemma":[0.0030898575,0.00029422092,0.11590059,0.0002964022,0.00027093152,0.00009186826,0.016673038,0.7423819,0.017605599,0.062605724,0.040476225,0.00031367195],"about_ca_topic_score_codex":0.0000063802936,"about_ca_topic_score_gemma":0.000012308244,"teacher_disagreement_score":0.49812013,"about_ca_system_score_codex":0.00024449182,"about_ca_system_score_gemma":0.0025895855,"threshold_uncertainty_score":0.8575251},"labels":[],"label_agreement":null},{"id":"W3199446100","doi":"10.2478/jms-2021-0007","title":"Advanced education for NCMs’ professional career development: a conclusive experience?","year":2021,"lang":"en","type":"article","venue":"Journal of Military Studies","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa; Royal Canadian Navy; Royal Military College of Canada","funders":"","keywords":"Career development; Professional development; Medical education; Psychology; Medicine","score_opus":0.24772530422635652,"score_gpt":0.542525370987562,"score_spread":0.2948000667612055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3199446100","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9518939,0.037291154,0.0005870503,0.005390178,0.0040222593,0.00020817036,0.0000055662176,0.0000042947204,0.0005974295],"genre_scores_gemma":[0.9536507,0.0012287819,0.03464669,0.001730631,0.00036707282,0.00008357799,0.000006168954,0.000007495066,0.008278851],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99728024,0.00013686526,0.0009475847,0.00019021242,0.001296029,0.00014904285],"domain_scores_gemma":[0.99305207,0.00090878643,0.00036583393,0.00016182616,0.0054341,0.00007737427],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019338408,0.00010684187,0.00033437624,0.00014438322,0.00034661556,0.000013026101,0.00025743974,0.00003202058,0.00026266128],"category_scores_gemma":[0.0037436723,0.00006890562,0.00012732699,0.00029095256,0.00007518101,0.0005456328,0.00011808831,0.00010500006,0.0000149744965],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005006094,0.00068205275,0.037242927,0.00009837194,0.00050069566,0.000022890757,0.24460016,0.0009010781,0.0025447311,0.0007926512,0.19106767,0.52104616],"study_design_scores_gemma":[0.0013395629,0.00025152834,0.061918583,0.00026636888,0.00003372236,0.00006178882,0.46070433,0.0001670017,0.0052929614,0.00857218,0.46118793,0.00020405816],"about_ca_topic_score_codex":8.500342e-7,"about_ca_topic_score_gemma":0.00006169748,"teacher_disagreement_score":0.52084213,"about_ca_system_score_codex":0.00014806741,"about_ca_system_score_gemma":0.00251578,"threshold_uncertainty_score":0.44817957},"labels":[],"label_agreement":null},{"id":"W3199664501","doi":"10.1016/j.evalprogplan.2021.102008","title":"How and why are Theory of Change and Realist Evaluation used in food security contexts? A scoping review","year":2021,"lang":"en","type":"review","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of Alberta; University of Guelph","funders":"Canadian Institutes of Health Research","keywords":"Theory of change; Food security; Context (archaeology); Management science; Process (computing); Program evaluation; Computer science; Risk analysis (engineering); Psychology; Sociology; Political science; Medicine; Engineering; Agriculture","score_opus":0.7144212184028079,"score_gpt":0.6168606542917522,"score_spread":0.09756056411105574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3199664501","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00066968147,0.9910269,0.0000560941,0.0004886765,0.00014000149,0.0073431325,0.00003508681,0.000020243831,0.00022019567],"genre_scores_gemma":[0.004214345,0.99300903,0.00022760995,0.0002664108,0.00007382627,0.0018753117,0.00029727365,0.000018631354,0.00001757553],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.99008095,0.0050375313,0.0013069329,0.0007999887,0.0025323771,0.00024221501],"domain_scores_gemma":[0.9951,0.001717069,0.0015994082,0.00042364612,0.0010409718,0.00011887339],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.037827116,0.00035323907,0.0017556796,0.0004732506,0.0001530907,0.00054222805,0.00018350556,0.00022693665,0.00020146796],"category_scores_gemma":[0.004929106,0.00026987467,0.00013453947,0.00094064337,0.0001307182,0.0005991163,0.00014106538,0.00031596204,0.0000013584215],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000058069377,0.000035441648,0.00075561664,0.014705662,0.00003554101,0.0000011372709,0.001122366,6.4354197e-7,5.5793947e-8,0.00031803388,0.00010265427,0.9829171],"study_design_scores_gemma":[0.0021708605,0.00062768563,0.0024121879,0.7730983,0.0016933639,0.000065606684,0.002818065,0.009332774,0.0000012173123,0.0057768887,0.20117275,0.0008302855],"about_ca_topic_score_codex":0.0000077510795,"about_ca_topic_score_gemma":0.0001650419,"teacher_disagreement_score":0.9820868,"about_ca_system_score_codex":0.000078217636,"about_ca_system_score_gemma":0.0006145908,"threshold_uncertainty_score":0.9999753},"labels":[],"label_agreement":null},{"id":"W3199732143","doi":"10.5539/jms.v11n2p151","title":"Organizational Leadership Styles and Utilization of Evaluation Results","year":2021,"lang":"en","type":"article","venue":"Journal of Management and Sustainability","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Leadership style; Cronbach's alpha; Psychology; Sample (material); Management styles; Applied psychology; Knowledge management; Public relations; Political science; Social psychology; Computer science; Psychometrics","score_opus":0.26695295349243403,"score_gpt":0.46644883530965264,"score_spread":0.1994958818172186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3199732143","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9799575,0.0010639818,0.0055484506,0.008255567,0.00011837218,0.00025953716,0.0000032705068,0.000003341546,0.0047899433],"genre_scores_gemma":[0.99819565,0.0002459823,0.0006049853,0.000085375286,0.000029068477,0.0000011517897,0.0000051176085,0.0000023477576,0.0008303512],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99703777,0.0004601963,0.0007719583,0.00016534657,0.0014807822,0.00008392639],"domain_scores_gemma":[0.99424946,0.00038048098,0.0004875244,0.00017228012,0.0046609784,0.000049249757],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01131178,0.000061712206,0.00016798552,0.00020103707,0.00007981112,0.00009569659,0.00008630514,0.000033965196,0.00025589488],"category_scores_gemma":[0.0050136396,0.00004620696,0.000035618345,0.0005291554,0.00007825162,0.0003751275,0.00007748445,0.00006620875,6.3003984e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044230907,0.00036439946,0.601099,0.0003834845,0.0001172334,0.000018522936,0.003952983,0.0020360982,0.000029288673,0.06372846,0.002810181,0.32501805],"study_design_scores_gemma":[0.0015634517,0.00012041234,0.79496735,0.000025617906,0.00007965824,0.000013065427,0.04634144,0.009483349,0.0002472114,0.14384721,0.0032408426,0.00007037537],"about_ca_topic_score_codex":0.0000010938157,"about_ca_topic_score_gemma":0.000010283734,"teacher_disagreement_score":0.32494766,"about_ca_system_score_codex":0.00008190267,"about_ca_system_score_gemma":0.00039163893,"threshold_uncertainty_score":0.60021573},"labels":[],"label_agreement":null},{"id":"W3199782640","doi":"10.7202/1079556ar","title":"Changement, incertitude et gestion en éducation","year":2021,"lang":"fr","type":"article","venue":"Éducation et francophonie","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université Laval","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.1610130713677598,"score_gpt":0.4775179100037083,"score_spread":0.31650483863594847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3199782640","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13080876,0.012300879,0.02757531,0.6388271,0.0636531,0.0009969261,0.00011692759,0.00014835307,0.12557265],"genre_scores_gemma":[0.8427297,0.0067750127,0.004738983,0.014289845,0.0013200941,0.00023304333,0.00048385633,0.0000443617,0.12938513],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9933451,0.0024911382,0.0010217888,0.0008590099,0.0018304918,0.00045250656],"domain_scores_gemma":[0.99505204,0.001626148,0.0005259071,0.000977939,0.0015936977,0.0002242918],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00850309,0.00032305936,0.000353453,0.0003371425,0.00032226674,0.0006278232,0.00045447957,0.0002663854,0.03286923],"category_scores_gemma":[0.003380721,0.00033554056,0.00016643429,0.0017344479,0.000105053645,0.0018086188,0.00015840074,0.0005230601,0.010294922],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003488979,0.001768351,0.0053488505,0.0001620708,0.00009985814,0.000010043298,0.06569812,0.005124658,0.0024975701,0.025272915,0.4504003,0.4435824],"study_design_scores_gemma":[0.000789134,0.000095698255,0.15901232,0.0002560567,0.00005270908,0.000026982541,0.006751397,0.006739418,0.002014103,0.011405613,0.8124555,0.00040111013],"about_ca_topic_score_codex":0.0003804968,"about_ca_topic_score_gemma":0.0040023187,"teacher_disagreement_score":0.7119209,"about_ca_system_score_codex":0.0013624443,"about_ca_system_score_gemma":0.0073490953,"threshold_uncertainty_score":0.99990964},"labels":[],"label_agreement":null},{"id":"W3200762504","doi":"10.5897/jpapr.9000023","title":"Evidence of democracy? The relationship between evidence-based policy and democratic government","year":2011,"lang":"en","type":"article","venue":"Journal of Public Administration and Policy Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Democracy; Politics; Scholarship; Pride; Public policy; Government (linguistics); Political science; Evidence-based policy; Representative democracy; Law and economics; Public administration; Economics; Law","score_opus":0.8235959125188197,"score_gpt":0.6189331266991814,"score_spread":0.20466278581963826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3200762504","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82532656,0.0006968448,0.002422034,0.16880219,0.000048293346,0.00027459415,0.000006753259,0.0000037920158,0.0024189167],"genre_scores_gemma":[0.99713326,0.0003642174,0.0007134271,0.00036355417,0.00040878673,0.0000064509304,3.928399e-7,0.0000057643224,0.0010041517],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9920345,0.002124088,0.0012450699,0.00019827898,0.0041026315,0.00029543918],"domain_scores_gemma":[0.97630364,0.020122917,0.00096231484,0.00043839603,0.0017748044,0.00039794383],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.032119036,0.00011023554,0.00025561347,0.00070626446,0.000471026,0.00040420637,0.0006355458,0.0000846967,0.0002448208],"category_scores_gemma":[0.07009803,0.0000646511,0.00007913236,0.0016253977,0.0005308448,0.0016036241,0.00011268559,0.00046957657,0.000011352818],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014293064,0.00006799484,0.88744646,0.000035534977,0.00001990764,0.0000022341956,0.001174523,0.000002255583,0.00014901411,0.07793478,0.001600631,0.03142371],"study_design_scores_gemma":[0.0003344351,0.0012949764,0.932996,0.00023031369,0.000015447906,0.00003604526,0.0013375741,0.00053384865,0.0005898885,0.061358366,0.0012003244,0.000072820294],"about_ca_topic_score_codex":0.00005150225,"about_ca_topic_score_gemma":0.00006782653,"teacher_disagreement_score":0.17180668,"about_ca_system_score_codex":0.00015806043,"about_ca_system_score_gemma":0.0049326997,"threshold_uncertainty_score":0.9966371},"labels":[],"label_agreement":null},{"id":"W3200872215","doi":"10.21203/rs.3.rs-877018/v1","title":"Applying Behaviour Change Models to Policymaking: Development and Validation of the Policymakers’ Information Use Questionnaire (POLIQ)","year":2021,"lang":"en","type":"preprint","venue":"Research Square","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto; McGill University; Autism Canada; McGill University Health Centre","funders":"Employment and Social Development Canada; Kids Brain Health Network; McGill University Health Centre; Centre for Interdisciplinary Research in Rehabilitation; McGill University","keywords":"Cronbach's alpha; Psychology; Confirmatory factor analysis; Construct validity; Face validity; Applied psychology; Social psychology; Structural equation modeling; Statistics; Psychometrics; Clinical psychology; Mathematics","score_opus":0.6207862142986479,"score_gpt":0.5703275214052564,"score_spread":0.050458692893391444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3200872215","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9888451,0.00009313126,0.003732047,0.0032415797,0.00028340926,0.0031131762,0.00006425086,0.000028210383,0.000599096],"genre_scores_gemma":[0.99578524,0.0000604816,0.0018647034,0.00037904578,0.0001116973,0.0014783664,0.00008418461,0.000013904855,0.00022240177],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9920398,0.0009733727,0.0010117382,0.00046721316,0.0050723064,0.0004355461],"domain_scores_gemma":[0.99460185,0.00039645613,0.00044012506,0.001044547,0.0032977345,0.00021926752],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.008000531,0.00021932724,0.00032998456,0.0012035696,0.0005244923,0.0013668333,0.00080220826,0.00024183729,0.000072684896],"category_scores_gemma":[0.0022100592,0.00015777512,0.00010957548,0.001512209,0.000106321386,0.0017765724,0.002453897,0.0006843296,0.00003821644],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010556877,0.00027891487,0.3485258,0.0010686653,0.00009359138,0.000003501715,0.22857611,0.037326157,0.00017220761,0.019017,0.0023563993,0.36247608],"study_design_scores_gemma":[0.0005697686,0.00011430324,0.91647965,0.003287474,0.000026522604,0.000009558437,0.021690844,0.032730825,0.0053120856,0.0057957293,0.013372498,0.0006107328],"about_ca_topic_score_codex":0.002386715,"about_ca_topic_score_gemma":0.0006640263,"teacher_disagreement_score":0.5679539,"about_ca_system_score_codex":0.0004520714,"about_ca_system_score_gemma":0.0018746583,"threshold_uncertainty_score":0.99966985},"labels":[],"label_agreement":null},{"id":"W3201242541","doi":"10.1016/j.evalprogplan.2021.102009","title":"Evaluating the integration of strategic priorities within a complex research-for-development funding program","year":2021,"lang":"en","type":"review","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"International Development Research Centre","keywords":"Theory of change; Participatory evaluation; Sustainability; Citizen journalism; Process (computing); Thematic analysis; Program evaluation; Equity (law); Management science; Process management; Research program; Psychology; Knowledge management; Computer science; Political science; Qualitative research; Sociology; Business; Engineering","score_opus":0.944340246966675,"score_gpt":0.7438204693076491,"score_spread":0.20051977765902584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3201242541","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025793503,0.9837209,0.00041700192,0.00013399754,0.00048734073,0.009973213,0.000018221595,0.0000898727,0.00258011],"genre_scores_gemma":[0.01063378,0.75965387,0.19910115,0.000096323165,0.0008796401,0.024120705,0.003070689,0.0001518604,0.0022919811],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9855318,0.004680686,0.0025622775,0.0008990553,0.005810554,0.0005156332],"domain_scores_gemma":[0.9886872,0.0050637093,0.0015933313,0.00062620506,0.003910693,0.000118849486],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.08439547,0.00040151947,0.0012388465,0.00070453726,0.0011099383,0.0015426627,0.0006619326,0.00025184613,0.00036319578],"category_scores_gemma":[0.005522982,0.0002414858,0.00027415252,0.0018663065,0.00028872048,0.00031402017,0.000211588,0.000702963,0.00001676163],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013801252,0.00007628608,0.000027387883,0.00097144186,0.00008655774,3.9767895e-7,0.0035502384,0.00021602296,0.0000032867706,0.002926663,0.00020797356,0.99191993],"study_design_scores_gemma":[0.00060061365,0.0011753676,0.00016566471,0.01225027,0.0004188421,0.000019844805,0.012961232,0.18703377,0.0000067906763,0.0036535987,0.78129,0.00042400273],"about_ca_topic_score_codex":0.000011221218,"about_ca_topic_score_gemma":0.000048906797,"teacher_disagreement_score":0.99149597,"about_ca_system_score_codex":0.00025942226,"about_ca_system_score_gemma":0.0044352068,"threshold_uncertainty_score":0.99949384},"labels":[{"model":"gpt","categories":["metaresearch"],"domain":"incentives","study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"},{"model":"opus","categories":["metaresearch"],"domain":"incentives","study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W3201592111","doi":"","title":"Genuinely working two-way with Indigenous communities utilizing both Indigenous and Western worldviews, knowledges and practices","year":2021,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Indigenous; Sociology; Traditional knowledge; Environmental ethics; Political science; Ecology; Philosophy","score_opus":0.3221365516403933,"score_gpt":0.49129359986565185,"score_spread":0.16915704822525857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3201592111","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97053623,0.007983101,0.0004764646,0.0005320042,0.00013334617,0.0002470412,0.0000027122812,0.000048224174,0.0200409],"genre_scores_gemma":[0.98974264,0.0013804085,0.00322617,0.00074211886,0.00008211868,0.00002051251,0.000008449366,0.000016519116,0.00478107],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9973146,0.00051941973,0.0005150427,0.00036749488,0.0009456433,0.00033785106],"domain_scores_gemma":[0.99686307,0.0015385606,0.00055483234,0.0005330041,0.00037070722,0.00013983177],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003118575,0.00021216326,0.00036339587,0.0002410119,0.00077026326,0.001335593,0.00032500818,0.00005532298,0.0005061457],"category_scores_gemma":[0.00020263731,0.00014212632,0.000030296873,0.0006142134,0.0001722804,0.0008174526,0.0002740853,0.0002780439,0.000054209453],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002750261,0.00007834953,0.7447608,0.000017985998,0.000040576997,0.00001798395,0.05912656,0.000039067705,0.00006329563,0.0001611237,0.000060395985,0.19560632],"study_design_scores_gemma":[0.0019772642,0.0004780802,0.6384297,0.00034268168,0.000115158866,0.0005113085,0.21099254,0.0021985346,0.0008034514,0.0015131136,0.14185487,0.00078330387],"about_ca_topic_score_codex":0.0003521646,"about_ca_topic_score_gemma":0.025068387,"teacher_disagreement_score":0.19482303,"about_ca_system_score_codex":0.000034909623,"about_ca_system_score_gemma":0.00039792527,"threshold_uncertainty_score":0.99970114},"labels":[],"label_agreement":null},{"id":"W3203243032","doi":"10.1186/s13643-021-01821-3","title":"Scoping reviews: reinforcing and advancing the methodology and application","year":2021,"lang":"en","type":"article","venue":"Systematic Reviews","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":834,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital; Queen's University; McMaster University; Impact; Toronto Rehabilitation Institute; Sunnybrook Health Science Centre; Royal College of Physicians and Surgeons of Canada; Institute for Work & Health; Ottawa Hospital; University of Toronto","funders":"Canada Research Chairs; World Health Organization","keywords":"Systematic review; Rigour; Terminology; CLARITY; Medicine; Presentation (obstetrics); Stakeholder; Management science; Consistency (knowledge bases); Process management; MEDLINE; Computer science; Engineering; Public relations","score_opus":0.4738319348272704,"score_gpt":0.5753126436374377,"score_spread":0.10148070881016735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3203243032","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003135967,0.3539882,0.620078,0.0037886323,0.00049480185,0.01284989,7.712685e-7,0.000026324817,0.005637373],"genre_scores_gemma":[0.14923424,0.44367784,0.35324213,0.022738356,0.0009702218,0.015687967,0.000023155702,0.00008980794,0.014336292],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9917234,0.00523393,0.0020348132,0.00034417203,0.00051388843,0.00014977632],"domain_scores_gemma":[0.9934841,0.0043448573,0.0010882937,0.0008179675,0.00020428747,0.000060508275],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.057400912,0.0001272912,0.0010521804,0.00005822624,0.00023626564,0.00019962188,0.00020999783,0.000036243804,0.00010931887],"category_scores_gemma":[0.020695556,0.000057968085,0.0000848458,0.00045027098,0.00004309059,0.000255783,0.00011474918,0.000090863265,0.00022167499],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005365697,0.000018213037,0.0031479714,0.19939879,0.000048957638,0.000002977847,0.008452037,0.0000954654,0.0027832896,0.027447937,0.0057261623,0.7528728],"study_design_scores_gemma":[0.0009814993,0.00014703382,0.0017769728,0.14582257,0.0004964185,0.0008609022,0.013569128,0.05977868,0.0007375722,0.027199648,0.74767846,0.0009511411],"about_ca_topic_score_codex":0.000004165572,"about_ca_topic_score_gemma":0.000055190732,"teacher_disagreement_score":0.7519217,"about_ca_system_score_codex":0.00002343036,"about_ca_system_score_gemma":0.00006986187,"threshold_uncertainty_score":0.98755354},"labels":[],"label_agreement":null},{"id":"W3203262347","doi":"10.1002/ev.20477","title":"A learning agenda for the advocacy evaluation field's future","year":2021,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact","funders":"","keywords":"Field (mathematics); Context (archaeology); Value (mathematics); Set (abstract data type); Political science; Public relations; Engineering ethics; Sociology; Computer science; Engineering","score_opus":0.25942037969970505,"score_gpt":0.5452853487151225,"score_spread":0.2858649690154174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3203262347","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10239966,0.0077450993,0.6805682,0.136775,0.02429066,0.013016364,0.000048213664,0.00033812915,0.034818664],"genre_scores_gemma":[0.93547463,0.00042165848,0.010638191,0.002486283,0.004643876,0.004459319,0.00051284523,0.000049191935,0.041314006],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99535906,0.0006964528,0.0006113049,0.0005176824,0.0025755751,0.0002399354],"domain_scores_gemma":[0.9898591,0.0045217625,0.0003291367,0.00054726814,0.0046718987,0.000070816175],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016003728,0.00014982987,0.00018549108,0.00018687166,0.0012677602,0.00041476937,0.00026758373,0.000113987626,0.005554328],"category_scores_gemma":[0.01832935,0.00010710282,0.0002743444,0.0010305893,0.0000197179,0.00047915222,0.000037762144,0.00017051397,0.0001073433],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048559996,0.00003679707,0.00043244715,0.0000037481054,0.000039840972,3.842633e-8,0.0012352517,0.018360065,0.00032065855,0.0006668158,0.0830245,0.8958313],"study_design_scores_gemma":[0.0016407135,0.00014156605,0.0068341214,0.000009000799,0.00025089007,0.00000393466,0.00379956,0.4461832,0.001436178,0.013257341,0.52633494,0.000108549044],"about_ca_topic_score_codex":0.000034869052,"about_ca_topic_score_gemma":0.0006329285,"teacher_disagreement_score":0.89572275,"about_ca_system_score_codex":0.00022823278,"about_ca_system_score_gemma":0.0025307469,"threshold_uncertainty_score":0.9953547},"labels":[],"label_agreement":null},{"id":"W3203723536","doi":"10.4102/aej.v9i1.553","title":"How to measure monitoring and evaluation system effectiveness?","year":2021,"lang":"en","type":"article","venue":"African Evaluation Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Université du Québec à Montréal","keywords":"Scarcity; Process management; Monitoring and evaluation; Corporate governance; Quality (philosophy); Business; Sample (material); Information system; Knowledge management; Environmental resource management; Management science; Computer science; Engineering; Economics; Economic growth","score_opus":0.27884330159616744,"score_gpt":0.48988338200161946,"score_spread":0.21104008040545202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3203723536","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9631973,0.001134385,0.017904783,0.0077184103,0.0022610917,0.0008366746,0.0000043229147,0.00003160901,0.006911425],"genre_scores_gemma":[0.9971464,0.000015125684,0.0017376888,0.0000497762,0.0006846967,0.00010632576,0.000003374827,0.000012892265,0.00024369973],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98626477,0.0044420734,0.00061537226,0.00048312257,0.007926884,0.00026780445],"domain_scores_gemma":[0.98927253,0.0009387626,0.00042501139,0.0004239788,0.008609683,0.0003300015],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.051722463,0.00016913426,0.00030102764,0.00040837965,0.0005569123,0.00164456,0.00027516566,0.00006907761,0.0005095666],"category_scores_gemma":[0.009632555,0.00013284772,0.00009819537,0.0012506001,0.000030432004,0.00095727836,0.00008071562,0.00023832907,0.00010260736],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007743796,0.000042086875,0.040564105,0.000017856808,0.000082286846,0.000010159143,0.0025840125,0.010213619,0.011510612,0.00068642944,0.0007732966,0.9334381],"study_design_scores_gemma":[0.0039068274,0.00034588634,0.7690413,0.0004500197,0.00042584463,0.0006708677,0.050939027,0.14635748,0.011125263,0.0070571867,0.009151686,0.0005286318],"about_ca_topic_score_codex":0.0000021978751,"about_ca_topic_score_gemma":0.000008143561,"teacher_disagreement_score":0.9329095,"about_ca_system_score_codex":0.0007408819,"about_ca_system_score_gemma":0.0014832636,"threshold_uncertainty_score":0.99939185},"labels":[],"label_agreement":null},{"id":"W3203797720","doi":"10.1002/ev.20478","title":"An introduction to policy advocacy evaluation: The concepts, history, and literature of the field","year":2021,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact","funders":"","keywords":"Field (mathematics); Adaptation (eye); Policy development; Engineering ethics; Management science; Evaluation methods; Computer science; Political science; Public administration; Psychology","score_opus":0.12003077569204998,"score_gpt":0.5220412336486495,"score_spread":0.4020104579565995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3203797720","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38657135,0.0057557183,0.01649167,0.56118995,0.011273864,0.0056260647,0.000038413844,0.00008037855,0.012972602],"genre_scores_gemma":[0.9823692,0.000067471214,0.00159819,0.0032523458,0.0025276393,0.0003723172,0.00006203856,0.000012702308,0.00973811],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99612737,0.0009714849,0.0004700996,0.0004101978,0.0018944457,0.00012638325],"domain_scores_gemma":[0.9946122,0.00080834236,0.00025117016,0.0008498271,0.0033993244,0.00007914507],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0076503833,0.00010723218,0.00014317097,0.00025737032,0.00038443165,0.00016312761,0.0002743523,0.00007397093,0.0019677945],"category_scores_gemma":[0.013627946,0.00006515134,0.000100028024,0.0017048424,0.000052963635,0.00046496626,0.000046976867,0.00011954533,0.0000113371125],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005500391,0.00007916832,0.0010412021,0.0000062784065,0.000025519776,3.3810874e-8,0.009098953,0.006305797,0.0032933508,0.011303944,0.27106616,0.6977246],"study_design_scores_gemma":[0.0011572224,0.00022863958,0.039314326,0.000025219788,0.00016668053,0.000014332527,0.00226073,0.06779349,0.0061487043,0.022240108,0.86051416,0.00013640425],"about_ca_topic_score_codex":0.00007740122,"about_ca_topic_score_gemma":0.0004808959,"teacher_disagreement_score":0.6975882,"about_ca_system_score_codex":0.0003630283,"about_ca_system_score_gemma":0.0027962695,"threshold_uncertainty_score":0.9989445},"labels":[],"label_agreement":null},{"id":"W3204124505","doi":"10.1037/cap0000302","title":"La validation transculturelle d’instruments de mesure en psychologie : Un portrait des pratiques utilisées dans les travaux publiés entre 1989 et 2019.","year":2021,"lang":"fr","type":"article","venue":"Canadian Psychology/Psychologie canadienne","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut du Savoir Montfort; University of Ottawa; Université du Québec en Outaouais","funders":"","keywords":"Humanities; Psychology; Philosophy","score_opus":0.11600163777816895,"score_gpt":0.44903536721730325,"score_spread":0.3330337294391343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3204124505","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70746964,0.00580793,0.0018833311,0.10566629,0.005052112,0.00082501274,0.0016971662,0.00016085898,0.1714377],"genre_scores_gemma":[0.94347256,0.009043049,0.007004141,0.014997796,0.00032107707,0.00017034865,0.00082943763,0.000114739494,0.024046833],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9856496,0.005883182,0.0019111359,0.0025504087,0.00095582264,0.0030498705],"domain_scores_gemma":[0.99233013,0.0009805844,0.0006181059,0.0021345257,0.0011892087,0.002747421],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010690427,0.0010500082,0.0010277849,0.0010611049,0.0010285905,0.0008678668,0.0023529325,0.0022429256,0.023700645],"category_scores_gemma":[0.0024967012,0.001031428,0.0005432,0.0025831743,0.0016249875,0.001403062,0.00008692679,0.0020793653,0.0005040412],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010412634,0.00066793367,0.08243707,0.000055569948,0.00045761093,0.0013234151,0.030843217,0.00014659193,0.0018003414,0.019115519,0.20029378,0.66275483],"study_design_scores_gemma":[0.0022345711,0.00042638677,0.41498667,0.00017515135,0.00017892063,0.00145282,0.017752206,0.00013113653,0.0006087087,0.021128064,0.5399684,0.00095697294],"about_ca_topic_score_codex":0.072876506,"about_ca_topic_score_gemma":0.85575575,"teacher_disagreement_score":0.78287923,"about_ca_system_score_codex":0.0022099381,"about_ca_system_score_gemma":0.008926294,"threshold_uncertainty_score":0.9992136},"labels":[],"label_agreement":null},{"id":"W3204738611","doi":"10.1002/ev.20471","title":"Contribution analysis: A promising method for assessing advocacy's impact","year":2021,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact","funders":"","keywords":"Context (archaeology); Policy analysis; Outcome (game theory); Political science; Public relations; Management science; Public administration; Economics","score_opus":0.24016093895790824,"score_gpt":0.6095421407491777,"score_spread":0.36938120179126943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3204738611","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.059366457,0.00034170324,0.9338968,0.0025913422,0.00077582605,0.0015571958,0.0000421319,0.00007009049,0.0013584786],"genre_scores_gemma":[0.8494359,0.000016447486,0.14572912,0.0002562421,0.00048451117,0.0007995724,0.00085433986,0.000021228187,0.0024025908],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956559,0.00080566993,0.0008594065,0.00064597046,0.0017292602,0.00030377644],"domain_scores_gemma":[0.98983455,0.0025923094,0.0005245784,0.00051565835,0.0063903397,0.0001425436],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017453302,0.00017277052,0.0004162315,0.0006952653,0.0007474457,0.0009706353,0.00017180202,0.00011597277,0.0015171642],"category_scores_gemma":[0.015724326,0.00014396434,0.0006780688,0.003289677,0.000016662572,0.0011123528,0.000026934364,0.00009355635,0.000027413405],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011985172,0.0001849386,0.008311507,0.000008261439,0.0007409541,1.8543366e-7,0.00070979516,0.082318075,0.009030892,0.0011636168,0.0124599105,0.884952],"study_design_scores_gemma":[0.0024917761,0.00009078541,0.06795547,0.000016867394,0.0018378923,0.000005528679,0.0006834483,0.86821884,0.006704398,0.025034849,0.026769836,0.00019032702],"about_ca_topic_score_codex":0.000070714785,"about_ca_topic_score_gemma":0.0004935118,"teacher_disagreement_score":0.8847617,"about_ca_system_score_codex":0.0005745921,"about_ca_system_score_gemma":0.0030782877,"threshold_uncertainty_score":0.9993956},"labels":[],"label_agreement":null},{"id":"W3205038101","doi":"10.3138/cjpe.69949","title":"Evaluation Advisory Groups: Considerations for Design and Management","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Advisory committee; Resource (disambiguation); Scale (ratio); Political science; Computer science; Public administration; Geography","score_opus":0.5679625182669052,"score_gpt":0.5376190604386261,"score_spread":0.030343457828279186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3205038101","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3019251,0.014297578,0.59732836,0.03727256,0.0068354104,0.024816278,0.000059050893,0.000059275757,0.0174064],"genre_scores_gemma":[0.86125714,0.000071513736,0.13733998,0.00045400538,0.0001532918,0.00051619235,0.000020161151,0.000011401406,0.0001763193],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9948416,0.0013195511,0.0008631463,0.00025883215,0.0024920527,0.00022485916],"domain_scores_gemma":[0.98895794,0.00084930577,0.0004868468,0.00025544522,0.009117982,0.00033248763],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.035933033,0.00011236477,0.00020311496,0.00051499123,0.00037391207,0.0006305628,0.00014232438,0.000065119035,0.0021271678],"category_scores_gemma":[0.0074075907,0.000097579956,0.00009672814,0.00045809703,0.00006805038,0.00061143015,0.000011981665,0.00009910088,0.00001868562],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001222341,0.00004494325,0.0008849272,0.000010045488,0.00008611879,0.000007702852,0.0008316045,0.0132241845,0.000048402955,0.0049866773,0.009357181,0.970506],"study_design_scores_gemma":[0.0033571478,0.00056389516,0.029927393,0.00008055454,0.00080955605,0.00015758586,0.0032193777,0.60074145,0.00028187278,0.3216194,0.039009474,0.0002323403],"about_ca_topic_score_codex":0.00002279899,"about_ca_topic_score_gemma":0.0041610417,"teacher_disagreement_score":0.9702737,"about_ca_system_score_codex":0.00037610994,"about_ca_system_score_gemma":0.0066483007,"threshold_uncertainty_score":0.9989831},"labels":[],"label_agreement":null},{"id":"W3205101414","doi":"10.31174/send-pp2021-256ix100-06","title":"An organisational framework of Masters of Education in universities in Canada","year":2021,"lang":"en","type":"article","venue":"Science and Education a New Dimension","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Bachelor; Competence (human resources); Face (sociological concept); Higher education; Asynchronous communication; Medical education; Political science; Sociology; Pedagogy; Management; Engineering; Medicine","score_opus":0.05281920729667033,"score_gpt":0.42728995625812827,"score_spread":0.37447074896145793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3205101414","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99617153,0.00007991143,0.00010539448,0.0017604122,0.00053446036,0.00006244592,9.56137e-7,0.0000010788391,0.0012838296],"genre_scores_gemma":[0.99570125,0.000019005,0.0032978444,0.0004823348,0.000014029646,9.869198e-7,0.000004673985,0.0000014242232,0.00047844174],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99822915,0.000072383176,0.000324008,0.0002223909,0.0010585849,0.0000934977],"domain_scores_gemma":[0.9986154,0.00015972898,0.00015135601,0.00021503626,0.00077260006,0.00008589242],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012467833,0.000046988134,0.00010477177,0.00039707418,0.000051504252,0.000032574768,0.00017439775,0.000021123338,0.0004377687],"category_scores_gemma":[0.0003881331,0.00004242056,0.000007654057,0.0017588184,0.00009697876,0.00065248914,0.000034376077,0.000052484706,0.000002352468],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026639329,0.0003715869,0.72868586,0.00001695146,0.0000015766282,4.7460125e-7,0.013624496,0.0026753994,0.023332428,0.029602325,0.0024215742,0.1992407],"study_design_scores_gemma":[0.00013005915,0.000026568503,0.8578617,0.000083054576,0.0000018407242,0.0000021679566,0.1198774,0.003165618,0.0070388587,0.011278982,0.000469925,0.00006381812],"about_ca_topic_score_codex":0.14605483,"about_ca_topic_score_gemma":0.20532818,"teacher_disagreement_score":0.1991769,"about_ca_system_score_codex":0.00043527043,"about_ca_system_score_gemma":0.09394737,"threshold_uncertainty_score":0.9111891},"labels":[],"label_agreement":null},{"id":"W3205524844","doi":"10.3138/cjpe.72833","title":"Beverly Parsons, Lovely Dhillon, and Matt Keene (Eds.). (2020). <i>Visionary Evaluation for a Sustainable, Equitable Future.</i>","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Business; Environmental ethics; Philosophy","score_opus":0.148458665966718,"score_gpt":0.471744497342231,"score_spread":0.32328583137551303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3205524844","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8222727,0.08297923,0.010188577,0.055929463,0.005664478,0.012524782,0.00014779798,0.000060822873,0.010232156],"genre_scores_gemma":[0.9784409,0.00036103372,0.016235001,0.0010240001,0.0009958644,0.00038785048,0.00017730745,0.00003673722,0.0023412963],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9930063,0.00095297577,0.0013311304,0.00047625214,0.0035494573,0.0006839219],"domain_scores_gemma":[0.98201156,0.00048863346,0.0009183522,0.00043089228,0.01543825,0.0007123336],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03302183,0.00022819625,0.00042330127,0.0005906903,0.0006360946,0.0010824027,0.0004131886,0.00016424365,0.002368441],"category_scores_gemma":[0.005753581,0.00019440823,0.00019538365,0.0012598354,0.00009368411,0.0013920938,0.000047908252,0.00024518828,0.000032688786],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006165507,0.00007908014,0.0031334357,0.00003225529,0.00006196437,0.000041437517,0.0006367396,0.001426764,0.00009232748,0.0015194573,0.038387626,0.95452726],"study_design_scores_gemma":[0.004852736,0.0013158879,0.06423739,0.00011967938,0.0005943261,0.00051878137,0.013568314,0.115267016,0.00023152785,0.061473124,0.73733556,0.00048567238],"about_ca_topic_score_codex":0.00022126915,"about_ca_topic_score_gemma":0.0055705095,"teacher_disagreement_score":0.9540416,"about_ca_system_score_codex":0.00064575765,"about_ca_system_score_gemma":0.016241966,"threshold_uncertainty_score":0.9999546},"labels":[],"label_agreement":null},{"id":"W3206030918","doi":"10.3138/cjpe.70053","title":"Cultivating Cultural Competence","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Conceptualization; Cultural competence; Competence (human resources); Cultural diversity; Psychology; Epistemology; Sociology; Engineering ethics; Social psychology; Pedagogy; Anthropology; Computer science; Philosophy","score_opus":0.5646603306791933,"score_gpt":0.585671718843883,"score_spread":0.021011388164689726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3206030918","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97222656,0.0009773767,0.001428187,0.005547762,0.0015634169,0.00048249622,0.000005277107,0.000010420657,0.017758504],"genre_scores_gemma":[0.9865387,0.000007810978,0.012477984,0.00030970704,0.00019774328,0.000015317786,0.000012258557,0.0000048247357,0.00043563783],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961861,0.0005375145,0.00079777575,0.00016439623,0.0020944453,0.00021976983],"domain_scores_gemma":[0.99105585,0.00021409393,0.00055452494,0.00021344607,0.0075829383,0.00037913377],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008819484,0.00008510931,0.00018198039,0.00024718334,0.00023971392,0.0005948459,0.0003295388,0.00004812279,0.0048154327],"category_scores_gemma":[0.007083871,0.00006239675,0.00011828052,0.0008936829,0.00006923576,0.000768074,0.000012420665,0.00018497519,0.000106351305],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037235159,0.000025936133,0.05044012,0.0000025286085,0.000019404024,0.000022605962,0.0015348201,0.0022185692,0.00060057914,0.0009954803,0.00589111,0.9382451],"study_design_scores_gemma":[0.0024125068,0.0005717378,0.3676543,0.00021089312,0.00014561474,0.00061664026,0.020256635,0.14435723,0.0035293014,0.020683134,0.43910983,0.0004521807],"about_ca_topic_score_codex":0.00016869631,"about_ca_topic_score_gemma":0.009303224,"teacher_disagreement_score":0.93779296,"about_ca_system_score_codex":0.0002668147,"about_ca_system_score_gemma":0.0065571596,"threshold_uncertainty_score":0.99907476},"labels":[],"label_agreement":null},{"id":"W3206200039","doi":"10.3138/cjpe.68386","title":"Practice Notes from a Participatory Impact Evaluation of a Leadership Development Program for People Living with HIV","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Pacific AIDS Network","funders":"","keywords":"Participatory evaluation; Citizen journalism; Participatory GIS; Work (physics); Sociology; Participatory development; Participatory action research; Knowledge management; Public relations; Management science; Political science; Computer science; Engineering; Social science","score_opus":0.6469295512114422,"score_gpt":0.5709009173924243,"score_spread":0.07602863381901792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3206200039","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98668903,0.0012683261,0.0059734154,0.0028516867,0.00032355383,0.00252686,0.000016274293,0.000012231337,0.0003386174],"genre_scores_gemma":[0.95130163,0.0000038175103,0.04774964,0.000130958,0.00012651208,0.00059079676,0.00005360824,0.000016664475,0.000026380754],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99201965,0.0016969563,0.0012495308,0.00031532656,0.0043182224,0.000400327],"domain_scores_gemma":[0.97846407,0.0023314864,0.0015003022,0.00034851226,0.016894743,0.00046086923],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03496646,0.00017817014,0.000394306,0.00043571586,0.00023214758,0.00043594025,0.0003046738,0.00009616488,0.0017913593],"category_scores_gemma":[0.028378608,0.0001333421,0.00016947175,0.0009979885,0.00007640812,0.0010565415,0.000013788664,0.0001852829,0.000018499111],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006790581,0.00028346144,0.092819124,0.000016306858,0.00019048183,0.0000022546778,0.008907839,0.011386874,0.000071176626,0.000023926968,0.00052435364,0.8857063],"study_design_scores_gemma":[0.0030295649,0.0014265429,0.7619543,0.00043130308,0.0011574839,0.000051604613,0.02329472,0.19787803,0.0013222421,0.0009447814,0.008195052,0.00031435213],"about_ca_topic_score_codex":0.00045820983,"about_ca_topic_score_gemma":0.05967409,"teacher_disagreement_score":0.88539195,"about_ca_system_score_codex":0.00085041916,"about_ca_system_score_gemma":0.032293357,"threshold_uncertainty_score":0.9991211},"labels":[],"label_agreement":null},{"id":"W3207991248","doi":"10.3138/cjpe.71575","title":"The Rights of Nature: An Emerging Transformation Opportunity for Evaluation","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"David and Lucile Packard Foundation","keywords":"Anthropocene; Generative grammar; Coronavirus disease 2019 (COVID-19); Natural (archaeology); Sociology; Epistemology; Environmental ethics; Law and economics; Political science; Business; Knowledge management; Computer science; Geography","score_opus":0.4074894549911969,"score_gpt":0.5699416873127253,"score_spread":0.16245223232152844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3207991248","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9708458,0.0019344179,0.007729346,0.0086907735,0.0029928149,0.0032277943,0.00005331214,0.0000095633095,0.004516185],"genre_scores_gemma":[0.9977262,0.000018511184,0.0017018319,0.00011393058,0.00016325407,0.00010908634,0.00009141803,0.000006653601,0.00006911708],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9939553,0.0012842121,0.0012688068,0.00017006882,0.0030873278,0.00023425979],"domain_scores_gemma":[0.9839411,0.00047595787,0.0010056606,0.0003534713,0.013835491,0.00038832158],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.041446622,0.000105606254,0.00020575202,0.00035081676,0.0006125628,0.00036380964,0.00041021686,0.00012141864,0.0008217791],"category_scores_gemma":[0.0047812383,0.00007023361,0.0001738991,0.00072779035,0.000080455226,0.0011760498,0.000004984181,0.0002336137,0.0000034022733],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029854578,0.00004829717,0.0004571396,0.0000057238262,0.00003250334,6.632631e-7,0.001820113,0.0028432235,0.00011947926,0.005782241,0.0009354482,0.9879253],"study_design_scores_gemma":[0.0029660512,0.0010466878,0.018726725,0.00006492158,0.00031013796,0.00004840915,0.007041048,0.61964184,0.0034382795,0.16743219,0.17907737,0.00020634755],"about_ca_topic_score_codex":0.00014662342,"about_ca_topic_score_gemma":0.043657333,"teacher_disagreement_score":0.98771894,"about_ca_system_score_codex":0.00029769653,"about_ca_system_score_gemma":0.0113180755,"threshold_uncertainty_score":0.99428684},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W3208871041","doi":"10.33524/cjar.v22i1.571","title":"Collaborative Action Research: An Inevitable Outcome?","year":2021,"lang":"en","type":"article","venue":"The Canadian Journal of Action Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Nipissing University","funders":"","keywords":"Action research; Outcome (game theory); Action (physics); Psychology; Engineering ethics; Mathematics education; Engineering; Economics","score_opus":0.8983298617681684,"score_gpt":0.7204539765123367,"score_spread":0.17787588525583176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3208871041","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8617494,0.0004447416,0.00021765825,0.104120895,0.0016710721,0.00033055237,0.000019542254,0.000006038103,0.031440087],"genre_scores_gemma":[0.9829605,0.00012030737,0.00021716086,0.00025900328,0.0004748353,0.000007760096,0.0000029917717,0.000009531671,0.01594791],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9878571,0.005643477,0.00070402375,0.00022384906,0.0050194296,0.0005521297],"domain_scores_gemma":[0.97935367,0.0021236348,0.00024198549,0.0005985192,0.016929246,0.0007529517],"candidate_categories":["metaresearch","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06014276,0.00008029713,0.0002040031,0.001492518,0.0022341001,0.0015514466,0.00088910287,0.00009345064,0.0071921535],"category_scores_gemma":[0.010696855,0.00005061138,0.000073149225,0.004805098,0.00039050434,0.00139832,0.00005302482,0.0016263278,0.0005212329],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046557563,0.0002570138,0.08996622,0.000027634545,0.00017034312,0.0004164633,0.01568231,0.00556334,0.012340192,0.02187748,0.5749039,0.2783295],"study_design_scores_gemma":[0.0005257083,0.00049073546,0.07240568,0.000030232139,0.000007921577,0.00016961506,0.07641271,0.0015127982,0.0069747535,0.021512376,0.8198437,0.00011375318],"about_ca_topic_score_codex":0.0060496456,"about_ca_topic_score_gemma":0.43513352,"teacher_disagreement_score":0.42908388,"about_ca_system_score_codex":0.0009985508,"about_ca_system_score_gemma":0.01831015,"threshold_uncertainty_score":0.999485},"labels":[],"label_agreement":null},{"id":"W3208939115","doi":"10.1177/1098214020936769","title":"The Use of Evaluability Assessments in Improving Future Evaluations: A Scoping Review of 10 Years of Literature (2008–2018)","year":2021,"lang":"en","type":"review","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of Guelph","funders":"","keywords":"Ambiguity; Psychology; Engineering ethics; Equity (law); Relevance (law); Management science; Political science; Engineering; Computer science","score_opus":0.36142971211574515,"score_gpt":0.6078438813411042,"score_spread":0.24641416922535908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3208939115","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009881364,0.99584,0.00024222938,0.00018988179,0.0006852604,0.0019522804,0.000043352764,0.0000019784043,0.00005688611],"genre_scores_gemma":[0.0003083153,0.9953063,0.003974634,0.000062267725,0.00015160312,0.00006913425,0.00005179028,0.000021527148,0.000054398246],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9744276,0.01011017,0.0068402165,0.00047947204,0.007875055,0.00026748597],"domain_scores_gemma":[0.9659846,0.0064841877,0.015390501,0.0012499319,0.010794957,0.00009581108],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06344813,0.00032834813,0.0031116481,0.00087057456,0.00007778259,0.00014513855,0.0008925869,0.00015082397,0.00086246803],"category_scores_gemma":[0.029408274,0.00021049095,0.0009969742,0.0045597735,0.0003184494,0.0008796083,0.00015141127,0.000626304,0.0000051793727],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024954143,0.00010677148,0.000095097384,0.008238254,0.00010957144,0.0000011066107,0.00023233781,0.00023318951,0.0000044521294,0.00001877128,0.00039886317,0.99053663],"study_design_scores_gemma":[0.0012176703,0.0016504569,0.0028988319,0.85312825,0.003162652,0.00008665565,0.0013164841,0.004767446,0.000010773536,0.0004746058,0.13079187,0.00049430144],"about_ca_topic_score_codex":0.000017595657,"about_ca_topic_score_gemma":0.000030167857,"teacher_disagreement_score":0.9900423,"about_ca_system_score_codex":0.0004433475,"about_ca_system_score_gemma":0.010661864,"threshold_uncertainty_score":0.9949468},"labels":[],"label_agreement":null},{"id":"W3209098918","doi":"10.36834/cmej.71966","title":"Five ways to get a grip on the drawbacks of logic models in program evaluation","year":2021,"lang":"en","type":"article","venue":"Canadian Medical Education Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta; Centre for Global Health Research; University of Toronto","funders":"","keywords":"Valuation (finance); Political science; Logic model; Humanities; Welfare economics; Computer science; Operations research; Business; Engineering; Philosophy; Economics; Accounting; Public administration","score_opus":0.19152681812423442,"score_gpt":0.5111071904392676,"score_spread":0.3195803723150331,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209098918","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44268903,0.00035504933,0.0018854619,0.48908886,0.0029214504,0.001265788,0.000010297315,0.000007972795,0.06177608],"genre_scores_gemma":[0.9601217,0.00003841655,0.0012427896,0.037638467,0.00032993598,0.00013919774,0.000009716424,0.0000052829732,0.00047451782],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99520135,0.0005013225,0.00065450824,0.00020542643,0.0032021669,0.00023524548],"domain_scores_gemma":[0.9953077,0.00041693056,0.00017858905,0.00030747987,0.0018805386,0.0019087638],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010751122,0.000080355516,0.00015096352,0.0004295761,0.0001665875,0.00018016725,0.000485859,0.0000906813,0.047712833],"category_scores_gemma":[0.0367399,0.000050282448,0.00006155865,0.0010581976,0.000060579354,0.00018660446,0.000019609299,0.0004194389,0.00015765369],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008782029,0.00016867724,0.00071005913,0.0000022122629,0.000008035842,0.0000075659555,0.0040231682,0.005297145,0.000005292139,0.026909024,0.113417864,0.8494422],"study_design_scores_gemma":[0.0011008183,0.00041264598,0.04058896,0.0004239451,0.00002814041,0.00021063123,0.025238633,0.30984786,0.00008531064,0.35247108,0.26928326,0.00030873937],"about_ca_topic_score_codex":0.0010392568,"about_ca_topic_score_gemma":0.04315937,"teacher_disagreement_score":0.84913343,"about_ca_system_score_codex":0.00043480974,"about_ca_system_score_gemma":0.06649894,"threshold_uncertainty_score":0.9743005},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W3209623811","doi":"10.3138/cjpe.71630","title":"Evaluation in Transition: The Promise and Challenge of South-South Cooperation","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Salience (neuroscience); Political science; Narrative; Engineering ethics; International development; Narrative review; Public relations; Sociology; Psychology; Engineering","score_opus":0.37214611116267754,"score_gpt":0.4892118189386274,"score_spread":0.11706570777594988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209623811","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98309743,0.002479419,0.00087125826,0.009609517,0.00043440258,0.0015800842,0.0000102540525,0.0000033084216,0.001914351],"genre_scores_gemma":[0.9989932,0.000027962342,0.0006305281,0.00011133274,0.00010251064,0.000083602965,0.000014871496,0.000006046948,0.000029909143],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99443156,0.0016532209,0.0009827991,0.00019839864,0.0025665502,0.00016749772],"domain_scores_gemma":[0.9923603,0.00017380316,0.0005498011,0.00024895582,0.006492117,0.00017500915],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.029420597,0.000098684926,0.00021988462,0.00039410635,0.00015393869,0.00022833029,0.00019236704,0.00007643716,0.0014119096],"category_scores_gemma":[0.0034120611,0.000068762194,0.00007382288,0.00085561693,0.000102115635,0.00049578794,0.000007752502,0.00018695393,0.000008827177],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027840022,0.000069785834,0.0057949745,0.000011025729,0.00003350067,0.0000056827666,0.03214069,0.013104532,0.00012967293,0.0006881572,0.00015186262,0.9478423],"study_design_scores_gemma":[0.0064108153,0.0011062141,0.16798979,0.00028352643,0.000554305,0.00009582436,0.028454036,0.76482564,0.00087777013,0.022940671,0.006126537,0.0003348499],"about_ca_topic_score_codex":0.00009815287,"about_ca_topic_score_gemma":0.01931494,"teacher_disagreement_score":0.94750744,"about_ca_system_score_codex":0.00023110125,"about_ca_system_score_gemma":0.0071850717,"threshold_uncertainty_score":0.99950093},"labels":[],"label_agreement":null},{"id":"W3209748599","doi":"10.3138/cjpe.72730","title":"Conclusion: Transforming Evaluation Practice for “Business Unusual”","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Key (lock); Business; Business practice; Clinical Practice; Process management; Knowledge management; Psychology; Computer science; Business administration; Medicine; Nursing; Computer security","score_opus":0.4903320513145368,"score_gpt":0.5952244765647577,"score_spread":0.10489242525022097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209748599","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6239059,0.012214959,0.17091143,0.11276736,0.015591614,0.015607432,0.00010580922,0.000064305204,0.04883117],"genre_scores_gemma":[0.97882676,0.00004020732,0.019138826,0.0008152381,0.00053548586,0.0002624045,0.000091719055,0.000018361652,0.00027098545],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99279594,0.0011544512,0.0013129049,0.0003012361,0.004104727,0.0003307622],"domain_scores_gemma":[0.96296585,0.0010958882,0.0009589397,0.00032395462,0.03423322,0.00042215476],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04070078,0.00015030327,0.00030264148,0.0005659637,0.00047928,0.0006516006,0.00037002287,0.000119326156,0.0027248478],"category_scores_gemma":[0.03094228,0.00012575854,0.0001854823,0.001646834,0.000070372625,0.0018173065,0.000012174462,0.00018740035,0.000036267375],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042743348,0.00007584614,0.00065430556,0.000009464031,0.000043030235,0.000008779004,0.0014552906,0.005563769,0.00019616715,0.0009417412,0.003131662,0.9878772],"study_design_scores_gemma":[0.0044186823,0.00064733677,0.010085114,0.00013730608,0.00077008974,0.00038968347,0.008948181,0.23079948,0.0014045577,0.02012387,0.72195953,0.0003162017],"about_ca_topic_score_codex":0.00015461243,"about_ca_topic_score_gemma":0.009886202,"teacher_disagreement_score":0.987561,"about_ca_system_score_codex":0.00072086847,"about_ca_system_score_gemma":0.025052872,"threshold_uncertainty_score":0.99818677},"labels":[],"label_agreement":null},{"id":"W3209821041","doi":"10.33524/cjar.v22i1.574","title":"Action Research Network of the Americas Annual Conference, June 28-30, 2022, Southern Utah University, Cedar City, Utah, USA","year":2021,"lang":"en","type":"article","venue":"The Canadian Journal of Action Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Nipissing University","funders":"","keywords":"Action research; Geography; Archaeology; Mathematics education; Psychology","score_opus":0.5548050925711294,"score_gpt":0.5487263198172331,"score_spread":0.006078772753896344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209821041","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9329141,0.0001379142,0.00026942434,0.046885982,0.0015213366,0.00028701022,0.000066410226,0.0000035583328,0.017914284],"genre_scores_gemma":[0.9608398,0.00019534377,0.000055847304,0.00011296359,0.0004217048,0.0000011365479,0.0000016400085,0.000008912031,0.038362615],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9883822,0.0050933985,0.00057236286,0.00024865483,0.0050293147,0.00067402184],"domain_scores_gemma":[0.98597294,0.0017414857,0.0004387815,0.0006789433,0.010679385,0.0004884559],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.028305888,0.00010482659,0.00025546827,0.0007298217,0.0021882225,0.00047234976,0.0016325715,0.000118945754,0.013898924],"category_scores_gemma":[0.002273171,0.00006532453,0.00016986343,0.004564887,0.0010402821,0.0004892836,0.00026339968,0.0019171649,0.00034442922],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006212255,0.00016477917,0.120811634,0.000032224394,0.00032268453,0.00022992448,0.01944893,0.010253795,0.0036731476,0.008661082,0.7210254,0.11475518],"study_design_scores_gemma":[0.00084785506,0.00039275078,0.11649195,0.00013081529,0.000031448497,0.00020067998,0.15887755,0.0021722168,0.0019119129,0.015146564,0.703607,0.00018922062],"about_ca_topic_score_codex":0.012220486,"about_ca_topic_score_gemma":0.25274146,"teacher_disagreement_score":0.24052095,"about_ca_system_score_codex":0.0007567158,"about_ca_system_score_gemma":0.0136014605,"threshold_uncertainty_score":0.9991108},"labels":[],"label_agreement":null},{"id":"W3209866185","doi":"10.3138/cjpe.71527","title":"Catching the Wave: Harnessing Data Science to Support Evaluation’s Capacity for Making a Transformational Contribution to Sustainable Development","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Natural Environment Research Council; Sight Research UK","keywords":"Transformational leadership; Sustainable development; Field (mathematics); Set (abstract data type); Engineering ethics; Key (lock); Politics; Political science; Knowledge management; Data science; Computer science; Sociology; Management science; Public relations; Engineering","score_opus":0.584620824737506,"score_gpt":0.5460516450026884,"score_spread":0.03856917973481755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209866185","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7313297,0.00017175399,0.23587987,0.0240574,0.0014583722,0.0059438604,0.00006666326,0.000013308514,0.0010791174],"genre_scores_gemma":[0.95196164,7.607994e-7,0.046276245,0.0010811855,0.00013804427,0.000321141,0.00012326999,0.000008464659,0.000089257315],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99220943,0.0005265535,0.0012426011,0.0004248606,0.0049971603,0.0005993773],"domain_scores_gemma":[0.9772136,0.0003751121,0.00051698775,0.0005821313,0.020768374,0.0005437626],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.084088124,0.00014414072,0.00023131185,0.000815806,0.0017983981,0.0018477717,0.0010884372,0.000052551506,0.00085667917],"category_scores_gemma":[0.020993616,0.000107218504,0.00007205677,0.0022759524,0.00010074252,0.0026855678,0.0000801012,0.00018064857,0.000025659589],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025735477,0.000036392372,0.0008737087,0.000010450138,0.00002420434,0.000003639689,0.008664751,0.012840588,0.0002471782,0.0027531467,0.0020745755,0.9724456],"study_design_scores_gemma":[0.0017680108,0.0003527948,0.07739492,0.00014845096,0.000206787,0.00015705562,0.012177737,0.32731932,0.0018573742,0.0079523,0.57029974,0.00036551515],"about_ca_topic_score_codex":0.00009599246,"about_ca_topic_score_gemma":0.011472904,"teacher_disagreement_score":0.9720801,"about_ca_system_score_codex":0.002401685,"about_ca_system_score_gemma":0.051625237,"threshold_uncertainty_score":0.9995011},"labels":[],"label_agreement":null},{"id":"W3209922870","doi":"10.7939/r38w38c91","title":"Creating and Capitalizing on Opportunities to Reduce Poverty: The Process and Power of Integrated Knowledge Translation","year":2016,"lang":"en","type":"article","venue":"University of Alberta Library","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Process (computing); Poverty; Power (physics); Computer science; Knowledge management; Process management; Business; Economic growth; Economics","score_opus":0.1280249614079549,"score_gpt":0.35105402196082497,"score_spread":0.22302906055287006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209922870","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92801446,0.000054639313,0.00009119758,0.005819367,0.000024297658,0.00009516417,0.0000067163096,0.000005374583,0.0658888],"genre_scores_gemma":[0.9901657,0.000057578378,0.0001843853,0.00015535935,0.000004385414,1.1689515e-7,0.0000021591836,0.0000029207322,0.009427393],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9993726,0.00008262479,0.00013492856,0.00013193903,0.00021880207,0.000059092898],"domain_scores_gemma":[0.998637,0.0010142111,0.00009819197,0.00012312636,0.00007802834,0.000049428225],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028696738,0.00005540797,0.00010578236,0.00013363814,0.000095458374,0.000024566933,0.00016523547,0.000026632264,0.0007162663],"category_scores_gemma":[0.000120999764,0.00003116447,0.00002003425,0.00014418567,0.00010505811,0.00077803864,0.000045355548,0.00002848643,0.000005393565],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010384567,0.00019520448,0.13851115,0.00007126069,0.00009699663,0.0000030985614,0.41477352,0.00006179773,0.0041036047,0.030353723,0.017646657,0.39314452],"study_design_scores_gemma":[0.004011493,0.0017358507,0.25430566,0.0015117008,0.00009935444,0.000011263696,0.45658895,0.008087821,0.026760146,0.009042913,0.23711814,0.0007267072],"about_ca_topic_score_codex":0.00007357387,"about_ca_topic_score_gemma":0.00007555257,"teacher_disagreement_score":0.39241782,"about_ca_system_score_codex":0.0000057644356,"about_ca_system_score_gemma":0.00012984722,"threshold_uncertainty_score":0.78426135},"labels":[],"label_agreement":null},{"id":"W3210619334","doi":"","title":"The Sensitivity of Impact Estimates to Data Sources Used: Analysis From an Access to Postsecondary Education Experiment","year":2017,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Statistics Canada","funders":"","keywords":"Context (archaeology); Psychological intervention; Survey data collection; Randomized experiment; Estimation; Psychology; Demographic economics; Political science; Econometrics; Statistics; Economics; Geography; Mathematics","score_opus":0.16596524694044465,"score_gpt":0.5602492865985127,"score_spread":0.394284039658068,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210619334","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9826196,0.00035309355,0.010577363,0.005724633,0.00031390713,0.00016907523,0.00005339719,0.0000061515825,0.00018280074],"genre_scores_gemma":[0.9988578,0.00011828902,0.0003072969,0.00021266243,0.00029009357,0.000005146472,0.000031338026,0.000007606931,0.00016977359],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.996681,0.0003748126,0.0005358519,0.00038171106,0.0012641359,0.0007624996],"domain_scores_gemma":[0.99576664,0.0006348691,0.0006612014,0.0020494116,0.00066907646,0.00021881425],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.015327736,0.00013951816,0.00029032005,0.00030860043,0.0011264539,0.0021424687,0.0027911672,0.000035374072,0.0003773567],"category_scores_gemma":[0.0024418791,0.00008074042,0.00012553626,0.00038917616,0.000056626115,0.0019747557,0.00051204767,0.00038200215,0.00004488589],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001988451,0.0001800006,0.48736602,6.6833144e-7,0.00082414685,6.0910804e-7,0.001982836,0.0038987533,0.003651509,0.00078722567,0.0018966146,0.49921274],"study_design_scores_gemma":[0.00022488278,0.00035821344,0.9398911,0.000012649944,0.00018541365,0.000010136417,0.0077029737,0.018839208,0.0037065446,0.027096642,0.001782067,0.0001901857],"about_ca_topic_score_codex":0.0025089737,"about_ca_topic_score_gemma":0.03330544,"teacher_disagreement_score":0.49902257,"about_ca_system_score_codex":0.00036431494,"about_ca_system_score_gemma":0.004568118,"threshold_uncertainty_score":0.9988934},"labels":[],"label_agreement":null},{"id":"W3211171909","doi":"10.33524/cjar.v22i1.573","title":"American Educational Research Association Special Interest Group: Action Research Annual Conference, April 22-25, 2022, San Diego, USA","year":2021,"lang":"en","type":"article","venue":"The Canadian Journal of Action Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Nipissing University","funders":"","keywords":"Action research; Library science; Theme (computing); Interest group; Action (physics); Political science; Sociology; Pedagogy; Law; Computer science","score_opus":0.6659141560427659,"score_gpt":0.6146661460683783,"score_spread":0.05124800997438761,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211171909","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87235683,0.00011679578,0.000084143445,0.06572356,0.0030303916,0.00039378405,0.00005863827,0.000004244963,0.058231603],"genre_scores_gemma":[0.94874555,0.00021397613,0.00009527982,0.0001687803,0.0054008435,0.00002902516,0.000022561158,0.000019303314,0.045304663],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97522837,0.011286881,0.0010976315,0.0005143572,0.010618724,0.0012540536],"domain_scores_gemma":[0.95930433,0.009598622,0.000604952,0.0007427905,0.028691722,0.0010575977],"candidate_categories":["metaresearch","sts","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.08159345,0.00016342835,0.0003630057,0.0034573707,0.0035159127,0.0024926867,0.0016789193,0.000189638,0.056608774],"category_scores_gemma":[0.027343703,0.00012326823,0.00017827026,0.006808442,0.0012095959,0.0013421787,0.00020563552,0.0044882745,0.0018888236],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.0001935804,0.00016262608,0.029229756,0.000008776603,0.000086496395,0.000026416703,0.004121414,0.000074871445,0.0021117865,0.01065309,0.8683873,0.08494393],"study_design_scores_gemma":[0.0005302003,0.00060424337,0.29879153,0.000063728534,0.000009632506,0.00008218586,0.06293766,0.0003277633,0.0013194226,0.021718856,0.6134504,0.0001643532],"about_ca_topic_score_codex":0.016196987,"about_ca_topic_score_gemma":0.73964936,"teacher_disagreement_score":0.7234524,"about_ca_system_score_codex":0.005232511,"about_ca_system_score_gemma":0.022559887,"threshold_uncertainty_score":0.9988883},"labels":[],"label_agreement":null},{"id":"W3211253945","doi":"10.3138/cjpe.70502","title":"L’évaluation évolutive, de la théorie à la pratique : perspectives de praticiens québécois","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"École Nationale d'Administration Publique; University of Victoria; Université de Sherbrooke","funders":"","keywords":"Summative assessment; Formative assessment; Valuation (finance); Sociology; Business; Knowledge management; Political science; Pedagogy; Computer science; Accounting","score_opus":0.17542502317927477,"score_gpt":0.5004563917657058,"score_spread":0.325031368586431,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211253945","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9174394,0.0015301866,0.018256744,0.009775922,0.0004391438,0.000925301,0.000011044995,0.000021623691,0.051600616],"genre_scores_gemma":[0.9767365,0.000051187388,0.022244789,0.00023379781,0.00021634363,0.000075116775,0.000008584959,0.000013222661,0.0004204984],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99190634,0.004674658,0.0007829025,0.00026003164,0.0020184184,0.000357631],"domain_scores_gemma":[0.9918192,0.0013696612,0.0006296541,0.00029577932,0.005389079,0.0004966171],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03574267,0.00014259898,0.0002415141,0.00048831035,0.0002828095,0.0007955001,0.00033622826,0.00016464358,0.0019126786],"category_scores_gemma":[0.01982739,0.00012172256,0.00015626548,0.0010313172,0.00019108893,0.0006571781,0.000014814705,0.00039078234,0.000025605643],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027934018,0.00024306148,0.07356227,0.000009973277,0.00010047268,0.00008342543,0.059814937,0.015684903,0.000819913,0.027446184,0.00437294,0.81783396],"study_design_scores_gemma":[0.001800678,0.000634942,0.5358978,0.000117494,0.0002796279,0.00079863146,0.066593334,0.20261626,0.0010546647,0.12641373,0.06343729,0.00035554575],"about_ca_topic_score_codex":0.00198681,"about_ca_topic_score_gemma":0.054482147,"teacher_disagreement_score":0.8174784,"about_ca_system_score_codex":0.001676209,"about_ca_system_score_gemma":0.056570835,"threshold_uncertainty_score":0.9989997},"labels":[],"label_agreement":null},{"id":"W3211298722","doi":"","title":"Strategies for Mentoring and Advising Evaluation Graduate Students of Color","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Honor; Ethnic group; Cultural competence; Psychology; Graduate students; Competence (human resources); Salient; Pedagogy; Women of color; Medical education; Identity (music); People of color; Sociology; Social psychology; Gender studies; Medicine","score_opus":0.6184423513416186,"score_gpt":0.611127572966471,"score_spread":0.007314778375147601,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211298722","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99326473,0.0009176636,0.0020720558,0.00083160144,0.00080062664,0.001236416,0.000008037573,0.0000032342673,0.0008656189],"genre_scores_gemma":[0.99461496,0.000020709289,0.0050370414,0.00004602126,0.000106385705,0.000082615596,0.000015190219,0.0000072500616,0.00006982729],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.994865,0.00055135356,0.000940796,0.00019471784,0.003241936,0.00020617832],"domain_scores_gemma":[0.98992974,0.00030695877,0.00080152217,0.0001807806,0.00853189,0.00024909567],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024425633,0.00009849399,0.00024842055,0.00040279594,0.00018614439,0.0006131785,0.00024152808,0.000053278778,0.00035362676],"category_scores_gemma":[0.0031072819,0.00008297307,0.00009345673,0.00050302985,0.00006675594,0.000805272,0.000016057136,0.00009705216,0.0000026041105],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028437204,0.00005988226,0.021165296,0.000020819025,0.00007231212,0.0000021409364,0.0033395165,0.0052167317,0.00079551677,0.0010410678,0.0005835025,0.9676748],"study_design_scores_gemma":[0.0067952843,0.0018102941,0.40897396,0.000367012,0.00089604914,0.000079036494,0.047668163,0.42453632,0.003241296,0.08868765,0.016555456,0.00038947904],"about_ca_topic_score_codex":0.0001075498,"about_ca_topic_score_gemma":0.00546609,"teacher_disagreement_score":0.9672853,"about_ca_system_score_codex":0.00029280194,"about_ca_system_score_gemma":0.0077399113,"threshold_uncertainty_score":0.9978853},"labels":[],"label_agreement":null},{"id":"W3211592701","doi":"10.1201/9781003077459-8","title":"Organizational Consequences of Participatory Evaluation: School District Case Study 1","year":2021,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Citizen journalism; Participatory evaluation; Sociology; Environmental planning; Geography; Computer science; Social science; World Wide Web","score_opus":0.47602816840924855,"score_gpt":0.5222107336914469,"score_spread":0.04618256528219833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211592701","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.091135025,0.0005919913,0.00026885024,0.00056403544,0.0008105765,0.0013022885,0.00008990513,0.00003646604,0.90520084],"genre_scores_gemma":[0.72677326,0.000025456378,0.00016863932,0.00015098637,0.00010717793,0.000031213753,0.00004983452,0.000014582844,0.27267882],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99229676,0.0003619387,0.0014735193,0.00051589863,0.0052082357,0.00014363881],"domain_scores_gemma":[0.9922749,0.0012038382,0.0007721708,0.00083106174,0.0047490424,0.00016898877],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.005732655,0.0002474015,0.00051346375,0.00030613135,0.00018241808,0.0001876687,0.0004003095,0.00014574241,0.2659398],"category_scores_gemma":[0.0029458464,0.0001825626,0.00012904611,0.00031741196,0.0002143892,0.00021982718,0.00015881303,0.00020207823,0.00084691134],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000077104116,0.0015537862,0.2947718,0.00009306,0.0014304217,0.0030001176,0.0069657136,0.002256702,0.00013720011,0.56012756,0.07649234,0.053094197],"study_design_scores_gemma":[0.012796792,0.003932865,0.04415972,0.0008012673,0.005090539,0.0062643206,0.23675145,0.021973303,0.0018326476,0.4424623,0.21807536,0.005859436],"about_ca_topic_score_codex":0.000047639027,"about_ca_topic_score_gemma":0.00062956713,"teacher_disagreement_score":0.63563824,"about_ca_system_score_codex":0.00017608398,"about_ca_system_score_gemma":0.0058336086,"threshold_uncertainty_score":0.99993104},"labels":[],"label_agreement":null},{"id":"W3211718553","doi":"10.3917/rfsen.531.0031","title":"10.3917/rfsen.531.0031","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Compromise; Publicity; Political science; Law","score_opus":0.09623820309470106,"score_gpt":0.40211707767125926,"score_spread":0.3058788745765582,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211718553","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0070510646,0.000020770287,0.000008418072,0.0021357634,0.000011180691,0.00015964865,0.0000076220726,0.000060417515,0.9905451],"genre_scores_gemma":[0.0040024393,6.1783965e-7,0.00030674282,0.00046377716,0.00011435379,0.000015767144,0.0000065432187,0.000008636978,0.9950811],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99767256,0.000114829534,0.00039132225,0.0003068674,0.0012903083,0.00022412131],"domain_scores_gemma":[0.99881315,0.00023987683,0.00005832763,0.00052919635,0.00019238383,0.00016703783],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0018435728,0.000107424,0.00016593277,0.00015561606,0.00013702668,0.00018990037,0.0004902589,0.00004556922,0.9990756],"category_scores_gemma":[0.00024907637,0.0000803879,0.00006697902,0.00064975483,0.000029424113,0.0002779303,0.000048554,0.00007488793,0.9971757],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002260313,0.000023113476,0.0000044035255,3.453496e-7,0.0000028429638,8.4525044e-7,0.000032717886,0.0003792289,0.000020634277,0.000006826006,0.31630796,0.6831985],"study_design_scores_gemma":[0.00019669005,0.00010736315,0.0011144993,0.00000509387,0.0000044193953,0.0000033910635,0.0000073833235,0.004064626,0.000054702163,0.00013787768,0.9941842,0.00011975047],"about_ca_topic_score_codex":0.000007845094,"about_ca_topic_score_gemma":5.4231396e-7,"teacher_disagreement_score":0.6830787,"about_ca_system_score_codex":0.000033462777,"about_ca_system_score_gemma":0.00009457217,"threshold_uncertainty_score":0.32781234},"labels":[],"label_agreement":null},{"id":"W3212008682","doi":"10.1007/s10459-021-10083-6","title":"Vitalizing the evaluation of curricular implementation: a framework for attending to the “how and whys” of curriculum evolution","year":2021,"lang":"en","type":"article","venue":"Advances in Health Sciences Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; Institute for Work & Health; University of Toronto","funders":"","keywords":"Summative assessment; Curriculum; Formative assessment; Computer science; Work (physics); Engineering ethics; Medical education; Management science; Psychology; Mathematics education; Pedagogy; Medicine; Engineering","score_opus":0.16421915522301672,"score_gpt":0.5989933205520342,"score_spread":0.4347741653290175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212008682","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75542283,0.022187779,0.13764995,0.07893977,0.002790632,0.002627688,0.000015752139,0.000007636436,0.00035793768],"genre_scores_gemma":[0.9797971,0.00039051802,0.018861623,0.0005645276,0.00009276456,0.00027412403,0.0000059113004,0.000002587144,0.000010790905],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99637043,0.00065099704,0.00068802806,0.00033886547,0.00175255,0.00019910355],"domain_scores_gemma":[0.99656665,0.0011582209,0.00070397055,0.00029168208,0.0012311361,0.000048316502],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018960873,0.00007711064,0.00016287081,0.00019843549,0.00045905606,0.00010328392,0.00034479136,0.000022882055,0.000074069496],"category_scores_gemma":[0.0031834652,0.000044661334,0.000038856226,0.0022945872,0.00014383005,0.0008339471,0.000055635384,0.00006792871,0.000001307016],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000043502523,0.00008337306,0.24481279,0.00007334349,0.0000030390136,1.0346854e-8,0.0048679183,0.015069241,0.00006427403,0.19204628,0.0005989931,0.5423764],"study_design_scores_gemma":[0.0004394209,0.0003703267,0.24532004,0.0005309991,0.000028875504,0.000006778148,0.23325247,0.09379571,0.00079591764,0.40132543,0.023951825,0.00018221619],"about_ca_topic_score_codex":0.00012687336,"about_ca_topic_score_gemma":0.000985115,"teacher_disagreement_score":0.5421942,"about_ca_system_score_codex":0.00016850398,"about_ca_system_score_gemma":0.0018782057,"threshold_uncertainty_score":0.6571498},"labels":[],"label_agreement":null},{"id":"W3212330795","doi":"10.33137/tijih.v1i2.36171","title":"Reflecting on the use of Concept Mapping as a Method for Community-Led Analysis of Talking Circles","year":2021,"lang":"en","type":"article","venue":"Turtle Island Journal of Indigenous Health","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mohawk College; Kahnawake Schools Diabetes Prevention Project; McGill University; Queen's University","funders":"","keywords":"Indigenous; Context (archaeology); Community engagement; Public relations; Process (computing); Sociology; Political science; Geography; Computer science; Ecology","score_opus":0.49072879852069734,"score_gpt":0.5641697758237502,"score_spread":0.07344097730305282,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212330795","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9347824,0.00030872622,0.06204127,0.0020667312,0.00017243807,0.00021867607,0.000040347386,0.000002854612,0.00036653847],"genre_scores_gemma":[0.98431957,0.00011190743,0.013819603,0.0015610557,0.000054464235,0.0000020271896,0.000007055865,0.0000069879984,0.00011730695],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99486834,0.0021965113,0.0014959538,0.00011345779,0.0011064941,0.00021923915],"domain_scores_gemma":[0.98670036,0.008928091,0.0024153756,0.00040169078,0.0014779121,0.00007658528],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01641822,0.000095506904,0.0007123475,0.0005963748,0.00064684165,0.00009496448,0.00039349782,0.000047077083,0.0002459281],"category_scores_gemma":[0.0027310732,0.00005786156,0.00032898432,0.0015386706,0.000043998734,0.00016257343,0.000040685773,0.000394465,0.0000011616787],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004181757,0.00076542853,0.027118696,0.00014589998,0.0025689055,0.000011554833,0.4624801,0.062925324,0.0036620984,0.0015757182,0.0018886263,0.43643945],"study_design_scores_gemma":[0.008711902,0.011452065,0.25527442,0.0025856497,0.0020809753,0.00052908505,0.48135057,0.08369664,0.058602758,0.028863525,0.06574651,0.0011058917],"about_ca_topic_score_codex":0.00063994416,"about_ca_topic_score_gemma":0.002413222,"teacher_disagreement_score":0.43533358,"about_ca_system_score_codex":0.00010387571,"about_ca_system_score_gemma":0.0016000329,"threshold_uncertainty_score":0.569026},"labels":[],"label_agreement":null},{"id":"W3212759353","doi":"10.1080/24751979.2021.1972767","title":"Methodological Quality and Validity Issues in the Crime Prevention Literature","year":2021,"lang":"en","type":"article","venue":"Justice Evaluation Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Public Safety Canada","keywords":"Fidelity; Psychological intervention; Crime prevention; External validity; Strengths and weaknesses; Quality (philosophy); Internal validity; Psychology; Inclusion (mineral); Management science; Applied psychology; Computer science; Medicine; Social psychology; Criminology; Engineering; Psychiatry","score_opus":0.8674694788525665,"score_gpt":0.6999287630133438,"score_spread":0.1675407158392227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212759353","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9048007,0.0040310565,0.028304398,0.053755645,0.0015393449,0.00040819834,0.000006004994,0.000013080031,0.007141533],"genre_scores_gemma":[0.9786539,0.00083472213,0.015844079,0.0025429754,0.00094567,0.00002286967,0.000019060397,0.000004867246,0.0011318472],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9759822,0.018816708,0.00098511,0.0003201649,0.0037177876,0.00017801557],"domain_scores_gemma":[0.9924917,0.0045514633,0.00044337992,0.00033159304,0.0021043739,0.000077442775],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11351128,0.00010552139,0.00023429941,0.00014915055,0.00035522407,0.0011045979,0.00029616882,0.00009540061,0.0032152259],"category_scores_gemma":[0.040936675,0.000059212565,0.00009670233,0.00082144147,0.00004622234,0.0007581837,0.000056057906,0.00050825375,0.000050633826],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029702738,0.0007504132,0.04911034,0.000108046064,0.00006728223,0.000094695395,0.041812666,0.0052674194,0.0035148922,0.0352269,0.039643932,0.8241064],"study_design_scores_gemma":[0.00091622217,0.00011760244,0.75574005,0.000058984922,0.0001487179,0.00030285463,0.013547886,0.017571194,0.0001737483,0.20021358,0.011087904,0.00012124527],"about_ca_topic_score_codex":0.0000015620247,"about_ca_topic_score_gemma":0.000019281291,"teacher_disagreement_score":0.82398516,"about_ca_system_score_codex":0.000066415094,"about_ca_system_score_gemma":0.0004642075,"threshold_uncertainty_score":0.99993235},"labels":[],"label_agreement":null},{"id":"W3212930202","doi":"","title":"Las herramientas de evaluación del riesgo de violencia : ventajas y límites","year":2012,"lang":"es","type":"article","venue":"L information psychiatrique","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Humanities; Political science; Philosophy; Psychology","score_opus":0.05138264292124179,"score_gpt":0.44803561931653646,"score_spread":0.3966529763952947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212930202","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9022913,0.0017403283,0.035876077,0.005492811,0.0045406786,0.001105208,0.00013228111,0.0001872294,0.048634112],"genre_scores_gemma":[0.98330724,0.0008166203,0.007323123,0.006950418,0.00077068823,0.00011116098,0.000124969,0.000022822414,0.00057297066],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9942199,0.00061996427,0.0017560018,0.0002666523,0.0020529996,0.0010844833],"domain_scores_gemma":[0.9964048,0.0004083373,0.0010458773,0.0007975194,0.00074287155,0.00060054136],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.009350832,0.00041541833,0.00039767593,0.0007182719,0.0005897859,0.00093680405,0.0008278687,0.00039806112,0.0045644185],"category_scores_gemma":[0.00083456305,0.00037036202,0.0002990926,0.0012306187,0.00013122353,0.006953337,0.00016124059,0.00053998805,0.007584969],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015212447,0.00040718,0.8036056,0.00014036726,0.0000897052,5.092624e-7,0.021301014,0.0026479496,0.00014478414,0.05905471,0.04468622,0.067769796],"study_design_scores_gemma":[0.0015343411,0.0002638688,0.37871304,0.00017233353,0.000104381616,0.00006098228,0.0075662187,0.039994247,0.001134993,0.008179585,0.5616015,0.0006744955],"about_ca_topic_score_codex":0.00012980621,"about_ca_topic_score_gemma":0.000042721906,"teacher_disagreement_score":0.51691526,"about_ca_system_score_codex":0.0006049992,"about_ca_system_score_gemma":0.0014457556,"threshold_uncertainty_score":0.99987483},"labels":[],"label_agreement":null},{"id":"W3213734767","doi":"10.3138/cjpe.0027.007","title":"Dissemination and Early Use of the Paris Declaration Evaluation","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Champion; Declaration; Transparency (behavior); Stakeholder; Corporate governance; Politics; Stakeholder engagement; Evaluation methods; Public relations; Impact evaluation; Political science; Business; Process management; Engineering; Medicine; Law","score_opus":0.4155863677781072,"score_gpt":0.5210278673679903,"score_spread":0.10544149958988314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3213734767","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99386144,0.00030291703,0.000625494,0.0024107834,0.00049132,0.0018651226,0.0000029351672,0.0000029840394,0.000436978],"genre_scores_gemma":[0.99807847,0.000012296646,0.0015145052,0.00005801152,0.00006350608,0.0001081314,0.000005532843,0.0000062606937,0.0001532737],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9949454,0.00094456685,0.0009608702,0.00015679494,0.0028328237,0.00015952282],"domain_scores_gemma":[0.99101144,0.00041367358,0.0011192008,0.00029299158,0.0069465926,0.00021612472],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.012757239,0.00009776883,0.00017504177,0.0004361675,0.00021150547,0.0006203068,0.00025961184,0.0000830599,0.0013253152],"category_scores_gemma":[0.0059820767,0.00006242411,0.00009185366,0.00071386335,0.000118619595,0.0018382984,0.000014784493,0.00014397813,0.000019209696],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000044009907,0.000020487872,0.19754364,0.0000026456037,0.000014168495,9.324842e-8,0.0013395965,0.001144875,0.00035878018,0.00022152704,0.0030836186,0.79626614],"study_design_scores_gemma":[0.00034860018,0.0001763283,0.8567335,0.00004853402,0.00009819625,0.000008472744,0.00044679016,0.13117541,0.0003910125,0.0068443846,0.0036604777,0.00006828654],"about_ca_topic_score_codex":0.0014492159,"about_ca_topic_score_gemma":0.005755063,"teacher_disagreement_score":0.7961979,"about_ca_system_score_codex":0.00024113075,"about_ca_system_score_gemma":0.00206068,"threshold_uncertainty_score":0.9995876},"labels":[],"label_agreement":null},{"id":"W3213991032","doi":"10.1007/978-3-030-83152-3","title":"Social Impact Measurement for a Sustainable Future: The Power of Aesthetics and Practical Implications","year":2021,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact","funders":"","keywords":"Aesthetics; Power (physics); Computer science; Psychology; Art","score_opus":0.2751828525670451,"score_gpt":0.5560496015177773,"score_spread":0.28086674895073216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3213991032","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27858493,0.00050408265,0.09436378,0.57209414,0.00021543392,0.0014652082,0.000020677044,0.000031194435,0.052720517],"genre_scores_gemma":[0.9965577,0.00001487277,0.0014107733,0.0005741501,0.00004911324,0.0000332896,0.0000015820414,0.0000032845198,0.0013552092],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99841964,0.000118081975,0.00028783825,0.00015179002,0.00087824045,0.00014440823],"domain_scores_gemma":[0.99661815,0.0003675809,0.000122010046,0.00025665687,0.0025936204,0.000041986732],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040800325,0.00005591719,0.00011109001,0.000035950576,0.00027200903,0.00016111172,0.00009842004,0.00003353622,0.00068024476],"category_scores_gemma":[0.0011863899,0.000028570612,0.0000836379,0.00032286477,0.000058587906,0.00018031537,0.00005921087,0.00005331524,0.0000065934237],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004838824,0.00020703573,0.0068370556,0.000008011604,0.000043438762,9.832517e-7,0.0026496616,0.000016699601,0.0004930427,0.84284896,0.13236997,0.014476725],"study_design_scores_gemma":[0.0009378801,0.00028496282,0.26731902,0.0000026381995,0.000050454866,0.000043917993,0.04732438,0.0014076512,0.0012362775,0.22933953,0.4518941,0.00015917889],"about_ca_topic_score_codex":0.0000048602888,"about_ca_topic_score_gemma":0.000029193601,"teacher_disagreement_score":0.71797276,"about_ca_system_score_codex":0.000050404487,"about_ca_system_score_gemma":0.0008289967,"threshold_uncertainty_score":0.7448203},"labels":[],"label_agreement":null},{"id":"W3217294128","doi":"","title":"Évaluation des connaissances et des besoins de formation d'enseignants au collégial sur les troubles envahissants de développement.","year":2010,"lang":"fr","type":"article","venue":"Revue francophone de la déficience intellectuelle","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Political science","score_opus":0.18188417063988987,"score_gpt":0.41212355306980675,"score_spread":0.23023938242991687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3217294128","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8309661,0.0031915747,0.15392546,0.001773774,0.002233488,0.000586448,0.000046211168,0.00008190507,0.007195],"genre_scores_gemma":[0.9619689,0.0051910705,0.027352206,0.0003999145,0.00047774595,0.00012786665,0.000017934984,0.000050324663,0.004414038],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9926011,0.0021515847,0.0014562142,0.00081442297,0.001517191,0.0014594954],"domain_scores_gemma":[0.9921903,0.0047780364,0.0006628576,0.000651817,0.0012468443,0.00047015975],"candidate_categories":["metaresearch","metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["sts"],"category_scores_codex":[0.018805644,0.0005374944,0.0006431735,0.00057144015,0.0019074174,0.0008252106,0.0011860423,0.00056779466,0.0064534266],"category_scores_gemma":[0.010826516,0.0005205954,0.00028145057,0.0023967377,0.002789896,0.0017108062,0.00019632753,0.0010038025,0.00061243895],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027046402,0.00074838067,0.20463368,0.00039369077,0.00004405191,0.000031177875,0.14370415,0.014326549,0.111835584,0.0010483537,0.005544989,0.5174189],"study_design_scores_gemma":[0.0021949536,0.0007314974,0.31910816,0.0014373173,0.00009021179,0.0006406119,0.02415768,0.49384394,0.09097651,0.030900242,0.034882665,0.001036218],"about_ca_topic_score_codex":0.0021926996,"about_ca_topic_score_gemma":0.011994746,"teacher_disagreement_score":0.5163827,"about_ca_system_score_codex":0.0014742769,"about_ca_system_score_gemma":0.0051740413,"threshold_uncertainty_score":0.99992394},"labels":[],"label_agreement":null},{"id":"W3217770674","doi":"10.3138/cjpe.69191","title":"Toward an Evidence-Based Approach to Building Evaluation Capacity","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"Children's Hospital Foundation; Stollery Children’s Hospital Foundation; Women and Children's Health Research Institute; Social Sciences and Humanities Research Council of Canada; Children's Health Research Institute","keywords":"Work (physics); Accountability; Process management; Capacity building; Computer science; Knowledge management; Management science; Risk analysis (engineering); Business; Political science; Engineering","score_opus":0.8095482787308166,"score_gpt":0.5628469968990902,"score_spread":0.24670128183172635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3217770674","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92625,0.0008857236,0.060252145,0.0059129666,0.0014782461,0.002121676,0.0000092558885,0.00001842693,0.0030715484],"genre_scores_gemma":[0.9302196,0.0000040724817,0.068436705,0.00079104013,0.0003129798,0.00016300082,0.000022651013,0.000013013541,0.00003696992],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9896759,0.0025370251,0.001191207,0.00045760916,0.0057450337,0.00039322127],"domain_scores_gemma":[0.9836304,0.00038399542,0.00067163113,0.00057621923,0.013653912,0.0010838091],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04746416,0.00017723921,0.00032572672,0.00094354554,0.00030694544,0.0010474311,0.0006645575,0.00011659425,0.0023800232],"category_scores_gemma":[0.01809813,0.00015029388,0.00017927958,0.0019293197,0.000069538975,0.0018242605,0.00001732523,0.00027606776,0.00006494322],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023978326,0.00012668582,0.008591261,0.000009613138,0.00002355364,0.000004699953,0.0018592644,0.11769326,0.00068787124,0.0007262862,0.0013623858,0.8688911],"study_design_scores_gemma":[0.0013871861,0.0008111352,0.077352144,0.00021844318,0.00026640703,0.00008834276,0.0026428066,0.8873598,0.0025474578,0.010446219,0.0165401,0.00033998457],"about_ca_topic_score_codex":0.00048195166,"about_ca_topic_score_gemma":0.0062028076,"teacher_disagreement_score":0.86855114,"about_ca_system_score_codex":0.0012200825,"about_ca_system_score_gemma":0.019382784,"threshold_uncertainty_score":0.99998957},"labels":[],"label_agreement":null},{"id":"W3217805655","doi":"10.7202/1084909ar","title":"Quelles sont les alternatives au placement en institution des enfants en situation de handicap dans un contexte post-soviétique ? Enjeux d’une évaluation participative en contexte interculturel","year":2021,"lang":"fr","type":"article","venue":"Alterstice Revue internationale de la recherche interculturelle","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Political science; Humanities; Art","score_opus":0.2716527538214854,"score_gpt":0.4841009692086547,"score_spread":0.2124482153871693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3217805655","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6322425,0.00602723,0.33814475,0.014079666,0.001298553,0.0007674772,0.0002154859,0.000074820695,0.0071494905],"genre_scores_gemma":[0.93516946,0.015453571,0.031245703,0.001018308,0.0007697559,0.00037590569,0.00037638147,0.00006304698,0.015527868],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9746612,0.019798793,0.0018519808,0.0012157504,0.0015572272,0.0009150715],"domain_scores_gemma":[0.97175056,0.022423673,0.0010703993,0.00063064706,0.0036526711,0.000472027],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.021961452,0.0007392594,0.00078114064,0.00033261778,0.00069432,0.00079604116,0.0011900667,0.0011116636,0.00237047],"category_scores_gemma":[0.04160287,0.0006830614,0.00046720283,0.00081839255,0.0008505297,0.0016285031,0.00046742146,0.0019908983,0.0004067302],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00050198456,0.0010174928,0.0048442413,0.00024068709,0.00092562224,0.00012352888,0.4992768,0.013955235,0.06888957,0.014602636,0.00036361566,0.39525858],"study_design_scores_gemma":[0.00611506,0.0013930836,0.040568534,0.0069933003,0.0010472967,0.0013175759,0.406644,0.27120724,0.17601846,0.0489068,0.037976813,0.0018118636],"about_ca_topic_score_codex":0.007203956,"about_ca_topic_score_gemma":0.018724112,"teacher_disagreement_score":0.3934467,"about_ca_system_score_codex":0.007630632,"about_ca_system_score_gemma":0.0031100877,"threshold_uncertainty_score":0.9995621},"labels":[],"label_agreement":null},{"id":"W32300766","doi":"10.1039/d0cc01311k","title":"Commentary on: Michael Baumtrog's \"Considering the roles of values in practical reasoning argumentation evaluation","year":2013,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"National Natural Science Foundation of China","keywords":"Argumentation theory; Epistemology; Sociology; Philosophy","score_opus":0.20750210003030573,"score_gpt":0.512578774132735,"score_spread":0.3050766741024293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W32300766","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9142368,0.000036004167,0.00077202317,0.06666648,0.00015831263,0.00064353313,0.000001195246,0.000014487194,0.017471207],"genre_scores_gemma":[0.9888522,0.000015869691,0.0049728877,0.005812542,0.000048231464,0.00009292102,0.000008122194,0.0000049749415,0.00019225378],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99644846,0.00072071515,0.00062270596,0.0002237607,0.0018424158,0.00014194615],"domain_scores_gemma":[0.997047,0.0020397159,0.00025812924,0.00033854585,0.00027836906,0.00003824452],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006564306,0.000090080626,0.00014375837,0.00017873498,0.00010605148,0.0001734173,0.00020212271,0.00003419954,0.0075776246],"category_scores_gemma":[0.0012551518,0.000051954205,0.000045468165,0.00034301652,0.00006470712,0.0009347224,0.000066919514,0.00012568489,0.00027079115],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011297116,0.00053012685,0.35800686,0.000010156259,0.00006440658,0.0000014102724,0.012231672,0.022673223,0.0035639317,0.019861313,0.20854843,0.3743955],"study_design_scores_gemma":[0.001232089,0.00019221757,0.20647757,0.0000634444,0.000028055449,0.000004480908,0.035522033,0.7008598,0.012510495,0.039926082,0.0030196744,0.00016408427],"about_ca_topic_score_codex":0.0001284688,"about_ca_topic_score_gemma":0.00031353987,"teacher_disagreement_score":0.67818654,"about_ca_system_score_codex":0.00006535501,"about_ca_system_score_gemma":0.0001148877,"threshold_uncertainty_score":0.9933296},"labels":[],"label_agreement":null},{"id":"W326624228","doi":"10.1057/9781137314154_11","title":"Mixed-Methods Designs in Comparative Public Policy Research: The Dismantling of Pension Policies","year":2014,"lang":"en","type":"book-chapter","venue":"Palgrave Macmillan UK eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; University of Ottawa","funders":"","keywords":"Terminology; Multimethodology; Triangulation; Qualitative research; Public policy; Management science; Sociology; Political science; Social science; Engineering ethics; Engineering; Linguistics; Geography; Law; Cartography","score_opus":0.6145601725379987,"score_gpt":0.5570203215303104,"score_spread":0.057539851007688214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W326624228","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034566217,0.0004591016,0.0040220967,0.0015933485,0.0003626012,0.0010085417,0.000042188607,0.00002796628,0.98902756],"genre_scores_gemma":[0.9876832,0.00010095816,0.0018536632,0.00029194914,0.0003543265,0.000044816526,0.000017751308,0.00004155926,0.009611771],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99060845,0.002650028,0.0017280483,0.0007679584,0.0035377943,0.00070770143],"domain_scores_gemma":[0.9875894,0.008123654,0.00094517745,0.0016321662,0.0015023308,0.0002072252],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.02491777,0.00045974148,0.0010652886,0.0024660046,0.00044459724,0.00038760292,0.0017673048,0.00032565545,0.0006444379],"category_scores_gemma":[0.0021345792,0.00027998068,0.0003165587,0.00029862457,0.001134998,0.0000037994712,0.00073384645,0.00094062457,0.0003163527],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029474575,8.926634e-7,0.00039539908,0.00001382012,0.00003106072,0.0000018705335,0.0032467647,0.000038979226,0.00031516835,0.93166006,0.00017391509,0.06409261],"study_design_scores_gemma":[0.0003511768,0.00018679701,0.0045196502,0.00016774141,0.000015569907,0.000008202665,0.001716603,0.0022688524,0.0006722878,0.9709807,0.018786263,0.00032614218],"about_ca_topic_score_codex":0.00045640042,"about_ca_topic_score_gemma":0.0018408422,"teacher_disagreement_score":0.9842266,"about_ca_system_score_codex":0.00020172402,"about_ca_system_score_gemma":0.0011798028,"threshold_uncertainty_score":0.99996525},"labels":[],"label_agreement":null},{"id":"W326774523","doi":"10.3138/cjpe.025.003","title":"Constructing and Verifying Program Theory Using Source Documentation","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Documentation; Computer science; A priori and a posteriori; Logic model; Management science; Program Design Language; Software engineering; Programming language; Epistemology; Engineering; Sociology","score_opus":0.31697774328765216,"score_gpt":0.5515263442620003,"score_spread":0.23454860097434815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W326774523","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9918916,0.0001448177,0.0040497826,0.00040248863,0.0010763374,0.00088277645,0.0000017769812,0.000013448602,0.001536927],"genre_scores_gemma":[0.95885795,0.0000025239453,0.040777028,0.00007224337,0.0002023786,0.000026193118,0.0000049744626,0.000009293197,0.000047390666],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970371,0.00046439684,0.0007370986,0.0001825588,0.0013398926,0.00023894697],"domain_scores_gemma":[0.9966684,0.00030414545,0.00075373164,0.00017890196,0.0017147737,0.00038002207],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016690766,0.000107819185,0.0001760961,0.00053083105,0.0003426129,0.0009502098,0.00022739201,0.00008258521,0.0015182454],"category_scores_gemma":[0.002989497,0.00008727966,0.0000665346,0.00047905056,0.00019504166,0.0010487577,0.000013430033,0.0003289716,0.00001189746],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008375517,0.000012543366,0.051273536,0.0000030096155,0.00001351708,0.0000015018933,0.000916287,0.00027363462,0.00039764305,0.0013816262,0.00004268438,0.9456757],"study_design_scores_gemma":[0.004126844,0.0012552211,0.10528817,0.00018418187,0.00049053883,0.0012151119,0.035284746,0.7035756,0.001581367,0.08118825,0.0651,0.00070996047],"about_ca_topic_score_codex":0.0002764753,"about_ca_topic_score_gemma":0.0082802465,"teacher_disagreement_score":0.94496566,"about_ca_system_score_codex":0.00017784216,"about_ca_system_score_gemma":0.0024156186,"threshold_uncertainty_score":0.9993945},"labels":[],"label_agreement":null},{"id":"W327931636","doi":"10.3138/cjpe.018.007","title":"CES Student Essay Award: Student and Professor Perspectives","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Carleton University","funders":"","keywords":"Psychology; Sociology","score_opus":0.26322550767730857,"score_gpt":0.5604918523129583,"score_spread":0.2972663446356497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W327931636","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9852477,0.0026607155,0.00027408815,0.0032498115,0.0009813952,0.0012341669,0.0000029591786,0.0000074168247,0.0063417773],"genre_scores_gemma":[0.9972999,0.000040334533,0.0017108108,0.000102910155,0.00010906896,0.00007341614,0.0000014928222,0.000008730134,0.0006533067],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9948212,0.0010931662,0.00080342626,0.00025485732,0.0027480733,0.00027928528],"domain_scores_gemma":[0.99544424,0.00025134932,0.00060214015,0.00024192047,0.0029687274,0.0004916116],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.018892711,0.00013712855,0.0002575398,0.00056964776,0.00031214402,0.0006614123,0.00036841872,0.00006450045,0.0015242525],"category_scores_gemma":[0.002500721,0.00009933455,0.00008995281,0.000510632,0.00012947385,0.00062721706,0.000013876464,0.00021291467,0.00003816709],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017645401,0.00029825314,0.42974398,0.000008222142,0.00013690526,0.000016123186,0.048655726,0.0008023021,0.00004623619,0.011652595,0.0027788917,0.5058431],"study_design_scores_gemma":[0.0021945885,0.0011233223,0.7510324,0.00006723229,0.00017899543,0.000087507105,0.13104555,0.0019670147,0.00011434815,0.013222282,0.09867879,0.00028794497],"about_ca_topic_score_codex":0.00008620943,"about_ca_topic_score_gemma":0.007914201,"teacher_disagreement_score":0.50555515,"about_ca_system_score_codex":0.0005943541,"about_ca_system_score_gemma":0.0054057813,"threshold_uncertainty_score":0.9993885},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"grok","categories":[],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W328689389","doi":"10.7202/1085564ar","title":"Instruments de collecte et outils d’analyse qualitatifs : un défi pour évaluer la capacité à transférer","year":2004,"lang":"fr","type":"article","venue":"Recherches qualitatives","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières; Université du Québec à Montréal; Université de Sherbrooke","funders":"","keywords":"Humanities; Physics; Philosophy","score_opus":0.5053905419421856,"score_gpt":0.5839920384796292,"score_spread":0.07860149653744364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W328689389","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7434929,0.0030500777,0.092706636,0.09332589,0.00092597335,0.0007232506,0.00020589662,0.00009499747,0.0654744],"genre_scores_gemma":[0.6608012,0.0018117036,0.2554011,0.0054449085,0.00019789134,0.00011382971,0.000029539837,0.00008440427,0.076115444],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9664449,0.026997989,0.0021278257,0.000939673,0.0025231747,0.0009664114],"domain_scores_gemma":[0.97731215,0.019755369,0.00070023624,0.0006855176,0.0010314047,0.00051531126],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.064579256,0.0006308147,0.0009780683,0.0006398995,0.00030403756,0.0006195031,0.00096607377,0.00066418306,0.0026094264],"category_scores_gemma":[0.014560925,0.0005440563,0.0005710534,0.002322507,0.0007645661,0.0016986275,0.000086183194,0.0011242395,0.0016725368],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042770276,0.0011531204,0.0017242117,0.00013479797,0.00070866256,0.000028912806,0.68999594,0.0021251917,0.0025727628,0.13495179,0.0019806966,0.16419624],"study_design_scores_gemma":[0.008713373,0.00071431656,0.014876772,0.0006750912,0.0003240842,0.00004499796,0.15649664,0.0016447665,0.008457243,0.76297504,0.043999154,0.0010785011],"about_ca_topic_score_codex":0.0011507804,"about_ca_topic_score_gemma":0.00064277207,"teacher_disagreement_score":0.62802327,"about_ca_system_score_codex":0.0018104863,"about_ca_system_score_gemma":0.0066251927,"threshold_uncertainty_score":0.9997011},"labels":[],"label_agreement":null},{"id":"W32893151","doi":"10.1016/j.bjps.2020.08.018","title":"CONTINUING A TRADITION OF EXCELLENCE – LESSONS LEARNED FROM TEN YEARS OF PROVIDING A DOCTOR OF PHARMACY CURRICULUM IN A DISTANCE CAMPUS ENVIRONMENT","year":2012,"lang":"en","type":"article","venue":"INTED2012 Proceedings","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Excellence; Pharmacy; Curriculum; Medical education; Medicine; Pedagogy; Sociology; Family medicine; Political science","score_opus":0.15762315191207044,"score_gpt":0.4321532119184283,"score_spread":0.2745300600063579,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W32893151","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99724096,0.00032639533,0.0007145234,0.0003013951,0.00014271813,0.0002811684,0.000034549987,0.000009504202,0.0009487857],"genre_scores_gemma":[0.99861234,0.000098312215,0.0010611555,0.000014511184,0.00004929563,0.000036904148,0.000003926374,0.000008977868,0.00011459984],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99748844,0.00004260082,0.0009020042,0.0002704993,0.0010633465,0.00023310639],"domain_scores_gemma":[0.998429,0.0002565902,0.00087859493,0.00014797653,0.00020639686,0.0000814173],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021325997,0.00012205986,0.0003621394,0.00025056457,0.000020898056,0.000023812101,0.00037621844,0.000048019316,0.00047073726],"category_scores_gemma":[0.00060841575,0.000104691404,0.00008686042,0.00045091714,0.00013927554,0.00090248603,0.000080375576,0.00015171766,0.0000217834],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011106295,0.00049473724,0.7054741,0.00006717332,0.000019474079,4.2870488e-7,0.020943921,0.000033037777,0.2060651,0.0028918001,0.00026302133,0.06363614],"study_design_scores_gemma":[0.0041769724,0.0003596987,0.55596834,0.001482395,0.000117604926,0.0000068052273,0.035821404,0.02612671,0.3445045,0.005575095,0.02519469,0.0006657779],"about_ca_topic_score_codex":0.00025397452,"about_ca_topic_score_gemma":0.000008496949,"teacher_disagreement_score":0.14950578,"about_ca_system_score_codex":0.000060399358,"about_ca_system_score_gemma":0.000049688744,"threshold_uncertainty_score":0.5154243},"labels":[],"label_agreement":null},{"id":"W331850763","doi":"10.55016/ojs/jet.v31i3.52486","title":"Challenges in Inclusive Research","year":2018,"lang":"en","type":"article","venue":"Journal of educational thought.","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Psychology; Educational research; Pedagogy; Sociology; Mathematics education; Political science","score_opus":0.6525633229840601,"score_gpt":0.6648736158870663,"score_spread":0.012310292903006226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W331850763","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55441886,0.0021017157,0.000045831996,0.18214554,0.0020545938,0.00011142366,0.0000013888865,0.0000015103855,0.25911915],"genre_scores_gemma":[0.9889092,0.00047374264,0.0034543595,0.00026018318,0.002520247,0.0000041210596,4.52585e-7,0.0000043326254,0.004373377],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.995791,0.0005432783,0.0007275933,0.00015274883,0.002614997,0.000170383],"domain_scores_gemma":[0.9923938,0.0031821681,0.00034846447,0.00023614858,0.0037423621,0.00009707191],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017910952,0.00005673767,0.00015581047,0.0009054019,0.00014651308,0.00008648782,0.00062714453,0.000043496468,0.0045950403],"category_scores_gemma":[0.006349446,0.000038210343,0.00005653629,0.000971949,0.00014583243,0.0005405765,0.000088748915,0.0002870786,0.0007548247],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021647298,0.00094180566,0.059107576,0.000008634947,0.000032522526,0.0000056482318,0.014139376,0.00012473289,0.0006902008,0.5408297,0.16426595,0.21963738],"study_design_scores_gemma":[0.00031124026,0.0002781834,0.2831405,0.000050214552,0.0000018991534,0.00004821417,0.0057575903,0.00016106476,0.00038548376,0.31113097,0.39867482,0.000059827722],"about_ca_topic_score_codex":0.000004154163,"about_ca_topic_score_gemma":0.00014737996,"teacher_disagreement_score":0.43449032,"about_ca_system_score_codex":0.00017783731,"about_ca_system_score_gemma":0.001652142,"threshold_uncertainty_score":0.9963149},"labels":[],"label_agreement":null},{"id":"W334332912","doi":"10.3138/cjpe.017.007","title":"Evaluation in the Context of the Social Union Framework Agreement: A Case Study of the National Child Benefit","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Aside; Context (archaeology); Government (linguistics); Attribution; Joint (building); Political science; Program evaluation; Test (biology); Public administration; Public relations; Public economics; Economics; Business; Psychology; Social psychology; Engineering","score_opus":0.4168994987204216,"score_gpt":0.5202938594688366,"score_spread":0.10339436074841496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W334332912","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98735654,0.00024308628,0.000025725807,0.007401568,0.00054351403,0.0025918293,0.000010818179,0.0000011746398,0.0018257593],"genre_scores_gemma":[0.9993108,0.0000030843707,0.000058320733,0.00035214477,0.00015046188,0.00009500908,0.0000014467557,0.000005181685,0.00002355477],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98791575,0.0032476643,0.0012588891,0.00016672382,0.0072273933,0.00018357414],"domain_scores_gemma":[0.9925118,0.00045621878,0.001480135,0.0003177653,0.005161969,0.000072090465],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03921446,0.00011485607,0.00020980381,0.00037059674,0.0005605418,0.00014503676,0.00085664034,0.0000846465,0.0012867177],"category_scores_gemma":[0.004614322,0.000058371937,0.00016982172,0.0017396538,0.00014800823,0.00031714622,0.000026484904,0.0003796266,0.000005666444],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012990397,0.00062909146,0.07732988,0.0000054365564,0.000082935134,0.000004297789,0.08355642,0.009617474,0.0000075105722,0.0016289483,0.001672622,0.8254524],"study_design_scores_gemma":[0.003582366,0.00088246894,0.7039659,0.00017804794,0.00043572567,0.00028053933,0.12343308,0.14609851,0.00004044284,0.018045962,0.0028876232,0.00016932513],"about_ca_topic_score_codex":0.001649763,"about_ca_topic_score_gemma":0.11252994,"teacher_disagreement_score":0.82528305,"about_ca_system_score_codex":0.000488171,"about_ca_system_score_gemma":0.0015221854,"threshold_uncertainty_score":0.9996262},"labels":[],"label_agreement":null},{"id":"W334783997","doi":"","title":"Performance Funding of Public Universities: A Case Study","year":2011,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Performance indicator; Accountability; Government (linguistics); Process (computing); Business; Performance measurement; Accounting; Unintended consequences; Public administration; Political science; Process management; Marketing; Computer science","score_opus":0.2936115077823939,"score_gpt":0.4455267421588871,"score_spread":0.15191523437649318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W334783997","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98513794,0.00011644837,0.0023987384,0.00009425997,0.00019695473,0.00011640109,7.0258517e-7,0.000011052369,0.011927503],"genre_scores_gemma":[0.9966923,0.00020781021,0.00009011248,0.000018855682,0.000067051624,0.0000018297013,2.1210882e-7,0.00000659541,0.0029152269],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99670607,0.0003164054,0.000550966,0.00018461591,0.0011367749,0.0011051788],"domain_scores_gemma":[0.99855494,0.00013794478,0.00041419506,0.00029073405,0.00050001877,0.00010218317],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.015795562,0.00010478537,0.00019389304,0.00049137924,0.00036435522,0.00007711726,0.00056860363,0.00003396647,0.0011979026],"category_scores_gemma":[0.00010807788,0.00007661504,0.00008825871,0.00068449596,0.00005951478,0.0010423118,0.00007686904,0.00068825635,0.00007196781],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000086422246,0.00047961032,0.71607226,0.000004585198,0.0002441222,0.00015874291,0.02704947,0.000070701695,0.00003736125,0.04508474,0.00006506425,0.21064694],"study_design_scores_gemma":[0.0014082139,0.002436646,0.019112466,0.000010154073,0.000047719157,0.006003565,0.94903475,0.0032881678,0.00005009755,0.01754375,0.00086770864,0.00019673468],"about_ca_topic_score_codex":0.00014266388,"about_ca_topic_score_gemma":0.0014201133,"teacher_disagreement_score":0.9219853,"about_ca_system_score_codex":0.0006166696,"about_ca_system_score_gemma":0.0044039353,"threshold_uncertainty_score":0.99971515},"labels":[],"label_agreement":null},{"id":"W335101932","doi":"10.1596/9610","title":"The Capacity to Evaluate : Why Countries Need It","year":2006,"lang":"en","type":"article","venue":"World Bank, Washington, DC eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mandate; Capacity building; General partnership; Transformative learning; Capacity development; Poverty reduction; Process management; Process (computing); Corporate governance; International development; Business; Developing country; Work (physics); Poverty; Computer science; Political science; Economic growth; Engineering; Environmental economics; Economics; Psychology; Pedagogy; Finance","score_opus":0.10492622885051234,"score_gpt":0.3961965253982643,"score_spread":0.29127029654775194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W335101932","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.53579116,0.00010025749,0.0010368967,0.04516634,0.0018217508,0.00087868056,0.0000236822,0.0001656051,0.41501564],"genre_scores_gemma":[0.849358,0.0000041818716,0.0006944895,0.008471305,0.0004187726,0.000095076015,0.000004153128,0.00002534598,0.14092863],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.993469,0.0005235647,0.0011576666,0.00062728836,0.0035540892,0.00066840916],"domain_scores_gemma":[0.99539924,0.0019257951,0.0003776062,0.0011830674,0.0009304003,0.00018388232],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.011296775,0.00031064884,0.0003622758,0.00040679573,0.001398131,0.0016684684,0.0014113457,0.000073514304,0.0013958032],"category_scores_gemma":[0.0007626419,0.00019132372,0.000178794,0.0006691992,0.00027398666,0.00035740843,0.00023295407,0.00033265562,0.0020745322],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016797523,0.000062011786,0.017962301,0.000010133411,0.000045501238,0.0000049919363,0.0041522305,0.002126809,0.0012971725,0.11804693,0.82522726,0.030896712],"study_design_scores_gemma":[0.00045269128,0.000049142116,0.018246414,0.000031479405,0.000023465962,0.0000031344466,0.0005351108,0.001870911,0.0031727038,0.040486135,0.9348367,0.00029210842],"about_ca_topic_score_codex":0.00062788243,"about_ca_topic_score_gemma":0.025292473,"teacher_disagreement_score":0.31356692,"about_ca_system_score_codex":0.00019469006,"about_ca_system_score_gemma":0.00031007355,"threshold_uncertainty_score":0.9999019},"labels":[],"label_agreement":null},{"id":"W335129781","doi":"10.2307/1602214","title":"Toward Evidence-Based Policy for Canadian Education/Vers des politiques canadiennes d'éducation fondées sur la recherche","year":2001,"lang":"fr","type":"article","venue":"Canadian Journal of Education / Revue canadienne de l éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Sociology; Political science; Pedagogy; Humanities; Art","score_opus":0.675336837717724,"score_gpt":0.5212506463768949,"score_spread":0.15408619134082913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W335129781","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.65070707,0.0151989255,0.001613115,0.29369158,0.021542192,0.0013521408,0.00028294756,0.000018873834,0.015593192],"genre_scores_gemma":[0.92419195,0.0020196075,0.009414014,0.0074353493,0.004313328,0.00027868352,0.00019524476,0.00009519372,0.052056633],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9925877,0.0023107051,0.0018978064,0.0007240476,0.0004402105,0.0020395322],"domain_scores_gemma":[0.9733796,0.0050263163,0.0015861759,0.00095647963,0.011802322,0.0072490736],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.015232455,0.00056378095,0.00065935036,0.0052791615,0.0010764039,0.0011020974,0.0014803024,0.0007671302,0.003020163],"category_scores_gemma":[0.062784925,0.00064754405,0.00041762902,0.0033428143,0.0005327792,0.0032861377,0.0000127016965,0.0008605159,0.000100643454],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000084434236,0.0003677737,0.03220447,0.00056184625,0.00013729767,0.000020407993,0.13085729,0.0013910652,0.000080591024,0.066489905,0.23397036,0.5338346],"study_design_scores_gemma":[0.00041567814,0.0003404439,0.041529644,0.00240281,0.00023548256,0.00096903625,0.082016155,0.0011128308,0.00010628143,0.051889174,0.8183057,0.0006767982],"about_ca_topic_score_codex":0.96585757,"about_ca_topic_score_gemma":0.9980131,"teacher_disagreement_score":0.5843353,"about_ca_system_score_codex":0.06847204,"about_ca_system_score_gemma":0.56412303,"threshold_uncertainty_score":0.99993485},"labels":[],"label_agreement":null},{"id":"W345405170","doi":"10.55016/ojs/jet.v19i1.44154","title":"Linking Theory and Practice: The Practitioners' Views","year":2018,"lang":"en","type":"article","venue":"Journal of educational thought.","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Psychology; Pedagogy; Epistemology; Sociology; Philosophy","score_opus":0.22343406163867635,"score_gpt":0.5665570882160995,"score_spread":0.34312302657742316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W345405170","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17980553,0.003986185,0.0124957105,0.53342134,0.0074800877,0.0003623847,0.000005738338,0.0000072588673,0.2624358],"genre_scores_gemma":[0.9382685,0.00043106164,0.029333526,0.010813055,0.0061171586,0.000007230047,0.000002048411,0.000009464247,0.015017945],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967974,0.0010773062,0.00062774133,0.00011290345,0.0012908794,0.00009376183],"domain_scores_gemma":[0.9818526,0.014671891,0.0011123548,0.00021702803,0.0020722281,0.000073882016],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02365346,0.00006794051,0.0001212531,0.000149784,0.00035597416,0.0002881392,0.00034707034,0.00003222132,0.0032278711],"category_scores_gemma":[0.017849008,0.000034471508,0.00006345117,0.00038712707,0.0001845758,0.0012547745,0.000041282474,0.00020410623,0.00026095612],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003197143,0.00023555492,0.0052978257,0.0000035115534,0.00006674394,9.835882e-7,0.006487669,0.000036598012,0.0004195655,0.803487,0.13099852,0.05264629],"study_design_scores_gemma":[0.0001501077,0.00010573951,0.020394826,0.000023341798,0.000026782425,0.00034374316,0.0045647514,0.000062395586,0.00007912047,0.180033,0.7941696,0.000046576693],"about_ca_topic_score_codex":8.241372e-7,"about_ca_topic_score_gemma":0.0000056619333,"teacher_disagreement_score":0.75846297,"about_ca_system_score_codex":0.000041751722,"about_ca_system_score_gemma":0.00078848103,"threshold_uncertainty_score":0.9976833},"labels":[],"label_agreement":null},{"id":"W347468065","doi":"10.3138/cjpe.0023.005","title":"The Road to Evaluation Capacity Building: A Case Study from Israel","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Presentation (obstetrics); Curriculum; Outcome (game theory); Relation (database); Capacity building; Psychology; Political science; Mathematics education; Sociology; Medical education; Pedagogy; Economics; History; Computer science; Medicine; Law; Archaeology","score_opus":0.5869895881998264,"score_gpt":0.5568682661750065,"score_spread":0.030121322024819874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W347468065","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98850214,0.00031368886,0.0007815619,0.0053696265,0.0010902137,0.003144827,0.000007287293,0.000009685716,0.0007809813],"genre_scores_gemma":[0.99642354,0.0000021329024,0.0025875238,0.00047289464,0.0003371447,0.00011960386,0.0000037475404,0.000007735796,0.00004567788],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99135005,0.0018910256,0.0013092175,0.00032731565,0.004753226,0.00036914702],"domain_scores_gemma":[0.99117595,0.00044652776,0.00078840513,0.00059697183,0.0062591396,0.0007330246],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.045115404,0.00017224195,0.00026433222,0.00058607315,0.0008591939,0.0012347567,0.00069905503,0.00007258916,0.00064018136],"category_scores_gemma":[0.0081747845,0.00011215395,0.00013835568,0.0011963639,0.00005828659,0.00069230126,0.0000141847995,0.00028404006,0.00008419783],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020954245,0.00009706214,0.011682958,2.245599e-7,0.00003056772,0.00004572726,0.004168433,0.0035854003,0.000047063026,0.000116899646,0.0016548397,0.9785499],"study_design_scores_gemma":[0.003692471,0.0044816053,0.5596265,0.00005526825,0.0005900239,0.0007032326,0.046759654,0.31195873,0.0001238653,0.039043974,0.03250885,0.00045578805],"about_ca_topic_score_codex":0.009889596,"about_ca_topic_score_gemma":0.16983685,"teacher_disagreement_score":0.9780941,"about_ca_system_score_codex":0.0008702355,"about_ca_system_score_gemma":0.004507436,"threshold_uncertainty_score":0.99980205},"labels":[],"label_agreement":null},{"id":"W37046082","doi":"10.1007/s00259-023-06227-y","title":"Piloting the RAISS tool in the Canadian Context","year":2010,"lang":"en","type":"article","venue":"European Journal of Nuclear Medicine and Molecular Imaging","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Computer science; History","score_opus":0.08636113613437253,"score_gpt":0.39987525258860146,"score_spread":0.31351411645422894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W37046082","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7381265,0.00032027572,0.00016789755,0.21362686,0.00047155138,0.000089908855,3.3754387e-7,0.000002801533,0.04719382],"genre_scores_gemma":[0.9552209,0.000014702519,0.00015730952,0.0443953,0.00018738928,1.1931843e-7,1.6015164e-7,0.000008764952,0.000015360887],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99785644,0.00063757476,0.00047544748,0.000094116476,0.00079430407,0.0001421199],"domain_scores_gemma":[0.99898493,0.00026255095,0.00023185289,0.00022338885,0.00021939358,0.00007785715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015609363,0.00006923994,0.00011873128,0.00020031795,0.00024174369,0.00020990423,0.0005650393,0.0000066290695,0.00027897692],"category_scores_gemma":[0.0019502783,0.000030497682,0.000038580863,0.00022541231,0.00017382414,0.00015788329,0.000035423225,0.0005113539,0.000032817545],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039537917,0.000033527875,0.019856527,0.000005091153,0.000027864624,0.0018661817,0.049337253,0.000040041774,0.030517144,0.013090391,0.14519913,0.7399873],"study_design_scores_gemma":[0.000827186,0.00010092688,0.073909834,0.00005662464,0.00001689706,0.00060342543,0.018338451,0.0016183885,0.000021136737,0.0005714815,0.9038639,0.00007174345],"about_ca_topic_score_codex":0.0006184474,"about_ca_topic_score_gemma":0.0026316808,"teacher_disagreement_score":0.7586648,"about_ca_system_score_codex":0.000011019456,"about_ca_system_score_gemma":0.00010817301,"threshold_uncertainty_score":0.5409925},"labels":[],"label_agreement":null},{"id":"W3833358","doi":"","title":"THE INCENTIVE EFFECTS OF FISCAL EQUALIZATION GRANTS","year":2002,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Incentive; Public policy; Equalization (audio); Public administration; Face (sociological concept); Public economics; Political science; Economics; Public relations; Economic growth; Sociology; Engineering","score_opus":0.18532164595496187,"score_gpt":0.4769242987896161,"score_spread":0.29160265283465425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3833358","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7600541,0.00043686238,0.042023323,0.0042140265,0.0014199147,0.00058396335,0.0000024951144,0.000041303832,0.19122398],"genre_scores_gemma":[0.9905121,0.00008224388,0.00010148472,0.00019095039,0.000018316774,0.000006050963,5.246698e-7,0.0000017489726,0.009086593],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99828726,0.00018171193,0.00029795695,0.000107026935,0.0010372082,0.000088816756],"domain_scores_gemma":[0.9979026,0.0015708115,0.00012563982,0.00021917232,0.00015567019,0.000026161068],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013322781,0.000042094616,0.00007728577,0.00004843774,0.00014075852,0.00006781262,0.00024372037,0.00002058745,0.0017174215],"category_scores_gemma":[0.0009877859,0.000019917388,0.000037779093,0.00037237213,0.000056147284,0.00017559242,0.000037566188,0.000031156684,0.0004475162],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026293652,0.00021041962,0.09039637,0.000013863653,0.000028442257,0.0000010951803,0.0039437125,0.00028067682,0.0020430863,0.09677608,0.08439019,0.7218898],"study_design_scores_gemma":[0.0020614674,0.0004272746,0.4492403,0.000048879443,0.000025280033,0.000001721879,0.0022388184,0.3434717,0.048000112,0.0430865,0.111106575,0.00029136922],"about_ca_topic_score_codex":0.0000051951015,"about_ca_topic_score_gemma":0.00003009257,"teacher_disagreement_score":0.7215984,"about_ca_system_score_codex":0.000010517154,"about_ca_system_score_gemma":0.000008021572,"threshold_uncertainty_score":0.99919516},"labels":[],"label_agreement":null},{"id":"W41033876","doi":"10.55016/ojs/ajer.v47i1.54842","title":"Extension of Authority to Confer Bachelor of Education Degrees in Alberta","year":2001,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Peace Arch Hospital","funders":"","keywords":"Accreditation; Bachelor; Public administration; Opposition (politics); Certification; Politics; Higher education; Political science; Public relations; Sociology; Law","score_opus":0.4468641968946842,"score_gpt":0.6068446399118911,"score_spread":0.15998044301720687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W41033876","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90892243,0.0001662789,0.000027214186,0.03169894,0.00047170333,0.00020521911,0.00000134313,1.2330861e-7,0.058506735],"genre_scores_gemma":[0.9659188,0.00010115865,0.0010678452,0.00011986939,0.00017429084,0.000011621924,0.0000040006216,0.0000067237875,0.032595716],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9947013,0.00062685035,0.0013829952,0.00023211016,0.0028095918,0.00024715133],"domain_scores_gemma":[0.97122157,0.022168105,0.0005199503,0.00041107653,0.00544424,0.00023507836],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008900574,0.000095016614,0.00032703357,0.0015128294,0.00008033089,0.000054414915,0.0007678998,0.00007223015,0.018668083],"category_scores_gemma":[0.04467756,0.00007105759,0.00010503538,0.0018989302,0.00013059328,0.00050662353,0.000096854994,0.00031325224,0.0003046003],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00061597273,0.0018350792,0.8453126,0.000031982843,0.00003680176,3.9509214e-7,0.004835053,0.0007087178,0.0063655926,0.05251433,0.04041122,0.04733227],"study_design_scores_gemma":[0.00041012422,0.0003880682,0.94854325,0.00020239982,0.000008835935,0.00003836875,0.002700545,0.00043686645,0.001359381,0.009149809,0.036667965,0.000094374554],"about_ca_topic_score_codex":0.00420877,"about_ca_topic_score_gemma":0.008437195,"teacher_disagreement_score":0.10323067,"about_ca_system_score_codex":0.00016615099,"about_ca_system_score_gemma":0.005510362,"threshold_uncertainty_score":0.982229},"labels":[],"label_agreement":null},{"id":"W4200127397","doi":"10.18357/otessaj.2021.1.1.7","title":"OTESSA's Submission for the Government of Canada's Federal Pre-Budget Consultations","year":2021,"lang":"en","type":"article","venue":"The Open/Technology in Education Society and Scholarship Association Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"Government of Canada; Australian Government","keywords":"Government (linguistics); Scholarship; Federal budget; Public administration; Political science; Public relations; Open government; Public policy; Library science; Business; Open data; Law; Fiscal year","score_opus":0.06243192440988227,"score_gpt":0.43360930515104645,"score_spread":0.3711773807411642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200127397","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67987853,0.0013429766,0.0012149855,0.31510836,0.0010131783,0.00055190414,0.000030468256,0.000006452641,0.0008531553],"genre_scores_gemma":[0.9898455,0.0006990929,0.001722856,0.002238574,0.00009083802,0.00008899068,0.0000049683044,0.0000060700645,0.0053030816],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9969131,0.00046059556,0.0007215426,0.0002056477,0.0014820015,0.00021712465],"domain_scores_gemma":[0.9943529,0.0027770922,0.0009268601,0.00029844412,0.0015868612,0.000057853355],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.012083617,0.000097562384,0.00020255097,0.000038917435,0.0013943678,0.00057794503,0.00077812915,0.00015834927,0.00019963189],"category_scores_gemma":[0.007936712,0.000060098406,0.0000826151,0.0008395574,0.00007901079,0.00048596144,0.00015346338,0.00061527407,0.0000010131927],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005973344,0.00025071096,0.7927863,0.000009741359,0.00015370268,3.992486e-7,0.0051473547,0.0006192557,0.0010901617,0.026040684,0.06446895,0.10937299],"study_design_scores_gemma":[0.0015146394,0.00004812307,0.7032563,0.00006601826,0.000052073283,0.000041582152,0.07576203,0.0021638393,0.0025949024,0.10421404,0.11011919,0.00016722319],"about_ca_topic_score_codex":0.00029530894,"about_ca_topic_score_gemma":0.0075906483,"teacher_disagreement_score":0.3128698,"about_ca_system_score_codex":0.00061996526,"about_ca_system_score_gemma":0.004899137,"threshold_uncertainty_score":0.9999057},"labels":[],"label_agreement":null},{"id":"W4200215402","doi":"10.53967/cje-rce.v44i4.4885","title":"Les déterminants de la résilience et de la réussite scolaire : une approche bayésienne","year":2021,"lang":"fr","type":"article","venue":"Canadian Journal of Education / Revue canadienne de l éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Royal College of Physicians and Surgeons of Canada; Université de Moncton","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.10177743806699159,"score_gpt":0.4514944963055915,"score_spread":0.34971705823859994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200215402","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9172145,0.003455694,0.002856949,0.04071199,0.005533412,0.0001793114,0.000038441343,0.000006072164,0.030003605],"genre_scores_gemma":[0.97038686,0.00046750013,0.0070055113,0.002427048,0.0007987342,0.00003005896,0.00003046701,0.00003342284,0.018820398],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99461085,0.00260445,0.0010530915,0.00043078663,0.00033614875,0.00096469244],"domain_scores_gemma":[0.9923653,0.001481313,0.000938719,0.0005671547,0.0021190608,0.0025284335],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01152336,0.00027461085,0.00038539033,0.0008715969,0.0005708348,0.0008596547,0.0007658009,0.00032968246,0.0019239468],"category_scores_gemma":[0.008902464,0.0003061029,0.00018838918,0.0018676218,0.0004543214,0.0010332816,0.00002258322,0.0008223775,0.00005694083],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00002578058,0.0005107118,0.15082835,0.00030271345,0.00008824014,0.00040034318,0.30776438,0.0044109174,0.0016420229,0.058917902,0.07201459,0.40309405],"study_design_scores_gemma":[0.00040940405,0.000115294286,0.39639938,0.0010601286,0.00014084684,0.007584833,0.09714919,0.002426329,0.0004883742,0.019245282,0.4745835,0.00039742354],"about_ca_topic_score_codex":0.06559744,"about_ca_topic_score_gemma":0.5847195,"teacher_disagreement_score":0.51912206,"about_ca_system_score_codex":0.008371469,"about_ca_system_score_gemma":0.13107291,"threshold_uncertainty_score":0.9999391},"labels":[],"label_agreement":null},{"id":"W4200437955","doi":"10.4000/dms.6864","title":"Rencontres entre deux mondes : pratique et recherche","year":2021,"lang":"fr","type":"article","venue":"Distances et médiations des savoirs","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université TÉLUQ","funders":"","keywords":"Humanities; Philosophy; Art","score_opus":0.34084087326496554,"score_gpt":0.5121373830525309,"score_spread":0.17129650978756533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200437955","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1427853,0.06674552,0.06886119,0.17726746,0.003583996,0.0008588069,0.0009968353,0.0002035789,0.5386973],"genre_scores_gemma":[0.74335605,0.02428018,0.047782216,0.005985025,0.00023331812,0.0001763339,0.00033731834,0.00004488414,0.17780465],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9916173,0.004315186,0.0011427955,0.000816251,0.001483542,0.0006249048],"domain_scores_gemma":[0.9906142,0.006104451,0.00050289265,0.00087296515,0.0016181903,0.000287317],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.007539204,0.00036852225,0.00046780813,0.0002217851,0.00059656805,0.0012421866,0.0005852886,0.00036498866,0.012731529],"category_scores_gemma":[0.009087095,0.00034210496,0.0002777571,0.0021321087,0.00055404997,0.0022009178,0.00015261007,0.00073985703,0.0009311653],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006024035,0.00096446316,0.054204237,0.00015432778,0.00021672303,0.000069815855,0.042738073,0.014127695,0.00046741287,0.55346644,0.06111455,0.27241603],"study_design_scores_gemma":[0.0009211864,0.00012428784,0.02536284,0.00039724217,0.00011619057,0.000029363855,0.049987793,0.012224239,0.0015812918,0.20052834,0.7080985,0.0006287679],"about_ca_topic_score_codex":0.00022493083,"about_ca_topic_score_gemma":0.033100173,"teacher_disagreement_score":0.6469839,"about_ca_system_score_codex":0.0007791182,"about_ca_system_score_gemma":0.005821664,"threshold_uncertainty_score":0.9999031},"labels":[],"label_agreement":null},{"id":"W4200523229","doi":"10.18357/otessaj.2021.1.2.12","title":"Reconsidering the Mandatory in Ontario Online Learning Policies","year":2021,"lang":"en","type":"article","venue":"The Open/Technology in Education Society and Scholarship Association Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Graduation (instrument); Context (archaeology); Jurisdiction; Government (linguistics); Political science; Pandemic; Public relations; Business; Coronavirus disease 2019 (COVID-19); Engineering; Medicine; Law; Geography","score_opus":0.2683481112386572,"score_gpt":0.4612022108143008,"score_spread":0.1928540995756436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200523229","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8797527,0.0008408358,0.000021287484,0.11783028,0.0004950681,0.00013747328,8.903759e-7,0.000008869518,0.0009126259],"genre_scores_gemma":[0.9866718,0.0012209561,0.00095525593,0.0034035363,0.000101688216,0.00002531845,0.0000046762493,0.0000063657635,0.007610374],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9971322,0.000998326,0.0007053576,0.00023208058,0.0006819974,0.0002500454],"domain_scores_gemma":[0.99744314,0.0010160218,0.000611501,0.00027628394,0.0006105946,0.000042432228],"candidate_categories":["scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.01684455,0.000103655606,0.00020949056,0.00016816331,0.00094132795,0.0010880975,0.0007622691,0.00020951999,0.0005792574],"category_scores_gemma":[0.0036886039,0.00006728676,0.00007404472,0.001165538,0.00008879028,0.00098557,0.0002725983,0.0024420798,0.00002127262],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000042741945,0.00006989946,0.95506704,7.26535e-7,0.000018736182,6.9167623e-7,0.011190808,0.00021575417,0.000104234656,0.0014625528,0.0010690561,0.030796217],"study_design_scores_gemma":[0.00046378962,0.000016830933,0.7749131,0.00004908195,0.000009210144,0.000079925514,0.09724788,0.0001758084,0.00010603244,0.07443053,0.05241759,0.00009023317],"about_ca_topic_score_codex":0.00024928863,"about_ca_topic_score_gemma":0.034786332,"teacher_disagreement_score":0.18015397,"about_ca_system_score_codex":0.0008278658,"about_ca_system_score_gemma":0.0022103288,"threshold_uncertainty_score":0.99994886},"labels":[],"label_agreement":null},{"id":"W4200544394","doi":"10.25248/reas.e9290.2021","title":"Evaluation in healthcare organizations: a literature review about innovation assessment","year":2021,"lang":"en","type":"review","venue":"Revista Eletrônica Acervo Saúde","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières; Université de Montréal; Institut National de Santé Publique du Québec","funders":"","keywords":"Perspective (graphical); Process (computing); Health care; Field (mathematics); Knowledge management; Management science; Computer science; Psychological intervention; Process management; Psychology; Business; Engineering; Political science; Artificial intelligence","score_opus":0.23227888668137553,"score_gpt":0.578147159482925,"score_spread":0.3458682728015495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200544394","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000025244588,0.9877194,0.0005747095,0.00408846,0.0004889573,0.0045431717,0.00013635628,0.00006224541,0.0023841613],"genre_scores_gemma":[0.000024011157,0.9891424,0.001525792,0.0026698953,0.00029886598,0.0010552935,0.0042581614,0.000094042916,0.0009315096],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.97751033,0.006696614,0.0060202577,0.0018489462,0.007286592,0.0006372279],"domain_scores_gemma":[0.9808696,0.0015043719,0.003312858,0.0027747485,0.011355516,0.00018293317],"candidate_categories":["metaresearch","metaepi_narrow","bibliometrics","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.038681455,0.00084249856,0.0039225207,0.0019167906,0.00028250366,0.0014000102,0.0015862489,0.0006633456,0.0039022777],"category_scores_gemma":[0.020767797,0.0006406862,0.00057397457,0.030710032,0.00006400207,0.00084951817,0.00041304232,0.0016484233,0.0005608513],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010775942,0.0001058442,0.000086194275,0.021507554,0.00006498068,0.0000137751595,0.000036055106,0.000004942759,1.9676574e-7,0.019468278,0.014159155,0.94455194],"study_design_scores_gemma":[0.00026905444,0.00005354275,0.00012599849,0.1729793,0.00053876004,0.00006591437,0.000015667609,0.000284337,8.4028315e-8,0.00048048963,0.82468325,0.0005036214],"about_ca_topic_score_codex":0.000010751783,"about_ca_topic_score_gemma":0.000046686346,"teacher_disagreement_score":0.94404835,"about_ca_system_score_codex":0.00237455,"about_ca_system_score_gemma":0.012057524,"threshold_uncertainty_score":0.99963665},"labels":[],"label_agreement":null},{"id":"W4205108972","doi":"10.1002/9781444311747.ch1","title":"Introduction","year":2009,"lang":"en","type":"other","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Canadian Institutes of Health Research; University of Toronto; St. Michael's Hospital","funders":"","keywords":"Computer science","score_opus":0.1606350329300717,"score_gpt":0.5120671528135385,"score_spread":0.35143211988346684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205108972","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000012625015,0.00007383456,0.0023038608,0.0077810567,0.0009548238,0.000087316104,0.0000015948709,0.000108464395,0.9886878],"genre_scores_gemma":[0.000055882687,0.00004763643,0.0016830815,0.0007156508,0.0024974947,0.000002518691,0.000010139638,0.000038474038,0.9949491],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982468,0.000054450324,0.00021821719,0.00026968992,0.0011310772,0.00007975613],"domain_scores_gemma":[0.9992371,0.00003235314,0.00015432914,0.000476942,0.00006568594,0.000033596458],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0011308047,0.00008231996,0.0001409379,0.00034156663,0.00001987329,0.00009620047,0.0002514844,0.0000937402,0.49811915],"category_scores_gemma":[0.00017474219,0.000050546492,0.000044628225,0.00027134168,0.000014866292,0.000055258988,0.00001637643,0.00006948798,0.027790295],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.57029e-7,0.000006970617,0.000021246211,3.3341354e-7,0.0000020914472,1.0688549e-7,0.000005833128,0.0000029043138,0.0000016782465,0.003191084,0.86169946,0.13506772],"study_design_scores_gemma":[0.000055207423,0.000018962864,0.0003213323,0.0000028140876,0.000002692248,9.619731e-7,0.000026505457,0.00013904469,0.000009495046,0.0024070444,0.99694604,0.00006992423],"about_ca_topic_score_codex":0.000013803985,"about_ca_topic_score_gemma":0.00012878334,"teacher_disagreement_score":0.47032887,"about_ca_system_score_codex":0.000015395717,"about_ca_system_score_gemma":0.00006093274,"threshold_uncertainty_score":0.9729667},"labels":[],"label_agreement":null},{"id":"W4205935405","doi":"10.1016/s1701-2163(17)31086-1","title":"Evaluation, Decision-Making and Follow-Up","year":2002,"lang":"en","type":"article","venue":"Journal of Obstetrics and Gynaecology Canada","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Cegep de Sainte Foy; Congress of Aboriginal Peoples; Ontario Neurotrauma Foundation","funders":"","keywords":"Medicine; MEDLINE","score_opus":0.09833900615763815,"score_gpt":0.38795164343799865,"score_spread":0.2896126372803605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205935405","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96898955,0.009915353,0.00040580172,0.0011783332,0.0146782035,0.000110737696,0.000004385699,0.0000017469876,0.0047158604],"genre_scores_gemma":[0.9979344,0.00024633488,0.00088894647,0.00062478276,0.000026369526,0.0000013401772,1.59706e-7,0.0000039758993,0.00027371346],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99633783,0.00019994604,0.0007664194,0.00016122319,0.0023741021,0.00016045793],"domain_scores_gemma":[0.98654664,0.010597114,0.0005894967,0.00015555107,0.0019590682,0.00015211999],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005224231,0.000089567584,0.00026326787,0.00038984482,0.000198586,0.00012646218,0.0002344378,0.000065998276,0.0053490032],"category_scores_gemma":[0.04407259,0.00006301101,0.000039402166,0.0006031813,0.00004525496,0.00026432407,0.000056501463,0.0001760148,0.0000045770585],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011761642,0.000012593664,0.07550637,0.0000010759369,0.000022162807,0.00004820406,0.00016056122,0.00024071401,8.4151804e-7,0.000104501036,0.015762035,0.90813977],"study_design_scores_gemma":[0.0028629312,0.0002908367,0.8272835,0.000009024734,0.00010789519,0.0000909878,0.001196929,0.05651823,0.000003892031,0.014630009,0.09683137,0.00017437368],"about_ca_topic_score_codex":0.0003847044,"about_ca_topic_score_gemma":0.019193323,"teacher_disagreement_score":0.9079654,"about_ca_system_score_codex":0.00043696357,"about_ca_system_score_gemma":0.0010865473,"threshold_uncertainty_score":0.99870384},"labels":[],"label_agreement":null},{"id":"W4205964595","doi":"10.3918/jsicm.28_180","title":"A guide to conduct a high-quality survey research","year":2021,"lang":"en","type":"article","venue":"Journal of the Japanese Society of Intensive Care Medicine","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Centre Hospitalier Universitaire Sainte-Justine; Children's Hospital of Eastern Ontario; University of Ottawa","funders":"","keywords":"Survey research; Quality (philosophy); Political science; Psychology; Applied psychology; Philosophy; Epistemology","score_opus":0.529560313562239,"score_gpt":0.6176964259274537,"score_spread":0.08813611236521468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205964595","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85959667,0.0010146663,0.00011161926,0.13597345,0.0019088277,0.00016773115,0.000021226595,0.0000026539008,0.0012031745],"genre_scores_gemma":[0.9732941,0.00014157283,0.00075986166,0.019944144,0.0004487373,0.0000019076663,0.000004260499,0.00000910274,0.0053963494],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.98949003,0.002680642,0.0016640298,0.00024764627,0.005664905,0.0002527245],"domain_scores_gemma":[0.86596537,0.0053872885,0.0008746694,0.00074719003,0.12682392,0.0002015597],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.035224013,0.00013155131,0.0007547843,0.00014293047,0.00019757489,0.00004106471,0.0010859946,0.00008972479,0.0010186596],"category_scores_gemma":[0.13302715,0.000063897096,0.00043719434,0.0019830877,0.0005286316,0.0001520007,0.0003689881,0.0006748272,0.000023254634],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010592846,0.000023517368,0.014451138,0.000029142102,0.00011323733,0.0000064294236,0.054629266,0.00010038951,0.027174264,0.00004714058,0.9010808,0.002238787],"study_design_scores_gemma":[0.0013863437,0.00054011476,0.20562935,0.00048373718,0.000038864306,0.00011253718,0.7464657,0.000043626147,0.009691642,0.00063426595,0.034873743,0.00010007296],"about_ca_topic_score_codex":0.0010669674,"about_ca_topic_score_gemma":0.00042657752,"teacher_disagreement_score":0.866207,"about_ca_system_score_codex":0.00026295963,"about_ca_system_score_gemma":0.0012559313,"threshold_uncertainty_score":0.99989456},"labels":[],"label_agreement":null},{"id":"W4206380901","doi":"10.9707/1944-5660.1576","title":"Lost Causal: Debunking Myths About Causal Analysis in Philanthropy","year":2021,"lang":"en","type":"article","venue":"The Foundation Review","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact","funders":"","keywords":"Mythology; Causal analysis; Foundation (evidence); Causal inference; Causal model; Theory of change; Political science; Sociology; Positive economics; Economics; Management; History; Econometrics; Law","score_opus":0.20208921063289978,"score_gpt":0.5175858778005868,"score_spread":0.3154966671676871,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206380901","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14801477,0.24950635,0.06900881,0.27258047,0.00433573,0.00403218,0.00005384455,0.0002476351,0.25222018],"genre_scores_gemma":[0.88640106,0.094141796,0.00061954116,0.012496498,0.00016347939,0.000060650065,0.00017008302,0.000015796719,0.0059310687],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962793,0.00086769107,0.0009379696,0.0003579186,0.0013689881,0.00018815351],"domain_scores_gemma":[0.99756074,0.00068001216,0.00036526704,0.0008071305,0.0005357499,0.000051114737],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0070807682,0.00012539337,0.0004422896,0.0002096559,0.00018820037,0.00028163582,0.00041738103,0.0000335685,0.024636244],"category_scores_gemma":[0.0014467419,0.000075679134,0.00018323948,0.004119562,0.000069677764,0.00035726218,0.000096621945,0.00015278273,0.0033421386],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023100523,0.00028120226,0.14346671,0.00044358172,0.0005237437,0.000039603136,0.0018553428,0.0032539822,0.00025835936,0.029764643,0.026006075,0.79408365],"study_design_scores_gemma":[0.00029522824,0.000021092059,0.15972751,0.0006815062,0.00045979506,0.0000143539455,0.00038726773,0.009951083,0.000085149586,0.002224897,0.8259205,0.000231615],"about_ca_topic_score_codex":0.000046092006,"about_ca_topic_score_gemma":0.0014828335,"teacher_disagreement_score":0.7999144,"about_ca_system_score_codex":0.00006710324,"about_ca_system_score_gemma":0.000321266,"threshold_uncertainty_score":0.9974339},"labels":[],"label_agreement":null},{"id":"W4206388338","doi":"10.1037/cbs0000251.supp","title":"Supplemental Material for On the Quest for Quality Self-Report Data: HEXACO and Indicators of Careless Responding","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Behavioural Science/Revue canadienne des sciences du comportement","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Quality (philosophy); Social psychology; Applied psychology; Epistemology","score_opus":0.40390554288260777,"score_gpt":0.46138807691903044,"score_spread":0.05748253403642267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206388338","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99200976,0.00005040515,0.00023646698,0.0042010755,0.0018545837,0.00049512985,0.00094406103,0.000003229999,0.0002053013],"genre_scores_gemma":[0.995981,0.000007418285,0.0035178391,0.00020004311,0.00013692176,0.000019183517,0.00005069006,0.000006875875,0.0000800713],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99580944,0.00020108177,0.0015384062,0.00063709327,0.001088686,0.00072529336],"domain_scores_gemma":[0.99483407,0.0007103523,0.0013324245,0.0006091623,0.001573093,0.0009409166],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.031687584,0.0001792457,0.00041795633,0.0010874452,0.0020322022,0.00072889286,0.0022143445,0.00004369166,0.0004973651],"category_scores_gemma":[0.002085425,0.00012104349,0.000115712675,0.0019369656,0.0022186218,0.0010194534,0.00015178618,0.00011803591,5.9543527e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052602365,0.00009954569,0.9357036,0.00003497362,0.000042519674,0.0001428307,0.0056721023,0.00018022797,0.0027021118,0.04550062,0.0028090302,0.00705983],"study_design_scores_gemma":[0.0020468154,0.0024861565,0.8693826,0.00028929763,0.00021616727,0.0012675362,0.047163475,0.0037901404,0.0123816375,0.00748672,0.052727524,0.0007619311],"about_ca_topic_score_codex":0.009176623,"about_ca_topic_score_gemma":0.29441443,"teacher_disagreement_score":0.28523782,"about_ca_system_score_codex":0.0009084756,"about_ca_system_score_gemma":0.00811215,"threshold_uncertainty_score":0.99926704},"labels":[],"label_agreement":null},{"id":"W4206541865","doi":"10.22329/il.v41i4.7062","title":"In Memoriam","year":2021,"lang":"en","type":"article","venue":"Informal Logic","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Argumentation theory; Field (mathematics); Epistemology; Sociology; Philosophy; Mathematics","score_opus":0.2688778067387211,"score_gpt":0.5181205932034403,"score_spread":0.2492427864647192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206541865","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25052744,0.00010613468,0.0007628746,0.004845353,0.0027641617,0.0000919559,0.0000032393473,0.000023933993,0.7408749],"genre_scores_gemma":[0.97644645,0.000030830943,0.0013303991,0.007237034,0.00020137624,0.000009487487,0.0000054939997,0.0000021802375,0.014736731],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99836665,0.00005516062,0.0004410039,0.00012902694,0.0008462837,0.00016189321],"domain_scores_gemma":[0.9991889,0.00020218086,0.00007633274,0.00026989108,0.00021630964,0.00004639671],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0019235037,0.000056338165,0.000116345494,0.00012298327,0.00004534286,0.00012835929,0.00023767752,0.000041798063,0.012183901],"category_scores_gemma":[0.0007995268,0.00003896391,0.0000436063,0.0006678505,0.000020784813,0.0008415574,0.0000950278,0.00009906708,0.003474623],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010714616,0.00033002987,0.22176021,0.000018339519,0.000020620793,0.0003357267,0.0051551894,0.015557389,0.0006584114,0.3357154,0.18088754,0.23945399],"study_design_scores_gemma":[0.0005246469,0.0000462055,0.1363641,0.000004518569,0.0000014022468,0.000027296808,0.0009633748,0.006558168,0.00094731373,0.03252886,0.8219187,0.00011538924],"about_ca_topic_score_codex":0.0000057803945,"about_ca_topic_score_gemma":0.000097590724,"teacher_disagreement_score":0.7261382,"about_ca_system_score_codex":0.000021047435,"about_ca_system_score_gemma":0.00022711618,"threshold_uncertainty_score":0.9973013},"labels":[],"label_agreement":null},{"id":"W4206885021","doi":"","title":"L'évaluation réaliste des programmes en santé publique : décrypter l'ADN des interventions pour mieux en expliquer les effets","year":2017,"lang":"fr","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Political science","score_opus":0.12900930292525842,"score_gpt":0.41245929529365527,"score_spread":0.28344999236839685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206885021","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5095563,0.0053767385,0.3856526,0.040808767,0.0010333239,0.0020396367,0.00015778774,0.00031152574,0.055063333],"genre_scores_gemma":[0.72938305,0.0049611307,0.18389219,0.00016153234,0.0001560536,0.00076518086,0.0007085098,0.000101720565,0.079870604],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.96009517,0.031760346,0.0025186406,0.0019945912,0.0025575538,0.0010737278],"domain_scores_gemma":[0.9726232,0.008792258,0.002418393,0.0048130522,0.010771849,0.0005812037],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.058608852,0.00095895777,0.0010728615,0.00083501585,0.0027523327,0.004508976,0.0047549605,0.00090836623,0.004619497],"category_scores_gemma":[0.022001127,0.00090535986,0.0012404812,0.00076960557,0.0017328494,0.0019396917,0.0030891672,0.0014512163,0.00081821193],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004487709,0.0015490112,0.0519855,0.0005488656,0.0002377346,0.000007872369,0.039754592,0.00033277075,0.00094121153,0.05810594,0.0023896468,0.84410197],"study_design_scores_gemma":[0.0027701037,0.000013067757,0.6022023,0.01602359,0.00047150737,0.00008074613,0.0038232966,0.068307154,0.020475768,0.18081182,0.103100345,0.0019203338],"about_ca_topic_score_codex":0.0053627184,"about_ca_topic_score_gemma":0.031401947,"teacher_disagreement_score":0.8421816,"about_ca_system_score_codex":0.0008656203,"about_ca_system_score_gemma":0.00198305,"threshold_uncertainty_score":0.99995977},"labels":[],"label_agreement":null},{"id":"W4210289463","doi":"10.1177/016146810510701006","title":"Toward an Evaluation Habit of Mind: Mapping the Journey","year":2005,"lang":"en","type":"article","venue":"Teachers College Record The Voice of Scholarship in Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Mindset; Context (archaeology); Habit; Meaning (existential); Psychology; Principal (computer security); Meaning-making; Epistemology; Sociology; Pedagogy; Social psychology; Computer science","score_opus":0.35309932199417465,"score_gpt":0.48526479680984064,"score_spread":0.13216547481566598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210289463","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9798701,0.000459639,0.00011764519,0.012425062,0.0006981014,0.0007975637,0.00000525857,0.0000069642224,0.005619671],"genre_scores_gemma":[0.99468863,0.00005400211,0.00368275,0.00030963405,0.00022719626,0.00009571421,0.0000071626205,0.000010527411,0.0009243959],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9941204,0.00213053,0.0011318186,0.0003101893,0.0021055127,0.0002015278],"domain_scores_gemma":[0.99598444,0.0011115482,0.00091678894,0.00083438953,0.0010817557,0.00007110558],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.035429467,0.00014015728,0.00024203234,0.0004806711,0.0001962761,0.000121211815,0.0011543444,0.00010295773,0.0009563007],"category_scores_gemma":[0.0037637851,0.00008420928,0.00010050298,0.0015855876,0.00013175941,0.0014487403,0.00005626843,0.00045578543,0.00009732409],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053021995,0.00043955795,0.10790067,0.0000082351635,0.00001730603,4.1979284e-8,0.025900483,0.0012187032,0.0011111367,0.00087938196,0.001155412,0.861316],"study_design_scores_gemma":[0.000791895,0.00015411919,0.81520325,0.00015384582,0.000058247908,0.0000073414626,0.10404365,0.026107663,0.0018193406,0.015951967,0.035500154,0.00020852241],"about_ca_topic_score_codex":0.00012440978,"about_ca_topic_score_gemma":0.0010204609,"teacher_disagreement_score":0.8611075,"about_ca_system_score_codex":0.00035678924,"about_ca_system_score_gemma":0.0016871475,"threshold_uncertainty_score":0.99995697},"labels":[],"label_agreement":null},{"id":"W4210474721","doi":"10.32920/cd.v6i2.1592","title":"Deepening our Relation-in-Practice","year":2022,"lang":"en","type":"article","venue":"Journal of Critical Dietetics","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Prince Edward Island","funders":"","keywords":"Relation (database); Psychology; Sociology; Computer science; Data mining","score_opus":0.20266842832988446,"score_gpt":0.559586253688745,"score_spread":0.3569178253588606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210474721","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24680327,0.0016525455,0.06475795,0.5718548,0.014785378,0.00032585234,0.000019399557,0.000028208471,0.099772595],"genre_scores_gemma":[0.98776656,0.000015305824,0.010347233,0.0014837167,0.00014154652,0.0000019131899,3.195123e-7,0.000005427514,0.00023795973],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.995322,0.00060011336,0.001004096,0.000112527196,0.0027941454,0.00016714308],"domain_scores_gemma":[0.99502814,0.0033582721,0.00031130103,0.00017506363,0.001013257,0.000113959904],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008999309,0.00006261715,0.0001895202,0.00028313624,0.00019080917,0.00013807404,0.00040968746,0.000026144717,0.00095500925],"category_scores_gemma":[0.024433099,0.000050289575,0.00010025882,0.00052679976,0.00002835296,0.00073890603,0.00012257801,0.00059556705,0.000060388436],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011307816,0.0034772202,0.11852323,0.00004515773,0.00011803164,0.0015532746,0.013919922,0.18642011,0.0012715488,0.46825504,0.09694427,0.1083414],"study_design_scores_gemma":[0.0022452779,0.0020264776,0.10193413,0.000050396346,0.00014640157,0.0007006511,0.07818061,0.06982296,0.00012432992,0.17667198,0.56770504,0.00039176727],"about_ca_topic_score_codex":0.0000012842505,"about_ca_topic_score_gemma":0.000001718436,"teacher_disagreement_score":0.74096334,"about_ca_system_score_codex":0.00011765026,"about_ca_system_score_gemma":0.00025296613,"threshold_uncertainty_score":0.9999583},"labels":[],"label_agreement":null},{"id":"W4210664852","doi":"10.15353/juhr.v1i1.january.4673","title":"Community policing in action","year":2022,"lang":"en","type":"article","venue":"University of Waterloo Journal of Undergraduate Health Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Unit (ring theory); Strengths and weaknesses; Officer; Public relations; Stakeholder; Service (business); Resource (disambiguation); Quality (philosophy); Population; Business; Knowledge management; Computer science; Psychology; Political science; Sociology; Marketing","score_opus":0.6680037609981075,"score_gpt":0.5794339598694171,"score_spread":0.0885698011286904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210664852","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9336377,0.000035243203,0.00025732315,0.06508006,0.00014320138,0.00012012163,0.000004472852,0.0000026354198,0.0007192908],"genre_scores_gemma":[0.9954959,0.0002626863,0.00031859145,0.00012750461,0.000017557148,1.0518673e-7,0.0000017492926,0.0000035085027,0.003772362],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.98873246,0.0070232134,0.0006117007,0.00010235411,0.0032159807,0.00031427183],"domain_scores_gemma":[0.9971586,0.00094266515,0.0005616209,0.00027088058,0.00090522366,0.00016102601],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.042245816,0.00005411058,0.0002690343,0.001742362,0.0012248916,0.000032759297,0.0009421531,0.000022858103,0.00038752146],"category_scores_gemma":[0.00032569224,0.000048948914,0.00008072675,0.0013873444,0.00013170709,0.00039619723,0.00036453502,0.0014758655,0.000015175235],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0038737925,0.0032524932,0.24707492,0.00029205054,0.00013609881,0.00018093619,0.1843058,0.075317696,0.00412124,0.013097548,0.09023952,0.3781079],"study_design_scores_gemma":[0.006510174,0.0071077887,0.24402186,0.00019335005,0.00001079518,0.00020459732,0.51857454,0.0125724785,0.0005467842,0.105877824,0.10411308,0.00026671714],"about_ca_topic_score_codex":0.014677159,"about_ca_topic_score_gemma":0.007173094,"teacher_disagreement_score":0.3778412,"about_ca_system_score_codex":0.0009571196,"about_ca_system_score_gemma":0.0015136418,"threshold_uncertainty_score":0.9918842},"labels":[],"label_agreement":null},{"id":"W4210830042","doi":"10.14507/epaa.30.7002","title":"Shifting meanings: The struggle over public funding of private schools in Alberta, Canada","year":2022,"lang":"en","type":"article","venue":"Education Policy Analysis Archives","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"York University","funders":"","keywords":"Argumentative; Neoliberalism (international relations); Dominance (genetics); Discourse analysis; Public administration; Policy analysis; Government (linguistics); Sociology; Public policy; Education policy; School choice; Political science; Political economy; Higher education; Law","score_opus":0.08689183500266684,"score_gpt":0.4345089103902307,"score_spread":0.34761707538756387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210830042","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9534407,0.000049638424,0.00022665576,0.032172587,0.00015489671,0.00014005468,0.00001739708,0.000004187984,0.013793839],"genre_scores_gemma":[0.9951168,0.000005987544,0.000228683,0.0013009841,0.00008750876,0.00006661286,0.000032240336,0.0000054567417,0.0031557279],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9965501,0.00078460627,0.0007539774,0.00028829856,0.0013774174,0.00024563834],"domain_scores_gemma":[0.99696636,0.001725716,0.0005861194,0.0005635356,0.0000701952,0.00008806944],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002498403,0.000098093704,0.00023780811,0.0014985206,0.0004703506,0.00015910505,0.0008430206,0.000010080856,0.0025379483],"category_scores_gemma":[0.0019575683,0.000071116,0.00013279838,0.0051333765,0.00004750819,0.00027943528,0.0002340893,0.00022885144,0.000005447487],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007036891,0.00009204454,0.905829,0.0000029339228,0.00016273676,9.185116e-8,0.00938262,0.017123649,0.00009788912,0.048957005,0.0028916206,0.0154533405],"study_design_scores_gemma":[0.0001239664,0.000015088437,0.8856679,0.000005361959,0.000061075036,6.918485e-7,0.019267581,0.027151732,0.00006439008,0.01648788,0.051035482,0.000118858545],"about_ca_topic_score_codex":0.4903675,"about_ca_topic_score_gemma":0.64302665,"teacher_disagreement_score":0.15265912,"about_ca_system_score_codex":0.0002197777,"about_ca_system_score_gemma":0.0047614984,"threshold_uncertainty_score":0.99837387},"labels":[],"label_agreement":null},{"id":"W4210874157","doi":"10.1522/rhe.v5i2.1257","title":"Comment développer ses compétences en TIC? L’expérience des personnes expertes de divers milieux du Réseau CompéTICA","year":2022,"lang":"fr","type":"article","venue":"Revue hybride de l éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Moncton","funders":"","keywords":"Humanities; Political science; Sociology; Philosophy","score_opus":0.15762875169793764,"score_gpt":0.4185371050238507,"score_spread":0.2609083533259131,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210874157","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8343608,0.0036906404,0.0056595397,0.14986332,0.0033888074,0.00051374856,0.00008009281,0.00006625371,0.0023768037],"genre_scores_gemma":[0.97478366,0.0018215443,0.012400866,0.006081169,0.0004893076,0.00030178824,0.00007177059,0.000027163927,0.004022703],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.99439174,0.001859257,0.00083340856,0.0007163901,0.001448248,0.0007509702],"domain_scores_gemma":[0.99592453,0.002222848,0.0004164083,0.0006144713,0.000496623,0.00032510047],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0057451,0.00033036713,0.00042507763,0.00031169725,0.0019681912,0.0004484503,0.0011923267,0.00007371792,0.00898235],"category_scores_gemma":[0.0013346156,0.0003419419,0.0002022492,0.0009258233,0.00048407278,0.00082453433,0.0004283633,0.0003982892,0.0006526614],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000092464084,0.0012032631,0.14460245,0.00022061069,0.00009721125,0.00005244041,0.52978474,0.015983673,0.0008101839,0.00882801,0.19817199,0.100152984],"study_design_scores_gemma":[0.00059929286,0.0003521053,0.04459208,0.00021124282,0.00011244511,0.00050265226,0.36160535,0.17762347,0.0008138565,0.0061115157,0.40689537,0.0005806336],"about_ca_topic_score_codex":0.0019075288,"about_ca_topic_score_gemma":0.0004438703,"teacher_disagreement_score":0.20872337,"about_ca_system_score_codex":0.0032279897,"about_ca_system_score_gemma":0.001764458,"threshold_uncertainty_score":0.99990326},"labels":[],"label_agreement":null},{"id":"W4211037962","doi":"10.1177/000841740407100401","title":"From the Editor","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Occupational Therapy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology","score_opus":0.4030225389604186,"score_gpt":0.5275654557861482,"score_spread":0.1245429168257296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211037962","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9604875,0.00077104435,0.0034438472,0.025882842,0.008057253,0.00009844356,0.0000709474,0.0000026028247,0.0011855483],"genre_scores_gemma":[0.98842645,0.00002907513,0.0007848841,0.0037370096,0.0068583284,0.0000014031555,0.0000048213833,0.0000041447142,0.00015386428],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981999,0.00009136498,0.00043505925,0.00008272441,0.0010747091,0.0001162853],"domain_scores_gemma":[0.9979772,0.0005127708,0.0002896412,0.00018825715,0.0007977112,0.00023442745],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0018934492,0.00006204003,0.00010347022,0.00014228419,0.000212018,0.0002111967,0.00060706306,0.000033413762,0.004343266],"category_scores_gemma":[0.00053135375,0.00003288126,0.00009499273,0.0002862035,0.000072511546,0.0003264365,0.000003800619,0.00013122293,0.00019244531],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002597661,0.000049615126,0.30843136,3.015007e-7,0.000114218754,0.000023970471,0.007018435,0.012160765,0.00022608823,0.011849075,0.56143135,0.09843506],"study_design_scores_gemma":[0.00062735594,0.00006690664,0.41902882,0.000007900534,0.0000020717155,0.000008475489,0.0004510245,0.000034413028,0.000097883516,0.0440303,0.5355979,0.000046922825],"about_ca_topic_score_codex":0.002447152,"about_ca_topic_score_gemma":0.009759533,"teacher_disagreement_score":0.11059745,"about_ca_system_score_codex":0.00012432886,"about_ca_system_score_gemma":0.0048719444,"threshold_uncertainty_score":0.9965669},"labels":[],"label_agreement":null},{"id":"W4211156794","doi":"10.1177/000841740607300301","title":"From the Editor","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Occupational Therapy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology","score_opus":0.34001833854189306,"score_gpt":0.5106910529367303,"score_spread":0.17067271439483728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211156794","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97060466,0.0010609366,0.0020392274,0.0147226285,0.007775306,0.00009792541,0.00009880726,0.0000028719016,0.0035976246],"genre_scores_gemma":[0.9852001,0.0000122322435,0.00046711572,0.0018722526,0.011774137,0.0000013970633,0.000009677415,0.0000041382386,0.0006589365],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981289,0.00013231461,0.00048234907,0.00008086165,0.0010595497,0.000116052615],"domain_scores_gemma":[0.9977509,0.0007914266,0.0003227688,0.00017575428,0.00081708,0.00014210826],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0019210158,0.00006139591,0.00010259645,0.00014395945,0.00020533406,0.00023712237,0.0005409962,0.000032639553,0.006301031],"category_scores_gemma":[0.0002836104,0.00003267724,0.00009360381,0.0002728143,0.00006732241,0.00028155328,0.000003324332,0.00011111144,0.00014351195],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042693497,0.000009264269,0.25754404,5.466712e-8,0.000013109231,0.0000034081254,0.00028502083,0.0008415159,0.00005430732,0.0019739065,0.72329366,0.015939016],"study_design_scores_gemma":[0.00022209765,0.000024561403,0.4683044,0.0000027301032,0.0000012956049,0.0000035097826,0.00012594135,0.00012694985,0.000040894698,0.017389776,0.5137283,0.000029547424],"about_ca_topic_score_codex":0.005447483,"about_ca_topic_score_gemma":0.017107325,"teacher_disagreement_score":0.21076033,"about_ca_system_score_codex":0.00007254878,"about_ca_system_score_gemma":0.0025170567,"threshold_uncertainty_score":0.9946073},"labels":[],"label_agreement":null},{"id":"W4212912101","doi":"10.7202/1086425ar","title":"Public Expectations of School Board Trustees","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Educational Administration and Policy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Wilfrid Laurier University; Conestoga College","funders":"","keywords":"Delegate; Judgement; Sample (material); Psychology; Public relations; Political science; Law","score_opus":0.2269662685585933,"score_gpt":0.48122593209669295,"score_spread":0.25425966353809965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4212912101","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71028376,0.00050702563,0.00005350144,0.2511011,0.0007442886,0.00012611809,0.00011672247,0.0000016622091,0.03706584],"genre_scores_gemma":[0.99475056,0.000009782577,0.0003832599,0.00082128285,0.00031570508,0.000010786896,0.00001530976,0.000003744467,0.0036895517],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99818075,0.00018356666,0.0006844942,0.00010179471,0.0007233115,0.00012611019],"domain_scores_gemma":[0.9975753,0.0004237343,0.0005352112,0.00013784363,0.00075371645,0.0005742047],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011387706,0.00006391399,0.00012980877,0.0010602286,0.00040389496,0.0001704182,0.00029128778,0.000020342051,0.016733352],"category_scores_gemma":[0.0026811922,0.0000573718,0.00006721162,0.00057093444,0.00009054723,0.00038640513,0.000012117536,0.00013712511,0.000022928552],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032499673,0.00014198688,0.2541824,0.0000069454095,0.000043577445,0.0000025341835,0.0050596762,0.00030850613,0.00010871839,0.6517876,0.07623067,0.012094877],"study_design_scores_gemma":[0.00059264386,0.0006484988,0.5240072,0.000009530675,0.00001780617,0.0003408492,0.020473452,0.00024061308,0.000096988646,0.07409615,0.3793039,0.00017235093],"about_ca_topic_score_codex":0.00046747163,"about_ca_topic_score_gemma":0.006414077,"teacher_disagreement_score":0.57769144,"about_ca_system_score_codex":0.0001739151,"about_ca_system_score_gemma":0.027191464,"threshold_uncertainty_score":0.9841655},"labels":[],"label_agreement":null},{"id":"W4213063025","doi":"10.3138/cjpe.72865.en","title":"Roots and Relations: Celebrating Good Medicine in Indigenous Evaluation","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Indigenous; Traditional medicine; Sociology; Psychology; Political science; Medicine; Biology; Ecology","score_opus":0.27978764456850475,"score_gpt":0.5262429699080209,"score_spread":0.24645532533951614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213063025","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9775889,0.0049584657,0.0005268059,0.00791092,0.00075792253,0.0012292688,0.0000029296978,0.0000061849614,0.0070186025],"genre_scores_gemma":[0.99665123,0.000034791974,0.0026925178,0.00019480259,0.00017146727,0.00006495977,0.000027922924,0.0000081587,0.00015417121],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99406713,0.001324287,0.0012636663,0.00025026992,0.0028433716,0.00025129583],"domain_scores_gemma":[0.99346375,0.0004549975,0.0007303446,0.00024212802,0.00477355,0.0003352137],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.030536922,0.00011555905,0.00026597249,0.000920401,0.00024222917,0.0002678779,0.00019931329,0.00009770841,0.0034133026],"category_scores_gemma":[0.0102188885,0.000094504896,0.00005048755,0.0014287628,0.00008354196,0.0007792089,0.000012797006,0.0002675326,0.000027757325],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004596401,0.000027510516,0.16425598,0.0000034150412,0.000013107188,0.0000115716575,0.0041026645,0.003866218,0.00009962884,0.00034405905,0.0004991876,0.82677203],"study_design_scores_gemma":[0.0024406686,0.0004332862,0.80741656,0.00019082477,0.00013511017,0.00015084111,0.005734523,0.13922137,0.000085221596,0.03364631,0.010378179,0.0001671233],"about_ca_topic_score_codex":0.0007310564,"about_ca_topic_score_gemma":0.10389733,"teacher_disagreement_score":0.82660496,"about_ca_system_score_codex":0.0006167421,"about_ca_system_score_gemma":0.009383112,"threshold_uncertainty_score":0.9982663},"labels":[],"label_agreement":null},{"id":"W4213266427","doi":"10.1002/ev.20337","title":"Issue Information","year":2019,"lang":"en","type":"paratext","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Citation; Action (physics); World Wide Web; Information retrieval","score_opus":0.20791329578082282,"score_gpt":0.5385400636795997,"score_spread":0.3306267678987769,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213266427","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00024144747,0.0009448001,0.07355205,0.0045913914,0.06122267,0.0054220525,0.00044038362,0.00009016799,0.85349506],"genre_scores_gemma":[0.0024065133,0.00029006903,0.0018545921,0.000993277,0.0023534442,0.0008362252,0.0044923048,0.000036184305,0.9867374],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.993071,0.00040294646,0.0014343439,0.000562716,0.0042070136,0.00032198595],"domain_scores_gemma":[0.9927869,0.0010831314,0.0011773505,0.0010132203,0.0037969283,0.00014246858],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008838729,0.0003340359,0.00050516607,0.0012814364,0.00041582587,0.00085002056,0.0006003324,0.0004449764,0.11123613],"category_scores_gemma":[0.003589746,0.0002840584,0.0003441547,0.001224117,0.000029955749,0.0021803929,0.000066058856,0.00029133208,0.26169512],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002342681,0.000016409407,0.000013124994,0.000014773145,0.000025489455,3.1654679e-9,0.0002860884,0.009440855,0.0000067757483,0.00011850827,0.67054886,0.31950566],"study_design_scores_gemma":[0.0014609336,0.00014032953,0.00039785934,0.000043049637,0.00012222133,0.0000014910187,0.00031785396,0.07297323,0.00013815651,0.0024111066,0.92169315,0.0003006422],"about_ca_topic_score_codex":0.00013313135,"about_ca_topic_score_gemma":0.00012014309,"teacher_disagreement_score":0.31920502,"about_ca_system_score_codex":0.0005915871,"about_ca_system_score_gemma":0.0034036806,"threshold_uncertainty_score":0.99996114},"labels":[],"label_agreement":null},{"id":"W4213418543","doi":"10.1080/0142159x.2022.2041191","title":"Implementation of competence committees during the transition to CBME in Canada: A national fidelity-focused evaluation","year":2022,"lang":"en","type":"article","venue":"Medical Teacher","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary; University of Toronto; University of Alberta; Queen's University; Royal College of Physicians and Surgeons of Canada; University of Ottawa","funders":"Royal College of Physicians and Surgeons of Canada","keywords":"Competence (human resources); Fidelity; Transition (genetics); MEDLINE; Program evaluation","score_opus":0.14175828394901532,"score_gpt":0.47312357857073745,"score_spread":0.33136529462172215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213418543","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9795551,0.000020394891,0.0006698175,0.018588176,0.00016165375,0.00039028205,0.000022278316,0.000004234191,0.0005880869],"genre_scores_gemma":[0.9982397,0.0000012247725,0.000074844276,0.001326124,0.000039032744,0.00019941614,0.000021776175,0.0000032090907,0.000094648596],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99018425,0.0010728096,0.00065945846,0.00019522272,0.0077499794,0.00013829567],"domain_scores_gemma":[0.9990468,0.00027251084,0.0001404639,0.00016714254,0.00030349358,0.00006957556],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.013976699,0.00006135048,0.00012727117,0.000135934,0.00018526368,0.000018963523,0.00042061834,0.000016232909,0.041148987],"category_scores_gemma":[0.0007567336,0.000043370328,0.00002886446,0.0006437159,0.000028649212,0.00011003868,0.00008352026,0.00021818875,0.000012086098],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012654328,0.00026474614,0.71968555,0.000015510019,0.000035031328,0.0000054603015,0.018428043,0.033989027,0.000642023,0.0014420379,0.022551706,0.20281433],"study_design_scores_gemma":[0.0008991646,0.000037446393,0.8143124,0.0000059771814,0.0000048034026,0.0000025863792,0.011115102,0.16911663,0.00005690203,0.0013347948,0.0030492262,0.00006497902],"about_ca_topic_score_codex":0.21084994,"about_ca_topic_score_gemma":0.788679,"teacher_disagreement_score":0.57782906,"about_ca_system_score_codex":0.00095877814,"about_ca_system_score_gemma":0.0034282997,"threshold_uncertainty_score":0.9597275},"labels":[],"label_agreement":null},{"id":"W4214479423","doi":"10.18438/b8j62j","title":"Conducting Your Own Research: Something to Consider","year":2009,"lang":"en","type":"article","venue":"Evidence Based Library and Information Practice","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Data science; World Wide Web","score_opus":0.5950059816843779,"score_gpt":0.5666374111403778,"score_spread":0.028368570544000105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214479423","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05854328,0.00040031166,0.010368232,0.8332908,0.0004486217,0.00076583604,0.000007451637,0.00016194176,0.09601353],"genre_scores_gemma":[0.7288123,0.00021207544,0.024963468,0.24494733,0.00012332674,0.000016906579,0.0000084460235,0.0000045096467,0.00091163046],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99533504,0.0011538385,0.0008507086,0.00025675813,0.0021132624,0.00029036732],"domain_scores_gemma":[0.9861784,0.012080834,0.00040423544,0.0004669618,0.0006150051,0.00025455526],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["scholarly_communication","insufficient_payload"],"category_scores_codex":[0.016106244,0.00011882529,0.00016200726,0.0008096654,0.00058097637,0.002383033,0.0004239078,0.00007437984,0.0020682819],"category_scores_gemma":[0.046224818,0.0000913191,0.000036686455,0.0018245672,0.00006541004,0.30207795,0.00013065751,0.00045380648,0.001173215],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00054313574,0.00007345574,0.0013166199,0.000025776893,0.000011312328,0.000006836843,0.0047107167,0.0028609943,0.00079576427,0.5254686,0.06462188,0.39956492],"study_design_scores_gemma":[0.00031134178,0.0003638764,0.008109075,0.00016713205,0.000007826464,0.000022017388,0.011365325,0.010634419,0.003419672,0.0061614527,0.9592545,0.00018335092],"about_ca_topic_score_codex":0.0000044056096,"about_ca_topic_score_gemma":5.8198573e-8,"teacher_disagreement_score":0.89463264,"about_ca_system_score_codex":0.000019245357,"about_ca_system_score_gemma":0.00059730303,"threshold_uncertainty_score":0.99960446},"labels":[],"label_agreement":null},{"id":"W4214512210","doi":"10.1016/j.jneb.2007.04.250","title":"Evaluation Roadmap","year":2007,"lang":"en","type":"article","venue":"Journal of Nutrition Education and Behavior","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.20812986869299913,"score_gpt":0.5538534307566955,"score_spread":0.34572356206369637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214512210","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99167585,0.0006869486,0.0013848036,0.0017930308,0.001982629,0.0002543441,0.0000012753898,0.000004407637,0.0022166802],"genre_scores_gemma":[0.99490416,0.00009105932,0.0036257035,0.00033070432,0.0005536982,0.00002353211,0.000003862783,0.00000372281,0.00046354896],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99667865,0.00016419486,0.0008194026,0.000112620975,0.002129164,0.000095973905],"domain_scores_gemma":[0.99550307,0.00019902825,0.0006136476,0.00013227764,0.0034115596,0.00014039747],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01444412,0.00006629181,0.00013352222,0.0005460048,0.000100399884,0.00013703611,0.00014196713,0.000052845982,0.001619959],"category_scores_gemma":[0.0007428206,0.000049401522,0.00007066342,0.00037901048,0.00003279697,0.0006469859,0.000010535207,0.00011787479,0.000039659666],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015704176,0.0035317747,0.020414185,0.000003898625,0.000004758493,9.444784e-7,0.0005302309,0.0000028425561,0.0019449597,0.00033370726,0.008656778,0.9645602],"study_design_scores_gemma":[0.0011828502,0.00025165323,0.8858705,0.000046634188,0.0001692086,0.00022242326,0.011296481,0.0001569571,0.001552428,0.005277357,0.09387224,0.00010127801],"about_ca_topic_score_codex":0.0000028054703,"about_ca_topic_score_gemma":0.000014660886,"teacher_disagreement_score":0.96445894,"about_ca_system_score_codex":0.00011713866,"about_ca_system_score_gemma":0.00052668573,"threshold_uncertainty_score":0.9992927},"labels":[],"label_agreement":null},{"id":"W4214553715","doi":"10.1002/ev.20486","title":"How does teaching with cases support the development of evaluation competencies?","year":2021,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Adaptability; Craft; Evaluation methods; Professional development; Medical education; Psychology; Computer science; Knowledge management; Pedagogy; Engineering; Medicine; Management","score_opus":0.2469212988547501,"score_gpt":0.49329140127841276,"score_spread":0.24637010242366267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214553715","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8607902,0.0002918822,0.1043453,0.013260816,0.0018444513,0.002941698,0.000031070762,0.00007475683,0.016419848],"genre_scores_gemma":[0.9648371,0.0000063739,0.02707852,0.00011468968,0.00015439397,0.0004217245,0.00014619323,0.000012248909,0.0072287996],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99401885,0.0007884622,0.0006669287,0.00041772588,0.0039183707,0.00018963215],"domain_scores_gemma":[0.99317056,0.0015887308,0.0005124198,0.0005450607,0.0041137454,0.00006948125],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017232427,0.00014608008,0.00021787168,0.00021609459,0.0008875165,0.00035044368,0.00020652989,0.000052883664,0.0015876264],"category_scores_gemma":[0.006729027,0.00007824304,0.00010254022,0.00071639643,0.000057343226,0.0006435508,0.000043081756,0.00012007604,0.000020273525],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057560286,0.00014328444,0.0049280836,0.000011571336,0.000092286326,3.2130592e-7,0.00588848,0.003547771,0.0024132817,0.0015831402,0.005159792,0.9761744],"study_design_scores_gemma":[0.005898815,0.0005534716,0.13618669,0.00012202798,0.00095734297,0.00009666706,0.042952344,0.22881223,0.0636058,0.019312836,0.500869,0.00063278864],"about_ca_topic_score_codex":0.000026136799,"about_ca_topic_score_gemma":0.0042983885,"teacher_disagreement_score":0.97554165,"about_ca_system_score_codex":0.00026127408,"about_ca_system_score_gemma":0.004420108,"threshold_uncertainty_score":0.99932504},"labels":[],"label_agreement":null},{"id":"W4214576671","doi":"10.52358/mm.vi9.254","title":"L’intégration des technologies numériques à l’évaluation des apprentissages à distance en enseignement supérieur : quelles transformations des pratiques évaluatives?","year":2022,"lang":"fr","type":"article","venue":"Médiations et médiatisations","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université du Québec en Abitibi-Témiscamingue; Université de Sherbrooke","funders":"","keywords":"Political science; Humanities; Art","score_opus":0.09611295305263336,"score_gpt":0.40672660755075507,"score_spread":0.3106136544981217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214576671","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32715696,0.019098122,0.60529965,0.017131886,0.0014019777,0.0036352598,0.002733496,0.00096085225,0.02258177],"genre_scores_gemma":[0.896203,0.015754359,0.065367855,0.000282999,0.000136827,0.0043783947,0.0015761525,0.00008732815,0.016213119],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9863324,0.005575676,0.0025392342,0.0011309152,0.0034224733,0.0009992805],"domain_scores_gemma":[0.99216175,0.0033433351,0.0011587883,0.0011425179,0.0019720336,0.00022159747],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01019365,0.00074995816,0.000694715,0.0015168492,0.008114123,0.0015595305,0.0011786644,0.00030878332,0.008155613],"category_scores_gemma":[0.0039625824,0.00079904014,0.00041903427,0.004186726,0.0017808108,0.0061717066,0.00041760947,0.0009641046,0.0002910635],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000436748,0.001517351,0.024581807,0.0001780174,0.00024615563,0.000005132936,0.23010464,0.12155221,0.0006056986,0.13011488,0.012996254,0.4780542],"study_design_scores_gemma":[0.001694892,0.00092697504,0.13723987,0.0002924045,0.00036312762,0.000060612296,0.32952335,0.13388811,0.001630822,0.29455242,0.09851328,0.001314117],"about_ca_topic_score_codex":0.000528079,"about_ca_topic_score_gemma":0.009218054,"teacher_disagreement_score":0.569046,"about_ca_system_score_codex":0.002460357,"about_ca_system_score_gemma":0.0032742661,"threshold_uncertainty_score":0.99947697},"labels":[],"label_agreement":null},{"id":"W4214649046","doi":"10.3821/1913-701x(2008)141[256a:dp]2.0.co;2","title":"Defining “practice”","year":2008,"lang":"en","type":"article","venue":"Canadian Pharmacists Journal / Revue des Pharmaciens du Canada","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.19465904461911251,"score_gpt":0.44106514417827525,"score_spread":0.24640609955916273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214649046","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8862084,0.0027668336,0.0010032945,0.0024833838,0.009812671,0.00047639429,0.00036724098,0.00006395763,0.09681783],"genre_scores_gemma":[0.9799616,0.0036359185,0.0010209046,0.01081632,0.00074619876,0.000010562287,0.000013737557,0.000035197972,0.0037595953],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9942992,0.0005245784,0.001175589,0.0005156895,0.0024201747,0.0010648139],"domain_scores_gemma":[0.99295574,0.0009689315,0.0005940048,0.000452044,0.0022391507,0.002790125],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004567631,0.00033287847,0.00040942483,0.0007439681,0.0024497064,0.0005006636,0.0013566875,0.00006319923,0.0088048745],"category_scores_gemma":[0.0034084707,0.0003017517,0.00018837457,0.0015179368,0.00024966153,0.0016726664,0.00006526739,0.00082403445,0.0004939069],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015757355,0.000086036875,0.01730576,0.00002303564,0.00020631621,0.13429506,0.0054399516,0.009954293,0.0004323537,0.0011816701,0.4794817,0.35143626],"study_design_scores_gemma":[0.0009298391,0.00002931897,0.00012796288,0.0000046161376,0.000036830585,0.489409,0.00005650803,0.0066233417,0.00034858866,0.00021776825,0.50187355,0.00034268235],"about_ca_topic_score_codex":0.018108029,"about_ca_topic_score_gemma":0.0850986,"teacher_disagreement_score":0.35511392,"about_ca_system_score_codex":0.0022720774,"about_ca_system_score_gemma":0.015046114,"threshold_uncertainty_score":0.99994344},"labels":[],"label_agreement":null},{"id":"W4220680129","doi":"10.3138/cjpe.73686","title":"Michael D. Fetters. (2020). <i>The Mixed Methods Research Workbook: Activities for Designing Implementing, and Publishing Projects</i> .","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Workbook; Publishing; Management; Library science; Sociology; Political science; Computer science; Economics; Law","score_opus":0.573506722105812,"score_gpt":0.60678165072158,"score_spread":0.033274928615767974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220680129","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84028107,0.005984673,0.066250406,0.06938068,0.0041076136,0.0106238155,0.00005264958,0.000033973014,0.0032851023],"genre_scores_gemma":[0.9118855,0.000011441339,0.08522473,0.0007527543,0.00039021703,0.0012044457,0.000018951623,0.000021319624,0.0004906172],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9900618,0.005093637,0.00085937354,0.00028974723,0.0031101035,0.00058533787],"domain_scores_gemma":[0.9934396,0.0029455947,0.0007360206,0.0002731183,0.0023309493,0.0002747095],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.16884273,0.00011134995,0.0002117425,0.0008732485,0.0023335847,0.0031283698,0.00077130744,0.000043724864,0.0007253903],"category_scores_gemma":[0.008394346,0.00008190744,0.0001076912,0.001239718,0.00014671055,0.0013990839,0.00011551182,0.000637818,0.0000013380611],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028577331,0.000014752091,0.0046784254,0.000005976339,0.000032189175,0.0000018435725,0.0054357247,0.00042153828,0.00029882928,0.00034231803,0.0677884,0.9209514],"study_design_scores_gemma":[0.0013920309,0.00095944933,0.006645488,0.00003407059,0.00010500895,0.00010486658,0.068605624,0.07160179,0.00051362213,0.021219734,0.82861745,0.00020083808],"about_ca_topic_score_codex":0.0005210855,"about_ca_topic_score_gemma":0.006009505,"teacher_disagreement_score":0.92075056,"about_ca_system_score_codex":0.0005567383,"about_ca_system_score_gemma":0.005559565,"threshold_uncertainty_score":0.9999584},"labels":[],"label_agreement":null},{"id":"W4220683166","doi":"10.3138/cjpe.73683","title":"Why a Focus on Integration and Complex Mixed Methods Evaluation Designs?: Introducing this Special Issue of the <i>Canadian Journal of Program Evaluation</i>","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Queen's University; University of Alberta","funders":"","keywords":"Focus (optics); Management science; Engineering ethics; Program evaluation; Sociology; Computer science; Political science; Engineering; Public administration","score_opus":0.4085758629978245,"score_gpt":0.5421811162476561,"score_spread":0.13360525324983158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220683166","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79589653,0.0051997695,0.016436744,0.08448081,0.03682384,0.036404587,0.00017549474,0.00004451118,0.024537738],"genre_scores_gemma":[0.97180945,0.000008659741,0.025691837,0.00060308736,0.0013913565,0.0003725316,0.00003321671,0.000026032987,0.00006385353],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97909874,0.010128319,0.002414211,0.00039599813,0.0075135953,0.00044915406],"domain_scores_gemma":[0.98266774,0.0008112181,0.003427791,0.0005819848,0.011878119,0.0006331444],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10336724,0.00027775473,0.00058952166,0.0019217015,0.0013357421,0.0007384312,0.0010435405,0.00013439982,0.016071681],"category_scores_gemma":[0.014582077,0.00020392684,0.000321758,0.0022574884,0.00033865197,0.00081803265,0.00004709744,0.000810898,0.000008801129],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000069669324,0.0000993053,0.0022828926,0.00000603386,0.000073385454,0.000001677159,0.0043871533,0.016620424,0.0002623894,0.00036849704,0.042504225,0.93332434],"study_design_scores_gemma":[0.0050961007,0.005383277,0.08609597,0.00020757245,0.0014145292,0.0003092722,0.0098429695,0.5588755,0.0020779336,0.044207502,0.28597587,0.00051347364],"about_ca_topic_score_codex":0.00547071,"about_ca_topic_score_gemma":0.20998779,"teacher_disagreement_score":0.9328109,"about_ca_system_score_codex":0.0024790128,"about_ca_system_score_gemma":0.022517025,"threshold_uncertainty_score":0.99996436},"labels":[],"label_agreement":null},{"id":"W4220735178","doi":"10.3138/cjpe.71488","title":"A Framework to Combine Mixed Methods Integration and Developmental Evaluation to Study Complex Systems","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Stakeholder; Context (archaeology); Scale (ratio); Work (physics); Key (lock); Computer science; Literacy; Data collection; Process management; Management science; Knowledge management; Data science; Sociology; Business; Political science; Public relations; Engineering; Social science; Geography","score_opus":0.5638809926219458,"score_gpt":0.6081958073315192,"score_spread":0.044314814709573436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220735178","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93464243,0.00019710288,0.05408008,0.0026382841,0.002013852,0.005999939,0.000013580102,0.000011703282,0.00040302597],"genre_scores_gemma":[0.9119889,6.8321015e-7,0.08641133,0.00039641577,0.00008653526,0.001035029,0.000024159675,0.000012532265,0.000044382024],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98843443,0.005070539,0.0013445165,0.00036736293,0.004465838,0.0003173208],"domain_scores_gemma":[0.9943734,0.0005944391,0.00057859597,0.0002728222,0.0034770488,0.0007037071],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.07062779,0.00016697777,0.00035012775,0.001375372,0.0008135756,0.00068316195,0.00050996814,0.00004526079,0.0033401647],"category_scores_gemma":[0.008052069,0.00014377138,0.000062325504,0.0019545332,0.000029747913,0.0004438978,0.00008999078,0.00030420715,0.000042564032],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000435071,0.00012757885,0.008710627,0.0000016324119,0.00004262944,0.0000024686753,0.011100038,0.015608054,0.0001495409,0.00037556796,0.0025470646,0.9612913],"study_design_scores_gemma":[0.0023496614,0.004977043,0.481616,0.000056666882,0.00026869366,0.00014246278,0.13413844,0.33010417,0.000077126104,0.008142937,0.03772621,0.00040062153],"about_ca_topic_score_codex":0.0007284707,"about_ca_topic_score_gemma":0.006962473,"teacher_disagreement_score":0.96089065,"about_ca_system_score_codex":0.0017027915,"about_ca_system_score_gemma":0.0039430014,"threshold_uncertainty_score":0.99757093},"labels":[],"label_agreement":null},{"id":"W4220870230","doi":"10.3138/cjpe.36.3.ann-en","title":"Announcement from Roots and Relations: Celebrating Good Medicine in Indigenous Evaluation","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Indigenous; Traditional medicine; Political science; Social science; Sociology; History; Medicine; Biology; Ecology","score_opus":0.26152087117811373,"score_gpt":0.5024621923116173,"score_spread":0.24094132113350353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220870230","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98627293,0.0031238855,0.00031726825,0.00507677,0.0009232503,0.0019230961,0.000019841656,0.000006114595,0.0023368637],"genre_scores_gemma":[0.99776775,0.00001365655,0.0013553223,0.00024376185,0.00015927294,0.00028231787,0.00009574481,0.000008481438,0.00007371128],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9919996,0.0017562232,0.0013287263,0.00027491915,0.0043841545,0.00025634136],"domain_scores_gemma":[0.9962669,0.00043104016,0.0009900079,0.00024312014,0.0017933408,0.0002756093],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03738723,0.00012238139,0.0002557585,0.0011332657,0.0005618665,0.0001771652,0.00033432277,0.000050140796,0.0073728603],"category_scores_gemma":[0.0029252872,0.00010461313,0.000046111738,0.0012092221,0.00007160386,0.0006185558,0.000030077377,0.00036049302,0.0000123215805],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001625537,0.00004786269,0.19577709,0.0000014426024,0.000019786385,0.000005546967,0.009968947,0.02714721,0.00007649368,0.00016561271,0.0011621304,0.76561165],"study_design_scores_gemma":[0.003105009,0.0012198332,0.6409743,0.00006532271,0.00014295707,0.000035669636,0.013397944,0.27466822,0.000011452702,0.036801275,0.029387163,0.00019088664],"about_ca_topic_score_codex":0.0057122204,"about_ca_topic_score_gemma":0.07802388,"teacher_disagreement_score":0.76542073,"about_ca_system_score_codex":0.0014927584,"about_ca_system_score_gemma":0.005845272,"threshold_uncertainty_score":0.99979067},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W4220912151","doi":"10.46697/001c.33157","title":"Agenda for Practice-Oriented Research: From Relevance versus Rigor to Relevance with Rigor","year":2022,"lang":"en","type":"article","venue":"AIB Insights","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"","keywords":"Relevance (law); Rigour; Engineering ethics; Political science; Public relations; Sociology; Epistemology; Engineering; Law","score_opus":0.46562993543000325,"score_gpt":0.5577739879556807,"score_spread":0.09214405252567742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220912151","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8534968,0.0014061565,0.025017912,0.039833985,0.007994142,0.0046316255,0.00043558594,0.00024905746,0.06693478],"genre_scores_gemma":[0.9428271,0.000088741675,0.03374006,0.0037178192,0.00042427945,0.0012860862,0.00009268164,0.00004792872,0.017775308],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9921185,0.00091164064,0.0006341405,0.0010009037,0.004818208,0.00051665783],"domain_scores_gemma":[0.98240215,0.014044641,0.00032850352,0.0012312428,0.0017686381,0.00022485557],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.005037695,0.00019617562,0.00029959032,0.00041536815,0.001458158,0.00023441523,0.0009940387,0.000051060513,0.0018401409],"category_scores_gemma":[0.011169945,0.00014236038,0.000079641664,0.0023123522,0.00011303862,0.0009722787,0.0003707841,0.00050413224,0.00090621127],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.023429897,0.0011115661,0.00076123676,0.000017895783,0.00026921195,0.0001571438,0.029417457,0.012879196,0.0026262559,0.06425229,0.74021924,0.12485859],"study_design_scores_gemma":[0.0022377302,0.0018244226,0.00070527213,0.000016525013,0.000018833773,0.0000034156265,0.005959798,0.004010527,0.0010916421,0.006414129,0.977488,0.00022970793],"about_ca_topic_score_codex":0.00019264572,"about_ca_topic_score_gemma":0.0008967378,"teacher_disagreement_score":0.23726873,"about_ca_system_score_codex":0.00035362475,"about_ca_system_score_gemma":0.0006477182,"threshold_uncertainty_score":0.9998717},"labels":[],"label_agreement":null},{"id":"W4220992975","doi":"10.21810/jicw.v4i3.4205","title":"Solution-Based Approach to Civil Discourse","year":2022,"lang":"en","type":"article","venue":"The Journal of Intelligence Conflict and Warfare","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Presentation (obstetrics); Racism; Period (music); Political science; Media studies; Discourse analysis; Civil discourse; Sociology; Law; Linguistics; Art; Aesthetics; Medicine","score_opus":0.21871437921941358,"score_gpt":0.4598800721875769,"score_spread":0.24116569296816334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220992975","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39404568,0.0023528829,0.55562896,0.0321911,0.0012584431,0.0005430832,0.000033980523,0.000017799623,0.0139280725],"genre_scores_gemma":[0.9965288,0.00007478856,0.00047423298,0.0018663236,0.000079950114,0.0000074508043,0.000001129152,0.0000052093383,0.00096211134],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970775,0.0003774589,0.0006220139,0.0001237905,0.0016342887,0.00016490168],"domain_scores_gemma":[0.9981056,0.00063744816,0.0003787865,0.0002916154,0.0004566603,0.0001298864],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0075958055,0.00009676443,0.00019267088,0.00023117567,0.0005470654,0.00010560253,0.00090013933,0.000017770675,0.0014887286],"category_scores_gemma":[0.00041275314,0.000052541734,0.000086200984,0.0005697564,0.00010366572,0.00016427628,0.00015661829,0.0002949447,0.00003147838],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00093959534,0.0005541193,0.014866149,0.00001668726,0.00009226274,0.00000937291,0.0478536,0.554329,0.0010445014,0.008424933,0.057144366,0.3147254],"study_design_scores_gemma":[0.0007470555,0.0022796632,0.014678544,0.000061282284,0.00013117581,0.0003957033,0.13877158,0.3008992,0.0032886285,0.005872923,0.53229,0.0005842505],"about_ca_topic_score_codex":0.000017805478,"about_ca_topic_score_gemma":0.000010855731,"teacher_disagreement_score":0.6024831,"about_ca_system_score_codex":0.000051096362,"about_ca_system_score_gemma":0.00026192176,"threshold_uncertainty_score":0.99942404},"labels":[],"label_agreement":null},{"id":"W4220996640","doi":"10.3138/cjpe.71288","title":"Leveraging Mixed Methods Designs for Promoting Evaluation and Evaluation Capacity Building","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Capacity building; Evaluation methods; Resource (disambiguation); Business; Process management; Knowledge management; Computer science; Political science; Engineering","score_opus":0.6983590582177419,"score_gpt":0.594212927107646,"score_spread":0.10414613111009596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220996640","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92208487,0.0010280391,0.06676176,0.0020502456,0.0020429434,0.005638423,0.000013182241,0.000014840622,0.00036569542],"genre_scores_gemma":[0.8861568,0.00000260828,0.11216054,0.00012556487,0.00019156777,0.0012927306,0.00003186388,0.00001920994,0.000019140536],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9847623,0.0072128996,0.0015105555,0.00048203484,0.005572919,0.0004592539],"domain_scores_gemma":[0.9887518,0.001224149,0.001550136,0.0003257847,0.007720808,0.00042730046],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.204169,0.00019615721,0.00035724815,0.0011978461,0.0014123038,0.0006211166,0.00047780978,0.000073190946,0.0020316292],"category_scores_gemma":[0.016707383,0.00018159367,0.00017027595,0.0010999553,0.000083951614,0.000942092,0.00004565711,0.00035696858,0.0000028118807],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002187818,0.000035477537,0.0031329608,0.000008968258,0.000041266834,4.5444423e-7,0.004275049,0.031520776,0.0011835329,0.00024893647,0.0005804665,0.9589502],"study_design_scores_gemma":[0.0020065506,0.0006487898,0.019206963,0.000032115164,0.00042960266,0.00007173287,0.004397142,0.91157866,0.0007913764,0.049641743,0.010990237,0.00020508876],"about_ca_topic_score_codex":0.00026492972,"about_ca_topic_score_gemma":0.0015348003,"teacher_disagreement_score":0.9587451,"about_ca_system_score_codex":0.0020270643,"about_ca_system_score_gemma":0.007978697,"threshold_uncertainty_score":0.9998877},"labels":[],"label_agreement":null},{"id":"W4221079982","doi":"10.1177/1035719x221080575","title":"Evaluation in the field of early childhood development: A scoping review","year":2022,"lang":"en","type":"review","venue":"Evaluation Journal of Australasia","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Bridging (networking); Field (mathematics); Evaluation methods; Inclusion (mineral); Program evaluation; Early childhood education; Impact evaluation; Capacity building; Early childhood; Psychology; Political science; Management science; Computer science; Engineering; Medicine; Pedagogy; Social psychology; Developmental psychology","score_opus":0.43272754631129584,"score_gpt":0.5948855563214568,"score_spread":0.16215801001016095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221079982","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00034536462,0.9935125,0.0000532131,0.0005351694,0.000594214,0.003216775,0.0000032836244,0.0000026062457,0.0017368468],"genre_scores_gemma":[0.0011153144,0.9977635,0.00036883727,0.00027966936,0.00013590099,0.0002551552,0.000023460396,0.000015224918,0.000042909418],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9690884,0.008993531,0.005662453,0.00038367877,0.0156013435,0.00027062325],"domain_scores_gemma":[0.98736346,0.0041399472,0.0056365337,0.0006414216,0.0021439781,0.00007463207],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14245601,0.00030046926,0.0016162171,0.0010558168,0.00015471768,0.00014117334,0.0016276438,0.00013681651,0.01974411],"category_scores_gemma":[0.016715068,0.00017935617,0.00059419544,0.0023198358,0.000034417673,0.0006032061,0.000089330875,0.00087854173,0.00006764579],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000035718422,0.000089232235,0.0000419497,0.0023546817,0.000062713945,0.0000017458914,0.0012855429,0.00011988315,3.677255e-8,0.000013662501,0.0015460566,0.9944809],"study_design_scores_gemma":[0.0014371711,0.000761228,0.0043515293,0.30046332,0.0034060976,0.00023853108,0.0008437159,0.00023102539,0.0000032914986,0.0011626822,0.68663865,0.00046277823],"about_ca_topic_score_codex":0.00000228786,"about_ca_topic_score_gemma":0.000016269947,"teacher_disagreement_score":0.99401814,"about_ca_system_score_codex":0.00041671158,"about_ca_system_score_gemma":0.013194819,"threshold_uncertainty_score":0.99239945},"labels":[],"label_agreement":null},{"id":"W4221091289","doi":"10.1891/9780826186935.0002","title":"Assessing the Practice (Know-Do) Gap","year":2022,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; Gillings School of Public Health; Government of Canada; Agency for Healthcare Research and Quality; University of Oxford; World Health Organization","keywords":"Need to know; Gap analysis (conservation); Quality (philosophy); Knowledge translation; Reading (process); Computer science; Process (computing); Knowledge management; Political science","score_opus":0.40962437512882943,"score_gpt":0.5704726415065995,"score_spread":0.16084826637777005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221091289","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000063641014,0.0007212215,0.0006327853,0.017535087,0.0012649073,0.00029395617,0.000007107427,0.000045675304,0.9794929],"genre_scores_gemma":[0.0029273515,0.00045869438,0.0012831632,0.006953534,0.00030452528,0.000024368048,0.00001482099,0.00002930282,0.98800427],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9930855,0.0003146733,0.0008433074,0.0005754984,0.00497608,0.00020494183],"domain_scores_gemma":[0.99166614,0.0054548583,0.0008752697,0.0012312777,0.0006964153,0.0000760501],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.012646588,0.0002449045,0.0003044117,0.00023254924,0.00072255684,0.0017193434,0.0012160598,0.00012316971,0.2775946],"category_scores_gemma":[0.0018803076,0.00013229801,0.00020794485,0.00015805832,0.00010253826,0.0014700058,0.00047967545,0.0007887548,0.0050074314],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005775537,0.000015005865,0.000022444949,0.0000018395154,0.000040012703,0.000008559447,0.00026301676,0.00009631325,0.0000018852649,0.71016866,0.13161103,0.15776545],"study_design_scores_gemma":[0.00009774073,0.000039159848,0.00007789844,0.000013271387,0.000060673687,0.000026479041,0.001978208,0.00070866826,0.0000017747682,0.06117499,0.93563277,0.000188354],"about_ca_topic_score_codex":0.000015552772,"about_ca_topic_score_gemma":0.00001955972,"teacher_disagreement_score":0.8040218,"about_ca_system_score_codex":0.00012616199,"about_ca_system_score_gemma":0.00076393335,"threshold_uncertainty_score":0.999317},"labels":[],"label_agreement":null},{"id":"W4224228919","doi":"10.3138/cjpe.69932","title":"Examining the Process and Effects of Engaging Patients and Family in Health Service Evaluation: Results from a One-Year Prospective Intervention Study","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa; Home and Community Care Support Services","funders":"","keywords":"General partnership; Intervention (counseling); Context (archaeology); Nursing; Service (business); Health care; Psychology; Process (computing); Medical education; Medicine; Business; Political science; Computer science","score_opus":0.2617535692198355,"score_gpt":0.49518366530346136,"score_spread":0.23343009608362586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224228919","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99445254,0.00069173175,0.00003063506,0.0008822214,0.00028243396,0.003552684,0.000015314072,0.0000026970472,0.0000897705],"genre_scores_gemma":[0.99928415,0.000005383863,0.00021787148,0.0001439644,0.000030943076,0.00028907415,0.000018182725,0.0000064410215,0.000003975974],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99239933,0.0033049802,0.0011490788,0.00027396783,0.0027074818,0.00016513713],"domain_scores_gemma":[0.9956456,0.00066088623,0.0012547498,0.00018126809,0.002111856,0.0001456788],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.036571376,0.00009655486,0.00024166735,0.00049219915,0.00037566878,0.0001705958,0.00025393572,0.000022142647,0.000082565566],"category_scores_gemma":[0.0034407561,0.00007484436,0.000027339294,0.00096642366,0.000042068674,0.00042991716,0.000044682445,0.00029776673,7.6378666e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000105756466,0.00023934415,0.46997124,0.000020386877,0.000032942746,7.0745057e-7,0.046871915,0.0027069713,0.0000058066507,0.000010596619,0.000041090734,0.47999325],"study_design_scores_gemma":[0.0053138365,0.001981611,0.8923333,0.0001302105,0.000061140105,0.0000013093293,0.0524016,0.045342512,0.000008967092,0.0022981707,0.00006249444,0.0000648227],"about_ca_topic_score_codex":0.0039070807,"about_ca_topic_score_gemma":0.024902534,"teacher_disagreement_score":0.47992843,"about_ca_system_score_codex":0.0004923886,"about_ca_system_score_gemma":0.0020517977,"threshold_uncertainty_score":0.9928905},"labels":[],"label_agreement":null},{"id":"W4224229215","doi":"10.3138/cjpe.71300","title":"Professionalism in Program Evaluators: A Comparison of American and Canadian Evaluators","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Professionalization; Credentialing; Autonomy; Exploratory research; Field (mathematics); Perception; Psychology; Sociology; Medical education; Pedagogy; Social science; Political science; Medicine; Law","score_opus":0.4228532574958362,"score_gpt":0.5923266515598159,"score_spread":0.1694733940639797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224229215","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99133605,0.001190618,0.000014311889,0.0031515174,0.00079277554,0.0025113435,0.00003121654,0.000008251818,0.00096394075],"genre_scores_gemma":[0.99682474,0.000005841843,0.002283016,0.00020223059,0.00006000406,0.0005197826,0.000028889555,0.00001705814,0.000058410744],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99037725,0.0024641391,0.001822781,0.00035214456,0.004455364,0.00052831165],"domain_scores_gemma":[0.994511,0.00034728946,0.0015646169,0.00036720213,0.0023931018,0.00081676623],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.029424105,0.00019516137,0.0005863548,0.0025550565,0.00046306013,0.00019641986,0.000696274,0.000065761276,0.0028699643],"category_scores_gemma":[0.002731338,0.00016964122,0.00013328835,0.0026633488,0.00029614393,0.00043859318,0.000050420884,0.00056933204,0.000009508004],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002628317,0.00014806949,0.2960329,0.0000054353054,0.000022035203,0.000005689003,0.003719577,0.003297336,0.000011304321,0.00021641518,0.0014082752,0.6951067],"study_design_scores_gemma":[0.002243588,0.003247332,0.6424399,0.000090129215,0.0001443454,0.000065859,0.026992213,0.22021309,0.00004146445,0.0062336475,0.09793392,0.00035448972],"about_ca_topic_score_codex":0.074025266,"about_ca_topic_score_gemma":0.62354314,"teacher_disagreement_score":0.6947522,"about_ca_system_score_codex":0.0015047486,"about_ca_system_score_gemma":0.020823931,"threshold_uncertainty_score":0.9994121},"labels":[],"label_agreement":null},{"id":"W4224793496","doi":"10.3138/cjpe.71430","title":"Redesigning a University-Based Evaluator Education Program for Scholarship and Practice","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Scholarship; Premise; Curriculum; Process (computing); Medical education; Pedagogy; Engineering ethics; Sociology; Psychology; Computer science; Engineering; Political science; Medicine","score_opus":0.4058180102937288,"score_gpt":0.5556122397401135,"score_spread":0.1497942294463847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224793496","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86500365,0.0043757926,0.019413607,0.063412815,0.0058701863,0.029931305,0.00010053187,0.000114536786,0.011777588],"genre_scores_gemma":[0.9176187,0.000003963729,0.08085257,0.0006656414,0.00012840435,0.0004388801,0.000035350822,0.000012895265,0.00024358481],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9946605,0.0021486953,0.0005596971,0.00024883947,0.0021431514,0.00023911038],"domain_scores_gemma":[0.9927693,0.0010787058,0.0009061515,0.00022177838,0.0046043317,0.00041975337],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.038800385,0.000104850624,0.00017209293,0.00093587616,0.00089211616,0.00047103254,0.00040324382,0.000047119796,0.00076417596],"category_scores_gemma":[0.011037154,0.00010188124,0.00010017399,0.0009899825,0.00007004551,0.0010407228,0.000018726087,0.00026973087,0.0000057412567],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001444301,0.00014689457,0.0039155036,0.0000064880905,0.00002175848,0.0000024125943,0.0006358425,0.0029872563,0.000043330878,0.0007894672,0.0030108031,0.9882958],"study_design_scores_gemma":[0.0019944499,0.0024796545,0.012248867,0.000034527045,0.00028563727,0.00010354818,0.010995443,0.09396074,0.00003148239,0.0056486595,0.8720331,0.00018389404],"about_ca_topic_score_codex":0.00013479794,"about_ca_topic_score_gemma":0.0009968302,"teacher_disagreement_score":0.9881119,"about_ca_system_score_codex":0.0009327774,"about_ca_system_score_gemma":0.022411311,"threshold_uncertainty_score":0.9972933},"labels":[],"label_agreement":null},{"id":"W4224862209","doi":"10.3138/cjpe.71349","title":"Collaborative Evaluation Frameworks for Indigenous-Led Community Health Interventions: A Narrative Review","year":2022,"lang":"en","type":"review","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Indigenous; Psychological intervention; Narrative; Context (archaeology); Participatory action research; Equity (law); Sociology; Traditional knowledge; Citizen journalism; Community-based participatory research; Health equity; Community development; Narrative review; Engineering ethics; Medicine; Political science; Psychology; Geography; Nursing; Public health; Anthropology; Ecology; Engineering; Psychotherapist","score_opus":0.5641203596982542,"score_gpt":0.6521167436229571,"score_spread":0.08799638392470288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224862209","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000018648412,0.9716064,0.0011055615,0.0012266896,0.001914396,0.023443364,0.00027039347,0.000013441567,0.00040114947],"genre_scores_gemma":[0.00007744555,0.9854752,0.0032064226,0.00072578917,0.00023611511,0.008655813,0.001456665,0.00004791403,0.00011865154],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.96473634,0.023889469,0.0050941124,0.00048772924,0.0052088844,0.00058349007],"domain_scores_gemma":[0.97402924,0.0031318523,0.00952573,0.0009932254,0.011579936,0.0007400369],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.15306132,0.0004981181,0.0027414828,0.0019449613,0.002148797,0.00066333864,0.0016783815,0.00039921456,0.009285927],"category_scores_gemma":[0.03052667,0.00039325465,0.0015732993,0.0037977744,0.00015119837,0.00076376216,0.00006316171,0.0026781058,0.000037935984],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000007909904,0.00013900633,0.0000075786465,0.00472326,0.00025017918,8.524135e-7,0.0070718415,0.00011375913,2.782553e-9,0.00005635244,0.016779749,0.9708495],"study_design_scores_gemma":[0.00071886624,0.00202479,0.000034884633,0.033846363,0.0019653577,0.000046403624,0.0077513917,0.001114353,2.9090868e-8,0.0040387386,0.94814545,0.00031335646],"about_ca_topic_score_codex":0.00061512354,"about_ca_topic_score_gemma":0.04463242,"teacher_disagreement_score":0.9705362,"about_ca_system_score_codex":0.0062409635,"about_ca_system_score_gemma":0.08534402,"threshold_uncertainty_score":0.99985194},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W4224866913","doi":"10.3138/cjpe.72386","title":"Evaluation Utility Metrics (EUMs) in Reflective Practice","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of General Medical Sciences","keywords":"Quality (philosophy); Negotiation; Computer science; Evaluation methods; Management science; Process management; Risk analysis (engineering); Psychology; Medicine; Business; Reliability engineering; Sociology; Engineering","score_opus":0.5800774051525978,"score_gpt":0.6115541890215195,"score_spread":0.03147678386892172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224866913","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8902088,0.004783796,0.002588208,0.017193928,0.0056158523,0.0073326873,0.000043129956,0.00002570776,0.0722079],"genre_scores_gemma":[0.9960427,0.0000097633265,0.0030074792,0.00042313602,0.00009734366,0.0003248661,0.000017786637,0.000009402238,0.000067512585],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98045856,0.007188049,0.0014725018,0.00034716068,0.010176695,0.00035703293],"domain_scores_gemma":[0.98698246,0.0010863034,0.0013428361,0.0003801053,0.009865666,0.00034260374],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.15872046,0.00012719163,0.00026250578,0.0022371481,0.00045851356,0.0003251662,0.00062254636,0.000060126073,0.0093865935],"category_scores_gemma":[0.044602763,0.00011532523,0.00012324768,0.0043587075,0.0000629419,0.0013443884,0.000039046063,0.0005886337,0.00004069535],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054261505,0.00014062457,0.01552068,0.0000012838668,0.000028328084,0.000009048811,0.0024340576,0.020213649,0.000009387164,0.00027501964,0.002833664,0.95848],"study_design_scores_gemma":[0.0023902107,0.0012535456,0.13926625,0.000014663539,0.0002986005,0.00012648824,0.015243135,0.5985043,0.00003697706,0.036958177,0.20568629,0.00022132428],"about_ca_topic_score_codex":0.0014772441,"about_ca_topic_score_gemma":0.025800275,"teacher_disagreement_score":0.9582587,"about_ca_system_score_codex":0.0034589607,"about_ca_system_score_gemma":0.018219441,"threshold_uncertainty_score":0.9919763},"labels":[],"label_agreement":null},{"id":"W4224927296","doi":"10.1002/ev.20494","title":"Evaluation policy and organizational evaluation capacity building: A study of international aid agency evaluation policies","year":2022,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Agency (philosophy); Pace; Evaluation methods; Program evaluation; Policy analysis; Capacity building; Public relations; Management science; Knowledge management; Process management; Business; Political science; Computer science; Public administration; Economics; Sociology; Economic growth","score_opus":0.3393749749893569,"score_gpt":0.529793832087028,"score_spread":0.1904188570976711,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224927296","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9749468,0.00039913933,0.003908445,0.0026099854,0.0025698238,0.008554827,0.00012835817,0.00007449843,0.006808142],"genre_scores_gemma":[0.9930107,0.000029605768,0.0014496872,0.00015240994,0.000669078,0.0036071287,0.0004806008,0.00003867874,0.0005620984],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9721263,0.0048717037,0.0018619674,0.0011220168,0.019641984,0.00037601858],"domain_scores_gemma":[0.9817331,0.0011339502,0.0014060073,0.000785499,0.014772064,0.00016936866],"candidate_categories":["metaresearch","metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0702406,0.00033194732,0.00042626722,0.0023284494,0.0015243079,0.000310774,0.00065656146,0.00010993042,0.011292953],"category_scores_gemma":[0.027306203,0.00033553416,0.0001647515,0.0035454251,0.0000897113,0.0012023353,0.0002698326,0.00025253746,0.000020236392],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021945807,0.0016786032,0.028784622,0.000010364674,0.00036884355,7.767655e-8,0.017744599,0.2687704,0.0035334576,0.0058064116,0.0047651427,0.66831803],"study_design_scores_gemma":[0.00819758,0.00071289035,0.14001735,0.000010782363,0.0010982841,0.000012913982,0.005615712,0.75866777,0.00041943265,0.07785241,0.0070916153,0.00030326084],"about_ca_topic_score_codex":0.001098213,"about_ca_topic_score_gemma":0.001091184,"teacher_disagreement_score":0.66801476,"about_ca_system_score_codex":0.0031241442,"about_ca_system_score_gemma":0.005966497,"threshold_uncertainty_score":0.99990964},"labels":[],"label_agreement":null},{"id":"W4224940934","doi":"10.3138/cjpe.71050","title":"Realistic Evaluation and the Process-Tracing Method: A Combined Approach to Scrutinizing Causal Mechanisms","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Operationalization; Scrutiny; Framing (construction); Process tracing; Tracing; Causal model; Computer science; Process (computing); Causal inference; Psychology; Management science; Process management; Epistemology; Econometrics; Political science; Engineering; Economics; Mathematics","score_opus":0.34706621608805643,"score_gpt":0.5365759557097144,"score_spread":0.18950973962165796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224940934","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46707392,0.0017537336,0.4430212,0.03189943,0.0043597133,0.022231419,0.00006643769,0.000067937704,0.029526202],"genre_scores_gemma":[0.9762182,0.0000015924514,0.022103008,0.00065051444,0.00009488537,0.0008250916,0.000023099665,0.0000137908,0.00006979393],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9892115,0.0039417804,0.0010928137,0.00033586074,0.0050938553,0.00032420122],"domain_scores_gemma":[0.9943823,0.0006849616,0.0008861811,0.00032025226,0.0032989206,0.00042735366],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.099355064,0.00014896314,0.0003242643,0.00078012823,0.0011147292,0.00059123803,0.00058255624,0.000044201795,0.00091238006],"category_scores_gemma":[0.007989855,0.000102877675,0.000097201635,0.0014950973,0.00008662509,0.0004048615,0.00004770486,0.00037915458,0.0000074089667],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020193701,0.000071838964,0.000735709,0.000010826412,0.00005785547,0.0000023162413,0.013235679,0.19538611,0.0000419639,0.016998004,0.0012746181,0.77198315],"study_design_scores_gemma":[0.0028691941,0.0005664865,0.0046903347,0.000020929707,0.00027164535,0.00013230421,0.013569495,0.8680088,0.000031097705,0.107864596,0.0018221673,0.00015293976],"about_ca_topic_score_codex":0.0006551677,"about_ca_topic_score_gemma":0.0022824667,"teacher_disagreement_score":0.7718302,"about_ca_system_score_codex":0.0005991992,"about_ca_system_score_gemma":0.0052622,"threshold_uncertainty_score":0.9989922},"labels":[],"label_agreement":null},{"id":"W4225929430","doi":"10.3138/cjpe.73685","title":"Pat Bazeley. (2018). <i>Integrating Analyses in Mixed Methods Research</i> .","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology","score_opus":0.8220107669184188,"score_gpt":0.7166431773534617,"score_spread":0.10536758956495706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225929430","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9570402,0.0046429294,0.006473159,0.008726217,0.0041374452,0.002710508,0.000024809531,0.00002049064,0.016224226],"genre_scores_gemma":[0.96736175,0.000009195239,0.031866755,0.00016836995,0.0001261142,0.00020943217,0.000011876238,0.000011761334,0.00023477565],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9822384,0.010452636,0.0014809713,0.00030874758,0.0050109373,0.0005083145],"domain_scores_gemma":[0.9938296,0.0014670225,0.0006999278,0.00038554013,0.003174828,0.0004430865],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12263103,0.000120778925,0.000319694,0.0025238064,0.0006889202,0.00048204264,0.0008754666,0.000052672098,0.006716306],"category_scores_gemma":[0.012044523,0.000096336305,0.0001573749,0.003645101,0.000114350696,0.00058145146,0.000061581915,0.0008595508,0.000034915392],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017320855,0.000051989897,0.009515124,0.0000019483527,0.000016609016,0.000014205456,0.0019421295,0.0102701355,0.0005349439,0.00036752227,0.0075713247,0.96969676],"study_design_scores_gemma":[0.0019366257,0.0018050815,0.10324251,0.000063924985,0.00008318242,0.000121648765,0.05411251,0.31792912,0.0006787907,0.05150673,0.46817395,0.00034592944],"about_ca_topic_score_codex":0.002718627,"about_ca_topic_score_gemma":0.05086131,"teacher_disagreement_score":0.9693508,"about_ca_system_score_codex":0.0014490895,"about_ca_system_score_gemma":0.00869532,"threshold_uncertainty_score":0.99692446},"labels":[],"label_agreement":null},{"id":"W4225936008","doi":"10.3138/cjpe.73771","title":"Jill Anne Chouinard &amp; Fiona Cram. (2020). <i>Culturally responsive approaches to evaluation: Empirical implications for theory and practice.</i>","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sociology; Empirical research; Psychology; Epistemology; Philosophy","score_opus":0.7071106155438179,"score_gpt":0.5753760736915132,"score_spread":0.1317345418523047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225936008","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5060367,0.0060410625,0.021340916,0.44062787,0.0023757338,0.01632479,0.00038607832,0.00005139955,0.006815434],"genre_scores_gemma":[0.9617542,0.000015947624,0.030119184,0.004114132,0.00037274632,0.00271793,0.00016036142,0.000025097806,0.0007204204],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9907859,0.004449929,0.0011197997,0.0004703424,0.0027999515,0.00037409316],"domain_scores_gemma":[0.9885985,0.0032805107,0.000914698,0.0004644979,0.0060470896,0.0006946658],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07074684,0.00018227457,0.00029847934,0.00063841464,0.0011357114,0.0005540988,0.000587256,0.00007224571,0.0017557654],"category_scores_gemma":[0.03436423,0.00014987742,0.00015915137,0.0013226497,0.00011117148,0.0008784526,0.00006290584,0.00030459723,0.000028969536],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00069913984,0.00015615475,0.003853935,0.0000063374623,0.0000961167,0.0000019573586,0.008495332,0.021609884,0.00009279296,0.006244892,0.09708923,0.8616542],"study_design_scores_gemma":[0.001649292,0.0014866173,0.08011646,0.00001593824,0.00037869727,0.00043134368,0.010157078,0.010784401,0.0000093510325,0.07308408,0.8216011,0.00028564673],"about_ca_topic_score_codex":0.000046908215,"about_ca_topic_score_gemma":0.0023777473,"teacher_disagreement_score":0.8613686,"about_ca_system_score_codex":0.00092848646,"about_ca_system_score_gemma":0.007500404,"threshold_uncertainty_score":0.9991568},"labels":[],"label_agreement":null},{"id":"W4226081941","doi":"10.9707/1944-5660.1591","title":"Localizing the 2030 Agenda With Community Data: Lessons From the Community Foundations of Canada’s Vital Signs Program","year":2021,"lang":"en","type":"article","venue":"The Foundation Review","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"International Institute for Sustainable Development","funders":"Clayoquot Biosphere Trust; Vancouver Foundation; London Community Foundation; Northwestern University","keywords":"Sustainable development; Political science; Community development; Sustainable community; Economic growth; Public administration; Public relations; Economics","score_opus":0.5988448937633328,"score_gpt":0.5534263373406585,"score_spread":0.04541855642267434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226081941","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11625401,0.031557057,0.05050149,0.7345167,0.0019996732,0.0086245155,0.0015975761,0.0001929962,0.054756004],"genre_scores_gemma":[0.9774035,0.0052323397,0.0009819018,0.012833287,0.000100764126,0.00014930594,0.002155876,0.000017953547,0.0011250298],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9903031,0.0069208387,0.00078856817,0.00019465173,0.0016033843,0.00018943165],"domain_scores_gemma":[0.98736066,0.0069124764,0.00065051526,0.0040443726,0.0009835209,0.00004844277],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.015146291,0.00015249173,0.00032262146,0.000017741442,0.0031050118,0.00042302042,0.0028867382,0.000025014166,0.0017654465],"category_scores_gemma":[0.0023155313,0.00006314691,0.00006992849,0.0010600877,0.00039902664,0.00046850037,0.00070986827,0.0007397685,0.00006816013],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002938254,0.0006689049,0.0036497333,0.00030671395,0.00038319099,0.0000020993414,0.0062103802,0.0006000335,0.00012498951,0.012854131,0.1677303,0.80744016],"study_design_scores_gemma":[0.00021776055,0.00006496646,0.014930612,0.00068171596,0.0002034594,0.000010174975,0.009800447,0.0022009825,0.00005453802,0.0026988727,0.9689948,0.00014168152],"about_ca_topic_score_codex":0.14050475,"about_ca_topic_score_gemma":0.79515034,"teacher_disagreement_score":0.86114955,"about_ca_system_score_codex":0.000097723234,"about_ca_system_score_gemma":0.003053301,"threshold_uncertainty_score":0.99914706},"labels":[],"label_agreement":null},{"id":"W4226083882","doi":"10.3138/cjpe.71482","title":"Learning and Leading: Integrating Mixed Methods in a Collaborative Approach to Educational Evaluation","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Alberta; Western University; Queen's University","funders":"","keywords":"Multimethodology; Perspective (graphical); Context (archaeology); Mental health; Value (mathematics); Collaborative learning; Qualitative property; Qualitative research; Phenomenon; Psychology; Knowledge management; Sociology; Pedagogy; Computer science; Epistemology; Social science","score_opus":0.35869882773020634,"score_gpt":0.6077636009537061,"score_spread":0.24906477322349974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226083882","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9466424,0.0016668849,0.012277377,0.009850387,0.0019123277,0.004741582,0.000012018095,0.000011979069,0.022885025],"genre_scores_gemma":[0.90167415,0.0000026729763,0.09713544,0.00013616045,0.00008737962,0.00070283207,0.000028665905,0.00000972229,0.00022294925],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9901146,0.0054877214,0.0010266878,0.00031624877,0.0027922834,0.0002624041],"domain_scores_gemma":[0.9946153,0.00078640116,0.0007156785,0.0001400929,0.0033787957,0.00036369226],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06729252,0.00012702683,0.0002722126,0.0016385359,0.00053902727,0.0004054779,0.00032011748,0.00004366824,0.0017554337],"category_scores_gemma":[0.014144973,0.00011381951,0.000057280373,0.0026404806,0.000054341308,0.0004964794,0.000040233972,0.00048046774,0.000009236074],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019981397,0.00006424526,0.02464444,0.0000026862797,0.00001522867,4.9353355e-7,0.01302375,0.058438268,0.00015088395,0.0011670854,0.0011853895,0.90128756],"study_design_scores_gemma":[0.0015180736,0.0011846572,0.09079633,0.000038701368,0.00008923199,0.00007134486,0.07677867,0.7643225,0.000066533714,0.019073633,0.04579341,0.00026686542],"about_ca_topic_score_codex":0.0002520109,"about_ca_topic_score_gemma":0.005059473,"teacher_disagreement_score":0.9010207,"about_ca_system_score_codex":0.0014106336,"about_ca_system_score_gemma":0.010012442,"threshold_uncertainty_score":0.9991571},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"},{"model":"grok","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W4226101427","doi":"10.1007/978-3-030-91959-7_4","title":"Policy Borrowing and Evidence in Danish Education Policy Preparation: The Case of the Public School Reform of 2013","year":2022,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Norges Forskningsråd","keywords":"Danish; Context (archaeology); Political science; Politics; Public administration; Evidence-based policy; Scale (ratio); Empirical evidence; Regional science; Public relations; Sociology; Geography; Law","score_opus":0.22450400771349954,"score_gpt":0.502663472810088,"score_spread":0.2781594650965885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226101427","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024168642,0.0012089681,0.000019666944,0.0572017,0.00039402535,0.0010661822,0.000020064197,0.000010747784,0.91591],"genre_scores_gemma":[0.78009397,0.00080555736,0.00009126301,0.0011518019,0.00018497262,0.00005239252,0.0000037040152,0.000010359367,0.21760601],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99708325,0.0002004518,0.0009967813,0.00032797008,0.0012561929,0.0001353384],"domain_scores_gemma":[0.99687487,0.0005629666,0.00086110353,0.0010851427,0.000546738,0.00006919159],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0044840975,0.00015632616,0.00026340448,0.0006279673,0.00024036344,0.00015819588,0.000768952,0.00009218842,0.004024529],"category_scores_gemma":[0.0016014848,0.000080640566,0.000105981875,0.00059501786,0.0001747918,0.0009464996,0.00045674178,0.0002918505,0.000022480013],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014346875,0.000026194417,0.0010343171,0.000025471863,0.000012352933,0.0000011155488,0.0009387181,0.000045726898,0.000019319323,0.96668965,0.005747367,0.02544544],"study_design_scores_gemma":[0.0008108027,0.0005360272,0.02548341,0.0009167181,0.00009558163,0.00092906534,0.020724919,0.005391365,0.00020281672,0.3680359,0.57606316,0.0008102342],"about_ca_topic_score_codex":0.0063065947,"about_ca_topic_score_gemma":0.0077940472,"teacher_disagreement_score":0.7559253,"about_ca_system_score_codex":0.00046111134,"about_ca_system_score_gemma":0.006012915,"threshold_uncertainty_score":0.99962205},"labels":[],"label_agreement":null},{"id":"W4226119644","doi":"10.3138/cjpe.73687","title":"The Contributions of Innovations in Integration in Complex Mixed Methods Evaluation Designs in This Issue and Beyond","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Closing (real estate); Management science; Psychology; Computer science; Epistemology; Business; Economics; Philosophy","score_opus":0.4642771256930222,"score_gpt":0.5952877465304317,"score_spread":0.1310106208374095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226119644","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9674415,0.0016760043,0.0073604872,0.015766026,0.0010864225,0.004132914,0.00004688915,0.0000051447087,0.0024846098],"genre_scores_gemma":[0.99247915,0.00001991287,0.006857106,0.000117931915,0.000027564993,0.00040050125,0.000058074827,0.000005631019,0.000034154404],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9900854,0.0055554505,0.0018329646,0.00020694235,0.002060021,0.00025921976],"domain_scores_gemma":[0.99462575,0.0012725759,0.00089801487,0.00022750236,0.002865571,0.0001106075],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08397856,0.000103665916,0.000270798,0.0018621017,0.00033714526,0.00016962668,0.0003566378,0.000057079673,0.0018563524],"category_scores_gemma":[0.010179714,0.00008166485,0.00005053264,0.003430356,0.00012933159,0.00048997055,0.000029215196,0.00041304788,0.0000026754399],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030701638,0.000075623706,0.0180719,0.0000017499293,0.000007896983,0.0000011460884,0.0035213062,0.013755363,0.00079491484,0.0033333334,0.0014104799,0.9589956],"study_design_scores_gemma":[0.0020420197,0.0004048086,0.3564094,0.000027594246,0.00003646163,0.000014915558,0.012982923,0.57049894,0.00031232895,0.0446928,0.012466846,0.00011095369],"about_ca_topic_score_codex":0.0017843962,"about_ca_topic_score_gemma":0.112096526,"teacher_disagreement_score":0.95888466,"about_ca_system_score_codex":0.0013100732,"about_ca_system_score_gemma":0.004570174,"threshold_uncertainty_score":0.9990561},"labels":[],"label_agreement":null},{"id":"W4226263038","doi":"10.3138/cjpe.70920","title":"Responding to the Evaluation Capacity Needs of the Early Childhood Field: Insights from a Mixed Methods Community-based Participatory Design","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Capacity building; Interdependence; Citizen journalism; Knowledge management; Participatory action research; Multimethodology; Resource (disambiguation); Capacity development; Qualitative property; Sociology; Management science; Psychology; Pedagogy; Environmental resource management; Computer science; Engineering; Political science; Social science","score_opus":0.6312424150244843,"score_gpt":0.5375796860218353,"score_spread":0.09366272900264905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226263038","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97525793,0.00019934951,0.016248865,0.0045371014,0.0014181489,0.002047593,0.000018397053,0.0000054615166,0.00026713524],"genre_scores_gemma":[0.99034745,4.2253006e-7,0.007882344,0.0012647393,0.00008409564,0.00038315807,0.000008993519,0.00000998869,0.000018808818],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.964317,0.030285915,0.001126366,0.00014163823,0.0038800451,0.000249027],"domain_scores_gemma":[0.99221605,0.0032588262,0.0010675233,0.00078183477,0.0024019198,0.00027382452],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07678471,0.00013186522,0.00025483532,0.0012386293,0.0014639152,0.00024161258,0.0013441718,0.000059463084,0.0014318884],"category_scores_gemma":[0.009859901,0.000081099344,0.00017254068,0.00319335,0.00009153005,0.00029335002,0.000058317524,0.0007130683,0.000009622618],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009259405,0.00013509169,0.006684137,0.0000022340114,0.00007334371,4.6349032e-7,0.062428515,0.17161919,0.0008193095,0.00035109738,0.0028635748,0.75493044],"study_design_scores_gemma":[0.0025219105,0.0028659035,0.60953856,0.00010296314,0.0006713112,0.000010358133,0.03752649,0.25954756,0.008729595,0.036440346,0.041713458,0.0003315238],"about_ca_topic_score_codex":0.0022831848,"about_ca_topic_score_gemma":0.009209466,"teacher_disagreement_score":0.7545989,"about_ca_system_score_codex":0.00064800127,"about_ca_system_score_gemma":0.007165092,"threshold_uncertainty_score":0.999836},"labels":[],"label_agreement":null},{"id":"W4226406422","doi":"10.3138/cjpe.73684","title":"Donna Mertens. (2018). <i>Mixed Methods Design in Evaluation</i> .","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology","score_opus":0.5744650939781201,"score_gpt":0.5931184524350988,"score_spread":0.018653358456978686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226406422","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6328445,0.018954078,0.22771825,0.03977698,0.0308152,0.024798818,0.000088029716,0.00010616772,0.024897983],"genre_scores_gemma":[0.9392788,0.000013575241,0.059052866,0.00059929624,0.0001459638,0.00070382754,0.000021886353,0.000018817595,0.00016500583],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9797209,0.01155475,0.0017973672,0.0003850233,0.006067562,0.00047443452],"domain_scores_gemma":[0.99343276,0.0010013585,0.0011295377,0.00049008563,0.0034659598,0.00048030727],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.15702192,0.00017400524,0.00038497325,0.001777161,0.0005115673,0.00035908382,0.00090943597,0.000069959584,0.014228218],"category_scores_gemma":[0.0086573,0.0001505796,0.00017105868,0.0023807867,0.00008642388,0.0007179695,0.000045790188,0.0005003411,0.00006001056],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002959452,0.00006438093,0.0036163884,0.0000013708957,0.000021806942,0.000007370621,0.0012731252,0.08718261,0.00008483916,0.00017630334,0.012299714,0.8952425],"study_design_scores_gemma":[0.0026946242,0.0010111505,0.050942827,0.00002180349,0.00018183235,0.00013295682,0.00518071,0.72025615,0.00020099706,0.040345423,0.1787395,0.0002919997],"about_ca_topic_score_codex":0.00062963174,"about_ca_topic_score_gemma":0.008715989,"teacher_disagreement_score":0.8949505,"about_ca_system_score_codex":0.0018131185,"about_ca_system_score_gemma":0.014502859,"threshold_uncertainty_score":0.9996932},"labels":[],"label_agreement":null},{"id":"W4226507667","doi":"10.3138/cjpe.71237","title":"A Multi-Stage Approach to Qualitative Sampling within a Mixed Methods Evaluation: Some Reflections on Purpose and Process","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Economic and Social Research Council","keywords":"Randomized controlled trial; Scale (ratio); Sampling (signal processing); Process (computing); Qualitative property; Sample (material); Computer science; Intervention (counseling); Multimethodology; Psychology; Process management; Mathematics education; Business; Machine learning; Geography; Medicine","score_opus":0.8290454090139003,"score_gpt":0.7062106398700911,"score_spread":0.1228347691438092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226507667","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86651117,0.0010273425,0.11089235,0.005355739,0.0033931676,0.008705301,0.000093784685,0.000043281412,0.003977875],"genre_scores_gemma":[0.7894692,0.0000014441454,0.20825164,0.00053348404,0.00011338916,0.0013662952,0.000027228918,0.000017660877,0.00021968859],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98765457,0.006291381,0.0012445372,0.00047143968,0.004008813,0.00032926432],"domain_scores_gemma":[0.9937488,0.00068908784,0.0009844693,0.00033854874,0.0035927226,0.0006463855],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08511748,0.00018854608,0.00034196852,0.0015539991,0.0010871474,0.000502952,0.00048910326,0.000060535946,0.00085399015],"category_scores_gemma":[0.009353917,0.00016038692,0.00011017275,0.001948444,0.000088480876,0.00070013636,0.000031863732,0.0004965261,0.000013822558],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009777286,0.0002622263,0.00031130263,0.000012901575,0.00006935516,0.0000016590076,0.11846542,0.3269271,0.00023025683,0.002318587,0.00044865286,0.55085474],"study_design_scores_gemma":[0.0024447453,0.0021235577,0.007996258,0.00004255494,0.00020788994,0.000076120275,0.24189028,0.7107358,0.00014459442,0.01700569,0.0169559,0.0003766208],"about_ca_topic_score_codex":0.00023274841,"about_ca_topic_score_gemma":0.0033456713,"teacher_disagreement_score":0.55047816,"about_ca_system_score_codex":0.001091506,"about_ca_system_score_gemma":0.0067000124,"threshold_uncertainty_score":0.9989907},"labels":[],"label_agreement":null},{"id":"W4230488502","doi":"10.3138/cjpe.230","title":"Useful Theory of Change Models","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":213,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Causality (physics); Theory of change; Development theory; Intervention (counseling); Epistemology; Computer science; Psychological intervention; Management science; Psychology; Sociology; Economics; Philosophy; Physics","score_opus":0.8815743086593234,"score_gpt":0.5830366120430426,"score_spread":0.2985376966162808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4230488502","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95964456,0.002650479,0.00972136,0.0034881167,0.002291091,0.0019165735,0.00001772277,0.000012306121,0.020257823],"genre_scores_gemma":[0.9969894,0.000007206828,0.0024429155,0.00017880819,0.00018884783,0.00003806376,0.0000045625,0.0000066679577,0.00014349655],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.995709,0.000712624,0.00080876506,0.00012122727,0.0024613836,0.00018701832],"domain_scores_gemma":[0.9930302,0.0001720576,0.00075566175,0.00026301024,0.005218913,0.0005601838],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.029516792,0.00008291962,0.00021489646,0.00064535695,0.00006086782,0.00013213043,0.00043061728,0.00006207573,0.0009688999],"category_scores_gemma":[0.0025231948,0.00006067476,0.0001000823,0.0006161088,0.00008981459,0.0010544589,0.000010740537,0.00011993154,0.000047256257],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030111445,0.0000372332,0.014560733,0.0000027214232,0.000021238911,0.000002753057,0.0053672697,0.004864279,0.0000065628965,0.0056105354,0.002937779,0.96655875],"study_design_scores_gemma":[0.0024415264,0.0015677082,0.060294893,0.000098611206,0.00016923127,0.0000638531,0.008755816,0.28167215,0.0002045228,0.59057784,0.053905766,0.0002480593],"about_ca_topic_score_codex":0.00031486075,"about_ca_topic_score_gemma":0.005280161,"teacher_disagreement_score":0.96631074,"about_ca_system_score_codex":0.00024369179,"about_ca_system_score_gemma":0.005279141,"threshold_uncertainty_score":0.9999443},"labels":[],"label_agreement":null},{"id":"W4230653595","doi":"10.1111/ejed.12246","title":"Issue Information","year":2018,"lang":"en","type":"paratext","venue":"European Journal of Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Citation; Computer science; Agency (philosophy); Library science; World Wide Web; Information retrieval; Sociology; Social science","score_opus":0.14282075777530787,"score_gpt":0.49690300838873114,"score_spread":0.35408225061342324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4230653595","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038430807,0.00047519198,0.0046952902,0.0025648093,0.04404757,0.00013311233,0.000012508901,0.0000040976347,0.94422436],"genre_scores_gemma":[0.065244496,0.0005819533,0.0055809994,0.0047101052,0.018632717,0.000003133785,0.0001779189,0.000044347584,0.90502435],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99510473,0.0010101591,0.0018054772,0.00012858177,0.0018192711,0.00013179045],"domain_scores_gemma":[0.9920464,0.00018036955,0.0033501785,0.0004278948,0.0038552047,0.00013993813],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.009667715,0.00016140568,0.00028544752,0.0009228735,0.00011904954,0.00057582377,0.00096584624,0.00005219203,0.058560815],"category_scores_gemma":[0.0014973531,0.00011357881,0.00015654402,0.0004808792,0.000053072188,0.0011449596,0.0000593703,0.00034508752,0.23346153],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000132282275,0.000032208864,0.000021271233,0.000006982935,0.000010471195,2.1279813e-7,0.0011477588,0.00007275761,0.0000061867886,0.000018844734,0.7910138,0.2076563],"study_design_scores_gemma":[0.00018507593,0.00026107984,0.0022727977,0.00013756995,0.000019975752,0.000031868207,0.0014096481,0.00004882965,0.0000477755,0.00016362137,0.9953022,0.000119566634],"about_ca_topic_score_codex":0.0000017898883,"about_ca_topic_score_gemma":6.7854256e-7,"teacher_disagreement_score":0.20753673,"about_ca_system_score_codex":0.00012209037,"about_ca_system_score_gemma":0.0021495153,"threshold_uncertainty_score":0.9422998},"labels":[],"label_agreement":null},{"id":"W4231695362","doi":"10.3233/wor-2010-1027","title":"From the Editor","year":2010,"lang":"en","type":"editorial","venue":"Work","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.07891278689220502,"score_gpt":0.4709320426781631,"score_spread":0.3920192557859581,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4231695362","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015276474,0.00013792745,0.00008726218,0.002991435,0.9888411,0.00012901783,0.00012636922,0.000027972506,0.007506132],"genre_scores_gemma":[0.00020705724,0.000027642647,0.00031295232,0.00027505372,0.9763678,0.000027535252,0.0001513393,0.000014910714,0.022615729],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9936063,0.00021109855,0.00049502496,0.00044294816,0.0050551654,0.0001894296],"domain_scores_gemma":[0.984426,0.013233156,0.00037156048,0.0013239227,0.00057152397,0.00007378741],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0044987667,0.00017339709,0.0002629731,0.00005315873,0.00024500323,0.00065147504,0.0019205388,0.000689949,0.012427921],"category_scores_gemma":[0.008753908,0.00008619657,0.00014109004,0.0004529245,0.000091772374,0.00011995319,0.0001851378,0.0014613348,0.009334643],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010868811,0.000008067467,0.0002700763,2.7754837e-7,0.0000083998275,3.7193414e-7,0.00025352792,0.0000031552293,0.0000011227387,0.000010716763,0.9877766,0.011656859],"study_design_scores_gemma":[0.00012537741,0.0000115505945,0.0007442533,0.000024049294,0.000015162929,2.1513792e-8,0.000115908944,0.000017027935,0.000002711623,0.0037798241,0.995043,0.00012115293],"about_ca_topic_score_codex":0.000082513594,"about_ca_topic_score_gemma":0.00027207966,"teacher_disagreement_score":0.015109597,"about_ca_system_score_codex":0.000024536363,"about_ca_system_score_gemma":0.0006729681,"threshold_uncertainty_score":0.99959576},"labels":[],"label_agreement":null},{"id":"W4231760037","doi":"10.21203/rs.2.23235/v1","title":"Applying an intersectionality lens to the Theoretical Domains Framework: a tool for thinking about how intersecting social identities and structures of power influence behaviour","year":2020,"lang":"en","type":"preprint","venue":"Research Square","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; University of Waterloo; University of British Columbia; Ottawa Hospital","funders":"Canadian Institutes of Health Research","keywords":"Intersectionality; Context (archaeology); Delphi method; Through-the-lens metering; Delphi; Voting; Identity (music); Computer science; Sociology; Lens (geology); Political science; Engineering; Artificial intelligence; Gender studies","score_opus":0.25049751271031834,"score_gpt":0.5555617109953894,"score_spread":0.3050641982850711,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4231760037","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9539344,0.0000476356,0.03375905,0.00897791,0.00034415186,0.002257031,0.0002343517,0.00003231334,0.0004131805],"genre_scores_gemma":[0.99589425,0.000014180497,0.0025844192,0.00040625333,0.00035451952,0.00067555223,0.000019084628,0.000020697527,0.00003104062],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9928626,0.0013136909,0.0006503488,0.0007946473,0.0039291563,0.0004495819],"domain_scores_gemma":[0.9934287,0.003504022,0.00030300385,0.0006098124,0.0020295756,0.00012488032],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.014382468,0.00022478815,0.00041811034,0.00038861085,0.0010803244,0.0019087777,0.0013733029,0.00027727347,0.00033857848],"category_scores_gemma":[0.010445605,0.00015083248,0.00021472179,0.00050499575,0.00066990295,0.00044255878,0.002169494,0.0016519396,0.0000050097037],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005225016,0.00008124206,0.072871715,0.00044764773,0.00012340446,0.0000048133707,0.12362986,0.001264786,0.00051012245,0.78432536,0.0020899638,0.0141286],"study_design_scores_gemma":[0.00020990703,0.00029255054,0.21408959,0.00035636645,0.000019969526,0.0000035622227,0.07643703,0.0027436644,0.00022377311,0.70495373,0.00045032412,0.00021951809],"about_ca_topic_score_codex":0.00007375257,"about_ca_topic_score_gemma":0.00013865356,"teacher_disagreement_score":0.14121789,"about_ca_system_score_codex":0.0001703112,"about_ca_system_score_gemma":0.00044336662,"threshold_uncertainty_score":0.9991273},"labels":[],"label_agreement":null},{"id":"W4232046647","doi":"10.1506/7cpf-uh15-qq9g-qa58","title":"Editorial: Performance Measurement in and of Postsecondary Education /Éditorial L'évaluation de la performance des établissements d'enseignement postsecondaire","year":2003,"lang":"fr","type":"editorial","venue":"Canadian Accounting Perspectives","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Valuation (finance); Citation; Library science; Computer science; Accounting; Business","score_opus":0.0332768237614217,"score_gpt":0.36250044739958465,"score_spread":0.32922362363816293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4232046647","genre_codex":"editorial","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4920211,0.0029332906,0.000008191947,0.00017691891,0.49280584,0.0007730818,0.0001018499,0.00001363431,0.011166102],"genre_scores_gemma":[0.6003812,0.002788471,0.00080124923,0.00009307259,0.3945797,0.00016520183,0.000079658945,0.00007606025,0.0010354111],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98990554,0.0013550723,0.0018119765,0.0012822094,0.004498382,0.0011467952],"domain_scores_gemma":[0.99095976,0.0011291453,0.0011916679,0.0007008013,0.0054605966,0.0005580018],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.020847512,0.0007536872,0.0009183819,0.0020679955,0.0009540408,0.0008883086,0.0008483404,0.001127669,0.0016095885],"category_scores_gemma":[0.008307951,0.0008104633,0.0001719146,0.0013371232,0.0009065526,0.0021849785,0.00011443205,0.0013446002,0.000056715897],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00021617343,0.0004683371,0.11262128,0.00076695444,0.00015045333,0.0000022286752,0.037325468,0.00047116933,0.00062801724,0.0003514296,0.7332987,0.11369976],"study_design_scores_gemma":[0.002255014,0.0005368396,0.23332836,0.0018898046,0.00013054814,0.000011410424,0.030594759,0.001609583,0.0003543779,0.0008044632,0.7274887,0.0009961318],"about_ca_topic_score_codex":0.044435803,"about_ca_topic_score_gemma":0.068435214,"teacher_disagreement_score":0.12070708,"about_ca_system_score_codex":0.010847179,"about_ca_system_score_gemma":0.046018593,"threshold_uncertainty_score":0.99943465},"labels":[],"label_agreement":null},{"id":"W4232361437","doi":"10.4337/9781784719326.00014","title":"The elements of effective program design: a two-level analysis","year":2017,"lang":"en","type":"book-chapter","venue":"Edward Elgar Publishing eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan; Simon Fraser University","funders":"","keywords":"Theme (computing); Management science; Program Design Language; Work (physics); Computer science; Policy analysis; Engineering ethics; Engineering; Political science; Software engineering; Public administration","score_opus":0.2439654780855621,"score_gpt":0.465690038247234,"score_spread":0.22172456016167189,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4232361437","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000107168154,0.00016939461,0.006726748,0.0005571304,0.0011191197,0.002052294,0.00008693033,0.000086027096,0.9890952],"genre_scores_gemma":[0.04119055,0.000030188527,0.00832272,0.00021403546,0.00049107673,0.00036530642,0.00006919729,0.000066431174,0.9492505],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9920219,0.00043257928,0.0015427307,0.0008641524,0.0046569738,0.0004816371],"domain_scores_gemma":[0.98965865,0.0027947684,0.002858039,0.002411529,0.0020833502,0.0001936631],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.020413883,0.00045823766,0.00095094607,0.00087802624,0.0009818618,0.006608627,0.0034303616,0.0003343074,0.0006008592],"category_scores_gemma":[0.0040014307,0.0002817843,0.00078324415,0.00012973767,0.00039859323,0.0010296522,0.00060261646,0.00080900267,0.00017124126],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006866693,0.000026042753,0.00062820636,0.000009876159,0.0015094776,0.0000042530855,0.00053665444,0.00009578675,0.0000058926103,0.02538748,0.018209731,0.9535179],"study_design_scores_gemma":[0.0008724811,0.00034187722,0.003946043,0.00012921091,0.00096088654,0.000002480286,0.00010514378,0.0046661,0.00013046988,0.10223718,0.8860765,0.00053160597],"about_ca_topic_score_codex":0.00009028942,"about_ca_topic_score_gemma":0.00093614135,"teacher_disagreement_score":0.9529863,"about_ca_system_score_codex":0.0001815524,"about_ca_system_score_gemma":0.0007899723,"threshold_uncertainty_score":0.9999634},"labels":[],"label_agreement":null},{"id":"W4232369538","doi":"10.1108/9781800718173","title":"Understanding Decision-Making in Educational Contexts","year":2021,"lang":"en","type":"book","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Knowledge management","score_opus":0.45835266253340895,"score_gpt":0.53665185874941,"score_spread":0.07829919621600107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4232369538","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000090204914,0.000378847,0.026616592,0.0017466025,0.001363837,0.00019781527,0.000009469952,0.000012666575,0.969584],"genre_scores_gemma":[0.07503865,0.000061220715,0.0027868429,0.0012651895,0.00026212892,0.0000143358275,0.000041857893,0.000017995057,0.9205118],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.994999,0.0001312625,0.0010717025,0.0006265046,0.0029481885,0.00022335314],"domain_scores_gemma":[0.9909327,0.007632422,0.00035759434,0.00057979877,0.00042062454,0.000076885495],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003764842,0.00021065664,0.00043109525,0.00082068355,0.0001301709,0.00048322318,0.0005932906,0.00022317021,0.083773345],"category_scores_gemma":[0.0022064382,0.00016451692,0.00015636695,0.0004796625,0.00006027702,0.0003267276,0.00017509788,0.00035583126,0.0015279343],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014180606,0.000044013592,0.0025749998,0.0000064742567,0.000015811962,0.000010910684,0.00036620803,0.00039117655,9.953969e-7,0.41580927,0.54098374,0.03978221],"study_design_scores_gemma":[0.00024835128,0.000014504583,0.003488885,0.0005115183,0.000006094867,0.000008104905,0.00066440686,0.0017124411,6.685209e-7,0.79010934,0.20300648,0.00022923049],"about_ca_topic_score_codex":0.000002618745,"about_ca_topic_score_gemma":0.0011148,"teacher_disagreement_score":0.37430003,"about_ca_system_score_codex":0.0013735187,"about_ca_system_score_gemma":0.005007814,"threshold_uncertainty_score":0.9992495},"labels":[],"label_agreement":null},{"id":"W4232397894","doi":"10.3138/cpp.37.4.479","title":"Do Strikes and Work-to-Rule Campaigns Change Elementary School Assessment Results?","year":2011,"lang":"en","type":"article","venue":"Canadian Public Policy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Wilfrid Laurier University","funders":"","keywords":"Disadvantaged; Work (physics); Mathematics education; Student achievement; Academic achievement; Political science; Psychology; Engineering; Law","score_opus":0.34883222805050046,"score_gpt":0.46304515832551313,"score_spread":0.11421293027501267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4232397894","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7194666,0.00015700283,0.0002059003,0.124011114,0.0007231697,0.0013079236,0.00077275065,0.000084935855,0.1532706],"genre_scores_gemma":[0.9720936,0.000034574095,0.0015277216,0.023649657,0.00051000353,0.00014141279,0.000040573024,0.000016559476,0.0019858982],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9967087,0.0002180323,0.0006352074,0.0005779932,0.0010395898,0.0008204584],"domain_scores_gemma":[0.99596506,0.000144118,0.00017625354,0.00082663854,0.00034798277,0.0025399195],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0037450707,0.00020526916,0.00024120166,0.0019482435,0.00039044884,0.0006912562,0.00078960706,0.00009382824,0.004457754],"category_scores_gemma":[0.0014263773,0.00017008946,0.000057930978,0.0021009056,0.00008877815,0.0009699284,0.00014544651,0.00020811502,0.0007103706],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002232634,0.000051351526,0.477955,0.000003794847,0.00003719675,0.000013185157,0.0034465352,0.0000017850701,0.0000073405745,0.020071978,0.17150994,0.32687956],"study_design_scores_gemma":[0.00044268227,0.000090587404,0.61104214,0.0000116142455,0.0000048809575,0.000003905759,0.0014915741,0.00005592009,0.000009058748,0.0029284204,0.38371274,0.00020649373],"about_ca_topic_score_codex":0.10598584,"about_ca_topic_score_gemma":0.21739912,"teacher_disagreement_score":0.32667306,"about_ca_system_score_codex":0.00074244506,"about_ca_system_score_gemma":0.004334214,"threshold_uncertainty_score":0.99645233},"labels":[],"label_agreement":null},{"id":"W4232707640","doi":"10.1177/1356389015580672","title":"Canadian Evaluation Society 36th Conference 2015: <i>Evaluation for the world we want</i>","year":2015,"lang":"en","type":"article","venue":"Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Engineering ethics; Environmental ethics; Engineering; Philosophy","score_opus":0.5302600051866425,"score_gpt":0.5674058189989668,"score_spread":0.03714581381232429,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4232707640","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13269062,0.008225206,0.099003814,0.52670425,0.020051008,0.040938277,0.00040924747,0.00032022138,0.17165737],"genre_scores_gemma":[0.988943,0.00005232011,0.0016921755,0.0015171826,0.0005712643,0.0019274878,0.00034780856,0.000024450641,0.004924334],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9848996,0.0018146978,0.0010592225,0.00075406546,0.010949274,0.00052318414],"domain_scores_gemma":[0.98264664,0.0016269572,0.00062838773,0.0010486497,0.013670123,0.00037922416],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.10284872,0.00027745165,0.000293268,0.00039046168,0.0007794687,0.00073437643,0.0008270883,0.00014125841,0.008080318],"category_scores_gemma":[0.0058870814,0.00018920278,0.00022603494,0.0014449529,0.00010658174,0.0011519067,0.00006524509,0.00022631479,0.00093806477],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047078054,0.00004300964,0.0014455611,0.0000043595796,0.000052160398,5.803412e-8,0.004731103,0.04406756,0.000070555434,0.0019658764,0.43225658,0.5153161],"study_design_scores_gemma":[0.0022282267,0.00008234342,0.0055739363,0.000020361025,0.00032755276,0.00000212914,0.0041039926,0.81583184,0.00017250289,0.06983407,0.101601176,0.00022184412],"about_ca_topic_score_codex":0.0031160417,"about_ca_topic_score_gemma":0.19679792,"teacher_disagreement_score":0.8562524,"about_ca_system_score_codex":0.0023562675,"about_ca_system_score_gemma":0.013129653,"threshold_uncertainty_score":0.99983984},"labels":[],"label_agreement":null},{"id":"W4232722672","doi":"10.1007/978-981-10-2779-6_102-1","title":"Content Analysis: Using Critical Realism to Extend Its Utility","year":2017,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Phenomenon; Epistemology; Popularity; Rigour; Critical realism (philosophy of perception); Transparency (behavior); Interpretation (philosophy); Realism; Connotation; Context (archaeology); Sociology; Psychology; Social psychology; Computer science; Philosophy; History","score_opus":0.7575075864138798,"score_gpt":0.5977229495804409,"score_spread":0.1597846368334389,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4232722672","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00040913216,0.00016176321,0.015517695,0.0024850587,0.0007180295,0.0003328534,0.000120820354,0.000035280562,0.98021936],"genre_scores_gemma":[0.2015311,0.000031985273,0.0017184956,0.0014072537,0.00019501398,0.0000068628374,0.000018651792,0.000015727082,0.79507494],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99437004,0.0001219517,0.0011321988,0.0009254444,0.0031534582,0.00029690342],"domain_scores_gemma":[0.99452883,0.0008436006,0.0003890225,0.001891134,0.001969807,0.0003776276],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.006506977,0.0003083293,0.00086137914,0.00072675204,0.0004836721,0.0007353224,0.0010566813,0.00026490766,0.046537098],"category_scores_gemma":[0.0030572133,0.00021399098,0.0005108408,0.000099538884,0.00014330838,0.0003720824,0.0003324094,0.00033250207,0.0024168647],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011817456,0.00009465974,0.0010800806,0.0000258906,0.00091807364,0.000055075267,0.0007927707,0.00025009346,0.000096078234,0.86570805,0.031431533,0.09942951],"study_design_scores_gemma":[0.00038747487,0.00015757766,0.015944095,0.00015241613,0.001615788,0.000011878505,0.0004892668,0.07632372,0.00009030267,0.091652445,0.812139,0.0010360855],"about_ca_topic_score_codex":0.00009563916,"about_ca_topic_score_gemma":0.0006885315,"teacher_disagreement_score":0.7807074,"about_ca_system_score_codex":0.00009930332,"about_ca_system_score_gemma":0.00033282148,"threshold_uncertainty_score":0.99835986},"labels":[],"label_agreement":null},{"id":"W4234009060","doi":"10.35648/20.500.12413/11781/ii364","title":"Evidencing Impact Across a Diverse Portfolio of Research","year":2021,"lang":"en","type":"report","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; Arts and Humanities Research Council; Economic and Social Research Council; Foreign, Commonwealth and Development Office; Department for International Development; University of Bath; Global Challenges Research Fund; University of Liverpool; University of Cambridge; Engineering and Physical Sciences Research Council; UK Research and Innovation; Overseas Development Institute; International Development Research Centre; Government of the United Kingdom; Oxfam America; University of Nottingham; Imperial College London; Leeds Beckett University","keywords":"Portfolio; Economics; Financial economics","score_opus":0.8309329051199658,"score_gpt":0.7488470068245779,"score_spread":0.08208589829538782,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4234009060","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28591546,0.0016270687,0.0002129473,0.00030740927,0.0018258559,0.0004772854,0.00012675692,0.000032853157,0.7094743],"genre_scores_gemma":[0.75986487,0.002543366,0.0003229247,0.000044397297,0.00042721722,0.000019167454,0.000047968777,0.000020250933,0.23670982],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9769072,0.000697003,0.0016842226,0.00078745576,0.0193286,0.00059555203],"domain_scores_gemma":[0.9799402,0.002674718,0.0008141282,0.0015897974,0.014766445,0.00021471536],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0678579,0.00022430212,0.00081914174,0.0007737704,0.0002739619,0.00047778987,0.0011155895,0.00030985638,0.07043697],"category_scores_gemma":[0.018018411,0.00013996557,0.000547236,0.002668853,0.00021243675,0.0004674662,0.0009597486,0.0007397337,0.0006732496],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028205015,0.000103699334,0.1687888,0.000096606425,0.0001316582,0.00009711384,0.0014029356,0.00022806603,0.00013998077,0.00008516103,0.7441288,0.08476897],"study_design_scores_gemma":[0.00070635165,0.0005388725,0.35755178,0.0013476764,0.00006577262,0.00020160455,0.044699393,0.0018078699,0.0014472806,0.002539592,0.58834326,0.0007505485],"about_ca_topic_score_codex":0.0036815207,"about_ca_topic_score_gemma":0.0013919411,"teacher_disagreement_score":0.4739494,"about_ca_system_score_codex":0.0006954125,"about_ca_system_score_gemma":0.015371897,"threshold_uncertainty_score":0.9902532},"labels":[],"label_agreement":null},{"id":"W4234160001","doi":"10.3138/cjpe.34.3.v","title":"Editor’s Remarks","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Philosophy; Psychology","score_opus":0.3130698758640696,"score_gpt":0.5203254987844013,"score_spread":0.20725562292033167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4234160001","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.52900785,0.0040491326,0.027930891,0.27963135,0.053766813,0.0069849757,0.00004936131,0.000109825014,0.09846981],"genre_scores_gemma":[0.99058664,0.0000053420094,0.0038575812,0.0013054257,0.0041178796,0.000018446484,0.00000620796,0.0000075254093,0.00009497755],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9958979,0.00040524476,0.00080519787,0.00016036778,0.0025289329,0.00020235057],"domain_scores_gemma":[0.9951727,0.000161213,0.00056355965,0.00017884086,0.0030918855,0.0008318189],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010229976,0.00008598123,0.00018712904,0.0002938923,0.00013863586,0.00038374503,0.0004830046,0.0000647104,0.0061310297],"category_scores_gemma":[0.0065565505,0.000064959335,0.00011773652,0.0007403048,0.000056413235,0.00059451355,0.000009513816,0.00020880539,0.00028931972],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013141119,0.000012106104,0.0115501555,0.0000022819681,0.000014669857,0.000005402182,0.0012205056,0.0013830048,0.000036111567,0.00020052133,0.20221043,0.78335166],"study_design_scores_gemma":[0.00076907175,0.000649044,0.028208481,0.000020196903,0.00005483759,0.000017999322,0.0011803188,0.087478034,0.00007881379,0.004332372,0.877088,0.00012279728],"about_ca_topic_score_codex":0.00010812263,"about_ca_topic_score_gemma":0.0030603046,"teacher_disagreement_score":0.7832289,"about_ca_system_score_codex":0.00018679582,"about_ca_system_score_gemma":0.0055253017,"threshold_uncertainty_score":0.9947775},"labels":[],"label_agreement":null},{"id":"W4234575970","doi":"10.32920/ryerson.14658162.v1","title":"Implementing participatory research within a northern Ontario First Nations community","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Toronto Metropolitan University; Education and Early Childhood Development","funders":"","keywords":"Mainstream; Participatory action research; Citizen journalism; Government (linguistics); Political science; Decolonization; Economic growth; Meaning (existential); Sociology; Public administration; Politics; Anthropology; Law; Psychology","score_opus":0.795307548937539,"score_gpt":0.6220525606245707,"score_spread":0.17325498831296826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4234575970","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87737614,0.000033925502,0.0014368349,0.0017855726,0.00059952657,0.00047043615,0.0000112884545,0.000045046683,0.11824125],"genre_scores_gemma":[0.9842936,0.0000066984444,0.003103927,0.0001702303,0.00007573937,0.0002604516,0.00010816282,0.000014518472,0.011966692],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98955834,0.00316999,0.0014240114,0.00057847047,0.0046532573,0.00061595155],"domain_scores_gemma":[0.9887596,0.0049667545,0.00043548795,0.0021105781,0.0035451523,0.00018244874],"candidate_categories":["metaresearch","sts","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.058973245,0.00020530348,0.00037433224,0.0006654702,0.003539896,0.0016689582,0.0016242696,0.00018455487,0.020070571],"category_scores_gemma":[0.005372907,0.00016286384,0.00018227928,0.0009840963,0.00015133544,0.0003109598,0.004658985,0.00284441,0.0005624842],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009364616,0.00034571235,0.88158226,0.00004879887,0.00008529059,0.000004946962,0.099793956,0.00693572,0.000013154436,0.005264481,0.0033099407,0.0026063956],"study_design_scores_gemma":[0.0008992217,0.00017070332,0.5746662,0.00046181996,0.00006619542,0.0000057157063,0.19499104,0.02443133,0.0005405205,0.046328783,0.15652715,0.0009112976],"about_ca_topic_score_codex":0.13630775,"about_ca_topic_score_gemma":0.99847937,"teacher_disagreement_score":0.8621716,"about_ca_system_score_codex":0.00084818766,"about_ca_system_score_gemma":0.005641147,"threshold_uncertainty_score":0.99999595},"labels":[],"label_agreement":null},{"id":"W4234603440","doi":"10.32920/ryerson.14658162","title":"Implementing participatory research within a northern Ontario First Nations community","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Toronto Metropolitan University; Education and Early Childhood Development","funders":"","keywords":"Mainstream; Participatory action research; Citizen journalism; Government (linguistics); Political science; Decolonization; Meaning (existential); Economic growth; Sociology; Public administration; Politics; Anthropology; Law; Psychology","score_opus":0.795307548937539,"score_gpt":0.6220525606245707,"score_spread":0.17325498831296826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4234603440","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87737614,0.000033925502,0.0014368349,0.0017855726,0.00059952657,0.00047043615,0.0000112884545,0.000045046683,0.11824125],"genre_scores_gemma":[0.9842936,0.0000066984444,0.003103927,0.0001702303,0.00007573937,0.0002604516,0.00010816282,0.000014518472,0.011966692],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98955834,0.00316999,0.0014240114,0.00057847047,0.0046532573,0.00061595155],"domain_scores_gemma":[0.9887596,0.0049667545,0.00043548795,0.0021105781,0.0035451523,0.00018244874],"candidate_categories":["metaresearch","sts","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.058973245,0.00020530348,0.00037433224,0.0006654702,0.003539896,0.0016689582,0.0016242696,0.00018455487,0.020070571],"category_scores_gemma":[0.005372907,0.00016286384,0.00018227928,0.0009840963,0.00015133544,0.0003109598,0.004658985,0.00284441,0.0005624842],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009364616,0.00034571235,0.88158226,0.00004879887,0.00008529059,0.000004946962,0.099793956,0.00693572,0.000013154436,0.005264481,0.0033099407,0.0026063956],"study_design_scores_gemma":[0.0008992217,0.00017070332,0.5746662,0.00046181996,0.00006619542,0.0000057157063,0.19499104,0.02443133,0.0005405205,0.046328783,0.15652715,0.0009112976],"about_ca_topic_score_codex":0.13630775,"about_ca_topic_score_gemma":0.99847937,"teacher_disagreement_score":0.8621716,"about_ca_system_score_codex":0.00084818766,"about_ca_system_score_gemma":0.005641147,"threshold_uncertainty_score":0.99999595},"labels":[],"label_agreement":null},{"id":"W4234678424","doi":"10.35648/20.500.12413/11781/ii367","title":"Annexe: Impact Stories - Maximising the Impact of Global Development Research – A New Approach to Knowledge Brokering","year":2021,"lang":"en","type":"report","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; Arts and Humanities Research Council; Economic and Social Research Council; Foreign, Commonwealth and Development Office; Department for International Development; University of Bath; Global Challenges Research Fund; University of Liverpool; University of Cambridge; Engineering and Physical Sciences Research Council; UK Research and Innovation; Overseas Development Institute; International Development Research Centre; Government of the United Kingdom; Oxfam America; University of Nottingham; Imperial College London; Leeds Beckett University","keywords":"Development (topology); Knowledge management; Process management; Computer science; Data science; Business; Mathematics","score_opus":0.7291537039015842,"score_gpt":0.6732861260042807,"score_spread":0.055867577897303455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4234678424","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07225908,0.0025115951,0.0074164583,0.0003853235,0.0010588886,0.001109802,0.00005344225,0.000042606738,0.9151628],"genre_scores_gemma":[0.8278136,0.0002506603,0.009905296,0.000031546773,0.00086692104,0.00007776236,0.00008652547,0.00005058211,0.1609171],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9869128,0.00079644873,0.0016325903,0.000987473,0.00887867,0.0007920357],"domain_scores_gemma":[0.9897854,0.0011271767,0.00049887534,0.0015909213,0.006491946,0.0005057352],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.030478815,0.00043618015,0.00093314063,0.0004779743,0.00050979026,0.0010585553,0.0017514772,0.00027459796,0.0037050876],"category_scores_gemma":[0.006074618,0.0002195422,0.00055213645,0.004420368,0.0001281588,0.0003201861,0.001123805,0.000636326,0.00032599233],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.0000677436,0.00025686284,0.028097201,0.000061853825,0.00036683996,0.000004078365,0.0066599003,0.003901589,0.000037251157,0.00031965773,0.74118775,0.21903926],"study_design_scores_gemma":[0.0004918791,0.00032954407,0.41807005,0.0003846229,0.00004147371,0.0001505703,0.009996412,0.002269486,0.000263853,0.0008115959,0.56643283,0.00075765373],"about_ca_topic_score_codex":0.004833884,"about_ca_topic_score_gemma":0.0019828407,"teacher_disagreement_score":0.7555545,"about_ca_system_score_codex":0.004657878,"about_ca_system_score_gemma":0.0626304,"threshold_uncertainty_score":0.9999784},"labels":[],"label_agreement":null},{"id":"W4234905662","doi":"10.1037/e584752012-097","title":"First Nations/Tribal leadership perspective on the use of research and program evaluation in their communities","year":2010,"lang":"en","type":"dataset","venue":"PsycEXTRA Dataset","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Perspective (graphical); Sociology; Political science; Management science; Engineering ethics; Computer science; Engineering; Artificial intelligence","score_opus":0.8489635842500021,"score_gpt":0.6258028135471623,"score_spread":0.2231607707028398,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4234905662","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001683194,0.00016420115,0.000002183787,0.00661625,0.00020622202,0.002399259,0.98880345,0.000008757844,0.00011646384],"genre_scores_gemma":[0.009378334,0.0005627553,0.00012506872,0.00029377494,0.00008405719,0.00076572504,0.98875076,0.000009784137,0.000029727666],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.992095,0.0023369093,0.00077385904,0.0004925487,0.003946061,0.00035561065],"domain_scores_gemma":[0.9775751,0.018062541,0.00040083463,0.0022842025,0.0016009602,0.00007633104],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.021976324,0.00025712757,0.00035227445,0.0014729059,0.0006835139,0.00072153436,0.0016738441,0.00028370455,0.0026803345],"category_scores_gemma":[0.008753234,0.00015396769,0.00005327382,0.0016569629,0.0010535185,0.00058050244,0.00031911934,0.0017357371,0.00018636869],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000812133,0.00044520403,0.00018828502,0.000031584303,0.000020981015,7.0247694e-7,0.0008388795,0.000068984795,6.5061164e-7,0.00095704873,0.9944234,0.0029430524],"study_design_scores_gemma":[0.00043674698,0.00035192,0.0024541738,0.00022155646,0.000019605093,0.000003835708,0.017399155,0.0034604035,0.0000071220816,0.0026394697,0.9728424,0.00016359868],"about_ca_topic_score_codex":0.0030704767,"about_ca_topic_score_gemma":0.1654613,"teacher_disagreement_score":0.16239083,"about_ca_system_score_codex":0.00017235166,"about_ca_system_score_gemma":0.0004919252,"threshold_uncertainty_score":0.9995965},"labels":[],"label_agreement":null},{"id":"W4234946968","doi":"10.3138/cjpe.30.3.04","title":"Lessons on Decolonizing Evaluation from Kaupapa Māori Evaluation","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Aotearoa; Indigenous; Sociology; Traditional knowledge; Equity (law); Christian ministry; Community development; Cultural competence; Pedagogy; Public relations; Political science; Gender studies","score_opus":0.6218029580620157,"score_gpt":0.5966281862836175,"score_spread":0.02517477177839822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4234946968","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9594777,0.0008938044,0.0029264065,0.01931495,0.0040838,0.0036810867,0.000055407672,0.000027335254,0.0095395],"genre_scores_gemma":[0.99641144,0.000022851691,0.001998685,0.00034696082,0.00064630306,0.00033308365,0.00004879966,0.000024254758,0.00016760209],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9858571,0.002900598,0.0016683901,0.0005500306,0.008518367,0.0005054679],"domain_scores_gemma":[0.9845241,0.0013719837,0.001603414,0.00071467593,0.0110867,0.0006991334],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.058124952,0.00026448964,0.00040006728,0.0012778983,0.0004523172,0.0005933336,0.00077739725,0.00019679208,0.019662144],"category_scores_gemma":[0.019394701,0.00017384806,0.00024294358,0.001030944,0.00013277824,0.0014127949,0.000020870215,0.00026287622,0.0009154424],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043138112,0.00006247364,0.011369663,0.0000011128104,0.000052071373,0.0000023579335,0.0006137678,0.002794091,0.0003966936,0.0004391378,0.005214055,0.9790114],"study_design_scores_gemma":[0.008954713,0.0018509018,0.46356136,0.000508078,0.0010589805,0.00003315095,0.0018462199,0.29799646,0.0018805807,0.13820444,0.083402075,0.00070303655],"about_ca_topic_score_codex":0.0005779843,"about_ca_topic_score_gemma":0.02840033,"teacher_disagreement_score":0.9783084,"about_ca_system_score_codex":0.002719115,"about_ca_system_score_gemma":0.013221617,"threshold_uncertainty_score":0.99986243},"labels":[],"label_agreement":null},{"id":"W4235017088","doi":"10.4095/301332","title":"Location of study inside Canada, different province or territory than province or territory of residence, 2006 (by census division)","year":2010,"lang":"en","type":"report","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Census; Residence; Geography; Division (mathematics); Socioeconomics; Archaeology; Physical geography; Demography; Population; Sociology","score_opus":0.13985368108510762,"score_gpt":0.4371361849694346,"score_spread":0.297282503884327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4235017088","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94965225,0.0011156003,0.0007289012,0.0010703275,0.009064886,0.007985038,0.0012498825,0.0001204288,0.029012697],"genre_scores_gemma":[0.86298007,0.00011992719,0.00021269714,0.00007452717,0.00028973524,0.00011883603,0.00009627359,0.00004289109,0.13606504],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9826926,0.0006465813,0.0034624536,0.0012388466,0.011476119,0.0004833902],"domain_scores_gemma":[0.9895432,0.0016408584,0.0032551216,0.0018991324,0.003379903,0.00028180252],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0057060146,0.0006284527,0.0014475619,0.00062131375,0.0002276654,0.00015089037,0.001842404,0.00042392054,0.0013457788],"category_scores_gemma":[0.0030870002,0.0003478361,0.00014747151,0.00050015515,0.00028545497,0.0004884164,0.00049803744,0.0008024667,0.000012934591],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004449017,0.0018750993,0.3060083,0.00080036453,0.00014220453,0.00005987271,0.00026452576,0.00008971093,0.00062116026,0.000026138006,0.63970953,0.049958207],"study_design_scores_gemma":[0.0010619295,0.0015954833,0.7760145,0.0009738765,0.00014039552,0.00001907677,0.0026422855,0.00066197827,0.002637607,0.000059555034,0.21339834,0.000794975],"about_ca_topic_score_codex":0.55462164,"about_ca_topic_score_gemma":0.98551995,"teacher_disagreement_score":0.4700062,"about_ca_system_score_codex":0.00093009527,"about_ca_system_score_gemma":0.04812057,"threshold_uncertainty_score":0.99989736},"labels":[],"label_agreement":null},{"id":"W4235238479","doi":"10.18870/hlrc.v6i3.349","title":"Editorial","year":2016,"lang":"en","type":"editorial","venue":"Higher Learning Research Communications","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Scholarship; Publication; Publishing; Citation; Quarter (Canadian coin); Psychology; Value (mathematics); Library science; Public relations; Political science; Sociology; Computer science; Law; History","score_opus":0.4076641032416535,"score_gpt":0.6345727241413951,"score_spread":0.22690862089974162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4235238479","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000032903583,0.0007101918,0.00007015556,0.0070186444,0.8682729,0.00030527872,0.00006168402,0.00011786022,0.12344002],"genre_scores_gemma":[0.0005396888,0.0024234965,0.0003250423,0.000014346397,0.7774842,0.00024840876,0.00024708005,0.000050697832,0.21866703],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9714782,0.00835237,0.0011673479,0.00087134837,0.017313356,0.00081732566],"domain_scores_gemma":[0.91525954,0.0644207,0.0006067714,0.0071382686,0.012246838,0.00032788183],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.04486776,0.00029206745,0.00051945227,0.0011589216,0.0023345414,0.0013868344,0.0094568,0.0010611616,0.008437614],"category_scores_gemma":[0.05729701,0.00020181996,0.00022584647,0.0017376961,0.00093338644,0.0005580187,0.0034733198,0.006775292,0.02051625],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024031433,0.00006421185,0.00010413,0.000005594582,0.00002660664,3.859304e-7,0.0001693289,0.000008640593,0.000031190164,0.0022946242,0.98517174,0.01209952],"study_design_scores_gemma":[0.00044831415,0.00013917086,0.00009719618,0.000115467476,0.000009961879,1.2097885e-7,0.00009893799,0.00010315758,0.0000025826132,0.008550453,0.9901865,0.0002481379],"about_ca_topic_score_codex":0.00012242519,"about_ca_topic_score_gemma":0.00008804447,"teacher_disagreement_score":0.09522701,"about_ca_system_score_codex":0.0005728285,"about_ca_system_score_gemma":0.0032769025,"threshold_uncertainty_score":0.9996498},"labels":[],"label_agreement":null},{"id":"W4235308384","doi":"10.1002/9781118901731.iecrm0214","title":"Research Program","year":2017,"lang":"en","type":"other","venue":"The International Encyclopedia of Communication Research Methods","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Research program; Foundation (evidence); Computer science; Engineering ethics; Line (geometry); Management science; Sociology; Political science; Epistemology; Engineering; Mathematics; Philosophy","score_opus":0.6811238925593182,"score_gpt":0.7488880519459689,"score_spread":0.0677641593866507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4235308384","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000020132888,0.002254377,0.0011522259,0.015110477,0.00070369407,0.0012305072,0.000034805595,0.000062641666,0.97943115],"genre_scores_gemma":[0.0006365937,0.019769546,0.08638152,0.000050213454,0.00042730535,0.0006122096,0.000053817235,0.000112411486,0.8919564],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.96980965,0.01693528,0.0010223264,0.00057894306,0.011134113,0.0005196783],"domain_scores_gemma":[0.967997,0.019236404,0.0010275383,0.0062698843,0.0053369235,0.00013225006],"candidate_categories":["metaresearch","open_science","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.14783755,0.00019624905,0.0004289636,0.0020248983,0.0007945014,0.0006531891,0.016847745,0.00028468895,0.015150579],"category_scores_gemma":[0.029493313,0.00012196758,0.00018227166,0.0010277987,0.0021925163,0.00025098238,0.0032854876,0.002122437,0.0010446836],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016615826,0.00009482742,0.000079529,0.0000052661394,0.000048621292,3.2452212e-7,0.0002066033,0.000005870441,0.000011867859,0.014227349,0.5727068,0.41259632],"study_design_scores_gemma":[0.00019729647,0.00007487564,0.0007825474,0.00019400477,0.000006324305,0.0000018292193,0.00060771685,0.00166564,0.0000693719,0.045451347,0.9508391,0.00010994009],"about_ca_topic_score_codex":0.0014144136,"about_ca_topic_score_gemma":0.0009734438,"teacher_disagreement_score":0.41248637,"about_ca_system_score_codex":0.00016909529,"about_ca_system_score_gemma":0.001275111,"threshold_uncertainty_score":0.9997331},"labels":[],"label_agreement":null},{"id":"W4235318396","doi":"10.1177/109821400002100306","title":"Planning for Community-based Evaluation","year":2000,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Program evaluation; Unit (ring theory); Management science; Set (abstract data type); Process (computing); Conflict resolution; Process management; Psychology; Computer science; Sociology; Political science; Business; Engineering; Mathematics education; Social science","score_opus":0.355370496696108,"score_gpt":0.5926022913441982,"score_spread":0.2372317946480902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4235318396","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97119504,0.0000836268,0.021226972,0.0020041321,0.00029903871,0.0005212631,0.0000054459224,0.000007950127,0.0046565332],"genre_scores_gemma":[0.9918718,0.0000048603206,0.006567748,0.0011978636,0.00017642937,0.000042391548,0.000026928317,0.000009950096,0.00010203072],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9909324,0.003138678,0.0011117165,0.00014423732,0.0044991253,0.00017383517],"domain_scores_gemma":[0.99139667,0.002398506,0.0012933873,0.00038363825,0.004428474,0.00009931434],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.062370263,0.000115685485,0.00031484058,0.00041459184,0.0003348171,0.0001538117,0.00040411297,0.000030891046,0.0047241133],"category_scores_gemma":[0.0032913194,0.00008755118,0.0001753835,0.000762441,0.00011680328,0.000566063,0.000009255357,0.0002414249,0.0000750351],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021897495,0.000075713375,0.0026774323,0.0000016634191,0.000018585042,1.6175443e-7,0.0011870371,0.19519553,0.00016251094,0.000024981127,0.0018481534,0.7985893],"study_design_scores_gemma":[0.003456121,0.0024610232,0.05898298,0.000072969604,0.0002517479,0.00001941933,0.0047213444,0.8889052,0.00042753326,0.015081334,0.025429545,0.00019076462],"about_ca_topic_score_codex":0.0000148748995,"about_ca_topic_score_gemma":0.000009231274,"teacher_disagreement_score":0.7983985,"about_ca_system_score_codex":0.00022742034,"about_ca_system_score_gemma":0.0011802013,"threshold_uncertainty_score":0.9961857},"labels":[],"label_agreement":null},{"id":"W4235778091","doi":"10.24124/2007/bpgub1331","title":"The importance of change management for BC First Nations' treaty implementation","year":2007,"lang":"en","type":"dissertation","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Victoria; University of Northern British Columbia","funders":"University of Northern British Columbia","keywords":"Treaty; Political science; Public administration; Law","score_opus":0.3207278024445081,"score_gpt":0.5867986452859414,"score_spread":0.2660708428414333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4235778091","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13474768,0.0015869396,0.00948934,0.006286486,0.006861978,0.014820847,0.00035141935,0.0001309209,0.82572436],"genre_scores_gemma":[0.6217869,0.00428881,0.008755413,0.000858008,0.0006663393,0.0053645563,0.0051718024,0.000082852566,0.3530253],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9963141,0.00004797197,0.0012047496,0.00037403463,0.0018205096,0.00023861439],"domain_scores_gemma":[0.9959038,0.0015804736,0.0010038819,0.0005267887,0.0009389063,0.000046141435],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00486032,0.00018431434,0.00024022133,0.00048811454,0.00067420537,0.0001551778,0.0005629539,0.000098888144,0.0021022456],"category_scores_gemma":[0.00021225373,0.00011145866,0.00018882426,0.0007495849,0.000027170772,0.0002809582,0.000026260857,0.000067598274,0.00006730646],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002726508,0.00012270197,0.036469843,0.0002462926,0.00018537304,7.971893e-7,0.0032889163,0.000020226844,0.000007844878,0.19431536,0.0470539,0.7180161],"study_design_scores_gemma":[0.0015959968,0.00024090681,0.29762977,0.00008757898,0.00016268315,5.7229624e-7,0.0630995,0.0013959863,0.0014654433,0.01505489,0.6188645,0.00040220682],"about_ca_topic_score_codex":0.00009846113,"about_ca_topic_score_gemma":0.121810615,"teacher_disagreement_score":0.7176139,"about_ca_system_score_codex":0.000100985155,"about_ca_system_score_gemma":0.00010465329,"threshold_uncertainty_score":0.99881},"labels":[],"label_agreement":null},{"id":"W4235919605","doi":"10.3138/cjpe.30.3.03","title":"Getting to the Roots of Evaluation Capacity Building in the Global South: Multiple Streams Model to Frame the Agenda Status of Evaluation in Turkey","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Frame (networking); Capacity building; Window of opportunity; Political science; Business; Public administration; Public economics; Economic growth; Economics; Computer science","score_opus":0.44681448485405895,"score_gpt":0.5082014368718829,"score_spread":0.06138695201782396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4235919605","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98243314,0.00020869853,0.0060419403,0.006817719,0.0003837045,0.0037731922,0.00006107345,0.0000028607196,0.0002776901],"genre_scores_gemma":[0.99620944,0.0000044726426,0.003099974,0.00030361715,0.000094753246,0.00026801927,0.0000059421554,0.000008625499,0.000005175448],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9876095,0.0034578103,0.0018030375,0.00033355088,0.006255284,0.0005408326],"domain_scores_gemma":[0.9920117,0.0012796427,0.0011870342,0.00062178937,0.0046397373,0.0002600443],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07228505,0.00017997876,0.00031062085,0.00061694544,0.00020702148,0.00020357239,0.0007944043,0.00009809897,0.0002511758],"category_scores_gemma":[0.028655706,0.000085318265,0.0001389793,0.0020474277,0.00011297868,0.00054213183,0.00003868932,0.00024312745,0.000012647535],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003677378,0.000037620048,0.0730728,0.0000029686526,0.000013283315,3.8105506e-7,0.009824901,0.40213165,0.00036663038,0.00018539066,0.00020874341,0.51411885],"study_design_scores_gemma":[0.001158377,0.0002333254,0.32945964,0.00014437789,0.000081665436,0.000005361129,0.0047680256,0.65497637,0.00016496185,0.008420636,0.00048924825,0.000097999895],"about_ca_topic_score_codex":0.005316777,"about_ca_topic_score_gemma":0.12935029,"teacher_disagreement_score":0.51402086,"about_ca_system_score_codex":0.0017013742,"about_ca_system_score_gemma":0.006016409,"threshold_uncertainty_score":0.99961853},"labels":[],"label_agreement":null},{"id":"W4236108016","doi":"10.1332/policypress/9781447334910.003.0002","title":"The policy analysis profession in Canada","year":2018,"lang":"en","type":"book-chapter","venue":"Policy Press eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Professionalization; Craft; Situated; Power (physics); Phenomenon; Policy analysis; Corporate governance; Political science; State (computer science); Public relations; Sociology; Public administration; Social science; Epistemology; History; Management; Economics","score_opus":0.22757285867885083,"score_gpt":0.4917554903432765,"score_spread":0.2641826316644257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236108016","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00052970427,0.00014441431,0.000023003988,0.002590733,0.0003233492,0.0004282408,0.00007996735,0.000016238457,0.99586433],"genre_scores_gemma":[0.06355401,0.000100741956,0.000023729992,0.0013415836,0.00085370895,0.00005348323,0.00001188688,0.000026999563,0.9340339],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9948465,0.0002204482,0.0011470811,0.00056592637,0.002733935,0.0004860805],"domain_scores_gemma":[0.9961774,0.0009575158,0.0007509164,0.0014737311,0.00045465791,0.00018583173],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023407235,0.00033324465,0.0005630886,0.0010651465,0.00035311587,0.0002794314,0.0014525187,0.00018866562,0.0006933103],"category_scores_gemma":[0.00062044075,0.00019506832,0.00022296041,0.00018566696,0.00018192979,0.000080403355,0.00041681674,0.0004263986,0.00012773844],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000089411726,0.000011579131,0.0014973049,0.000018230225,0.00052477606,0.00001152204,0.0026117377,0.00028867554,0.0000048588886,0.71030265,0.110258274,0.17438096],"study_design_scores_gemma":[0.00018428422,0.000019151847,0.0022453163,0.000038751452,0.00007667152,0.0000010757861,0.00009904456,0.0019192805,0.000037866306,0.05680643,0.9383265,0.00024565158],"about_ca_topic_score_codex":0.89449155,"about_ca_topic_score_gemma":0.98294663,"teacher_disagreement_score":0.8280682,"about_ca_system_score_codex":0.0010922506,"about_ca_system_score_gemma":0.011072902,"threshold_uncertainty_score":0.9945334},"labels":[],"label_agreement":null},{"id":"W4236219061","doi":"10.1332/policypress/9781447339854.001.0001","title":"The Impact Agenda","year":2020,"lang":"en","type":"book","venue":"Policy Press eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Discipline; Political science; Engineering ethics; Work (physics); Public relations; Sociology; Engineering; Law","score_opus":0.45783918564322057,"score_gpt":0.5677923288799037,"score_spread":0.10995314323668315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236219061","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000009275848,0.00040818052,0.00007748079,0.0015418961,0.00034541092,0.00043146702,0.00013035387,0.000062654486,0.9969933],"genre_scores_gemma":[0.0016983266,0.00011033913,0.000029664632,0.0017310033,0.0017420817,0.000054667147,0.0000170843,0.000038875834,0.99457794],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9955844,0.00028453523,0.0008128317,0.0005015691,0.0023989086,0.00041773912],"domain_scores_gemma":[0.99619585,0.0014257547,0.00060219516,0.0012232444,0.00031974484,0.00023322167],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0019839038,0.000340096,0.00042483007,0.00018149662,0.00041917624,0.0009868888,0.0018864574,0.0001975519,0.00041909915],"category_scores_gemma":[0.0011058492,0.00017433969,0.00041050775,0.000054958153,0.00020486052,0.00009265094,0.00043698962,0.00052583724,0.0012562398],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022024133,0.0000034117095,0.000006312692,0.0000047083317,0.000059767597,0.0000029849987,0.0007340675,0.000049573086,0.00000417872,0.06737116,0.8407255,0.09101635],"study_design_scores_gemma":[0.0001652057,0.00006209228,0.00013811664,0.000015327176,0.000016800155,0.0000041957337,0.000014599218,0.0013062092,0.00005013462,0.06808059,0.9299555,0.00019123251],"about_ca_topic_score_codex":0.00034424133,"about_ca_topic_score_gemma":0.000059290407,"teacher_disagreement_score":0.09082512,"about_ca_system_score_codex":0.0002457584,"about_ca_system_score_gemma":0.0033206514,"threshold_uncertainty_score":0.9995214},"labels":[],"label_agreement":null},{"id":"W4236265963","doi":"10.3233/wor-2011-1185","title":"From the Editor","year":2011,"lang":"en","type":"article","venue":"Work","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.32417507899043163,"score_gpt":0.47274474039521597,"score_spread":0.14856966140478434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236265963","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61858284,0.00025753485,0.0038166752,0.010126845,0.031180922,0.00024271297,0.000010952736,0.00007405852,0.33570743],"genre_scores_gemma":[0.9880492,0.0000032864323,0.0012472868,0.0012995402,0.0047636935,0.000007187131,0.0000011543912,0.0000023822333,0.004626246],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989325,0.00007351092,0.00015102047,0.000112599,0.000658768,0.00007163332],"domain_scores_gemma":[0.9989799,0.0004956597,0.000055292363,0.0003715915,0.000069377464,0.000028167102],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0012765802,0.00003426997,0.000048189348,0.000014361695,0.00009250449,0.00006207512,0.00042984847,0.000020144938,0.018668953],"category_scores_gemma":[0.0002747415,0.000015993726,0.00003063686,0.00026718556,0.000030692267,0.00009363862,0.00004303566,0.000056638175,0.0065416005],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000945307,0.000011976,0.11716502,3.6985977e-8,0.000003312958,2.4884898e-7,0.0033371933,0.0000030032602,0.000004362585,0.0006126036,0.8425295,0.036323335],"study_design_scores_gemma":[0.000056122575,0.000008136417,0.36425564,0.0000028609174,0.0000021135218,5.5507535e-8,0.0007761284,0.000060266695,0.00005662006,0.01721289,0.61753994,0.00002921351],"about_ca_topic_score_codex":0.000041286636,"about_ca_topic_score_gemma":0.00002715992,"teacher_disagreement_score":0.36946636,"about_ca_system_score_codex":0.0000045286333,"about_ca_system_score_gemma":0.000034057302,"threshold_uncertainty_score":0.99423194},"labels":[],"label_agreement":null},{"id":"W4236457953","doi":"10.47678/cjhe.v50i1.188301","title":"The Impact of Quality Assurance Policies on Curriculum Development in Ontario Postsecondary Education","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Higher Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Quality assurance; Accountability; Curriculum; Context (archaeology); Higher education; Quality (philosophy); Quality management; Postsecondary education; Political science; Public relations; Business; Pedagogy; Sociology; Marketing","score_opus":0.14146963313147348,"score_gpt":0.4828812715166655,"score_spread":0.341411638385192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236457953","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9804754,0.0005670982,0.0000060130965,0.01190132,0.0012006126,0.000111308225,0.0000023955504,0.0000010120416,0.005734793],"genre_scores_gemma":[0.9956692,0.0000057466764,0.00016684298,0.0013330957,0.00013235575,0.0000050036606,0.0000041202998,0.0000040400314,0.0026796337],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9980612,0.00020994268,0.0008777717,0.00011323285,0.0005746025,0.00016326661],"domain_scores_gemma":[0.99766845,0.000235653,0.000692849,0.00017552215,0.0008890965,0.00033843794],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017456891,0.000088949244,0.00017900161,0.00028844737,0.0001342647,0.0001340406,0.0004098674,0.000036962952,0.0014421599],"category_scores_gemma":[0.00051409786,0.00005494645,0.000086374996,0.00047392037,0.00004551487,0.00031627223,0.0000064602127,0.00022379457,0.00003995847],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016647537,0.00007380355,0.9189948,0.000002894945,0.000012610391,2.3628724e-7,0.0063092615,0.00038791768,0.000039500956,0.0012891338,0.052971065,0.019902172],"study_design_scores_gemma":[0.000109444496,0.000092901,0.8601407,0.00003598566,0.0000022334918,0.0000024908159,0.001284646,0.0000067376063,0.00006537725,0.0010640937,0.1371391,0.000056315483],"about_ca_topic_score_codex":0.13506307,"about_ca_topic_score_gemma":0.5197259,"teacher_disagreement_score":0.38466284,"about_ca_system_score_codex":0.001129511,"about_ca_system_score_gemma":0.052276254,"threshold_uncertainty_score":0.99947065},"labels":[],"label_agreement":null},{"id":"W4236526761","doi":"10.1177/109821400002100304","title":"Legal and Ethical Issues in Evaluating Abortion Services","year":2000,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto","funders":"","keywords":"Confidentiality; Abortion; Context (archaeology); Legal service; Ethical issues; Business; Public relations; Internet privacy; Engineering ethics; Law; Political science; Computer science; Engineering","score_opus":0.11986276787814307,"score_gpt":0.5591065619368589,"score_spread":0.43924379405871583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236526761","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9900986,0.00029406013,0.00013273272,0.0070406115,0.00012900411,0.00014175198,8.290036e-7,0.000004485951,0.0021579326],"genre_scores_gemma":[0.9958149,0.00022006543,0.002666073,0.0010056356,0.00015101218,0.000005525077,0.00000213859,0.0000057686198,0.00012886756],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99332285,0.0015464184,0.0011669644,0.00021043532,0.0035984619,0.00015485342],"domain_scores_gemma":[0.9970525,0.000620799,0.0008187489,0.00018516563,0.0012329656,0.000089848225],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.028836446,0.00010239531,0.00032052954,0.00037089852,0.00008690719,0.00020345238,0.0002030708,0.000056470504,0.0034034504],"category_scores_gemma":[0.0010801823,0.00007547455,0.000058909394,0.00082935125,0.00012034892,0.000678344,0.000017605038,0.0003634765,0.00006821895],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013182109,0.000028506809,0.025376137,0.000002332999,0.000008594177,0.000001953618,0.0021715008,0.008551056,0.00044560916,0.00019826027,0.00010491324,0.9629793],"study_design_scores_gemma":[0.0014024104,0.0014003959,0.6300365,0.0001092374,0.00005771734,0.000088531335,0.0054929946,0.34554273,0.00014483111,0.009715995,0.0058488324,0.00015985852],"about_ca_topic_score_codex":0.00015605641,"about_ca_topic_score_gemma":0.00017521145,"teacher_disagreement_score":0.96281946,"about_ca_system_score_codex":0.00009328346,"about_ca_system_score_gemma":0.00037113752,"threshold_uncertainty_score":0.9994194},"labels":[],"label_agreement":null},{"id":"W4236583971","doi":"10.7202/1084711ar","title":"La recherche qualitative en Argentine :des apports renouvelés, des perspectives originales,des défis redoublés","year":2012,"lang":"fr","type":"article","venue":"Recherches qualitatives","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.8577458625197404,"score_gpt":0.6683078364805137,"score_spread":0.18943802603922666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236583971","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6486542,0.16713125,0.09126229,0.010117222,0.0016198439,0.0010564682,0.00020527325,0.00025215928,0.07970129],"genre_scores_gemma":[0.33226365,0.024171483,0.46983612,0.00027511874,0.0011322154,0.00018636187,0.000046054316,0.00014186565,0.17194714],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.839353,0.15148737,0.0027474482,0.0014549836,0.0029004677,0.0020567395],"domain_scores_gemma":[0.82827085,0.16415504,0.0016788605,0.0010991677,0.0036202488,0.00117583],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity","insufficient_payload"],"category_scores_codex":[0.25571477,0.0010510455,0.0014297208,0.00088170485,0.000809389,0.0006874537,0.0012201192,0.001453076,0.005873607],"category_scores_gemma":[0.13612397,0.0008811058,0.00070767064,0.003637193,0.005985008,0.0060098213,0.00033626411,0.002512608,0.0020513535],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026312945,0.0013175381,0.004050472,0.0003864463,0.0004193761,0.000010098356,0.7555493,0.000013566964,0.0005886627,0.05101262,0.0031781138,0.18321069],"study_design_scores_gemma":[0.0008260887,0.00053702126,0.014173774,0.00076015847,0.00017927166,0.00005687699,0.601023,0.00011552871,0.0011108547,0.26444182,0.11592729,0.0008483159],"about_ca_topic_score_codex":0.0007737309,"about_ca_topic_score_gemma":0.00034281283,"teacher_disagreement_score":0.3785738,"about_ca_system_score_codex":0.005493379,"about_ca_system_score_gemma":0.0029731998,"threshold_uncertainty_score":0.99984324},"labels":[],"label_agreement":null},{"id":"W4236759579","doi":"10.18296/em.0047","title":"Evaluation for the Anthropocene: Challenges ahead and making it happen","year":2019,"lang":"en","type":"article","venue":"Evaluation Matters—He Take Tō Te Aromatawai","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Anthropocene; History; Environmental ethics; Philosophy","score_opus":0.34891597194028834,"score_gpt":0.5177430182061655,"score_spread":0.1688270462658772,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236759579","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40288845,0.008224248,0.007952988,0.53318405,0.0046557905,0.013463573,0.00010318776,0.00021394802,0.029313743],"genre_scores_gemma":[0.9902487,0.00025968073,0.001008723,0.006639084,0.00023399424,0.0005371781,0.000053477852,0.00003608175,0.0009831146],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99045944,0.0011792367,0.0010361164,0.00088589295,0.006008499,0.00043079373],"domain_scores_gemma":[0.9936343,0.002583394,0.00069744047,0.0012263856,0.001767724,0.00009078824],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.041481093,0.00030950177,0.00039279019,0.00031468467,0.0005896869,0.0005906294,0.0007618564,0.00012229002,0.01399633],"category_scores_gemma":[0.0017636784,0.00020758281,0.00014158376,0.00043922046,0.00014721206,0.0011245894,0.00016391123,0.00017521693,0.0021538467],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009128026,0.00009681308,0.006744609,0.000060606653,0.0001714162,2.9380115e-7,0.0041165524,0.0051740613,0.0006069127,0.0020753006,0.09808012,0.88278204],"study_design_scores_gemma":[0.0027762982,0.00021506794,0.14697197,0.00011071388,0.00039580764,0.000015257144,0.009489025,0.70680887,0.00020170359,0.02100268,0.11161824,0.00039438155],"about_ca_topic_score_codex":0.0000172564,"about_ca_topic_score_gemma":0.00021069404,"teacher_disagreement_score":0.88238764,"about_ca_system_score_codex":0.00020371919,"about_ca_system_score_gemma":0.00046977506,"threshold_uncertainty_score":0.9986231},"labels":[],"label_agreement":null},{"id":"W4236772578","doi":"10.1002/ev.239","title":"Editor's notes","year":2007,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Citation; Computer science; Library science; Sociology","score_opus":0.2516694502734112,"score_gpt":0.5602664481446863,"score_spread":0.3085969978712751,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236772578","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09408283,0.0003643102,0.78037757,0.008008094,0.03957959,0.0023888242,0.000019443743,0.00026195502,0.0749174],"genre_scores_gemma":[0.9634696,0.000016384964,0.012544029,0.00044022384,0.0112263,0.00013915423,0.000061683124,0.000018947874,0.012083666],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99644333,0.00011313596,0.0005797027,0.00033679596,0.002305403,0.00022162122],"domain_scores_gemma":[0.99552995,0.0022052699,0.00021769461,0.00037464246,0.0015481065,0.00012431819],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017940685,0.00010065,0.00013062023,0.0004196514,0.00038106207,0.00017164854,0.00021068913,0.00008040529,0.002860931],"category_scores_gemma":[0.0075505897,0.00008242649,0.000120734585,0.000900167,0.000026114512,0.0005144787,0.000019891539,0.00007535439,0.0005750006],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037853293,0.000046949368,0.0036393807,0.0000011029562,0.000010891697,3.572027e-8,0.00033746337,0.0011076169,0.000579137,0.0014145261,0.15451081,0.83831424],"study_design_scores_gemma":[0.00127118,0.00011762092,0.06442342,0.000006218946,0.0000543384,0.0000020340801,0.0003828021,0.042939857,0.0039025382,0.04095733,0.8457961,0.00014657092],"about_ca_topic_score_codex":0.000059401827,"about_ca_topic_score_gemma":0.000854121,"teacher_disagreement_score":0.8693868,"about_ca_system_score_codex":0.00018842024,"about_ca_system_score_gemma":0.00048747126,"threshold_uncertainty_score":0.9980506},"labels":[],"label_agreement":null},{"id":"W4236837390","doi":"10.1332/policypress/9781447334910.003.0003","title":"The “lumpiness” thesis revisited: the venues of policy work and the distribution of analytical techniques in Canada","year":2018,"lang":"en","type":"book-chapter","venue":"Policy Press eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Distribution (mathematics); Work (physics); Process (computing); Public policy; Public economics; Policy analysis; Political science; Business; Regional science; Public administration; Economics; Geography; Engineering; Computer science; Mathematics","score_opus":0.13014512527843694,"score_gpt":0.42787053094326233,"score_spread":0.2977254056648254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236837390","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010778955,0.0019734732,0.000069454734,0.014584672,0.00016157945,0.0017782327,0.0005907369,0.000020874213,0.97004205],"genre_scores_gemma":[0.9060117,0.00088323187,0.000012260003,0.00052963325,0.000542021,0.00006547135,0.000010469005,0.000020833202,0.09192436],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971686,0.00029820824,0.0008719615,0.00023230235,0.0012242823,0.00020462251],"domain_scores_gemma":[0.99528754,0.0026207531,0.00074204284,0.0009164381,0.0003873891,0.000045853852],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003370701,0.00018953237,0.00044322183,0.00012788786,0.00017416949,0.00009671979,0.0009287057,0.00010380037,0.00002839488],"category_scores_gemma":[0.0016579125,0.000080302874,0.00011180815,0.000099512436,0.0010732539,0.000037979797,0.00027370604,0.00024984087,0.0000016128076],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016405492,0.000004472204,0.00061208656,0.000025083551,0.00006275645,5.610066e-7,0.0010374207,0.0000043681775,0.0000010591483,0.8883575,0.010737776,0.09899282],"study_design_scores_gemma":[0.00028979467,0.00003432712,0.009247246,0.00028115712,0.00006981985,0.0000026234134,0.00011851659,0.00044527196,0.00021895046,0.102294266,0.88683933,0.00015869905],"about_ca_topic_score_codex":0.23938021,"about_ca_topic_score_gemma":0.1012644,"teacher_disagreement_score":0.89523274,"about_ca_system_score_codex":0.00018470161,"about_ca_system_score_gemma":0.0015901115,"threshold_uncertainty_score":0.9151352},"labels":[],"label_agreement":null},{"id":"W4236952314","doi":"10.1177/1356389014543594","title":"The 35 <sup>th</sup> Canadian Evaluation Society Annual Conference: ‘Celebrating Contributions to Canadian Evaluation’","year":2014,"lang":"en","type":"article","venue":"Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Library science; Computer science","score_opus":0.11994209496311921,"score_gpt":0.48091336084166886,"score_spread":0.36097126587854966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236952314","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6864747,0.00060153333,0.01442343,0.1682095,0.003862756,0.0136148995,0.0009919959,0.00017016236,0.11165103],"genre_scores_gemma":[0.991741,0.000013114426,0.0006584528,0.0040244334,0.00066621415,0.0011583513,0.0006346882,0.000026398626,0.0010773398],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98186386,0.0044854693,0.0014767008,0.0009888655,0.010090612,0.0010944754],"domain_scores_gemma":[0.97303504,0.0017792442,0.00051471824,0.0012894372,0.022234645,0.0011469338],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.10661256,0.0003648871,0.00036650998,0.0006108574,0.0036310782,0.0015279854,0.0010581884,0.0002782805,0.010138531],"category_scores_gemma":[0.03579605,0.0002818306,0.00022382228,0.0019161478,0.000148187,0.0011237062,0.00008084836,0.00041344052,0.0022907138],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000017496859,0.000044415472,0.0041008443,0.0000031463162,0.00007685674,1.9599233e-7,0.012221045,0.19990969,0.000083395666,0.009469066,0.18569079,0.5883831],"study_design_scores_gemma":[0.001173952,0.00013273885,0.030391058,0.000025156316,0.00016740515,0.0000028963184,0.007012899,0.82836527,0.00005420078,0.018017689,0.11434115,0.00031560884],"about_ca_topic_score_codex":0.13999821,"about_ca_topic_score_gemma":0.8704617,"teacher_disagreement_score":0.7304635,"about_ca_system_score_codex":0.0050721145,"about_ca_system_score_gemma":0.024638223,"threshold_uncertainty_score":0.9999634},"labels":[],"label_agreement":null},{"id":"W4236952887","doi":"10.24124/2006/bpgub1327","title":"Evaluation of the Carrier Sekani Family Services Family Support Services Program","year":2006,"lang":"en","type":"dissertation","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Northern British Columbia","funders":"","keywords":"Conceptualization; Logic model; Action research; Knowledge management; Action (physics); Process management; Psychology; Engineering; Computer science; Political science; Pedagogy; Artificial intelligence; Public administration","score_opus":0.13093172844434176,"score_gpt":0.4932286690740788,"score_spread":0.36229694062973705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236952887","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7109947,0.00037498504,0.000005017469,0.00009172713,0.0018492697,0.0016609613,0.00008392197,0.00006375686,0.28487563],"genre_scores_gemma":[0.95194143,0.00005503435,0.0003709975,0.0006970492,0.0001934164,0.00041139085,0.0015695438,0.00004411625,0.044717036],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9825106,0.00081166247,0.001776103,0.00080722524,0.013728097,0.00036628696],"domain_scores_gemma":[0.98941904,0.00020890492,0.0017265194,0.001385845,0.007165479,0.00009420414],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.012700901,0.0004462299,0.00061154075,0.00038412676,0.00030379565,0.00047589457,0.0019312202,0.00042641372,0.0025462818],"category_scores_gemma":[0.000097363896,0.0002600978,0.00039268436,0.0014054524,0.000060774033,0.00065554964,0.000111684974,0.00031979993,0.00030328555],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001314613,0.00074023806,0.046429466,0.00065054354,0.0003325215,0.0000011661558,0.008858152,0.003932148,0.004369222,0.00082774967,0.021990824,0.9117365],"study_design_scores_gemma":[0.0008975961,0.0001880753,0.8370547,0.0001956006,0.00070903526,0.0000012024494,0.032708228,0.04938867,0.0023623016,0.0039200103,0.0720772,0.0004973355],"about_ca_topic_score_codex":0.0016376772,"about_ca_topic_score_gemma":0.019041639,"teacher_disagreement_score":0.91123915,"about_ca_system_score_codex":0.00015441429,"about_ca_system_score_gemma":0.0021514674,"threshold_uncertainty_score":0.9999851},"labels":[],"label_agreement":null},{"id":"W4236954017","doi":"10.1177/135638900300900406","title":"Evaluability Assessment: A Tool for Incorporating Evaluation in Social Change Programmes","year":2003,"lang":"en","type":"article","venue":"Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; University of Calgary","funders":"","keywords":"Participatory evaluation; Accountability; Process management; Promotion (chess); Process (computing); Social change; Monitoring and evaluation; Theory of change; Citizen journalism; Plan (archaeology); Political science; Theme (computing); Politics; Public relations; Management science; Knowledge management; Sociology; Business; Engineering; Computer science; Public administration","score_opus":0.4539931329436821,"score_gpt":0.5881362452183663,"score_spread":0.13414311227468417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236954017","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9666018,0.00014199883,0.008847391,0.0023480614,0.0009464109,0.009916979,0.000018141756,0.000057110727,0.011122104],"genre_scores_gemma":[0.9837788,0.0000022154602,0.008671657,0.00028212252,0.00028671673,0.0067166216,0.00014313804,0.000017798486,0.00010098233],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9859606,0.0043205954,0.0015095995,0.00087435526,0.006894502,0.0004403371],"domain_scores_gemma":[0.9941632,0.0010792287,0.0007343861,0.0004998351,0.0034611674,0.00006217799],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11808656,0.00022942794,0.0003616562,0.00047265718,0.00048393814,0.0003664751,0.0003139536,0.00016008824,0.0024369794],"category_scores_gemma":[0.013360029,0.00019872378,0.00016141747,0.0014786106,0.00007076483,0.0013693722,0.00004091121,0.00018983333,0.000081349084],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005073347,0.00034721973,0.14789762,0.000021944626,0.000016173582,1.5099911e-7,0.0032805898,0.00228102,0.00026125592,0.020239754,0.00075291377,0.8248506],"study_design_scores_gemma":[0.0026764646,0.000147888,0.36203307,0.000015061472,0.000064256164,8.96538e-7,0.00092909427,0.4717394,0.00010413649,0.15933119,0.00274651,0.00021201151],"about_ca_topic_score_codex":0.000022984923,"about_ca_topic_score_gemma":0.00032365287,"teacher_disagreement_score":0.8246386,"about_ca_system_score_codex":0.0009796759,"about_ca_system_score_gemma":0.0018175447,"threshold_uncertainty_score":0.99847496},"labels":[],"label_agreement":null},{"id":"W4237047123","doi":"10.22215/etd/2002-05285","title":"Challenging the Harris government's mandate to improve the quality of public education with less public expediture : the political economy of public education reform in Ontario","year":2002,"lang":"en","type":"dissertation","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mandate; Politics; Public administration; Government (linguistics); Political science; Public education; Quality (philosophy); Economic growth; Economics","score_opus":0.21692945141326303,"score_gpt":0.45313818192928484,"score_spread":0.23620873051602181,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4237047123","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44197145,0.00019252051,0.00028887784,0.12080923,0.0014493801,0.0017823665,0.00002481027,0.000015318217,0.43346605],"genre_scores_gemma":[0.9723481,0.000023507935,0.00008387344,0.0018548054,0.00019794858,0.00068003783,0.00017819318,0.00002092895,0.024612596],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.99356437,0.00071803987,0.001731437,0.00064068986,0.00280959,0.0005359011],"domain_scores_gemma":[0.994479,0.00076279417,0.0014406743,0.0015780212,0.001540919,0.00019861497],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008946215,0.00034087678,0.0005076334,0.00035045308,0.00035177238,0.0007824667,0.0018187282,0.00021515823,0.0019087113],"category_scores_gemma":[0.0008041189,0.00014769926,0.00016960924,0.00085272646,0.00012696646,0.001269159,0.00012005076,0.0006709348,0.000028972949],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058299363,0.0007680088,0.024902917,0.00007703627,0.00009209645,5.627138e-8,0.012607914,0.000007225975,0.00002315681,0.8041619,0.0032499165,0.15405147],"study_design_scores_gemma":[0.00047223456,0.00016414284,0.36089787,0.00009615295,0.000042745538,0.0000027772612,0.5427812,0.000443975,0.00028670245,0.012381603,0.08204305,0.0003875915],"about_ca_topic_score_codex":0.019407464,"about_ca_topic_score_gemma":0.5071663,"teacher_disagreement_score":0.7917803,"about_ca_system_score_codex":0.0018796549,"about_ca_system_score_gemma":0.0062173465,"threshold_uncertainty_score":0.9994165},"labels":[],"label_agreement":null},{"id":"W4237364742","doi":"10.3138/cjpe.154","title":"Implementation and Evaluation of an Evidence-Based Treatment of Disruptive Behaviour within a Children's Mental Health Program","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Toronto; Centre for Addiction and Mental Health","funders":"","keywords":"Multidisciplinary approach; Mental health; Context (archaeology); Psychology; Program evaluation; Medical education; Applied psychology; Process management; Multidisciplinary team; Knowledge management; Nursing; Medicine; Computer science; Business; Psychiatry; Sociology; Political science","score_opus":0.5674638354909648,"score_gpt":0.6170743887808582,"score_spread":0.04961055328989339,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4237364742","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9923357,0.0012886592,0.00012184878,0.0013942185,0.00030870186,0.0044598975,0.0000497427,0.000006765586,0.000034507935],"genre_scores_gemma":[0.9921294,0.000021892916,0.007380417,0.000038531707,0.00006620069,0.00021784168,0.000130409,0.000010345554,0.0000049863256],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9919169,0.0019357316,0.0015396744,0.0002711555,0.00409398,0.00024256881],"domain_scores_gemma":[0.99105614,0.00010899973,0.0022419703,0.00028590445,0.005616305,0.0006906735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027095268,0.00016831183,0.00039324988,0.0007491126,0.00014485502,0.00016918281,0.0002264356,0.000061764564,0.000294417],"category_scores_gemma":[0.0007972223,0.00012849522,0.000108406624,0.0006583208,0.00015506132,0.001149057,0.000007856394,0.00007882837,0.0000022557492],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007248083,0.00028610876,0.20690893,0.0000040403634,0.000036104822,3.4906284e-7,0.007043483,0.00234511,0.00001995764,0.00004048167,0.00013632538,0.7831066],"study_design_scores_gemma":[0.0075395717,0.020984633,0.77777886,0.00019121502,0.00046379783,0.000038168673,0.01805647,0.17158726,0.0013959057,0.0015371059,0.00022785568,0.00019915939],"about_ca_topic_score_codex":0.0051614507,"about_ca_topic_score_gemma":0.04635285,"teacher_disagreement_score":0.7829075,"about_ca_system_score_codex":0.0013593439,"about_ca_system_score_gemma":0.01675551,"threshold_uncertainty_score":0.9888186},"labels":[],"label_agreement":null},{"id":"W4237914492","doi":"10.18438/b8j03v","title":"An Introduction to Critical Appraisal","year":2010,"lang":"en","type":"article","venue":"Evidence Based Library and Information Practice","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Critical appraisal; Computer science; Data science; Management science; Medicine; Engineering; Alternative medicine","score_opus":0.06378403257162366,"score_gpt":0.47287765025066864,"score_spread":0.40909361767904495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4237914492","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058037937,0.000020755268,0.052033313,0.88006073,0.0028757586,0.0002774646,0.000009922379,0.00015169568,0.0065324116],"genre_scores_gemma":[0.85849154,0.000030764957,0.051665083,0.08862152,0.0009773283,0.00003766746,0.000030887095,0.000006357719,0.00013886175],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99753374,0.0003656074,0.000601174,0.00025142796,0.0010861406,0.00016190564],"domain_scores_gemma":[0.99052864,0.008020264,0.00021469196,0.0005922158,0.00034128898,0.00030287073],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["scholarly_communication","insufficient_payload"],"category_scores_codex":[0.004467438,0.00010610101,0.00011189532,0.00035483422,0.00025951894,0.0017775977,0.00037766414,0.00007670825,0.0054859645],"category_scores_gemma":[0.046118356,0.00008335956,0.000026222087,0.0007735352,0.00007690654,0.37699497,0.00007078329,0.00032428847,0.00093638187],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043649256,0.000083120074,0.0017113197,0.000014237774,0.0000031229783,8.34538e-7,0.0005882704,0.00074578007,0.0016417567,0.8348343,0.035194192,0.12474659],"study_design_scores_gemma":[0.00013345119,0.00026043024,0.017097667,0.000009892068,0.000008170226,0.000020791078,0.0011938874,0.02839528,0.0020415958,0.00049008033,0.9502207,0.00012805137],"about_ca_topic_score_codex":0.0000017570229,"about_ca_topic_score_gemma":1.5817902e-7,"teacher_disagreement_score":0.9150265,"about_ca_system_score_codex":0.000004124233,"about_ca_system_score_gemma":0.0002791335,"threshold_uncertainty_score":0.9998415},"labels":[],"label_agreement":null},{"id":"W4238213994","doi":"10.1002/ev.20356","title":"Issue Information","year":2020,"lang":"en","type":"paratext","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of California, Los Angeles; Sierra Health Foundation; National Science Foundation; Claremont Graduate University; Duquesne University; Weizmann Institute of Science; Michigan State University; Northwestern University; Gordon and Betty Moore Foundation; University of Connecticut; College of Engineering, Michigan State University; École nationale d'administration publique; Syracuse University; University of Southern California; University of Hawai'i; John D. and Catherine T. MacArthur Foundation","keywords":"Citation; Computer science; World Wide Web; Library science; Internet privacy","score_opus":0.2442056670308427,"score_gpt":0.5390197065552901,"score_spread":0.2948140395244474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4238213994","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009861552,0.0010203358,0.11267402,0.01985888,0.03588432,0.004990023,0.00058292935,0.00015181213,0.82473904],"genre_scores_gemma":[0.0034495215,0.000627753,0.0060588527,0.00404276,0.0067661125,0.0018334531,0.0090071885,0.00006886006,0.9681455],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9931979,0.0004119988,0.0014589432,0.0005714062,0.004073548,0.00028621446],"domain_scores_gemma":[0.9940382,0.00083759805,0.0010794112,0.0006929029,0.0031222596,0.00022961055],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0058329254,0.00032999142,0.0004939335,0.000866345,0.0004993931,0.0008652741,0.00059518043,0.00036866695,0.08940218],"category_scores_gemma":[0.005661698,0.00028665064,0.00033624246,0.0015057054,0.00003406556,0.0018798627,0.00007165631,0.00031630576,0.14825784],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027093245,0.000012651171,0.000005128698,0.000012311127,0.000025584626,8.414348e-9,0.0004528151,0.0030915835,0.0000079922365,0.00011288971,0.65496,0.34129193],"study_design_scores_gemma":[0.0012395603,0.00015144008,0.000208353,0.0000291444,0.00015472097,0.0000014067589,0.0003539149,0.081128776,0.00018378737,0.0032324344,0.9130333,0.00028315024],"about_ca_topic_score_codex":0.000096071664,"about_ca_topic_score_gemma":0.0001028896,"teacher_disagreement_score":0.34100878,"about_ca_system_score_codex":0.00045925903,"about_ca_system_score_gemma":0.0030333088,"threshold_uncertainty_score":0.9999586},"labels":[],"label_agreement":null},{"id":"W4238524924","doi":"10.26434/chemrxiv-2021-7m4tw","title":"Response process validity evidence in chemistry education research","year":2021,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Process (computing); Cognition; Psychology; Management science; Applied psychology; Computer science; Engineering; Neuroscience","score_opus":0.7160760744590771,"score_gpt":0.6518589554735377,"score_spread":0.06421711898553939,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4238524924","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9849839,0.000808507,0.000069107715,0.0065893037,0.0006575975,0.00041148535,0.0000012288178,0.000026220905,0.006452617],"genre_scores_gemma":[0.9910293,0.00022628374,0.00034094573,0.00018871391,0.0002117976,0.00039519148,0.000024379304,0.000014986375,0.0075683747],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9912757,0.0018395184,0.0009800288,0.0012726593,0.004234736,0.00039731697],"domain_scores_gemma":[0.990776,0.0036678037,0.00034405437,0.0017647133,0.003282886,0.00016456343],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.043199137,0.00021578935,0.0003876433,0.00038324177,0.00014924501,0.00084839796,0.0016942795,0.00038233513,0.0043444447],"category_scores_gemma":[0.03454787,0.00019189711,0.00012445131,0.0017642069,0.000161068,0.00046443992,0.00094067195,0.0014990123,0.00027621217],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003308745,0.004322064,0.58027804,0.0034355735,0.00007691604,0.00011687688,0.044989448,0.0085430555,0.14931226,0.00016101149,0.0930265,0.11242952],"study_design_scores_gemma":[0.0007710845,0.000102620805,0.45252687,0.0068617584,0.0000292156,0.000025425701,0.03258529,0.013373966,0.42320016,0.047271423,0.02180836,0.00144383],"about_ca_topic_score_codex":0.000048090962,"about_ca_topic_score_gemma":0.000040121904,"teacher_disagreement_score":0.2738879,"about_ca_system_score_codex":0.0005342964,"about_ca_system_score_gemma":0.012741318,"threshold_uncertainty_score":0.9965657},"labels":[],"label_agreement":null},{"id":"W4238813095","doi":"10.1002/ev.20357","title":"Issue Information","year":2020,"lang":"en","type":"paratext","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of California, Los Angeles; Sierra Health Foundation; National Science Foundation; Claremont Graduate University; Duquesne University; Weizmann Institute of Science; Michigan State University; Northwestern University; Gordon and Betty Moore Foundation; University of Connecticut; College of Engineering, Michigan State University; École nationale d'administration publique; Syracuse University; University of Southern California; University of Hawai'i; John D. and Catherine T. MacArthur Foundation","keywords":"Computer science; Citation; World Wide Web; Information retrieval; Library science","score_opus":0.2442056670308427,"score_gpt":0.5390197065552901,"score_spread":0.2948140395244474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4238813095","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009861552,0.0010203358,0.11267402,0.01985888,0.03588432,0.004990023,0.00058292935,0.00015181213,0.82473904],"genre_scores_gemma":[0.0034495215,0.000627753,0.0060588527,0.00404276,0.0067661125,0.0018334531,0.0090071885,0.00006886006,0.9681455],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9931979,0.0004119988,0.0014589432,0.0005714062,0.004073548,0.00028621446],"domain_scores_gemma":[0.9940382,0.00083759805,0.0010794112,0.0006929029,0.0031222596,0.00022961055],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0058329254,0.00032999142,0.0004939335,0.000866345,0.0004993931,0.0008652741,0.00059518043,0.00036866695,0.08940218],"category_scores_gemma":[0.005661698,0.00028665064,0.00033624246,0.0015057054,0.00003406556,0.0018798627,0.00007165631,0.00031630576,0.14825784],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027093245,0.000012651171,0.000005128698,0.000012311127,0.000025584626,8.414348e-9,0.0004528151,0.0030915835,0.0000079922365,0.00011288971,0.65496,0.34129193],"study_design_scores_gemma":[0.0012395603,0.00015144008,0.000208353,0.0000291444,0.00015472097,0.0000014067589,0.0003539149,0.081128776,0.00018378737,0.0032324344,0.9130333,0.00028315024],"about_ca_topic_score_codex":0.000096071664,"about_ca_topic_score_gemma":0.0001028896,"teacher_disagreement_score":0.34100878,"about_ca_system_score_codex":0.00045925903,"about_ca_system_score_gemma":0.0030333088,"threshold_uncertainty_score":0.9999586},"labels":[],"label_agreement":null},{"id":"W4238820305","doi":"10.1177/109821400402500311","title":"Commentary: Minimizing Evaluation Misuse as Principled Practice","year":2004,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Psychology; Management science; Computer science; Sociology; Economics","score_opus":0.19120246854867498,"score_gpt":0.5583508310794473,"score_spread":0.3671483625307723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4238820305","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9330601,0.00020381455,0.0043454445,0.054929424,0.00081259495,0.00060164335,0.0000019138458,0.0000110252195,0.0060340166],"genre_scores_gemma":[0.97375345,0.00007298121,0.018394893,0.007387835,0.0003086499,0.000022560187,0.000011185489,0.000013761724,0.0000346817],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9862009,0.0024696267,0.0016136105,0.0003046525,0.009169579,0.00024161076],"domain_scores_gemma":[0.9867216,0.0016192786,0.0033486057,0.00047206273,0.007644819,0.00019364081],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.051461488,0.00017284995,0.00039581637,0.0005592022,0.00021796525,0.00025514423,0.00045484534,0.000039214156,0.0018916872],"category_scores_gemma":[0.018853717,0.0001326994,0.0001753346,0.0012355205,0.00015325366,0.0019820663,0.000054701195,0.00027211942,0.0002943819],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00077350944,0.0005899616,0.0033749198,0.0000032379733,0.00020190436,0.000012634153,0.008346802,0.104409344,0.0021595808,0.00091072614,0.005471374,0.873746],"study_design_scores_gemma":[0.04039069,0.016870826,0.15368918,0.0006496352,0.0043280437,0.0022360699,0.15548147,0.24369287,0.010188259,0.13898733,0.2315634,0.0019222284],"about_ca_topic_score_codex":0.00010625873,"about_ca_topic_score_gemma":0.000040216244,"teacher_disagreement_score":0.8718238,"about_ca_system_score_codex":0.00094122894,"about_ca_system_score_gemma":0.0022422622,"threshold_uncertainty_score":0.9990207},"labels":[],"label_agreement":null},{"id":"W4239244958","doi":"10.1093/obo/9780199756810-0121","title":"Program Evaluation","year":2015,"lang":"en","type":"reference-entry","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Summative assessment; Formative assessment; Transparency (behavior); Political science; Public relations; Accountability; Program evaluation; Work (physics); Public administration; Medical education; Psychology; Medicine; Engineering; Pedagogy","score_opus":0.6359398556251411,"score_gpt":0.6192121926041496,"score_spread":0.01672766302099149,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239244958","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017732533,0.0015828763,0.0002545292,0.0009883005,0.0033846272,0.0020175495,0.00003167112,0.00012875222,0.9914344],"genre_scores_gemma":[0.002658106,0.0034448926,0.0033677767,0.00046879455,0.0011244719,0.0010589032,0.00086124684,0.000027127628,0.98698866],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9860408,0.00063560647,0.0009792334,0.00068662525,0.011361167,0.0002965792],"domain_scores_gemma":[0.99341,0.0003769821,0.0005487599,0.0010326302,0.004415652,0.00021596557],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.01737532,0.00026887777,0.00047345998,0.00047685855,0.00010393448,0.0006655988,0.0009515485,0.00036428258,0.04762854],"category_scores_gemma":[0.0026673072,0.00016421457,0.00016155036,0.00082337577,0.000054927565,0.00037968034,0.00016951012,0.00037897652,0.010475724],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028359673,0.000039711427,0.00011248362,0.000003386786,0.000007962853,1.9881232e-7,0.000040481667,0.000019300922,1.0205157e-8,0.00017147952,0.49789676,0.50170535],"study_design_scores_gemma":[0.00039928115,0.0001530023,0.00062273635,0.000044112814,0.00005577703,0.0000024251397,0.00028497074,0.026409686,0.0000017277143,0.016830914,0.9549722,0.00022314921],"about_ca_topic_score_codex":0.000023675868,"about_ca_topic_score_gemma":0.00017075289,"teacher_disagreement_score":0.50148225,"about_ca_system_score_codex":0.0003362563,"about_ca_system_score_gemma":0.0044165673,"threshold_uncertainty_score":0.99029475},"labels":[],"label_agreement":null},{"id":"W4239429629","doi":"10.12688/f1000research.12496.2","title":"The peer review process for awarding funds to international science research consortia: a qualitative developmental evaluation","year":2017,"lang":"en","type":"preprint","venue":"F1000Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto","funders":"Royal Society; Department for International Development; Department for International Development, UK Government","keywords":"Peer review; CLARITY; Political science; Process (computing); Qualitative research; Psychology; Sociology; Social science; Computer science; Biology","score_opus":0.9180082488147815,"score_gpt":0.8021655283270901,"score_spread":0.1158427204876914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239429629","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08802484,0.0064529427,0.007762427,0.5615396,0.008316027,0.032081544,0.00075797626,0.00012419261,0.29494047],"genre_scores_gemma":[0.9246739,0.0018903887,0.0036283901,0.0007365517,0.0006760808,0.012083749,0.00021667239,0.00005093228,0.05604335],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9426806,0.0030501368,0.0015640227,0.0018009862,0.0496932,0.0012110599],"domain_scores_gemma":[0.91753405,0.008907255,0.00061019824,0.0017387234,0.0707897,0.0004200708],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.41736072,0.0002658838,0.0004608952,0.0013432,0.0046909046,0.004748739,0.009065462,0.00014773979,0.0013948703],"category_scores_gemma":[0.2652054,0.00017121028,0.00017692038,0.0016098252,0.001583428,0.0007283565,0.0043503293,0.0013443717,0.0010208234],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003636909,0.00015099044,0.0022055402,0.0005329684,0.00015876623,0.0000027729448,0.029930083,0.00079179986,0.00034520062,0.008469685,0.50277585,0.4542727],"study_design_scores_gemma":[0.0009270688,0.00023109437,0.007944847,0.0027587407,0.00003760885,0.000008115677,0.04588548,0.06993639,0.0010762368,0.14078338,0.72980845,0.0006025579],"about_ca_topic_score_codex":0.00007494045,"about_ca_topic_score_gemma":0.00021977529,"teacher_disagreement_score":0.83664906,"about_ca_system_score_codex":0.001981843,"about_ca_system_score_gemma":0.022619195,"threshold_uncertainty_score":0.999757},"labels":[],"label_agreement":null},{"id":"W4240315313","doi":"10.3821/1913-701x-144.5.207","title":"PharmacyWoRx resource from CACDS: Helping community pharmacy to engage in election campaigns and influence policy","year":2011,"lang":"en","type":"article","venue":"Canadian Pharmacists Journal / Revue des Pharmaciens du Canada","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Pharmacy; Resource (disambiguation); Public relations; Business; Public administration; Political science; Medicine; Nursing; Computer science","score_opus":0.2521790035692788,"score_gpt":0.43033593581249163,"score_spread":0.17815693224321283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4240315313","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9942795,0.00026719412,0.00016576111,0.00037201855,0.0007938934,0.00048795,0.0002823477,0.00003000699,0.0033213398],"genre_scores_gemma":[0.9863397,0.0009206023,0.00039048187,0.011409383,0.0005002499,0.00003571201,0.000017677006,0.000045905254,0.0003402713],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9935258,0.001953456,0.0013503864,0.0006085947,0.0013283159,0.0012334372],"domain_scores_gemma":[0.99421895,0.00077459053,0.0004654006,0.0005349449,0.00088139536,0.0031247202],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0065876585,0.0004687378,0.00053543225,0.0017743583,0.0019703594,0.00058214,0.0015918291,0.00006437654,0.0021935583],"category_scores_gemma":[0.0021365609,0.00046758316,0.00011317136,0.002703574,0.00021068784,0.001448907,0.00018541722,0.0019335747,0.000059859896],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010478395,0.00032321768,0.26584774,0.000106305466,0.0002717954,0.016273692,0.10160949,0.01185202,0.02414574,0.00017418886,0.023010207,0.5553378],"study_design_scores_gemma":[0.020165697,0.0005140186,0.052567337,0.00032265115,0.00041461477,0.16911839,0.004583765,0.07112883,0.04885657,0.005129423,0.62166756,0.0055311276],"about_ca_topic_score_codex":0.45778364,"about_ca_topic_score_gemma":0.5644164,"teacher_disagreement_score":0.59865737,"about_ca_system_score_codex":0.0032188445,"about_ca_system_score_gemma":0.0066281334,"threshold_uncertainty_score":0.9997776},"labels":[],"label_agreement":null},{"id":"W4240409218","doi":"10.22215/cjcr.v2i1.64","title":"From the Editor","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Children s Rights / Revue canadienne des droits des enfants","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science","score_opus":0.07165663375306543,"score_gpt":0.34398470217713,"score_spread":0.2723280684240646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4240409218","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9860406,0.0008438847,0.00018356956,0.0012948804,0.0061336257,0.00018379331,0.0001696569,0.000007254266,0.0051427605],"genre_scores_gemma":[0.98984563,0.000014858406,0.0006262936,0.00047410076,0.0070790937,0.000002964572,0.000017895572,0.000020836545,0.001918311],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967271,0.0003541755,0.0010655256,0.00033715946,0.0007590219,0.00075702375],"domain_scores_gemma":[0.99334574,0.00055551773,0.0006573793,0.00070749415,0.0018564899,0.0028773928],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004183664,0.00024874785,0.00046305076,0.00047541966,0.00066626206,0.00056379766,0.0019010269,0.00012612416,0.0012057399],"category_scores_gemma":[0.0022838062,0.00014863767,0.00020246004,0.0008438936,0.0006094379,0.00094409176,0.00003341902,0.00041440153,0.00020130877],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010757176,0.00005911694,0.45832407,0.0000065450313,0.0004560431,0.00050497754,0.06675692,0.0016565772,0.000027565695,0.009916846,0.3496725,0.11251127],"study_design_scores_gemma":[0.0013169872,0.00030815037,0.26112443,0.00020659443,0.00009658873,0.0008877982,0.001404513,0.00044071363,0.00012605512,0.20929141,0.52437484,0.0004218914],"about_ca_topic_score_codex":0.12004054,"about_ca_topic_score_gemma":0.86842215,"teacher_disagreement_score":0.7483816,"about_ca_system_score_codex":0.0008924287,"about_ca_system_score_gemma":0.002686465,"threshold_uncertainty_score":0.9997073},"labels":[],"label_agreement":null},{"id":"W4241517000","doi":"10.1108/978-1-80071-130-320211013","title":"Prelims","year":2021,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Christian Studies","funders":"Johns Hopkins University","keywords":"Psychology","score_opus":0.3613968506098106,"score_gpt":0.5095919581151478,"score_spread":0.1481951075053372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4241517000","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000012729746,0.00023536269,0.0007383626,0.0013729834,0.0006422613,0.00009984818,0.000007304785,0.0000291581,0.996862],"genre_scores_gemma":[0.0009483574,0.00016753086,0.0007058561,0.001378164,0.00018126641,0.0000035126036,0.000024014893,0.00001325725,0.99657804],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99665725,0.000022935674,0.00053937867,0.00040804406,0.0022659868,0.000106419146],"domain_scores_gemma":[0.99805564,0.0003568516,0.00020278507,0.0007386388,0.00056936574,0.000076719036],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0015033776,0.00014910931,0.00026986076,0.00015807115,0.000062640844,0.00023852942,0.0004149744,0.00016726748,0.3015896],"category_scores_gemma":[0.00018446424,0.000098511955,0.00017081744,0.000048355538,0.000035526446,0.00012135775,0.00014312868,0.00018586838,0.01613773],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020504592,0.0000048767192,0.000037026544,0.0000017400615,0.000014769545,0.000005477294,0.000034265,0.000013959769,0.0000043129367,0.7402314,0.16906534,0.0905848],"study_design_scores_gemma":[0.00007164272,0.000022619563,0.00012208501,0.00001917069,0.000008554816,0.0000036689798,0.000035550598,0.000215273,0.000024830106,0.08705547,0.9122923,0.00012886376],"about_ca_topic_score_codex":0.0000015051221,"about_ca_topic_score_gemma":0.00003597855,"teacher_disagreement_score":0.74322695,"about_ca_system_score_codex":0.00003476261,"about_ca_system_score_gemma":0.00036871928,"threshold_uncertainty_score":0.9846283},"labels":[],"label_agreement":null},{"id":"W4241619046","doi":"10.53967/cje-rce.v44i2.4761","title":"Élaboration et validation de l’Échelle de perception d’un centre d’aide en français du postsecondaire (ÉPCAFP)","year":2021,"lang":"fr","type":"article","venue":"Canadian Journal of Education / Revue canadienne de l éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Cégep Saint-Jean-sur-Richelieu; Canadian Society for the Study of Education; Université de Montréal; Canadian Association for the Study of Adult Education; Université de Sherbrooke","funders":"Ministère de l'Éducation et de l'Enseignement supérieur","keywords":"Humanities; Psychology; Art","score_opus":0.07339995068772033,"score_gpt":0.3665596880057036,"score_spread":0.2931597373179833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4241619046","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86414886,0.0019259844,0.0037128802,0.11738857,0.009129492,0.00024879066,0.00009945858,0.000008735795,0.0033372028],"genre_scores_gemma":[0.97226095,0.00075606996,0.006422505,0.004781519,0.0019235108,0.00002001882,0.0003742231,0.000045483637,0.0134157315],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99465644,0.0020969706,0.0014146302,0.0004774109,0.00041205488,0.000942492],"domain_scores_gemma":[0.9908462,0.0005838202,0.0010617601,0.00056955457,0.004790567,0.0021480913],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008959778,0.00031703472,0.00040749356,0.0009864205,0.00063691323,0.0007530876,0.0005503591,0.00041841177,0.016533034],"category_scores_gemma":[0.0075338245,0.0003830733,0.00023623863,0.0015384066,0.000115920266,0.001955797,0.000018796774,0.0006872621,0.00028741616],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.0000318692,0.0004272929,0.23262618,0.0002155204,0.000126925,0.00008041369,0.42213565,0.007167095,0.003920312,0.01048121,0.07537248,0.24741504],"study_design_scores_gemma":[0.00056486204,0.00015100294,0.5420117,0.0006766097,0.000266876,0.0021352672,0.16895343,0.0060009276,0.001898549,0.011010002,0.26580253,0.0005282531],"about_ca_topic_score_codex":0.04231209,"about_ca_topic_score_gemma":0.57148606,"teacher_disagreement_score":0.529174,"about_ca_system_score_codex":0.011276029,"about_ca_system_score_gemma":0.08198905,"threshold_uncertainty_score":0.99986213},"labels":[],"label_agreement":null},{"id":"W4241781952","doi":"10.1353/mpq.2002.0018","title":"Editorial","year":2002,"lang":"es","type":"editorial","venue":"Merrill-Palmer Quarterly","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Audience measurement; Scholarship; Excellence; Reputation; Discipline; Politics; Library science; Scope (computer science); Sociology; Publishing; Political science; Social science; Public relations; Law","score_opus":0.06221666661695784,"score_gpt":0.41637354532084914,"score_spread":0.3541568787038913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4241781952","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00063369295,0.00062591606,0.00025583644,0.0010622662,0.9539594,0.00088427245,0.0005120865,0.00018332708,0.041883223],"genre_scores_gemma":[0.004238067,0.00048280033,0.00023647521,0.0001627757,0.9578961,0.00016621465,0.00035465194,0.0001468358,0.03631605],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97561026,0.0013757355,0.003341336,0.0024860695,0.015597088,0.0015895366],"domain_scores_gemma":[0.987897,0.0036557089,0.0019642022,0.0027989808,0.0028798245,0.00080430356],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"category_scores_codex":[0.0070108743,0.0014880283,0.0020462219,0.0011356159,0.0010840828,0.002624659,0.0032548353,0.0025760971,0.04156913],"category_scores_gemma":[0.0017093499,0.0012256018,0.0010401877,0.0015730758,0.00048396966,0.0015573151,0.00016370394,0.00251874,0.045637373],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013386636,0.0002655496,0.00016849476,0.00004788824,0.00017510312,0.000011474757,0.0037528565,0.000017963417,0.000048255224,0.00017835305,0.93654525,0.05865494],"study_design_scores_gemma":[0.002498183,0.002567103,0.00019357778,0.00020838664,0.00022962806,0.0000046199016,0.0014937589,0.0019423866,0.000017035029,0.0012438599,0.98815364,0.0014478232],"about_ca_topic_score_codex":0.00031630977,"about_ca_topic_score_gemma":0.000107735184,"teacher_disagreement_score":0.05720712,"about_ca_system_score_codex":0.00048938557,"about_ca_system_score_gemma":0.0016751514,"threshold_uncertainty_score":0.9997869},"labels":[],"label_agreement":null},{"id":"W4241934550","doi":"10.1016/s1701-2163(16)32250-2","title":"Planning for the Future","year":2006,"lang":"en","type":"editorial","venue":"Journal of Obstetrics and Gynaecology Canada","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"The Society of Obstetricians and Gynaecologists of Canada","funders":"","keywords":"Medicine","score_opus":0.04843081696932627,"score_gpt":0.3861313536902652,"score_spread":0.3377005367209389,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4241934550","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00047271268,0.017163241,0.0003393489,0.0014089753,0.97970337,0.00013101002,0.00010192874,0.0000010995162,0.0006783432],"genre_scores_gemma":[0.031560868,0.0009795191,0.0008813422,0.000975263,0.957062,0.000019062936,0.00005040566,0.00003866604,0.008432866],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961961,0.000103720915,0.0009707904,0.00017466492,0.0023382732,0.00021647208],"domain_scores_gemma":[0.9352418,0.060692117,0.0015673725,0.00021044839,0.0021923727,0.00009586859],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0035678027,0.00015421682,0.0004660418,0.0002890562,0.00030881193,0.00019271145,0.0007200718,0.00036977723,0.00023936149],"category_scores_gemma":[0.024586191,0.000082158724,0.000116580384,0.0003917201,0.00004595484,0.00010357974,0.000054204294,0.000757263,6.3082894e-7],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025344582,0.000006639588,0.001644162,0.0000061962314,0.0000394197,0.000049414495,0.000026281372,0.00057901343,3.856379e-8,0.000034677934,0.9254768,0.07213485],"study_design_scores_gemma":[0.00075287285,0.00015836915,0.014386587,0.0000029904622,0.000070654285,0.0000032310086,0.0004736734,0.00044430155,3.6475754e-7,0.0006310251,0.98298115,0.00009478713],"about_ca_topic_score_codex":0.002414097,"about_ca_topic_score_gemma":0.051363166,"teacher_disagreement_score":0.07204006,"about_ca_system_score_codex":0.00061467616,"about_ca_system_score_gemma":0.008544109,"threshold_uncertainty_score":0.9970765},"labels":[],"label_agreement":null},{"id":"W4242041711","doi":"10.1007/s42413-019-00024-y","title":"An Invitation to Submit and Introduction to the Book, Policy and Initiative Reviews Section (Volume 2, Issue 1)","year":2019,"lang":"en","type":"article","venue":"International Journal of Community Well-Being","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Section (typography); Volume (thermodynamics); Political science; Library science; Computer science; Business; Physics; Advertising","score_opus":0.09030319047151007,"score_gpt":0.47255831337339926,"score_spread":0.3822551229018892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4242041711","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.895773,0.00009473307,0.0037589953,0.095628306,0.0012729568,0.0002692378,0.0000017046576,0.0000056190042,0.00319546],"genre_scores_gemma":[0.9838767,0.0002950131,0.0005916797,0.012473843,0.0018459592,0.000005193462,0.000004906331,0.0000064400915,0.000900281],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970666,0.0010430955,0.0006833688,0.00010993847,0.0009975504,0.000099453726],"domain_scores_gemma":[0.99734336,0.0005827782,0.0004753163,0.00030038544,0.001181199,0.00011697955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008576862,0.00009915628,0.00019748624,0.0006220817,0.00025124694,0.00035123152,0.0006222736,0.000036563593,0.00045710726],"category_scores_gemma":[0.0020702826,0.00006817867,0.00004653201,0.0003757826,0.00003355411,0.0014436737,0.00015375926,0.00041649982,0.00020145596],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00077862246,0.0003427763,0.0703671,0.000028932964,0.00019419668,0.0000031650277,0.16596901,0.013078034,0.013367563,0.011308268,0.12782371,0.59673864],"study_design_scores_gemma":[0.00045843187,0.0006414384,0.14446248,0.00008269331,0.000014311404,0.00009257331,0.007257189,0.0022952931,0.00070378237,0.007893577,0.8359746,0.00012362629],"about_ca_topic_score_codex":0.00012515562,"about_ca_topic_score_gemma":0.00019116416,"teacher_disagreement_score":0.70815086,"about_ca_system_score_codex":0.00014917563,"about_ca_system_score_gemma":0.00008709062,"threshold_uncertainty_score":0.5005004},"labels":[],"label_agreement":null},{"id":"W4242601229","doi":"10.1002/ev.20107","title":"Editors' Notes","year":2015,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Accreditation; Charter; Certification; Context (archaeology); Credentialing; Conversation; Public relations; Professional association; Scholarship; Task (project management); Computer science; Political science; Engineering ethics; Management; Psychology; Law; History","score_opus":0.41995704850429344,"score_gpt":0.5640301890940794,"score_spread":0.144073140589786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4242601229","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17682941,0.0010381868,0.47109112,0.05104867,0.08142015,0.005859904,0.00006818633,0.000688639,0.21195573],"genre_scores_gemma":[0.95684934,0.000011709371,0.012923772,0.0004691032,0.009742195,0.00046844405,0.00010362746,0.00002372671,0.019408057],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962952,0.00022496503,0.00045517617,0.00031712363,0.0025472993,0.00016022494],"domain_scores_gemma":[0.99589014,0.00096759136,0.00018980424,0.00038311307,0.0023793513,0.00019001601],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.01075822,0.00009687734,0.00013681214,0.00030286048,0.00022453218,0.0002173573,0.00021595767,0.000068402136,0.0015037485],"category_scores_gemma":[0.013407272,0.00007723775,0.00009613941,0.0007739752,0.000023729006,0.0006379562,0.000024785337,0.00006319691,0.0009479864],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003273582,0.000049701703,0.0029438608,8.349187e-7,0.0000110058745,2.6604063e-8,0.0007136293,0.005496763,0.000106022315,0.0010438847,0.53061336,0.45898816],"study_design_scores_gemma":[0.0016101375,0.00014512871,0.0070351595,0.000004504304,0.00004858347,0.0000019060271,0.0004888114,0.1392865,0.0009171578,0.07170197,0.7786421,0.00011800618],"about_ca_topic_score_codex":0.00008553909,"about_ca_topic_score_gemma":0.00024312778,"teacher_disagreement_score":0.78001994,"about_ca_system_score_codex":0.00021809063,"about_ca_system_score_gemma":0.001232757,"threshold_uncertainty_score":0.9998299},"labels":[],"label_agreement":null},{"id":"W4243162557","doi":"10.1177/07591063211019946","title":"Comment chercher ?","year":2021,"lang":"fr","type":"article","venue":"Bulletin of Sociological Methodology/Bulletin de Méthodologie Sociologique","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Humanities; Philosophy","score_opus":0.6630589679511459,"score_gpt":0.5550877966177591,"score_spread":0.10797117133338685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4243162557","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039006922,0.03240808,0.16140646,0.73135287,0.004219512,0.00096366875,0.00017889016,0.0002956197,0.030167988],"genre_scores_gemma":[0.033537947,0.024191635,0.83799726,0.068886325,0.0011612162,0.0003202032,0.00009182765,0.00008705183,0.033726558],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.8539984,0.13583077,0.0037246232,0.002479148,0.0014695278,0.002497477],"domain_scores_gemma":[0.8530327,0.14001375,0.0020372046,0.0018301865,0.0024525959,0.00063353777],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity","insufficient_payload"],"category_scores_codex":[0.13666001,0.0012164563,0.0035855253,0.00025088715,0.00070872303,0.00015789601,0.0027878708,0.0068328786,0.16432291],"category_scores_gemma":[0.20757845,0.0010073719,0.0018415663,0.0007672641,0.007210974,0.00006767544,0.0021187086,0.005120697,0.004645879],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000767744,0.0020852578,0.035090093,0.00035388197,0.0007848909,0.0005002374,0.0036475144,0.0011295633,0.0040455097,0.2621668,0.585762,0.1036665],"study_design_scores_gemma":[0.0015122603,0.0013070063,0.019802319,0.000167027,0.00021057029,0.0002315988,0.012665894,0.000108165885,0.0044097384,0.24163982,0.7170401,0.0009054942],"about_ca_topic_score_codex":0.00025380278,"about_ca_topic_score_gemma":0.000009368633,"teacher_disagreement_score":0.6765908,"about_ca_system_score_codex":0.0010410252,"about_ca_system_score_gemma":0.0030338892,"threshold_uncertainty_score":0.99923766},"labels":[],"label_agreement":null},{"id":"W4243286683","doi":"10.22215/etd/2006-08286","title":"Ways that visible and ethnic minority women in Ottawa think about the quality of their lives and social programs: developing grassroots indicators of quality of life","year":2006,"lang":"en","type":"dissertation","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Carleton University; Canadian Heritage","funders":"","keywords":"Grassroots; Ethnic group; Political science; Quality (philosophy); Gender studies; Sociology; Politics; Law","score_opus":0.26471423767723035,"score_gpt":0.4939506980435206,"score_spread":0.22923646036629025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4243286683","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9926864,0.0009600229,0.00006936147,0.00018123585,0.00011616974,0.00061030115,0.000036982492,0.000012457294,0.00532706],"genre_scores_gemma":[0.9987434,0.00024217225,0.00034216334,0.0000684971,0.000023058248,0.000047742673,0.00009393887,0.000008638333,0.00043038136],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99372774,0.0011548195,0.0022971407,0.00046988134,0.0020229602,0.000327477],"domain_scores_gemma":[0.9945797,0.0018289825,0.0026582396,0.00037096872,0.00049500685,0.000067146204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022121096,0.00026469654,0.0010725358,0.00047712063,0.00015777319,0.000079368205,0.00054719736,0.0002932171,0.00010124882],"category_scores_gemma":[0.00085592153,0.00015772202,0.00013384198,0.0009687741,0.0003435282,0.0002916143,0.000108751155,0.00030070104,9.239913e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001615062,0.00022734846,0.8261885,0.00089768483,0.00008251079,7.14024e-8,0.077225775,0.0000026337236,0.00021530116,0.012907426,0.000113356895,0.08197788],"study_design_scores_gemma":[0.0004846144,0.00006254814,0.906109,0.00006666904,0.000008685085,7.247103e-8,0.078105785,0.000036369915,0.0007001091,0.014186511,0.00006788041,0.00017179111],"about_ca_topic_score_codex":0.0026018268,"about_ca_topic_score_gemma":0.022481358,"teacher_disagreement_score":0.08180609,"about_ca_system_score_codex":0.000074306045,"about_ca_system_score_gemma":0.00091899687,"threshold_uncertainty_score":0.9953558},"labels":[],"label_agreement":null},{"id":"W4243309813","doi":"10.24124/2011/bpgub765","title":"The Tahltan Nation and our consultation process with mining industry: How a land use plan might improve the process.","year":2011,"lang":"en","type":"dissertation","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Association of Canadian Universities for Northern Studies; University of Northern British Columbia","keywords":"Plan (archaeology); Process (computing); Government (linguistics); Resource (disambiguation); Political science; Environmental planning; Public relations; Public administration; Business; Geography; Computer science","score_opus":0.17024554571175288,"score_gpt":0.43625995686111635,"score_spread":0.26601441114936347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4243309813","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9872975,0.00008769637,0.0000736656,0.0025740159,0.00044625995,0.0011480824,0.000025640127,0.000041159787,0.008305996],"genre_scores_gemma":[0.94962275,0.0000436694,0.00011571244,0.00018810133,0.00010697895,0.00026870103,0.00019593672,0.000022353655,0.0494358],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9966775,0.00018301037,0.00048670318,0.0005176843,0.0018902248,0.00024485495],"domain_scores_gemma":[0.99573326,0.0009141367,0.00096986815,0.00035858946,0.0019385997,0.00008556612],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0024106796,0.00028606446,0.00025064466,0.00018276228,0.0008000849,0.0017876261,0.0005066833,0.00034502434,0.000064838816],"category_scores_gemma":[0.0017945975,0.00011805466,0.000032643795,0.00065533124,0.00006803879,0.0009906174,0.000017857268,0.0005308114,0.000014835241],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0040910426,0.00034370474,0.3843322,0.0004851381,0.0006727031,0.000013502057,0.21631394,0.0003591371,0.00042144614,0.0051120096,0.022725271,0.3651299],"study_design_scores_gemma":[0.003364903,0.00085269957,0.24104981,0.00045130047,0.000333632,0.0000359572,0.707088,0.019820876,0.0037485699,0.005524855,0.016490342,0.0012390655],"about_ca_topic_score_codex":0.00007617308,"about_ca_topic_score_gemma":0.007730326,"teacher_disagreement_score":0.49077404,"about_ca_system_score_codex":0.000026297539,"about_ca_system_score_gemma":0.0007948627,"threshold_uncertainty_score":0.9992486},"labels":[],"label_agreement":null},{"id":"W4243463671","doi":"10.1080/j006v21n04_06","title":"Web Sites Related to Methods for Evaluating Web Sites","year":2002,"lang":"en","type":"article","venue":"Physical & Occupational Therapy In Pediatrics","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"World Wide Web; Web site; Web application; Column (typography); Computer science; Web standards; The Internet; Data science","score_opus":0.4124995209518606,"score_gpt":0.6010774720819724,"score_spread":0.18857795113011178,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4243463671","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99201447,0.00030637876,0.0028565652,0.0020351275,0.00029346716,0.0007506508,0.00005882106,0.000052576557,0.00163193],"genre_scores_gemma":[0.9527545,0.00015783726,0.044420574,0.001095501,0.0004789776,0.00022795789,0.000050775885,0.000021739057,0.0007921384],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958481,0.0006106601,0.0008454628,0.00056686637,0.00178134,0.0003475407],"domain_scores_gemma":[0.9896637,0.008647115,0.00029153874,0.0003834606,0.0008678164,0.00014634208],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0056913528,0.00021799932,0.00035527116,0.000503901,0.00021651854,0.0001851293,0.00052279764,0.00008821277,0.0017900112],"category_scores_gemma":[0.003632218,0.00017000704,0.000204659,0.0024339193,0.000039961516,0.0004391854,0.000068690315,0.00021358515,0.00063162803],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040906962,0.0013126301,0.3463426,0.000015349538,0.00004111618,8.679914e-7,0.004405457,0.021213977,0.037662186,0.010802034,0.020908628,0.5568861],"study_design_scores_gemma":[0.0015804999,0.0005899545,0.04708095,0.0000043716987,0.000015351508,6.5595736e-7,0.00011463434,0.8983642,0.00038060342,0.043265708,0.008297805,0.00030527075],"about_ca_topic_score_codex":0.0000024911162,"about_ca_topic_score_gemma":0.0000072800663,"teacher_disagreement_score":0.87715024,"about_ca_system_score_codex":0.00010797769,"about_ca_system_score_gemma":0.00020539996,"threshold_uncertainty_score":0.9991225},"labels":[],"label_agreement":null},{"id":"W4243789328","doi":"10.1177/160940690900800402","title":"The 10th Advances in Qualitative Methods Conference October 8–10, 2009, Vancouver, Canada","year":2009,"lang":"en","type":"article","venue":"International Journal of Qualitative Methods","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Library science; Geography; Political science; Computer science","score_opus":0.7269617712594691,"score_gpt":0.7489635920900978,"score_spread":0.022001820830628627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4243789328","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0070234747,0.0045649577,0.93579626,0.020578759,0.008131692,0.0002424607,0.0000523539,0.000009129101,0.02360091],"genre_scores_gemma":[0.16851847,0.0010843085,0.8152865,0.0031639526,0.00039129175,0.00001622515,0.0000044984126,0.000016114724,0.0115186265],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9667586,0.025762139,0.00264974,0.0003605535,0.004111992,0.00035696747],"domain_scores_gemma":[0.9573059,0.034215942,0.0021733053,0.00029792535,0.0058398237,0.00016706948],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09294201,0.00023680611,0.00056741113,0.00044829876,0.00017385285,0.00027684672,0.0017663472,0.0000628642,0.0012765283],"category_scores_gemma":[0.026069501,0.0001397806,0.00020013393,0.0007360708,0.00023611989,0.001358003,0.00007757125,0.0005198048,0.000014385355],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00050367427,0.00011140676,0.00012616871,0.0000022118625,0.00011833825,0.000020239358,0.07106242,0.0010853255,0.00044893744,0.037252866,0.03136671,0.8579017],"study_design_scores_gemma":[0.0009849169,0.00030471545,0.0018958849,0.00006804433,0.000012953445,0.000014774604,0.15622604,0.0023834074,0.0015135428,0.3639921,0.4723853,0.00021833328],"about_ca_topic_score_codex":0.0032685339,"about_ca_topic_score_gemma":0.09715625,"teacher_disagreement_score":0.85768336,"about_ca_system_score_codex":0.0005347961,"about_ca_system_score_gemma":0.0020452633,"threshold_uncertainty_score":0.9996364},"labels":[],"label_agreement":null},{"id":"W4244210830","doi":"10.1093/oxfordhb/9780190847388.013.25","title":"Content Analysis","year":2020,"lang":"en","type":"book-chapter","venue":"Oxford University Press eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Content analysis; Contextualization; Sample (material); Content (measure theory); Style (visual arts); Focus (optics); Relation (database); Qualitative research; Computer science; Psychology; Data science; Sociology; Social science; Data mining; Mathematics","score_opus":0.3399446338168125,"score_gpt":0.3738637835566835,"score_spread":0.03391914973987098,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4244210830","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000666121,0.000028654304,0.0028073923,0.0002546717,0.00017161419,0.0002517311,0.00013851421,0.0000637225,0.9962171],"genre_scores_gemma":[0.0058039045,0.000089075336,0.0002640136,0.00034084922,0.00006825381,4.507315e-7,0.000043969092,0.000014374774,0.9933751],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99694854,0.000076559205,0.00043340243,0.0006516962,0.001711348,0.00017844989],"domain_scores_gemma":[0.9977279,0.00025066172,0.00052256713,0.0007667858,0.00050144957,0.0002306631],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006240261,0.00026964693,0.0006191386,0.0005451802,0.00019529126,0.00016237536,0.0010815698,0.00022706225,0.0018398992],"category_scores_gemma":[0.00005379699,0.00024092263,0.0006194351,0.00006366785,0.00012764601,0.00015094217,0.00043258962,0.0003371096,0.000046413214],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009555738,0.00000753703,0.00015712275,0.000006696328,0.0009095857,0.0000568688,0.00025826853,0.00014386479,0.0000057349,0.97162163,0.007941443,0.018795704],"study_design_scores_gemma":[0.00032985682,0.000056692148,0.0002033495,0.000012008251,0.00088107446,7.754376e-7,0.00015086881,0.0020701836,0.000017584396,0.0017482638,0.99426156,0.0002677615],"about_ca_topic_score_codex":0.000025404257,"about_ca_topic_score_gemma":0.00007899549,"teacher_disagreement_score":0.98632014,"about_ca_system_score_codex":0.00012825323,"about_ca_system_score_gemma":0.00019188393,"threshold_uncertainty_score":0.99907255},"labels":[],"label_agreement":null},{"id":"W4244221056","doi":"10.3138/cjpe.202","title":"Inspiring Future Program Evaluators through Innovative Curriculum for Undergraduates","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Curriculum; Credentialing; Program evaluation; Medical education; Professionalization; Logic model; Psychology; Computer science; Engineering management; Pedagogy; Engineering; Medicine; Sociology; Political science","score_opus":0.4974043274798436,"score_gpt":0.5733680132125911,"score_spread":0.07596368573274753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4244221056","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93151635,0.0028570078,0.010774877,0.026494253,0.008836536,0.010770401,0.00003628002,0.00009978197,0.008614518],"genre_scores_gemma":[0.9504496,0.000011805941,0.047331497,0.00035919913,0.0010754473,0.0005793992,0.000048770515,0.000024627678,0.0001196882],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99390525,0.00060759246,0.0013745597,0.00033123253,0.0033000908,0.00048130407],"domain_scores_gemma":[0.98041534,0.00021424437,0.001241984,0.00034335937,0.017138261,0.0006468028],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020619873,0.00022681864,0.00038743732,0.0007256227,0.0003033746,0.0007027501,0.000651505,0.00014358062,0.00028139577],"category_scores_gemma":[0.006663735,0.00016745298,0.000179361,0.0025073763,0.00014051022,0.0015494947,0.000021103911,0.00029855114,0.000054112807],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027047232,0.0001313676,0.028404288,0.0000081981525,0.00006431305,0.0000028816476,0.002909922,0.0019697635,0.000006038011,0.0038274887,0.02586515,0.93678355],"study_design_scores_gemma":[0.004209193,0.0037514963,0.0164901,0.00010849855,0.00019833779,0.00006345313,0.019649377,0.107108496,0.00019213038,0.11740778,0.73035944,0.00046169708],"about_ca_topic_score_codex":0.00034558238,"about_ca_topic_score_gemma":0.008295364,"teacher_disagreement_score":0.93632185,"about_ca_system_score_codex":0.0008664044,"about_ca_system_score_gemma":0.012532327,"threshold_uncertainty_score":0.9930657},"labels":[],"label_agreement":null},{"id":"W4244535353","doi":"10.1016/j.ijrobp.2012.07.141","title":"Multicenter Collaborative Quality Assurance Program for the Province of Ontario, Canada: First Year Results","year":2012,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Medicine; Quality assurance; Multicenter study; Medical physics; Family medicine; Internal medicine; Pathology","score_opus":0.08482048478137502,"score_gpt":0.4606509388215188,"score_spread":0.3758304540401438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4244535353","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8762099,0.0008446021,0.054989573,0.039227396,0.019247234,0.0028658358,0.0013555743,0.000037291677,0.0052225636],"genre_scores_gemma":[0.9908644,0.000064984844,0.0070798337,0.00048746125,0.0010224885,0.000039953447,0.00003426747,0.000007998901,0.00039859282],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969176,0.00037070466,0.0013740746,0.00017403316,0.0009477494,0.00021583318],"domain_scores_gemma":[0.9895058,0.004282413,0.00266915,0.0002158388,0.0032369941,0.00008975635],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005120405,0.00013102524,0.0003514218,0.00007135269,0.00013334908,0.000050539373,0.00079513044,0.00010002774,0.00011344094],"category_scores_gemma":[0.003143486,0.00008335284,0.00014537814,0.00021368322,0.00015608703,0.00054151734,0.000058864996,0.00024923382,0.000009666232],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011924424,0.0006138643,0.81797063,0.0000057586058,0.00037238176,0.000001171683,0.002757609,0.0036844776,0.000090598616,0.0115350485,0.03367028,0.12810573],"study_design_scores_gemma":[0.0035910916,0.00047276882,0.34002832,0.000018220919,0.000037823873,0.0000040672544,0.00055455626,0.0025491202,0.00067702733,0.0015825406,0.6503704,0.00011401784],"about_ca_topic_score_codex":0.015330972,"about_ca_topic_score_gemma":0.3062877,"teacher_disagreement_score":0.6167002,"about_ca_system_score_codex":0.001459313,"about_ca_system_score_gemma":0.006755664,"threshold_uncertainty_score":0.9988751},"labels":[],"label_agreement":null},{"id":"W4244747690","doi":"10.18130/v3r06d","title":"Pragmatic Measurement for Education Science: A Method-Substance Synergy of Validation and Motivation","year":2017,"lang":"en","type":"dissertation","venue":"Libra","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"National Association for Research in Science Teaching; James Madison University; Sage Foundation","keywords":"Psychology; Substance use; Data science; Computer science; Mathematics education; Engineering ethics; Engineering; Clinical psychology","score_opus":0.23039115455044265,"score_gpt":0.5250959889791654,"score_spread":0.29470483442872275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4244747690","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8023657,0.0014309569,0.05538971,0.001726236,0.007458966,0.00465591,0.00007891228,0.00008308018,0.1268105],"genre_scores_gemma":[0.9522984,0.00011810772,0.026579577,0.00009491056,0.00021092645,0.0004667591,0.00043864019,0.00003143687,0.019761238],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9952634,0.00015690384,0.0008602494,0.00056109217,0.0029799382,0.00017843851],"domain_scores_gemma":[0.9940983,0.00054076186,0.0018441363,0.0007028593,0.0027311204,0.00008281136],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009362018,0.00018669233,0.0003679664,0.0006409834,0.0004426353,0.00053924025,0.00067615334,0.00013546813,0.00019103636],"category_scores_gemma":[0.006006993,0.00015145981,0.00008101256,0.00049288553,0.0000952133,0.0016150316,0.000018528643,0.000103270955,0.000008710727],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001754957,0.00023631028,0.0027953875,0.0006187316,0.000049480153,5.6631492e-8,0.0067446516,0.00023110426,0.03407009,0.048891213,0.003294869,0.9028926],"study_design_scores_gemma":[0.0020825157,0.00054858974,0.3361358,0.0023085098,0.0003356553,0.0000040690047,0.01341354,0.027732491,0.283954,0.28488138,0.047430974,0.0011724582],"about_ca_topic_score_codex":0.00001823298,"about_ca_topic_score_gemma":0.000068483765,"teacher_disagreement_score":0.90172017,"about_ca_system_score_codex":0.00008959729,"about_ca_system_score_gemma":0.0026320736,"threshold_uncertainty_score":0.7191366},"labels":[],"label_agreement":null},{"id":"W4245315102","doi":"10.18438/b8rd0q","title":"Evaluating the Results of Evidence Application, Part One","year":2010,"lang":"en","type":"article","venue":"Evidence Based Library and Information Practice","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Data science","score_opus":0.32520889358246974,"score_gpt":0.5082823919651314,"score_spread":0.18307349838266163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4245315102","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10228291,0.00069897313,0.02561981,0.84268975,0.0011147386,0.0020016083,0.000052039686,0.00016596602,0.025374211],"genre_scores_gemma":[0.9387806,0.00085223734,0.020243382,0.03908316,0.00019589868,0.000112266374,0.0000270094,0.0000064889537,0.0006989764],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9954665,0.0007294212,0.0013911146,0.00024091046,0.0020195686,0.00015249525],"domain_scores_gemma":[0.97334695,0.023230337,0.0016442563,0.00096615264,0.00071254367,0.00009975347],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017807636,0.00011587526,0.00015746389,0.00018583759,0.00034471854,0.0006622311,0.0007187176,0.00007427857,0.0009419838],"category_scores_gemma":[0.054689374,0.00006664884,0.000047677622,0.0010732721,0.00016979915,0.17755754,0.00015253267,0.0003627849,0.00028144228],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023396292,0.00013183555,0.0046620113,0.00009036262,0.000025012843,2.858009e-7,0.0016885399,0.0039131027,0.0046323696,0.24169019,0.014130761,0.7266959],"study_design_scores_gemma":[0.00054034725,0.0003866689,0.034657236,0.00025045,0.000042683147,0.000008759887,0.0010900871,0.14358276,0.0067464057,0.0017736168,0.8107523,0.00016868625],"about_ca_topic_score_codex":0.000009881127,"about_ca_topic_score_gemma":4.6069368e-7,"teacher_disagreement_score":0.83649766,"about_ca_system_score_codex":0.0000052763608,"about_ca_system_score_gemma":0.0006271254,"threshold_uncertainty_score":0.9999713},"labels":[],"label_agreement":null},{"id":"W4245842532","doi":"10.3138/cjpe.30.3.08","title":"A Transcultural Global Systems Perspective: In Search of <i>Blue Marble</i> Evaluators","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Framing (construction); Reflexivity; Indigenous; Sociology; Praxis; Perspective (graphical); Public relations; Engineering ethics; Political science; Social science; Epistemology; Computer science; Engineering","score_opus":0.3034525345500509,"score_gpt":0.5381338373521743,"score_spread":0.23468130280212346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4245842532","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9895033,0.001084313,0.0010714792,0.0029653443,0.00092225504,0.0012585329,0.00003176112,0.000005270749,0.0031577423],"genre_scores_gemma":[0.9992104,0.00001933992,0.00046433308,0.000027122891,0.00010560466,0.000043655466,0.0000017107968,0.0000062947715,0.00012150802],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9934442,0.001328877,0.0012310187,0.00023966898,0.0034121785,0.0003440669],"domain_scores_gemma":[0.9928841,0.00022894093,0.00053915445,0.00026649877,0.005665247,0.00041607226],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.021669034,0.00013341775,0.0003450386,0.0005770284,0.00008263691,0.00017941523,0.0005443365,0.000105307045,0.0011324905],"category_scores_gemma":[0.0022781051,0.00007855566,0.00016895655,0.0013102457,0.00016283458,0.00073584676,0.000009456638,0.00015148972,0.000038835977],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000107371074,0.00011579585,0.31125364,0.000015179192,0.000069373455,0.000013019382,0.004839717,0.006116169,0.00046101835,0.0059821396,0.0015271413,0.66949946],"study_design_scores_gemma":[0.008229752,0.0022228246,0.87778026,0.00068087876,0.00019982636,0.00028182013,0.03315467,0.051679976,0.000494658,0.013501898,0.011278725,0.00049473543],"about_ca_topic_score_codex":0.0036338128,"about_ca_topic_score_gemma":0.041297916,"teacher_disagreement_score":0.66900474,"about_ca_system_score_codex":0.0017485966,"about_ca_system_score_gemma":0.0073787197,"threshold_uncertainty_score":0.9997806},"labels":[],"label_agreement":null},{"id":"W4245992123","doi":"10.1002/ev.20367","title":"Issue Information","year":2021,"lang":"en","type":"paratext","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Citation; World Wide Web; Information retrieval; Library science","score_opus":0.2232214289072087,"score_gpt":0.5437897844404399,"score_spread":0.3205683555332312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4245992123","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00028106972,0.002638979,0.0847837,0.0071842866,0.04907193,0.0036923827,0.00045597472,0.00009903762,0.85179263],"genre_scores_gemma":[0.0012094196,0.000647451,0.004061347,0.0012194306,0.0033115642,0.0011455831,0.008266319,0.00003742157,0.98010147],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99292034,0.0005301491,0.0014697207,0.0005822469,0.0041873017,0.00031024034],"domain_scores_gemma":[0.99143666,0.0009826337,0.0010077797,0.00093942584,0.005464302,0.00016918452],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008122634,0.0003200991,0.0005006663,0.001027674,0.00055630616,0.0011104688,0.00048909563,0.00042427346,0.15065265],"category_scores_gemma":[0.005698301,0.00028436226,0.00037249477,0.0015982938,0.00003311803,0.0018537543,0.000074996904,0.00029302324,0.0650481],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012799608,0.00002062087,0.000006590805,0.000011599469,0.000029005947,1.4051583e-8,0.00030537436,0.0036494315,0.000009650434,0.00010443917,0.64091533,0.35493514],"study_design_scores_gemma":[0.0012239398,0.0000845906,0.00031476395,0.000054610904,0.00016399393,0.0000033413785,0.0005944876,0.037765533,0.000340976,0.002380333,0.95677525,0.00029817264],"about_ca_topic_score_codex":0.00013113157,"about_ca_topic_score_gemma":0.00026737803,"teacher_disagreement_score":0.35463697,"about_ca_system_score_codex":0.0005672496,"about_ca_system_score_gemma":0.004462644,"threshold_uncertainty_score":0.99996084},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":["insufficient_payload"],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":["insufficient_payload"],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4246372039","doi":"10.18438/b8z90j","title":"Research Methods: The Most Significant Change Technique","year":2016,"lang":"en","type":"article","venue":"Evidence Based Library and Information Practice","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Information retrieval; Data science","score_opus":0.3887561153752986,"score_gpt":0.5669800108542881,"score_spread":0.17822389547898948,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4246372039","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00059690565,0.00046814213,0.20500012,0.76552975,0.00028215421,0.0017845467,0.00001632196,0.000108874265,0.026213164],"genre_scores_gemma":[0.54078054,0.009768762,0.13940398,0.30096325,0.0006187212,0.0038990856,0.00002000375,0.000028781456,0.0045168702],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99342614,0.0036613662,0.00070290564,0.00022201087,0.0017427156,0.00024483772],"domain_scores_gemma":[0.96390927,0.0343761,0.0004257232,0.0006638777,0.0005057808,0.00011925785],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","scholarly_communication"],"category_scores_codex":[0.031775117,0.00010729113,0.000121158235,0.0004350584,0.00051094766,0.0010551965,0.00072367105,0.00007762569,0.002776777],"category_scores_gemma":[0.021325082,0.000048030004,0.000034623616,0.0016925407,0.00021991487,0.24897754,0.00023627565,0.00028573975,0.0007178817],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022886138,0.000024233483,0.000697584,0.000013744163,0.0000057320494,9.7865e-7,0.0004078494,0.000008955884,0.0009012811,0.21628793,0.017604811,0.763818],"study_design_scores_gemma":[0.00016433033,0.00015616679,0.006912809,0.00014965067,0.0000059380136,0.000008767459,0.002075536,0.0023403612,0.010491136,0.003016225,0.97458017,0.00009888093],"about_ca_topic_score_codex":0.00000785266,"about_ca_topic_score_gemma":5.9861584e-8,"teacher_disagreement_score":0.9569754,"about_ca_system_score_codex":0.000018689512,"about_ca_system_score_gemma":0.00045710322,"threshold_uncertainty_score":0.9999818},"labels":[],"label_agreement":null},{"id":"W4246400482","doi":"10.21203/rs.2.21766/v1","title":"Applying an intersectionality lens to the Theoretical Domains Framework: a tool for thinking about how intersecting social identities and structures of power influence behaviour","year":2020,"lang":"en","type":"preprint","venue":"Research Square","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; University of Waterloo; University of British Columbia; Ottawa Hospital","funders":"Canadian Institutes of Health Research","keywords":"Intersectionality; Context (archaeology); Delphi method; Through-the-lens metering; Delphi; Voting; Identity (music); Computer science; Sociology; Lens (geology); Political science; Engineering; Artificial intelligence; Gender studies","score_opus":0.25049751271031834,"score_gpt":0.5555617109953894,"score_spread":0.3050641982850711,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4246400482","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9539344,0.0000476356,0.03375905,0.00897791,0.00034415186,0.002257031,0.0002343517,0.00003231334,0.0004131805],"genre_scores_gemma":[0.99589425,0.000014180497,0.0025844192,0.00040625333,0.00035451952,0.00067555223,0.000019084628,0.000020697527,0.00003104062],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9928626,0.0013136909,0.0006503488,0.0007946473,0.0039291563,0.0004495819],"domain_scores_gemma":[0.9934287,0.003504022,0.00030300385,0.0006098124,0.0020295756,0.00012488032],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.014382468,0.00022478815,0.00041811034,0.00038861085,0.0010803244,0.0019087777,0.0013733029,0.00027727347,0.00033857848],"category_scores_gemma":[0.010445605,0.00015083248,0.00021472179,0.00050499575,0.00066990295,0.00044255878,0.002169494,0.0016519396,0.0000050097037],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005225016,0.00008124206,0.072871715,0.00044764773,0.00012340446,0.0000048133707,0.12362986,0.001264786,0.00051012245,0.78432536,0.0020899638,0.0141286],"study_design_scores_gemma":[0.00020990703,0.00029255054,0.21408959,0.00035636645,0.000019969526,0.0000035622227,0.07643703,0.0027436644,0.00022377311,0.70495373,0.00045032412,0.00021951809],"about_ca_topic_score_codex":0.00007375257,"about_ca_topic_score_gemma":0.00013865356,"teacher_disagreement_score":0.14121789,"about_ca_system_score_codex":0.0001703112,"about_ca_system_score_gemma":0.00044336662,"threshold_uncertainty_score":0.9991273},"labels":[],"label_agreement":null},{"id":"W4246545089","doi":"10.3821/144.3.cpj299","title":"Developing recommendations for the reimbursement of expanded professional pharmacist's services in Ontario","year":2011,"lang":"en","type":"article","venue":"Canadian Pharmacists Journal / Revue des Pharmaciens du Canada","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Reimbursement; Pharmacist; Professional services; Business; Professional development; Nursing; Medicine; Family medicine; Medical education; Pharmacy; Public relations; Political science; Health care","score_opus":0.4264929609471638,"score_gpt":0.4609703018867486,"score_spread":0.034477340939584766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4246545089","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9829017,0.00039897623,0.0017505176,0.0021834248,0.0084323045,0.001405229,0.00028665678,0.000013183408,0.0026279897],"genre_scores_gemma":[0.99223,0.00060010573,0.0020232312,0.0027531518,0.00018012572,0.00010511122,0.00002621154,0.000020731435,0.0020613386],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961769,0.0002821496,0.0014020836,0.00037806522,0.0010667819,0.0006939918],"domain_scores_gemma":[0.9963617,0.00060322596,0.00069956173,0.00031879338,0.0013450533,0.0006716725],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0046680723,0.00026457672,0.00035953455,0.00056844164,0.00096808164,0.00016164771,0.0014028936,0.00004784466,0.006127025],"category_scores_gemma":[0.00019036654,0.00019570207,0.00014878093,0.0008146289,0.00012451247,0.000669996,0.00007324271,0.00053457153,0.000011653745],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012565723,0.00043100366,0.24298905,0.00032339717,0.0007584426,0.0033021828,0.07550207,0.0028115683,0.0015347052,0.0036724634,0.11177628,0.55564225],"study_design_scores_gemma":[0.009668335,0.00016325274,0.010021857,0.0002070162,0.000284604,0.03601245,0.0019589495,0.032689925,0.010905186,0.0072147776,0.88946635,0.0014073242],"about_ca_topic_score_codex":0.1984763,"about_ca_topic_score_gemma":0.9564263,"teacher_disagreement_score":0.77769005,"about_ca_system_score_codex":0.0028793744,"about_ca_system_score_gemma":0.013491576,"threshold_uncertainty_score":0.9947815},"labels":[],"label_agreement":null},{"id":"W4246854086","doi":"10.1007/978-3-319-01669-6_562-1","title":"Impact","year":2014,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science","score_opus":0.32394943490841294,"score_gpt":0.5475407482924535,"score_spread":0.22359131338404054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4246854086","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004967189,0.00003440358,0.0037922305,0.00048347627,0.00035221415,0.00010097238,0.000008053797,0.00003247597,0.9951465],"genre_scores_gemma":[0.017500829,0.000026600019,0.00024202,0.0007282459,0.00022768161,0.0000017619756,0.000012165257,0.0000143634215,0.98124635],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99698687,0.000024006762,0.0005076692,0.0003283838,0.0020275332,0.00012554218],"domain_scores_gemma":[0.9980879,0.0004290499,0.000268685,0.0007358684,0.00037043568,0.000108054635],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0024237467,0.0001779893,0.0003040543,0.0002521989,0.000059262493,0.00019298213,0.0004921913,0.0001602451,0.26233056],"category_scores_gemma":[0.00017159134,0.000098138575,0.0002565287,0.000033762964,0.00004022761,0.00008355753,0.00007700689,0.00016447136,0.04203778],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004830181,0.0000028478628,0.00037999998,9.231127e-7,0.000019204534,7.5830417e-7,0.000022632687,0.000036066747,0.0000015524514,0.45653635,0.32921648,0.21377835],"study_design_scores_gemma":[0.000086463064,0.000072903946,0.0013649862,0.000007945871,0.0000071306686,0.0000024442988,0.000003343721,0.0008923847,0.0000018020553,0.12215732,0.875268,0.00013529252],"about_ca_topic_score_codex":0.000005380861,"about_ca_topic_score_gemma":0.00003086833,"teacher_disagreement_score":0.5460515,"about_ca_system_score_codex":0.00005433527,"about_ca_system_score_gemma":0.00022265578,"threshold_uncertainty_score":0.9587081},"labels":[],"label_agreement":null},{"id":"W4246975863","doi":"10.1080/1612197x.2016.1137699","title":"Editorial","year":2016,"lang":"en","type":"editorial","venue":"International Journal of Sport and Exercise Psychology","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Laurentian University","funders":"","keywords":"Psychology","score_opus":0.05552547660085447,"score_gpt":0.5010453435676655,"score_spread":0.445519866966811,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4246975863","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00096314884,0.00039610756,0.00010411707,0.002178726,0.99204963,0.00006301401,0.00003821211,0.0000060614043,0.004200953],"genre_scores_gemma":[0.0027562873,0.005247252,0.000183457,0.00014890637,0.98864305,0.0000036818287,0.000022835431,0.000016252314,0.0029783007],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99262345,0.000017756662,0.0015675181,0.00035325065,0.005251214,0.00018678934],"domain_scores_gemma":[0.9923422,0.00032300415,0.001862562,0.00029959017,0.0050095706,0.00016312744],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0046289004,0.00021281982,0.0006596638,0.0008032109,0.00004689811,0.00021525129,0.0016259949,0.00062788103,0.0020308841],"category_scores_gemma":[0.00052213646,0.00012971602,0.0002357548,0.00011737404,0.00014057601,0.00047806313,0.00013107585,0.00065270194,0.000286507],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00075711694,0.000054360702,0.0018080485,0.0000016073362,0.00006744601,0.0000347327,0.00009217614,9.3002984e-7,0.0000085972515,0.00007157648,0.94722426,0.049879164],"study_design_scores_gemma":[0.0014877624,0.00015169618,0.0013310061,0.00014607607,0.00003715308,0.000035775363,0.00003626159,0.000002322356,0.0000060638163,0.00936544,0.987258,0.00014242191],"about_ca_topic_score_codex":0.0000054876477,"about_ca_topic_score_gemma":0.000005270549,"teacher_disagreement_score":0.049736742,"about_ca_system_score_codex":0.00006970015,"about_ca_system_score_gemma":0.00056008645,"threshold_uncertainty_score":0.9988814},"labels":[],"label_agreement":null},{"id":"W4247534511","doi":"10.1515/9783839443767-006","title":"5. Present and Future of Gender in Impact Assessment: a Standpoint—a Paradigm Shift?","year":2018,"lang":"en","type":"book-chapter","venue":"transcript Verlag eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Paradigm shift; Psychology; Epistemology; Philosophy","score_opus":0.1512176913730504,"score_gpt":0.43367296481341094,"score_spread":0.28245527344036053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4247534511","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012478984,0.0014080451,0.0006814266,0.0007066446,0.0007767544,0.0010140875,0.0002554993,0.000036829962,0.98264176],"genre_scores_gemma":[0.7812946,0.0005696762,0.0006295285,0.00036008362,0.001217881,0.00004959518,0.000054271866,0.0001187699,0.21570559],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9948655,0.00015484578,0.0013556866,0.0007687243,0.002468657,0.0003866113],"domain_scores_gemma":[0.9978967,0.0002491539,0.0005169406,0.0009282303,0.00018875889,0.00022025824],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002607682,0.00050553377,0.0009290156,0.00066008815,0.00009633372,0.00018285608,0.00061725953,0.0004259477,0.011782368],"category_scores_gemma":[0.000008257156,0.00036772242,0.00035448378,0.00007175243,0.00033383406,0.00024346341,0.00006337614,0.00054766523,0.000071683375],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011608559,0.00021898285,0.003028577,0.00041457682,0.0007002786,0.00008851473,0.042871114,0.00006464421,0.0004104755,0.8004719,0.020854022,0.12971604],"study_design_scores_gemma":[0.0019256516,0.0005991944,0.019065868,0.00016633584,0.00010987777,0.0000123086875,0.00035681739,0.0005595274,0.00006023631,0.47553194,0.501052,0.0005601971],"about_ca_topic_score_codex":0.00003398861,"about_ca_topic_score_gemma":0.00026382823,"teacher_disagreement_score":0.76881564,"about_ca_system_score_codex":0.00016178834,"about_ca_system_score_gemma":0.0007508095,"threshold_uncertainty_score":0.99987745},"labels":[],"label_agreement":null},{"id":"W4247610456","doi":"10.1002/9781119373780.ch30","title":"Programme Evaluation","year":2018,"lang":"en","type":"other","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Evaluation methods; Impact evaluation; Engineering ethics; Curriculum; Program evaluation; Management science; Theory of change; Educational evaluation; Macro; Computer science; Medical education; Psychology; Engineering management; Process management; Political science; Pedagogy; Sociology; Engineering; Medicine; Public administration","score_opus":0.5017300995790568,"score_gpt":0.5956937588408802,"score_spread":0.09396365926182337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4247610456","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000013879784,0.000083176164,0.0014844332,0.00048743852,0.0010340216,0.00058389176,0.0000030760677,0.00013275983,0.9961773],"genre_scores_gemma":[0.00047071895,0.000013233382,0.003218293,0.00029769086,0.0006322922,0.00007513631,0.000030210116,0.00008854626,0.9951739],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9949594,0.00021801215,0.00035677906,0.00039478895,0.0038921821,0.0001788405],"domain_scores_gemma":[0.9982907,0.00010233174,0.00031140045,0.0006960716,0.00052482757,0.000074672826],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0077235675,0.00013418317,0.00018915058,0.00040861496,0.00004032545,0.0002132277,0.0004698251,0.00016154029,0.6704987],"category_scores_gemma":[0.0008539461,0.00008189996,0.00007145316,0.00041940043,0.00006230035,0.00007353608,0.000058024525,0.00005390407,0.07815371],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.379908e-7,0.000012815698,0.00031914818,0.0000010180006,0.000006832996,6.590775e-8,0.000016728,5.112132e-7,4.6000807e-7,0.0006673488,0.76705325,0.23192096],"study_design_scores_gemma":[0.00020746519,0.000045965822,0.0003207048,0.000015272399,0.000016529484,6.450685e-7,0.00009377433,0.005654711,0.000006551928,0.0040307473,0.9894897,0.000117972006],"about_ca_topic_score_codex":0.00004716193,"about_ca_topic_score_gemma":0.0008074035,"teacher_disagreement_score":0.59234506,"about_ca_system_score_codex":0.00004704421,"about_ca_system_score_gemma":0.00040023087,"threshold_uncertainty_score":0.922564},"labels":[],"label_agreement":null},{"id":"W4248262697","doi":"10.1007/978-1-4939-7131-2_100482","title":"Impact","year":2018,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science","score_opus":0.38333380359207353,"score_gpt":0.5661025517561785,"score_spread":0.182768748164105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248262697","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00021772856,0.00003745151,0.00049808866,0.00029903225,0.0004554642,0.00010989676,0.000015388534,0.000032341173,0.9983346],"genre_scores_gemma":[0.00475375,0.000029850267,0.00033539985,0.0005123751,0.00038095342,0.0000015893547,0.000011681078,0.000014191619,0.9939602],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99697924,0.00001697673,0.00048809312,0.00034585662,0.0020392179,0.00013063881],"domain_scores_gemma":[0.9980508,0.00026021036,0.00025149,0.00073766394,0.00059572194,0.00010409014],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0019931872,0.00017534393,0.00025795514,0.00025813642,0.00006908646,0.00020860884,0.0005131711,0.00016395166,0.670323],"category_scores_gemma":[0.00014473083,0.00009629302,0.00023162842,0.000043374646,0.000077955636,0.00016393341,0.00009647474,0.00013209182,0.093436524],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008317197,0.0000055199544,0.0003236303,7.022793e-7,0.000027924307,0.0000013896885,0.00008433044,0.00000399572,0.000002052553,0.080006965,0.8583227,0.061212476],"study_design_scores_gemma":[0.00007291282,0.000109484026,0.0010406105,0.000008063606,0.000006837506,0.00000277377,0.000010337032,0.00030491964,0.0000037954683,0.19055185,0.8077626,0.00012581024],"about_ca_topic_score_codex":0.000004323844,"about_ca_topic_score_gemma":0.00004274626,"teacher_disagreement_score":0.5768865,"about_ca_system_score_codex":0.000064976935,"about_ca_system_score_gemma":0.00032542433,"threshold_uncertainty_score":0.90726936},"labels":[],"label_agreement":null},{"id":"W4248480822","doi":"10.1007/978-1-4614-6170-8_100952","title":"Evaluation Approaches","year":2014,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science","score_opus":0.6874331699460952,"score_gpt":0.5121787404602547,"score_spread":0.17525442948584047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248480822","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00001124549,0.000113351074,0.010473182,0.0010315585,0.00047745646,0.00038399652,0.000003797478,0.00003680335,0.9874686],"genre_scores_gemma":[0.020740593,0.000018782728,0.0007953211,0.000505057,0.00030632803,0.000023026529,0.000028966191,0.000019615994,0.9775623],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9913714,0.00014722616,0.00071243284,0.0005381483,0.007097412,0.00013340985],"domain_scores_gemma":[0.9970049,0.0004711444,0.0004300063,0.0008853538,0.0011251232,0.000083460196],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.02059278,0.00021209403,0.00032327755,0.0003202995,0.000098577955,0.00022607186,0.00052796263,0.00022964853,0.13280782],"category_scores_gemma":[0.0006777264,0.00013969275,0.00016768984,0.00005043596,0.00006154523,0.00012948633,0.00008846113,0.00018854691,0.016806507],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002098833,0.000003447421,0.000014725562,0.0000015524249,0.00001821887,9.7667595e-8,0.000035946545,0.00020435023,6.3137054e-7,0.44007713,0.060784597,0.49885723],"study_design_scores_gemma":[0.00015101607,0.00003401086,0.00012503786,0.000010550338,0.000057660873,9.4027786e-7,0.000020687788,0.058606133,0.000006870605,0.25515467,0.6856718,0.00016060886],"about_ca_topic_score_codex":0.0000016755798,"about_ca_topic_score_gemma":0.00004570982,"teacher_disagreement_score":0.6248872,"about_ca_system_score_codex":0.00011116088,"about_ca_system_score_gemma":0.00045570463,"threshold_uncertainty_score":0.983959},"labels":[],"label_agreement":null},{"id":"W4248787508","doi":"10.3410/f.727687681.793571325","title":"Faculty Opinions recommendation of Reinstated episodic context guides sampling-based decisions for reward.","year":2020,"lang":"en","type":"dataset","venue":"Faculty Opinions – Post-Publication Peer Review of the Biomedical Literature","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"","keywords":"Context (archaeology); Experience sampling method; Psychology; Episodic memory; Cognitive psychology; Computer science; Social psychology; Neuroscience; Biology; Cognition","score_opus":0.2564339788947656,"score_gpt":0.5143685006961392,"score_spread":0.25793452180137355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248787508","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.898129e-7,0.00037808466,0.0022771787,0.31362653,0.0011313059,0.002031243,0.6804782,0.000035075653,0.00004208121],"genre_scores_gemma":[0.00002488168,0.0002591641,0.005102897,0.018266257,0.00027149552,0.00053776783,0.97472954,0.000031762615,0.0007762203],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9881628,0.0010696743,0.00441881,0.0011836995,0.004706665,0.00045834132],"domain_scores_gemma":[0.96768224,0.0029125279,0.0042166314,0.0024705282,0.022196677,0.0005214125],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008658387,0.00064835715,0.0015985367,0.00080331275,0.0005413617,0.00042324778,0.0036306821,0.0007230575,0.0015289767],"category_scores_gemma":[0.10821499,0.0003898683,0.0012690203,0.0046296883,0.00046699398,0.00056857144,0.0005400421,0.00097582967,0.0002650533],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052172356,0.00027907963,0.000008796981,0.0014509861,0.00009585727,9.9173135e-8,0.00011359631,0.0000044878657,0.0000013028657,0.00040792587,0.98030835,0.01727732],"study_design_scores_gemma":[0.0013718939,0.00031107606,0.00075532973,0.0072839498,0.00018525457,0.000007040838,0.0001167711,0.00042440125,0.00002002177,0.00034096846,0.9887921,0.0003911601],"about_ca_topic_score_codex":0.000038692026,"about_ca_topic_score_gemma":0.000031299005,"teacher_disagreement_score":0.29536027,"about_ca_system_score_codex":0.00018245762,"about_ca_system_score_gemma":0.002350938,"threshold_uncertainty_score":0.99985534},"labels":[],"label_agreement":null},{"id":"W4248910069","doi":"10.3138/cjpe.223","title":"Meeting at the Crossroads: Interactivity, Technology, and Evaluation Utilization","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Interactivity; Relevance (law); Creativity; Scholarship; Negotiation; Knowledge management; Computer science; Citizen journalism; Sociology; Psychology; Multimedia; Political science; Social psychology; World Wide Web; Social science","score_opus":0.6056598746697802,"score_gpt":0.5861427794867573,"score_spread":0.019517095183022914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248910069","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9805477,0.002237303,0.0005592415,0.009485436,0.0009263626,0.0012784818,0.0000033034105,0.00001138831,0.004950753],"genre_scores_gemma":[0.9986797,0.000011783869,0.0007501861,0.00013864657,0.0001241553,0.0000823844,0.000011306314,0.00000824444,0.00019360946],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99494237,0.00097572175,0.0007771944,0.00021759333,0.002859743,0.00022737168],"domain_scores_gemma":[0.99160045,0.0002975314,0.000884451,0.00030742618,0.0065774745,0.00033266307],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04159735,0.00011604843,0.00017926242,0.0009271357,0.0004126967,0.0005898573,0.00036985334,0.00009946297,0.000707305],"category_scores_gemma":[0.012620152,0.00007514428,0.000057271413,0.0013269507,0.00023889996,0.0008793022,0.000049046677,0.00021284884,0.000057809713],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016027649,0.000021528136,0.0545489,0.0000014095791,0.00001641485,0.0000010574089,0.0015166182,0.003271767,0.00004577472,0.00027886173,0.003734655,0.936547],"study_design_scores_gemma":[0.0028282413,0.00085761957,0.100062706,0.00011892411,0.00030015619,0.00027640662,0.011883047,0.6374953,0.00093628507,0.06259459,0.18236184,0.00028487793],"about_ca_topic_score_codex":0.00027856225,"about_ca_topic_score_gemma":0.029745437,"teacher_disagreement_score":0.93626213,"about_ca_system_score_codex":0.00087029306,"about_ca_system_score_gemma":0.0044872016,"threshold_uncertainty_score":0.99569696},"labels":[],"label_agreement":null},{"id":"W4248983552","doi":"10.3233/wor-131634","title":"From the Editor","year":2013,"lang":"en","type":"editorial","venue":"Work","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.0917923449021064,"score_gpt":0.46327643658294804,"score_spread":0.3714840916808416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248983552","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010960594,0.00027310368,0.000099222474,0.002992004,0.98750263,0.00018284304,0.00007993675,0.000027708571,0.008732924],"genre_scores_gemma":[0.00015919792,0.000045826608,0.00021598268,0.00031049555,0.9554635,0.000055555724,0.0001376629,0.000014379693,0.0435974],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9935694,0.0002759738,0.000524994,0.00043333418,0.0049979053,0.00019839345],"domain_scores_gemma":[0.9852366,0.0124649685,0.00037598517,0.0011876447,0.00066051324,0.00007429768],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0031254732,0.00017742666,0.00027388547,0.000051492043,0.00020838919,0.00082116015,0.0017625593,0.00043716803,0.021639666],"category_scores_gemma":[0.005958989,0.000086036525,0.00012852618,0.00045872777,0.00007189737,0.00017165231,0.00018923059,0.00068794074,0.029386697],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000590015,0.000007250223,0.00022233273,3.4876115e-7,0.000011322147,2.1738782e-7,0.00025845988,0.000007703677,2.190231e-7,0.000010799492,0.987986,0.011489414],"study_design_scores_gemma":[0.000117885924,0.000013236704,0.0008544833,0.000035027544,0.00001363972,1.3470843e-8,0.00019808178,0.000039457173,9.228889e-7,0.0039541307,0.9946514,0.00012174114],"about_ca_topic_score_codex":0.00016442842,"about_ca_topic_score_gemma":0.000056330085,"teacher_disagreement_score":0.034864474,"about_ca_system_score_codex":0.00004093129,"about_ca_system_score_gemma":0.0005107814,"threshold_uncertainty_score":0.97925466},"labels":[],"label_agreement":null},{"id":"W4249000756","doi":"10.1002/ev.220","title":"Editor's notes","year":2007,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Citation; Library science; Computer science; World Wide Web","score_opus":0.2516694502734112,"score_gpt":0.5602664481446863,"score_spread":0.3085969978712751,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4249000756","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09408283,0.0003643102,0.78037757,0.008008094,0.03957959,0.0023888242,0.000019443743,0.00026195502,0.0749174],"genre_scores_gemma":[0.9634696,0.000016384964,0.012544029,0.00044022384,0.0112263,0.00013915423,0.000061683124,0.000018947874,0.012083666],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99644333,0.00011313596,0.0005797027,0.00033679596,0.002305403,0.00022162122],"domain_scores_gemma":[0.99552995,0.0022052699,0.00021769461,0.00037464246,0.0015481065,0.00012431819],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017940685,0.00010065,0.00013062023,0.0004196514,0.00038106207,0.00017164854,0.00021068913,0.00008040529,0.002860931],"category_scores_gemma":[0.0075505897,0.00008242649,0.000120734585,0.000900167,0.000026114512,0.0005144787,0.000019891539,0.00007535439,0.0005750006],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037853293,0.000046949368,0.0036393807,0.0000011029562,0.000010891697,3.572027e-8,0.00033746337,0.0011076169,0.000579137,0.0014145261,0.15451081,0.83831424],"study_design_scores_gemma":[0.00127118,0.00011762092,0.06442342,0.000006218946,0.0000543384,0.0000020340801,0.0003828021,0.042939857,0.0039025382,0.04095733,0.8457961,0.00014657092],"about_ca_topic_score_codex":0.000059401827,"about_ca_topic_score_gemma":0.000854121,"teacher_disagreement_score":0.8693868,"about_ca_system_score_codex":0.00018842024,"about_ca_system_score_gemma":0.00048747126,"threshold_uncertainty_score":0.9980506},"labels":[],"label_agreement":null},{"id":"W4249478526","doi":"10.1080/13538322.2018.1440492","title":"Erratum","year":2018,"lang":"en","type":"erratum","venue":"Quality in Higher Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Higher education; Political science; Sociology; Psychology; Law","score_opus":0.4130119189687369,"score_gpt":0.5855444020811778,"score_spread":0.17253248311244085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4249478526","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002532081,0.00064547226,0.000013007249,0.015500161,0.19827437,0.0003289299,0.000021856273,0.000041249772,0.78264284],"genre_scores_gemma":[0.022143418,0.00007844957,0.00024885766,0.0029659069,0.006300525,0.00012627547,0.0005387517,0.0000233995,0.9675744],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99347913,0.001062038,0.00158219,0.00079246546,0.0027685952,0.00031555956],"domain_scores_gemma":[0.996013,0.00046191993,0.0009087545,0.0014327049,0.0010587536,0.00012486277],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008346676,0.00027931685,0.0005067299,0.00069830054,0.000120873476,0.00041690003,0.0010373016,0.0005805144,0.034569502],"category_scores_gemma":[0.00096693856,0.00022931509,0.00014019995,0.0012695573,0.000117846495,0.00045775867,0.00010114561,0.0007444182,0.0057158065],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008324758,0.00019691476,0.005014621,0.000025990612,0.0000059528993,1.4058352e-7,0.0006404467,0.0000018105465,0.0000027028047,0.008664072,0.97915137,0.0062876823],"study_design_scores_gemma":[0.00009703011,0.000029806002,0.21151996,0.000071069575,0.0000067546193,4.0730768e-7,0.00034706123,0.000027306729,0.000002043862,0.051761463,0.7359169,0.00022019749],"about_ca_topic_score_codex":0.00030957547,"about_ca_topic_score_gemma":0.00053757353,"teacher_disagreement_score":0.24323444,"about_ca_system_score_codex":0.00042970153,"about_ca_system_score_gemma":0.0038115159,"threshold_uncertainty_score":0.99505836},"labels":[],"label_agreement":null},{"id":"W4249543881","doi":"10.3138/cjpe.69771","title":"Reflective Practice: Moving Intention into Action","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reflective practice; Leverage (statistics); Pillar; Action (physics); Reflection (computer programming); Psychology; Embodied cognition; Engineering ethics; Knowledge management; Pedagogy; Computer science; Artificial intelligence; Engineering","score_opus":0.5098205725321647,"score_gpt":0.6235932080024176,"score_spread":0.11377263547025285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4249543881","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.858048,0.0029471102,0.043435615,0.0379169,0.008876205,0.0020937643,0.000005813994,0.000043591514,0.046632968],"genre_scores_gemma":[0.9776795,0.000032594606,0.02118932,0.0004386728,0.00023815031,0.000035247347,0.000014660671,0.000008710247,0.00036317486],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99517524,0.001210189,0.00086611457,0.00022301517,0.0023178898,0.00020753415],"domain_scores_gemma":[0.98600626,0.00038160352,0.0009453619,0.0002573033,0.0120614115,0.00034806898],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016461248,0.00009914036,0.00018391569,0.00060372846,0.00030576135,0.00065793254,0.00023803691,0.00008680361,0.0024139816],"category_scores_gemma":[0.02066719,0.00008422106,0.00013548815,0.0012143794,0.000053934138,0.0019951377,0.000014471141,0.00029145804,0.00011901576],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023355049,0.000049014878,0.0037412047,0.000003378782,0.00003845484,0.000017516506,0.0017686889,0.0009949646,0.0006885534,0.00062101864,0.0021628896,0.98989093],"study_design_scores_gemma":[0.002963071,0.0015998356,0.13563521,0.00024248453,0.0005764498,0.0009904518,0.058454666,0.12028977,0.0057984437,0.12203936,0.550877,0.0005332483],"about_ca_topic_score_codex":0.0005946538,"about_ca_topic_score_gemma":0.03466982,"teacher_disagreement_score":0.9893577,"about_ca_system_score_codex":0.0010191383,"about_ca_system_score_gemma":0.008718637,"threshold_uncertainty_score":0.99849796},"labels":[],"label_agreement":null},{"id":"W4249544226","doi":"10.1007/978-1-4614-6170-8_100690","title":"Validity","year":2014,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Psychology","score_opus":0.49774925009705934,"score_gpt":0.5161981313415913,"score_spread":0.01844888124453198,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4249544226","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000018593257,0.000014316462,0.009893276,0.0010339649,0.0007009155,0.00010546414,0.0000062459394,0.000041172723,0.98818606],"genre_scores_gemma":[0.007031939,0.000031706368,0.00052690704,0.0015162188,0.00030252602,0.0000025134073,0.000011434214,0.000012926694,0.9905638],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965742,0.000043526936,0.0005553185,0.00037816534,0.0023350578,0.00011368531],"domain_scores_gemma":[0.99777883,0.00065509405,0.00028524085,0.00078627246,0.00040440285,0.00009014277],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0041501867,0.00016349414,0.0003007584,0.00018888284,0.00007911678,0.00017202695,0.000549354,0.00017795333,0.17156628],"category_scores_gemma":[0.0002721143,0.00010321117,0.00016951056,0.000029641333,0.000050327068,0.00007649322,0.000105696345,0.00018027627,0.04257694],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020664645,0.0000020371479,0.00009830156,0.00000138832,0.0000043143996,5.633106e-7,0.000015305253,0.000007819217,8.073381e-7,0.6504511,0.28032425,0.069092035],"study_design_scores_gemma":[0.000060556118,0.00003244285,0.00016983513,0.000006790622,0.000006870156,0.0000012539545,0.000004081158,0.00059366063,0.0000072976104,0.22344494,0.77555525,0.000117025156],"about_ca_topic_score_codex":0.0000024682963,"about_ca_topic_score_gemma":0.00004118518,"teacher_disagreement_score":0.49523097,"about_ca_system_score_codex":0.000034041703,"about_ca_system_score_gemma":0.00015175375,"threshold_uncertainty_score":0.9581685},"labels":[],"label_agreement":null},{"id":"W4250159053","doi":"10.1007/bf03403553","title":"Reporting on Innovative Public Health Interventions","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Public Health","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychological intervention; Public health interventions; Public health; Medicine; Nursing","score_opus":0.7120059725864722,"score_gpt":0.5890293855043884,"score_spread":0.12297658708208381,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4250159053","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28448576,0.0014008214,0.051044814,0.6123486,0.0041951835,0.0005558321,0.00004382066,0.000022222564,0.04590291],"genre_scores_gemma":[0.9821894,0.00003149885,0.0017114648,0.014674601,0.00012023936,0.0000038017067,0.000005949094,0.00001115297,0.0012518526],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99014205,0.0019986173,0.005065844,0.00027159098,0.0015499804,0.00097192224],"domain_scores_gemma":[0.9847507,0.00042670243,0.0077996184,0.0004547202,0.0032668316,0.0033014358],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09647795,0.00013194185,0.0005460151,0.0021942663,0.000677327,0.00066958845,0.00052067934,0.000052887062,0.0031015514],"category_scores_gemma":[0.05197626,0.00010141269,0.0001972074,0.0030673412,0.00009504476,0.0008890195,0.000011624369,0.00054059667,0.00010051709],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014996352,0.00012134375,0.18019187,0.000029782774,0.00005030942,0.000028235943,0.0063790423,0.00005770452,8.719723e-7,0.1747894,0.13951594,0.498834],"study_design_scores_gemma":[0.00041026899,0.0007527135,0.13273695,0.00012453055,9.778256e-7,0.00017827429,0.009512924,0.00007200612,0.0000020728296,0.0032161279,0.8528791,0.00011405633],"about_ca_topic_score_codex":0.0017708756,"about_ca_topic_score_gemma":0.046147455,"teacher_disagreement_score":0.7133632,"about_ca_system_score_codex":0.0017214566,"about_ca_system_score_gemma":0.07255276,"threshold_uncertainty_score":0.99780977},"labels":[],"label_agreement":null},{"id":"W4250574314","doi":"10.12968/ijtr.2008.15.12.31815","title":"Books","year":2008,"lang":"en","type":"article","venue":"International Journal of Therapy and Rehabilitation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Perspective (graphical); Occupational therapy; Sociology; Medical education; Psychology; Library science; Medicine; Visual arts; Art; Computer science; Physical therapy","score_opus":0.1718490594901102,"score_gpt":0.4847159553644202,"score_spread":0.31286689587431,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4250574314","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9850767,0.0003075481,0.0013777119,0.010482443,0.00096396654,0.0000488966,0.0000011768813,0.0000033368622,0.0017382137],"genre_scores_gemma":[0.9944124,0.0005625381,0.0036944468,0.00047457337,0.00019644333,0.0000012588707,4.9616943e-7,0.0000024382832,0.0006554072],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99798936,0.00012401753,0.00051970716,0.00007909897,0.0012425237,0.0000452869],"domain_scores_gemma":[0.9972687,0.00096466485,0.00034821933,0.00007705731,0.0013003253,0.00004102811],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021008188,0.000046066278,0.00010235649,0.0002689002,0.00006338963,0.000054515516,0.000256736,0.000024531282,0.00036845135],"category_scores_gemma":[0.0008819216,0.000028622448,0.000087716195,0.00008294862,0.000097758,0.00049016415,0.000014550157,0.00007291755,0.000016224627],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008533136,0.00025913113,0.2374529,0.0000018654325,0.00013462288,0.000018019291,0.015343481,0.00078815204,0.0037420648,0.009534461,0.017994056,0.7138779],"study_design_scores_gemma":[0.0019016042,0.0008926401,0.72724986,0.000025101763,0.00000312473,0.00029486162,0.0013319866,0.0012129161,0.0004983853,0.04825792,0.21823847,0.0000931324],"about_ca_topic_score_codex":0.0000032088988,"about_ca_topic_score_gemma":0.0000016914591,"teacher_disagreement_score":0.7137848,"about_ca_system_score_codex":0.00002876797,"about_ca_system_score_gemma":0.00009470151,"threshold_uncertainty_score":0.4034284},"labels":[],"label_agreement":null},{"id":"W4250786345","doi":"10.3138/cjpe.30.3.06","title":"A Cross-cultural Evaluation Conversation in India: Benefits, Challenges, and Lessons Learned","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Conversation; Cross-cultural; Work (physics); Bridging (networking); Sociology; Principal (computer security); Public relations; Political science; Medical education; Psychology; Medicine; Engineering; Computer science","score_opus":0.5494404661293435,"score_gpt":0.5595244125498549,"score_spread":0.010083946420511358,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4250786345","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.973059,0.0050137946,0.00006168285,0.018076546,0.00060410006,0.0011369643,0.000010086629,0.000007657344,0.0020301577],"genre_scores_gemma":[0.99850947,0.0007079664,0.0003946696,0.00008094495,0.00012724916,0.00009711146,0.000010397466,0.000008545968,0.000063646505],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9950272,0.00091152586,0.0009553628,0.0003077742,0.0025011771,0.0002969867],"domain_scores_gemma":[0.99377984,0.00037510603,0.00072996825,0.00023686662,0.004516769,0.00036147237],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.027055254,0.00013924639,0.00023970848,0.00086799153,0.000142776,0.00040673622,0.00028370434,0.00013650632,0.0014605323],"category_scores_gemma":[0.006925618,0.00008966424,0.00007317548,0.00045198976,0.00017043266,0.0019196545,0.000015205644,0.00016410294,0.00005350037],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021217293,0.000020436719,0.03744981,0.0000028842508,0.000012194109,0.000001676243,0.002248701,0.0003410813,0.0000537307,0.0018979488,0.00008735935,0.957863],"study_design_scores_gemma":[0.0030984376,0.00032132646,0.95409214,0.00011907395,0.000053431584,0.000029989984,0.0019524719,0.014114902,0.00007980914,0.018248389,0.007740063,0.00014997146],"about_ca_topic_score_codex":0.00022566979,"about_ca_topic_score_gemma":0.01719881,"teacher_disagreement_score":0.957713,"about_ca_system_score_codex":0.00078422576,"about_ca_system_score_gemma":0.0033905292,"threshold_uncertainty_score":0.9994523},"labels":[],"label_agreement":null},{"id":"W4250811760","doi":"10.1093/ww/9780199540884.013.18975","title":"Harcourt, Michael Franklin, (born 6 Jan. 1943), Associate Director, Continuing Studies Centre for Sustainability, University of British Columbia, since 2009; Premier of British Columbia, 1991–96","year":2007,"lang":"en","type":"reference-entry","venue":"Who's Who","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Columbia university; Library science; Management; Sustainability; Art history; Art; Media studies; Sociology; Computer science; Economics; Biology","score_opus":0.047427103676175045,"score_gpt":0.35556492896617525,"score_spread":0.3081378252900002,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4250811760","genre_codex":"empirical","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88493735,0.033810128,0.00050360156,0.0007879567,0.005150174,0.0063518034,0.0325505,0.0001698905,0.035738572],"genre_scores_gemma":[0.07411868,0.033353563,0.00073945173,0.00015047674,0.00044284677,0.000021870901,0.0005237978,0.000079199664,0.8905701],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9912471,0.0006426061,0.0020885356,0.0014660493,0.003499961,0.0010557185],"domain_scores_gemma":[0.9842381,0.002814621,0.0026646254,0.0009747185,0.009019915,0.00028801727],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007620744,0.00037480137,0.0025392987,0.00022428,0.0004752445,0.0007929412,0.0015951169,0.0008203056,0.001441238],"category_scores_gemma":[0.0037590053,0.0007061131,0.0008135799,0.0010922428,0.00085645454,0.00059980917,0.0007037374,0.00072555244,0.000016923892],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043359305,0.00027030404,0.16709903,0.00082803617,0.0003437001,0.000032066735,0.0011399649,0.000011705706,0.0000012741102,0.000004529645,0.7064747,0.12375133],"study_design_scores_gemma":[0.0028865826,0.00024206488,0.22176631,0.0047171717,0.00041499417,0.000010615669,0.013826917,0.0002940146,0.0000042257097,0.0032948942,0.75168777,0.0008544507],"about_ca_topic_score_codex":0.23139921,"about_ca_topic_score_gemma":0.8704183,"teacher_disagreement_score":0.8548315,"about_ca_system_score_codex":0.0011435065,"about_ca_system_score_gemma":0.0014257703,"threshold_uncertainty_score":0.999539},"labels":[],"label_agreement":null},{"id":"W4251001152","doi":"10.1007/978-3-319-22011-6_6","title":"Practically Speaking","year":2015,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Nipissing University","funders":"","keywords":"Usability; Computer science; Engineering ethics; Engineering; Human–computer interaction","score_opus":0.5994238941184287,"score_gpt":0.5697271120531947,"score_spread":0.029696782065233962,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4251001152","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000042476036,0.00009453714,0.0021382065,0.002679555,0.000605887,0.00014363535,0.000004561883,0.00004266891,0.9942867],"genre_scores_gemma":[0.0020141497,0.000026301275,0.0026529364,0.0009956696,0.00029725314,0.0000021184328,0.000008732467,0.00001774661,0.9939851],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99504954,0.000036278525,0.0006657308,0.0004050747,0.003700455,0.00014294466],"domain_scores_gemma":[0.9968734,0.0006391473,0.00042069727,0.00068755023,0.0012236603,0.00015557044],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00546153,0.00017809945,0.00029755005,0.00022947048,0.00006103006,0.00029586264,0.00051787955,0.00018468105,0.12582198],"category_scores_gemma":[0.001226428,0.000113034694,0.00011241268,0.000048838257,0.00005409445,0.0003539658,0.00015884044,0.00028552953,0.034741983],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000075362414,0.0000056405047,0.00002832933,0.0000010285731,0.000012336571,0.0000059602776,0.000060155024,0.000016338925,0.0000011736529,0.67102206,0.22073963,0.108099826],"study_design_scores_gemma":[0.00008997454,0.000038389797,0.000038283935,0.000012345359,0.000011189873,0.0000073393753,0.000041731488,0.00054292066,0.0000014484324,0.22123,0.77785546,0.00013093438],"about_ca_topic_score_codex":0.000004713791,"about_ca_topic_score_gemma":0.00008333545,"teacher_disagreement_score":0.5571158,"about_ca_system_score_codex":0.00008859044,"about_ca_system_score_gemma":0.0006784567,"threshold_uncertainty_score":0.96600956},"labels":[],"label_agreement":null},{"id":"W4251075138","doi":"10.1097/01.htr.0000281834.69849.d2","title":"From the Editor","year":2007,"lang":"en","type":"article","venue":"Journal of Head Trauma Rehabilitation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Audience measurement; Event (particle physics); Public policy; Public relations; Psychology; Political science; History; Law","score_opus":0.11563901062939348,"score_gpt":0.5020204340886015,"score_spread":0.38638142345920806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4251075138","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9658251,0.00013033475,0.008257042,0.019276878,0.0051387497,0.00010272466,0.000002976376,0.0000046579144,0.0012615301],"genre_scores_gemma":[0.9859706,0.0000034904053,0.008273477,0.0003712987,0.005269015,9.885227e-7,9.1562475e-7,0.0000039206197,0.00010626311],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9963694,0.0002638494,0.0010928476,0.00011141207,0.0020435085,0.00011896893],"domain_scores_gemma":[0.9873308,0.010683743,0.0005868735,0.00025602884,0.001068547,0.0000739931],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016302032,0.00006485875,0.00015938446,0.00015000018,0.00011544433,0.00010966836,0.00037703622,0.000046138233,0.0006954389],"category_scores_gemma":[0.005021388,0.000033026496,0.00015788998,0.00038135692,0.00007518868,0.00058240385,0.000012959007,0.00019385372,0.00012786272],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003500451,0.00020403118,0.11958779,0.000003114455,0.000028042516,0.0000027509604,0.015007299,0.00053992355,0.0014975369,0.0010428114,0.20298058,0.6587561],"study_design_scores_gemma":[0.00051606155,0.0004478353,0.7808367,0.000021307922,0.00000969854,0.000004986673,0.009635853,0.00030502537,0.000205518,0.02626267,0.18171045,0.000043894393],"about_ca_topic_score_codex":0.000027041917,"about_ca_topic_score_gemma":0.00015160773,"teacher_disagreement_score":0.6612489,"about_ca_system_score_codex":0.00008394167,"about_ca_system_score_gemma":0.00012029797,"threshold_uncertainty_score":0.7614568},"labels":[],"label_agreement":null},{"id":"W4251204419","doi":"10.4018/978-1-4666-4157-0.ch014","title":"Multiple Solitudes","year":2013,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Affordance; Curriculum; Christian ministry; Political science; Public relations; Knowledge management; Sociology; Pedagogy; Psychology; Computer science","score_opus":0.15937407615003796,"score_gpt":0.4238951385868588,"score_spread":0.26452106243682083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4251204419","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003673036,0.00015745555,0.00028262747,0.00024137345,0.0009191762,0.00042489945,0.00009268819,0.00008642061,0.99742806],"genre_scores_gemma":[0.27895626,0.000005385608,0.0007787123,0.0011927806,0.0003124573,0.000025525469,0.0000046934765,0.000022023345,0.71870214],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99562025,0.000045265275,0.00086830603,0.0006472891,0.0024919964,0.00032689245],"domain_scores_gemma":[0.9973646,0.00031520246,0.00047087861,0.0009997102,0.00062629336,0.00022331096],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0010334603,0.0003690325,0.0005153459,0.00012527991,0.00015848665,0.00047680942,0.0009188307,0.00034141346,0.00801663],"category_scores_gemma":[0.00025409288,0.0002712116,0.0002948021,0.000029437098,0.00012887067,0.00015006574,0.0002521008,0.00025034766,0.026107235],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009383117,0.000006384137,0.0002914759,0.0000039503443,0.000031546813,0.000004994204,0.000046200843,0.000012006423,0.0000064903634,0.9021613,0.05145595,0.04597032],"study_design_scores_gemma":[0.000232314,0.000046309488,0.0005783752,0.00003672131,0.000017276296,0.000007493148,0.000024740679,0.00040260822,0.00001348012,0.5530463,0.44533756,0.00025685568],"about_ca_topic_score_codex":0.00006237173,"about_ca_topic_score_gemma":0.0002545569,"teacher_disagreement_score":0.39388162,"about_ca_system_score_codex":0.0002009401,"about_ca_system_score_gemma":0.00045070346,"threshold_uncertainty_score":0.999974},"labels":[],"label_agreement":null},{"id":"W4251780359","doi":"10.22163/fteval.2019.385","title":"Rethinking Research Impact Assessment: A Multidimensional Approach","year":2019,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact","funders":"Linköpings Universitet; University of Twente; Università degli Studi di Cagliari","keywords":"Reflexivity; Adaptability; Computer science; Management science; Perspective (graphical); Element (criminal law); Impact assessment; Identity (music); Engineering ethics; Data science; Sociology; Political science; Engineering; Social science; Artificial intelligence","score_opus":0.528681572127807,"score_gpt":0.6279210063214864,"score_spread":0.09923943419367942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4251780359","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6238805,0.00001614697,0.0029535647,0.00069484353,0.00020852515,0.00034124902,0.0000019253766,0.000033894434,0.37186936],"genre_scores_gemma":[0.94607294,0.000004797213,0.030294728,0.00029717953,0.00006599964,0.000018129278,0.000012706897,0.000009851726,0.023223678],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9913153,0.0008382262,0.00054262596,0.0005898539,0.006275473,0.00043851315],"domain_scores_gemma":[0.99564296,0.0020538257,0.000119720025,0.0008624718,0.0011668442,0.00015416776],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.028822638,0.00012674698,0.00023792786,0.0005369145,0.0002865381,0.00034591378,0.0006250604,0.00009375427,0.027186358],"category_scores_gemma":[0.00062812516,0.00007357996,0.00014070359,0.0013296461,0.00007482803,0.0006658584,0.00028335335,0.00053064397,0.0058435197],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010251236,0.00053117453,0.6989283,0.000014517863,0.000071204035,0.000003964183,0.0050047324,0.011125556,0.0072701047,0.18851921,0.054212585,0.034216106],"study_design_scores_gemma":[0.00094287936,0.000260314,0.34266207,0.000015309799,0.0000031209267,0.0000117949585,0.002285233,0.5945083,0.0002158003,0.042630035,0.0162461,0.00021904393],"about_ca_topic_score_codex":0.00008080823,"about_ca_topic_score_gemma":0.00001094842,"teacher_disagreement_score":0.5833827,"about_ca_system_score_codex":0.00018712426,"about_ca_system_score_gemma":0.0007693944,"threshold_uncertainty_score":0.9989408},"labels":[],"label_agreement":null},{"id":"W4251909684","doi":"10.1177/160940690200100403","title":"Symposium Introduction - Issues of Validity: Behavioral Concepts, Their Derivation and Interpretation","year":2002,"lang":"en","type":"article","venue":"International Journal of Qualitative Methods","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Interpretation (philosophy); Phenomenon; Frame (networking); Vulnerability (computing); Psychology; Epistemology; Computer science; Subject (documents); Management science; Engineering; Computer security","score_opus":0.7944162445385775,"score_gpt":0.7170468259051439,"score_spread":0.0773694186334336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4251909684","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5721649,0.000497499,0.40548283,0.018707206,0.0024150282,0.00011657894,0.00001921801,0.000007699347,0.0005890832],"genre_scores_gemma":[0.89548594,0.00024106645,0.10318929,0.00015290284,0.0004728549,0.0000034793266,0.0000053278195,0.000006698761,0.0004424612],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9929509,0.003945468,0.0013469908,0.00018883188,0.0014776648,0.00009012984],"domain_scores_gemma":[0.9923512,0.0024167704,0.0015487683,0.00014278163,0.0034820456,0.000058471443],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017266694,0.00011790327,0.00033307634,0.0005170733,0.000050037128,0.00013450113,0.00040495195,0.000052269184,0.0011753192],"category_scores_gemma":[0.0032310984,0.00008419929,0.0001313761,0.00027279046,0.00020446857,0.0011347105,0.00005948837,0.00017029628,0.000009117911],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002889731,0.00029901956,0.002934121,0.00000963372,0.00018745648,0.0000024058656,0.20024063,0.000494366,0.044481136,0.008222645,0.004948125,0.7378915],"study_design_scores_gemma":[0.0050554425,0.0043581952,0.024137616,0.0003209374,0.00023195602,0.0003244843,0.23531577,0.09720136,0.2755023,0.24764611,0.109087095,0.0008187473],"about_ca_topic_score_codex":0.000011635727,"about_ca_topic_score_gemma":0.0000032269961,"teacher_disagreement_score":0.73707277,"about_ca_system_score_codex":0.000086776185,"about_ca_system_score_gemma":0.000042984873,"threshold_uncertainty_score":0.99973774},"labels":[],"label_agreement":null},{"id":"W4252221244","doi":"10.1007/978-1-4614-6170-8_110007","title":"Impact","year":2014,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science","score_opus":0.32394943490841294,"score_gpt":0.5475407482924535,"score_spread":0.22359131338404054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4252221244","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004967189,0.00003440358,0.0037922305,0.00048347627,0.00035221415,0.00010097238,0.000008053797,0.00003247597,0.9951465],"genre_scores_gemma":[0.017500829,0.000026600019,0.00024202,0.0007282459,0.00022768161,0.0000017619756,0.000012165257,0.0000143634215,0.98124635],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99698687,0.000024006762,0.0005076692,0.0003283838,0.0020275332,0.00012554218],"domain_scores_gemma":[0.9980879,0.0004290499,0.000268685,0.0007358684,0.00037043568,0.000108054635],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0024237467,0.0001779893,0.0003040543,0.0002521989,0.000059262493,0.00019298213,0.0004921913,0.0001602451,0.26233056],"category_scores_gemma":[0.00017159134,0.000098138575,0.0002565287,0.000033762964,0.00004022761,0.00008355753,0.00007700689,0.00016447136,0.04203778],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004830181,0.0000028478628,0.00037999998,9.231127e-7,0.000019204534,7.5830417e-7,0.000022632687,0.000036066747,0.0000015524514,0.45653635,0.32921648,0.21377835],"study_design_scores_gemma":[0.000086463064,0.000072903946,0.0013649862,0.000007945871,0.0000071306686,0.0000024442988,0.000003343721,0.0008923847,0.0000018020553,0.12215732,0.875268,0.00013529252],"about_ca_topic_score_codex":0.000005380861,"about_ca_topic_score_gemma":0.00003086833,"teacher_disagreement_score":0.5460515,"about_ca_system_score_codex":0.00005433527,"about_ca_system_score_gemma":0.00022265578,"threshold_uncertainty_score":0.9587081},"labels":[],"label_agreement":null},{"id":"W4252541937","doi":"10.2307/j.ctt22rbkbb.7","title":"The policy analysis profession in Canada","year":2018,"lang":"en","type":"book-chapter","venue":"Bristol University Press eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Public administration","score_opus":0.116917558458376,"score_gpt":0.37507616987112125,"score_spread":0.25815861141274526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4252541937","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001151208,0.000047948666,0.00008481392,0.00046292463,0.00024235544,0.00028084373,0.00006406772,0.000012508463,0.9976533],"genre_scores_gemma":[0.03863741,0.000058007663,0.000023810257,0.00013450421,0.000081106504,7.236553e-7,0.000011512187,0.000009214133,0.9610437],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970284,0.00018050484,0.0004284151,0.00044565662,0.0016743629,0.00024262756],"domain_scores_gemma":[0.9975756,0.00045981695,0.0005260721,0.0008765744,0.0004443308,0.000117611315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011584109,0.00019985887,0.00037447351,0.0005640031,0.00043686983,0.00010443449,0.001238564,0.00014085247,0.0004137625],"category_scores_gemma":[0.00009596051,0.00014492197,0.00016979354,0.000118106094,0.00016603598,0.00009339703,0.00038314503,0.0003097354,0.000040205607],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045198918,0.000023674227,0.003377935,0.000023460325,0.0009516639,0.00021771535,0.0022884598,0.000497137,0.000003911943,0.5419742,0.3181495,0.13204034],"study_design_scores_gemma":[0.00020646975,0.000013364112,0.0017506356,0.000024318853,0.000120575285,7.757638e-7,0.0005778923,0.0014238656,0.0000055508845,0.0017042019,0.9939935,0.00017880385],"about_ca_topic_score_codex":0.68780184,"about_ca_topic_score_gemma":0.9668291,"teacher_disagreement_score":0.675844,"about_ca_system_score_codex":0.0014379736,"about_ca_system_score_gemma":0.005010248,"threshold_uncertainty_score":0.88879657},"labels":[],"label_agreement":null},{"id":"W4252641074","doi":"10.12688/f1000research.12496.1","title":"The peer review process for awarding funds to international science research consortia: a qualitative developmental evaluation","year":2017,"lang":"en","type":"preprint","venue":"F1000Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Royal Society; Department for International Development; Department for International Development, UK Government","keywords":"CLARITY; Peer review; Process (computing); Quality (philosophy); Medical education; Medicine; Political science; Computer science","score_opus":0.9180082488147815,"score_gpt":0.8021655283270901,"score_spread":0.1158427204876914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4252641074","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08802484,0.0064529427,0.007762427,0.5615396,0.008316027,0.032081544,0.00075797626,0.00012419261,0.29494047],"genre_scores_gemma":[0.9246739,0.0018903887,0.0036283901,0.0007365517,0.0006760808,0.012083749,0.00021667239,0.00005093228,0.05604335],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9426806,0.0030501368,0.0015640227,0.0018009862,0.0496932,0.0012110599],"domain_scores_gemma":[0.91753405,0.008907255,0.00061019824,0.0017387234,0.0707897,0.0004200708],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.41736072,0.0002658838,0.0004608952,0.0013432,0.0046909046,0.004748739,0.009065462,0.00014773979,0.0013948703],"category_scores_gemma":[0.2652054,0.00017121028,0.00017692038,0.0016098252,0.001583428,0.0007283565,0.0043503293,0.0013443717,0.0010208234],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003636909,0.00015099044,0.0022055402,0.0005329684,0.00015876623,0.0000027729448,0.029930083,0.00079179986,0.00034520062,0.008469685,0.50277585,0.4542727],"study_design_scores_gemma":[0.0009270688,0.00023109437,0.007944847,0.0027587407,0.00003760885,0.000008115677,0.04588548,0.06993639,0.0010762368,0.14078338,0.72980845,0.0006025579],"about_ca_topic_score_codex":0.00007494045,"about_ca_topic_score_gemma":0.00021977529,"teacher_disagreement_score":0.83664906,"about_ca_system_score_codex":0.001981843,"about_ca_system_score_gemma":0.022619195,"threshold_uncertainty_score":0.999757},"labels":[],"label_agreement":null},{"id":"W4253062526","doi":"10.12927/cjnl.2012.22800","title":"Evaluation Project: Introduction","year":2012,"lang":"en","type":"article","venue":"Nursing leadership","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Registered Nurses' Association of Ontario","funders":"","keywords":"Nursing; Process management; Nurse Administrator; Psychology; Business; Political science; Sociology; MEDLINE; Medicine","score_opus":0.7936560044787633,"score_gpt":0.556585236264709,"score_spread":0.23707076821405426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4253062526","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.532916,0.0029082731,0.020113772,0.17201763,0.021759538,0.0022209373,0.000004346131,0.00036968663,0.2476898],"genre_scores_gemma":[0.9936056,0.0000016698356,0.00096127,0.0003950574,0.0020222387,0.000026686528,0.00001053092,0.0000083813175,0.002968572],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9952067,0.0006751809,0.00034389575,0.00025369012,0.0031671368,0.0003533996],"domain_scores_gemma":[0.9985733,0.00019048266,0.00015566079,0.0003919586,0.0006121363,0.000076459015],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.01839689,0.000094566596,0.00011447924,0.00029102628,0.00017384875,0.00014513143,0.00020140945,0.00006812781,0.0026622834],"category_scores_gemma":[0.0022669386,0.00007381896,0.00005302319,0.00072237494,0.000084525214,0.0010643133,0.0000075001867,0.00014155605,0.001334498],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023664463,0.00018259486,0.007193494,0.000003402741,0.000008703206,4.154388e-8,0.014787846,0.00019093255,0.0009541632,0.0035554487,0.10627677,0.86682296],"study_design_scores_gemma":[0.0019562456,0.000305903,0.48102444,0.00012693569,0.00029075186,0.00006193693,0.115793996,0.07098386,0.0060225804,0.027228814,0.29539514,0.00080941163],"about_ca_topic_score_codex":0.00000373378,"about_ca_topic_score_gemma":0.0000029520509,"teacher_disagreement_score":0.8660135,"about_ca_system_score_codex":0.00030403511,"about_ca_system_score_gemma":0.00023414096,"threshold_uncertainty_score":0.99944305},"labels":[],"label_agreement":null},{"id":"W4253103282","doi":"10.1007/978-3-030-42091-8_125-1","title":"Evidence-Based Policy Development: National Adaptation Strategy and Plan of Action on Climate Change for Nigeria (NASPA-CCN)","year":2020,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Environment and Climate Change Canada","funders":"","keywords":"Mainstream; Action plan; Adaptation (eye); Climate change; Political science; Process (computing); Action (physics); Plan (archaeology); Policy development; Environmental planning; Economic growth; Public administration; Economics; Computer science; Geography; Psychology; Management; Ecology","score_opus":0.7688109637976317,"score_gpt":0.5218455617035601,"score_spread":0.24696540209407158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4253103282","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003611112,0.00045691727,0.017468132,0.01686785,0.0009569104,0.004169178,0.00067643716,0.00015374275,0.9556397],"genre_scores_gemma":[0.8882192,0.0011432079,0.0078285355,0.006458618,0.0014079286,0.00036306228,0.0007589331,0.000078476776,0.09374209],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99666613,0.00004551126,0.0007688736,0.00046331625,0.0019054367,0.00015074713],"domain_scores_gemma":[0.9970774,0.0011584826,0.0006921432,0.00016254744,0.0008111094,0.0000983295],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017861455,0.00023037846,0.00032932524,0.0006126784,0.00015346799,0.00013162532,0.00020600775,0.00017927622,0.0011999445],"category_scores_gemma":[0.00049579516,0.00018171725,0.000085383654,0.00011755049,0.000047330428,0.0004910142,0.000035831745,0.000118221134,0.00014679316],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007183729,0.000037231857,0.00022725984,0.00017449164,0.00005350788,6.31462e-7,0.0010183254,0.00087321125,0.00015748663,0.5502562,0.002461787,0.4440215],"study_design_scores_gemma":[0.005015913,0.0044069886,0.026864003,0.0033823757,0.000126571,0.000007434207,0.002621294,0.17166491,0.0047646062,0.20289283,0.5759269,0.0023261828],"about_ca_topic_score_codex":0.00001132344,"about_ca_topic_score_gemma":0.00024972565,"teacher_disagreement_score":0.88460803,"about_ca_system_score_codex":0.0001510643,"about_ca_system_score_gemma":0.0013519444,"threshold_uncertainty_score":0.9997131},"labels":[],"label_agreement":null},{"id":"W4253548485","doi":"10.1007/978-1-4939-7131-2_101416","title":"Validity","year":2018,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Psychology","score_opus":0.5582135193547928,"score_gpt":0.5341573531417813,"score_spread":0.024056166213011543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4253548485","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008185048,0.000015672198,0.001317665,0.0006438018,0.00091040833,0.00011538759,0.000011981285,0.000041230636,0.996862],"genre_scores_gemma":[0.0018909174,0.00003530652,0.0007230469,0.0010595529,0.0005018219,0.0000022513993,0.000010904672,0.000012679553,0.99576354],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99657136,0.00003081163,0.00053378835,0.00039809349,0.0023476712,0.00011824601],"domain_scores_gemma":[0.99781,0.0003981093,0.00026705908,0.00078823155,0.0006497128,0.000086859734],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0034177492,0.00016107428,0.00025527467,0.00019336895,0.00009216442,0.00018594743,0.00057277473,0.00018206229,0.5415599],"category_scores_gemma":[0.00022972046,0.000101276695,0.00015311467,0.00003804469,0.00009730498,0.00014992525,0.0001323423,0.00014492078,0.09452442],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004048161,0.0000044902017,0.00009560458,0.0000012031794,0.0000071353334,0.000001174501,0.000064777865,9.928053e-7,0.0000012157104,0.17646408,0.8020775,0.021277772],"study_design_scores_gemma":[0.000048658712,0.00004632291,0.00012354864,0.0000065605127,0.0000062747063,0.0000013542541,0.000011992531,0.00019388912,0.000014629948,0.29833215,0.70111096,0.00010367523],"about_ca_topic_score_codex":0.0000019824226,"about_ca_topic_score_gemma":0.000056986835,"teacher_disagreement_score":0.44703546,"about_ca_system_score_codex":0.000040659783,"about_ca_system_score_gemma":0.00022152992,"threshold_uncertainty_score":0.9061806},"labels":[],"label_agreement":null},{"id":"W4253838897","doi":"10.7202/1085881ar","title":"Considérations pour orienter la recherche future sur les groupes de discussion","year":2011,"lang":"fr","type":"article","venue":"Recherches qualitatives","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Political science; Humanities; Art","score_opus":0.9137355693239745,"score_gpt":0.6295302310285407,"score_spread":0.2842053382954338,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4253838897","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15372595,0.022966525,0.31151566,0.32659605,0.004828965,0.0012213576,0.00021384346,0.00027125655,0.17866038],"genre_scores_gemma":[0.10300263,0.004936634,0.5782133,0.0017662153,0.0012751047,0.00012048165,0.000030340081,0.000085285246,0.31057003],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95098263,0.04526041,0.0013060884,0.000692792,0.0011567816,0.0006013135],"domain_scores_gemma":[0.9628116,0.034242116,0.0006187484,0.0006352083,0.001339073,0.00035326593],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.062337663,0.00042895286,0.0005480695,0.00032561788,0.00028805708,0.0003080093,0.0007400904,0.0011082082,0.0067737116],"category_scores_gemma":[0.03203941,0.000270648,0.0003296706,0.0011042014,0.0006221537,0.0016767792,0.00014698118,0.0014883387,0.0010910424],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016074887,0.0007373935,0.0047714543,0.00008348308,0.00012983462,0.000014214273,0.44612348,0.000009714444,0.00066679285,0.123898335,0.017266845,0.4061377],"study_design_scores_gemma":[0.0009405127,0.00036626068,0.019652907,0.00039283364,0.00010561336,0.000028480406,0.23676765,0.0010331819,0.0014928146,0.39715573,0.34152138,0.0005426434],"about_ca_topic_score_codex":0.00037743268,"about_ca_topic_score_gemma":0.000833582,"teacher_disagreement_score":0.40559506,"about_ca_system_score_codex":0.00083128904,"about_ca_system_score_gemma":0.003038303,"threshold_uncertainty_score":0.99997455},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4254913236","doi":"10.47678/cjhe.v48i3.188165","title":"Provincial Oversight and University Autonomy in Canada: Findings of a Comparative Study of Canadian University Governance","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Higher Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université du Québec à Montréal; University of Toronto; University of Victoria","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Autonomy; Corporate governance; Higher education; Public administration; Order (exchange); Political science; Comparative case; State (computer science); Comparative research; Public relations; Sociology; Economic growth; Business; Economics; Social science; Law; Finance","score_opus":0.0852713448544082,"score_gpt":0.3585521696046582,"score_spread":0.27328082475025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4254913236","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99289614,0.00005187754,0.0000015296424,0.00094016106,0.00046193285,0.00012305593,0.00003972364,2.824385e-7,0.005485314],"genre_scores_gemma":[0.99776536,0.0000027731433,0.00006564898,0.00005565496,0.0000356758,5.517832e-8,9.0351233e-7,0.0000015334128,0.0020724018],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989982,0.00012656777,0.00029299487,0.000107740496,0.00034689685,0.0001275566],"domain_scores_gemma":[0.9983638,0.000072963914,0.0003913034,0.00011119347,0.00073215034,0.0003285702],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004915979,0.000059053677,0.00018916071,0.00080125895,0.00009793602,0.000011717045,0.0002842487,0.000025871164,0.00055989577],"category_scores_gemma":[0.000037987586,0.000058014808,0.00001854424,0.0009453908,0.0000913929,0.00034766854,0.0000096685335,0.00009040998,0.000001464727],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003005819,0.00003597573,0.97328365,0.0000024728201,0.000014489097,0.000008282626,0.007309493,0.000045031116,0.000008181733,0.0017996434,0.017019132,0.00044358283],"study_design_scores_gemma":[0.00036654115,0.00014320266,0.844031,0.000019599755,0.0000114607155,0.000002033785,0.01406854,0.000035715788,0.000028126819,0.000055264594,0.14119111,0.000047424535],"about_ca_topic_score_codex":0.995461,"about_ca_topic_score_gemma":0.999929,"teacher_disagreement_score":0.12925267,"about_ca_system_score_codex":0.0025946912,"about_ca_system_score_gemma":0.07239364,"threshold_uncertainty_score":0.932865},"labels":[],"label_agreement":null},{"id":"W4254951404","doi":"10.4095/301334","title":"Location of study inside Canada, same province or territory as province or territory of residence, 2006 (by census division)","year":2010,"lang":"en","type":"report","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Census; Residence; Geography; Division (mathematics); Demography; Population; Sociology","score_opus":0.1354028076157453,"score_gpt":0.45297593347271803,"score_spread":0.3175731258569727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4254951404","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7833676,0.0028908923,0.00091111107,0.0034333498,0.018475126,0.016928554,0.0022557026,0.0002785576,0.17145914],"genre_scores_gemma":[0.7358911,0.000137455,0.00060861325,0.00022938171,0.00035235085,0.00011658497,0.00009401898,0.000050333525,0.2625202],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9821076,0.0006155558,0.0035680362,0.0012613293,0.011970218,0.0004772593],"domain_scores_gemma":[0.9880153,0.0018700104,0.003396296,0.0019137536,0.0045210863,0.0002835763],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008565528,0.0005739298,0.0013520133,0.00066594547,0.00023151918,0.00015819263,0.0018779526,0.00046971248,0.002399266],"category_scores_gemma":[0.0061907475,0.00034602414,0.00013236917,0.0006883591,0.00032870544,0.00066517654,0.0004508991,0.0008318619,0.000040679985],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038376154,0.0010819518,0.080292426,0.00056268374,0.000105108564,0.000084591724,0.00023790085,0.00013252428,0.00043971243,0.000035696918,0.8637643,0.052879363],"study_design_scores_gemma":[0.0011432244,0.0019861746,0.26500034,0.0009967535,0.00014464023,0.00004582587,0.0040013324,0.0005430718,0.0022486423,0.00012943233,0.7228532,0.0009074026],"about_ca_topic_score_codex":0.7440809,"about_ca_topic_score_gemma":0.9818384,"teacher_disagreement_score":0.23775752,"about_ca_system_score_codex":0.0009246493,"about_ca_system_score_gemma":0.09508891,"threshold_uncertainty_score":0.99989915},"labels":[],"label_agreement":null},{"id":"W4255004666","doi":"10.3138/cjpe.30.3.05","title":"Decolonizing and Indigenizing Evaluation Practice in Africa: Toward African Relational Evaluation Approaches","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":103,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Indigenization; Decolonization; Sociology; African culture; Metaphor; Epistemology; African philosophy; Political science; Gender studies; Anthropology; Linguistics; Philosophy","score_opus":0.6556148384806202,"score_gpt":0.5116189627666728,"score_spread":0.14399587571394734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4255004666","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93572444,0.0052598123,0.004710685,0.02307783,0.0013497263,0.0057212277,0.000014383914,0.000021335934,0.024120536],"genre_scores_gemma":[0.9902479,0.000035872625,0.00904714,0.000078095865,0.00018292668,0.00032753038,0.000013662335,0.000015786844,0.00005107632],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9886178,0.0031119587,0.0015523541,0.0004511544,0.0058074305,0.00045933024],"domain_scores_gemma":[0.98957413,0.0019039495,0.0014756396,0.00030762915,0.0062951283,0.00044354345],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08925153,0.00019977007,0.0003175055,0.0016175024,0.0002873926,0.0004182764,0.0003562937,0.00016368974,0.0016030824],"category_scores_gemma":[0.03800416,0.0001420932,0.00009661925,0.0014030725,0.00014891039,0.002789038,0.000027711762,0.00026754424,0.00004579013],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004277796,0.00005646494,0.028917048,0.0000031277514,0.000033734024,0.0000028044396,0.007473428,0.0028450645,0.000048929254,0.0008893684,0.00033735912,0.9593499],"study_design_scores_gemma":[0.00613897,0.0008221081,0.5347691,0.0002531704,0.0006291003,0.00016237008,0.016303267,0.3467783,0.00010468415,0.05241629,0.041109595,0.0005130569],"about_ca_topic_score_codex":0.00022380236,"about_ca_topic_score_gemma":0.010278481,"teacher_disagreement_score":0.95883685,"about_ca_system_score_codex":0.0020036304,"about_ca_system_score_gemma":0.01060369,"threshold_uncertainty_score":0.9993096},"labels":[],"label_agreement":null},{"id":"W4255696005","doi":"10.1037/e734412011-067","title":"Early intervention and policy in Canada","year":2009,"lang":"en","type":"dataset","venue":"PsycEXTRA Dataset","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Intervention (counseling); Political science; Psychology; Psychiatry","score_opus":0.12234785448920096,"score_gpt":0.4983793799751946,"score_spread":0.3760315254859936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4255696005","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012800918,0.00018170281,0.000008439338,0.0012704749,0.0003356519,0.00021721388,0.99662954,0.000003736211,0.00007316954],"genre_scores_gemma":[0.0017152606,0.00029816377,0.000037576556,0.0015710064,0.00014333523,0.000016535996,0.9961423,0.0000051519396,0.00007064342],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.996156,0.0002794344,0.0009586909,0.0006115194,0.0016776201,0.0003167798],"domain_scores_gemma":[0.99794006,0.0002845557,0.00039224527,0.0011511213,0.000065531174,0.0001664927],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0022915462,0.0002480671,0.00038999415,0.0006458584,0.00006977085,0.00030646232,0.000994934,0.00011756063,0.0024673506],"category_scores_gemma":[0.0005989653,0.00020157921,0.000042965727,0.00069324666,0.000039582555,0.0004109119,0.00017298645,0.0003908846,0.00040776178],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001705204,0.000041674808,0.00078813115,0.000012808674,0.0000062618187,0.00001781704,0.000007691501,0.000007857343,2.300699e-7,0.000012353123,0.9670802,0.032007925],"study_design_scores_gemma":[0.00044131666,0.000058909904,0.056944568,0.000052010113,0.000011348516,0.00000975596,0.000060300987,0.0000874961,8.079488e-7,0.00075669645,0.94137585,0.0002009666],"about_ca_topic_score_codex":0.94463325,"about_ca_topic_score_gemma":0.9914138,"teacher_disagreement_score":0.056156438,"about_ca_system_score_codex":0.0003632938,"about_ca_system_score_gemma":0.0014157979,"threshold_uncertainty_score":0.99844456},"labels":[],"label_agreement":null},{"id":"W4255735068","doi":"10.35648/20.500.12413/11781/ii362","title":"A Network-based Approach to Brokering Research Evidence for Impact","year":2021,"lang":"en","type":"report","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; Arts and Humanities Research Council; Economic and Social Research Council; Foreign, Commonwealth and Development Office; Department for International Development; University of Bath; Global Challenges Research Fund; University of Liverpool; University of Cambridge; Engineering and Physical Sciences Research Council; UK Research and Innovation; Overseas Development Institute; International Development Research Centre; Government of the United Kingdom; Oxfam America; University of Nottingham; Imperial College London; Leeds Beckett University","keywords":"Computer science; Data science","score_opus":0.9170433068307423,"score_gpt":0.728017052058615,"score_spread":0.1890262547721273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4255735068","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013491564,0.00283715,0.3925779,0.002524937,0.002222544,0.0036945834,0.000051776584,0.000089634144,0.59465235],"genre_scores_gemma":[0.4090491,0.0008002404,0.15175973,0.0024707722,0.0067722634,0.0036070712,0.0003562875,0.00017736353,0.42500716],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9838912,0.0007257328,0.0012699324,0.0013232216,0.01188941,0.0009005163],"domain_scores_gemma":[0.978832,0.0090481145,0.00032152171,0.0016792121,0.009741515,0.00037761198],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07362516,0.0002997095,0.00075009454,0.00077879685,0.000425771,0.0013241217,0.001413231,0.00029620744,0.0031328911],"category_scores_gemma":[0.028024819,0.00019664146,0.0004826826,0.0029290807,0.000060896586,0.00031579085,0.00040431766,0.0006039053,0.00033780703],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007595915,0.00006443523,0.0048971805,0.00008860738,0.00003167543,0.0000021677797,0.000083513834,0.056184653,0.000018468845,0.00013243053,0.9003295,0.038091414],"study_design_scores_gemma":[0.0003889161,0.0005119937,0.012419011,0.000929302,0.000035289006,0.000016276263,0.00043352335,0.1001929,0.000102030564,0.0012826431,0.8831114,0.00057670346],"about_ca_topic_score_codex":0.000388698,"about_ca_topic_score_gemma":0.00024108587,"teacher_disagreement_score":0.40769994,"about_ca_system_score_codex":0.001007505,"about_ca_system_score_gemma":0.017672934,"threshold_uncertainty_score":0.9997126},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"evaluation","study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W4255851291","doi":"10.3138/cjpe.209","title":"Challenges in Evaluating a Prototype Project in a Large Health Authority: Lessons Learned","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Fraser Health; Centre for Advancing Health Outcomes","funders":"","keywords":"Pace; Health care; Bureaucracy; Bridge (graph theory); Process (computing); Process management; Business; Program evaluation; Test (biology); Public relations; Public sector; Nursing; Knowledge management; Medicine; Computer science; Political science; Public administration","score_opus":0.8786268415298759,"score_gpt":0.6676318817317606,"score_spread":0.21099495979811533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4255851291","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8629527,0.010495019,0.00040894825,0.10155855,0.0015790022,0.012172159,0.000016651878,0.000031370626,0.010785618],"genre_scores_gemma":[0.9951974,0.000088334826,0.0039619636,0.00015580769,0.00011918342,0.00040567806,0.0000087204735,0.000012937704,0.0000499312],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99145585,0.0029953301,0.0015087139,0.00035483498,0.003118108,0.00056717184],"domain_scores_gemma":[0.9956593,0.00021155394,0.0009145286,0.00032169404,0.0023502104,0.00054275093],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.102147155,0.00014993292,0.00042313055,0.0018888247,0.00011677633,0.00027000296,0.0004554402,0.00010681361,0.00018750553],"category_scores_gemma":[0.011050231,0.00012314577,0.00008145295,0.0016752005,0.00004332843,0.0007417122,0.000021801403,0.00047533086,0.000039591785],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005686246,0.00011448285,0.031236788,0.000011408477,0.0000066597268,0.0000091347965,0.013885094,0.0013850031,0.0000021054884,0.0007432563,0.00034016697,0.95220906],"study_design_scores_gemma":[0.009585535,0.0068768105,0.33799526,0.0006801749,0.000038603335,0.0000956289,0.054638043,0.46027577,0.000011350511,0.059133846,0.07019137,0.00047763073],"about_ca_topic_score_codex":0.0023467657,"about_ca_topic_score_gemma":0.3681619,"teacher_disagreement_score":0.9517314,"about_ca_system_score_codex":0.0015112992,"about_ca_system_score_gemma":0.031832885,"threshold_uncertainty_score":0.9972801},"labels":[],"label_agreement":null},{"id":"W4256107330","doi":"10.4324/9781315669465","title":"Collaborative Practice","year":2017,"lang":"en","type":"book","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.2612904548912655,"score_gpt":0.5880164587173231,"score_spread":0.3267260038260576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4256107330","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.9098863e-7,0.00028385044,0.00037503926,0.0063055623,0.00095117325,0.00027281683,0.00002807192,0.000026027257,0.99175686],"genre_scores_gemma":[0.000052902116,0.00025838532,0.0022787577,0.0020797087,0.000336456,0.000014543048,0.00002470584,0.000011691102,0.99494284],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99564,0.00017880852,0.00052544987,0.0004399158,0.0030789517,0.00013689885],"domain_scores_gemma":[0.9921628,0.0023207455,0.0011664,0.0013308214,0.0029294197,0.000089816596],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0058114524,0.00017405664,0.0003346682,0.00018663352,0.00032261913,0.0010454868,0.0011179077,0.00020198798,0.02363255],"category_scores_gemma":[0.0075772936,0.0001113403,0.000086292355,0.00009559549,0.00011001876,0.000991837,0.0001649307,0.0002700369,0.021761324],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011033789,0.0000100921125,0.000006940395,0.0000011477683,0.000019845347,0.000004864821,0.00016008924,0.0000050167137,3.4044905e-7,0.041599855,0.90474856,0.053432222],"study_design_scores_gemma":[0.00014539671,0.00005148928,0.00006101136,0.000016332646,0.00002278716,0.0000036237661,0.00027904607,0.00016784047,0.0000056102886,0.040892202,0.958203,0.00015165581],"about_ca_topic_score_codex":0.0000044023163,"about_ca_topic_score_gemma":0.00007408241,"teacher_disagreement_score":0.05345445,"about_ca_system_score_codex":0.0001145092,"about_ca_system_score_gemma":0.0045254366,"threshold_uncertainty_score":0.99999154},"labels":[],"label_agreement":null},{"id":"W4256173338","doi":"10.2202/1553-3840.1074","title":"Integrating CAM Research and Practice: A Focus on Outcome Measures - Abstracts from the 3rd Annual IN-CAM Symposium November 4th &amp; 5th, 2006, Calgary, Canada","year":2006,"lang":"en","type":"article","venue":"Journal of Complementary and Integrative Medicine","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Library science; Medical education; Alternative medicine; Family medicine; Gerontology; Pathology; Computer science","score_opus":0.2905318670149749,"score_gpt":0.5266167097659238,"score_spread":0.23608484275094888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4256173338","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.840881,0.0011871632,0.0006461232,0.13507704,0.0006784039,0.0004119533,0.00011348707,0.0000033180925,0.02100151],"genre_scores_gemma":[0.9948927,0.00015505285,0.00089333404,0.00279195,0.00055698684,0.000006178386,0.000021856133,0.000007871811,0.00067407015],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9930717,0.0014016166,0.0016948965,0.00028698787,0.00324498,0.00029983782],"domain_scores_gemma":[0.9845682,0.012478362,0.0008092587,0.00024599358,0.0017418077,0.00015640733],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016408945,0.00022823122,0.0005374463,0.00032036254,0.00034415294,0.00012835569,0.0004366367,0.00004117817,0.00091893866],"category_scores_gemma":[0.0044226153,0.00010140292,0.000042793163,0.0004909281,0.00037180958,0.0006220181,0.00009205469,0.0010953555,0.0000046769396],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016720402,0.0003888054,0.42823356,0.000008572969,0.00017160238,0.00008645899,0.013415831,0.0001899206,0.00191279,0.0063054846,0.5267174,0.020897506],"study_design_scores_gemma":[0.0033267343,0.002240575,0.5808331,0.0005072398,0.00006580164,0.00016031277,0.0920063,0.00042676987,0.00027696448,0.013893573,0.30603638,0.00022630361],"about_ca_topic_score_codex":0.44660038,"about_ca_topic_score_gemma":0.87233037,"teacher_disagreement_score":0.42573,"about_ca_system_score_codex":0.00028070292,"about_ca_system_score_gemma":0.0005951809,"threshold_uncertainty_score":0.99999434},"labels":[],"label_agreement":null},{"id":"W4256577654","doi":"10.1007/978-1-4939-7131-2_100348","title":"Evaluation Approaches","year":2018,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science","score_opus":0.7348958051093804,"score_gpt":0.529804795289752,"score_spread":0.20509100981962836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4256577654","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000045094293,0.00012353629,0.0015942154,0.0006635952,0.00060902955,0.00041780085,0.000006972872,0.00003688821,0.9965029],"genre_scores_gemma":[0.0062389392,0.000020885569,0.0010691191,0.00036324258,0.0004939121,0.000020920412,0.000027928028,0.000019390303,0.99174565],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.991401,0.00010650688,0.00068430835,0.0005624998,0.007107765,0.00013789111],"domain_scores_gemma":[0.99658215,0.0002967217,0.0004043003,0.000886998,0.0017492148,0.00008062156],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.017266443,0.00020918585,0.00027753288,0.0003276493,0.000113512266,0.00024317352,0.00054909714,0.0002345964,0.43825203],"category_scores_gemma":[0.0005796776,0.00013725989,0.00015259524,0.000063575055,0.00011350538,0.00024285608,0.000109068475,0.000154047,0.03664436],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006868778,0.000012586358,0.000025267653,0.0000023714983,0.000050818668,3.3894912e-7,0.00024134491,0.0000523964,0.0000016195609,0.20683527,0.3653156,0.42745554],"study_design_scores_gemma":[0.0001317595,0.00005056361,0.00009989339,0.000010913174,0.000056668494,0.0000010788366,0.000060536742,0.023164889,0.000014101122,0.35455903,0.62169707,0.00015349766],"about_ca_topic_score_codex":0.000001361576,"about_ca_topic_score_gemma":0.000061854866,"teacher_disagreement_score":0.42730203,"about_ca_system_score_codex":0.00013084199,"about_ca_system_score_gemma":0.00064750685,"threshold_uncertainty_score":0.9641057},"labels":[],"label_agreement":null},{"id":"W427885073","doi":"","title":"","year":2006,"lang":"fr","type":"article","venue":"PubMed","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sante Montreal","funders":"","keywords":"Humanities; Political science; Emancipation; Philosophy","score_opus":0.21183651776632992,"score_gpt":0.43207828309294793,"score_spread":0.22024176532661802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W427885073","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6930703,0.012033487,0.0042350814,0.21521717,0.010161134,0.0023935197,0.000052921612,0.00010546705,0.06273092],"genre_scores_gemma":[0.79451954,0.00020102068,0.00078893633,0.0026557902,0.001659864,0.0034173548,0.000014374825,0.000020494053,0.19672261],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9885373,0.0011386618,0.0022197089,0.0011360429,0.0049996683,0.0019685945],"domain_scores_gemma":[0.99472386,0.0018079671,0.00071156834,0.0011989491,0.0010107419,0.0005469158],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.019212281,0.0004360444,0.0005927984,0.0005382828,0.0006619558,0.0017372767,0.0013794567,0.00028663964,0.0017024727],"category_scores_gemma":[0.0014495933,0.00037837485,0.00037014505,0.002667249,0.0005767761,0.0034136097,0.0002836016,0.00039880167,0.0007099498],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004754796,0.00040994087,0.20990899,0.000012753281,0.000017342669,0.00001666845,0.00017635654,0.005354209,0.000006572684,0.036044784,0.018323636,0.7296812],"study_design_scores_gemma":[0.0011144624,0.000028307595,0.58621156,0.0000086164555,0.000036372727,0.000023160392,0.00037586968,0.004708808,0.00033398403,0.04977567,0.35708934,0.0002938611],"about_ca_topic_score_codex":0.0029354636,"about_ca_topic_score_gemma":0.0034631928,"teacher_disagreement_score":0.72938734,"about_ca_system_score_codex":0.0004638093,"about_ca_system_score_gemma":0.00043581094,"threshold_uncertainty_score":0.99986684},"labels":[],"label_agreement":null},{"id":"W4280567856","doi":"10.4324/9781003152781-5","title":"The Assessment Elephant in the Room: When Societies Discount Children","year":2022,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Business; Geography; Natural resource economics; Economics","score_opus":0.14446011678388967,"score_gpt":0.4566531181750671,"score_spread":0.31219300139117745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280567856","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002634449,0.00059607293,0.00019045471,0.029859874,0.0005994891,0.0009010751,0.000046645815,0.0000246997,0.96751827],"genre_scores_gemma":[0.013037713,0.0017914721,0.00024296486,0.0044515836,0.0002671279,0.00019947847,0.000079667545,0.000030251613,0.97989976],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9916736,0.00035336346,0.0010701779,0.00057973596,0.005978258,0.00034485306],"domain_scores_gemma":[0.9959636,0.0019628669,0.000520759,0.0013287136,0.00017536886,0.000048744427],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.013670054,0.0003307828,0.0003719604,0.00016442992,0.0010018857,0.0010255518,0.0025676358,0.00012019215,0.040736645],"category_scores_gemma":[0.00009521716,0.00013823285,0.00031116203,0.00011871706,0.00017375546,0.0003039031,0.00052024086,0.000919182,0.00048694943],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007666986,0.0000322866,0.0018377902,0.0000016033731,0.000052205567,0.000002225666,0.0012211129,0.000112100184,6.091314e-7,0.62498575,0.3476572,0.02408945],"study_design_scores_gemma":[0.00018636147,0.000079857105,0.01432168,0.00000975319,0.000020288575,0.0000063299954,0.0018874598,0.0005662654,5.5920754e-7,0.19944958,0.7832717,0.00020017984],"about_ca_topic_score_codex":0.00005771331,"about_ca_topic_score_gemma":0.00081535673,"teacher_disagreement_score":0.43561447,"about_ca_system_score_codex":0.00029123042,"about_ca_system_score_gemma":0.000720926,"threshold_uncertainty_score":0.98894197},"labels":[],"label_agreement":null},{"id":"W4280620480","doi":"10.55140/2782-5817-2022-2-1-16-20","title":"Outcome Mapping — creating a map of behavioral changes","year":2022,"lang":"en","type":"article","venue":"Positive changes","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Outcome (game theory); Assessment center; Process management; Environmental resource management; Operations management; Psychology; Engineering; Applied psychology; Environmental science","score_opus":0.4054906563440229,"score_gpt":0.5187392220023848,"score_spread":0.11324856565836183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280620480","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9788709,0.00031162673,0.000476342,0.011288379,0.0007041578,0.0003872292,0.00023799873,0.00004088556,0.0076824557],"genre_scores_gemma":[0.9938557,0.0000061449027,0.0006396559,0.00082639465,0.00009863674,0.00013182288,0.000026650197,0.000009971261,0.004405028],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9972818,0.00030062217,0.00036095583,0.0003003517,0.0015342238,0.00022205159],"domain_scores_gemma":[0.99860483,0.0004308917,0.00034374112,0.0002722076,0.00028979685,0.000058557423],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0026802635,0.0001171928,0.00027020634,0.00037861316,0.00038221857,0.000059290192,0.00040027482,0.000025145675,0.005731787],"category_scores_gemma":[0.00009240646,0.00009841623,0.000069783426,0.00047343705,0.00005653944,0.00011661627,0.0003695708,0.00014653352,0.00007193486],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011704383,0.0005270058,0.67386323,0.0000491827,0.0000693014,0.000030471643,0.080708764,0.0002849435,0.028937908,0.0042939726,0.004664794,0.20645337],"study_design_scores_gemma":[0.0018329263,0.002558641,0.6705928,0.00009596321,0.00009830206,0.00004104914,0.19795008,0.006592925,0.026478736,0.002811705,0.09003184,0.0009150679],"about_ca_topic_score_codex":0.00012798492,"about_ca_topic_score_gemma":0.0003194245,"teacher_disagreement_score":0.2055383,"about_ca_system_score_codex":0.0000976163,"about_ca_system_score_gemma":0.000046171146,"threshold_uncertainty_score":0.9951771},"labels":[],"label_agreement":null},{"id":"W4281571473","doi":"10.31219/osf.io/435ph","title":"Cultural Safety in Forensic Mental Health Services: A Scoping Review Protocol","year":2022,"lang":"en","type":"review","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Institut national de psychiatrie légale Philippe-Pinel","funders":"Canadian Institutes of Health Research","keywords":"Mental health; Protocol (science); Indigenous; Indigenous culture; Forensic science; Psychology; Cultural safety; Best practice; Applied psychology; Medical education; Medicine; Psychiatry; Political science; Alternative medicine","score_opus":0.45800717717767647,"score_gpt":0.6497791392316868,"score_spread":0.19177196205401037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281571473","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.3714861e-8,0.7609456,0.0000068046634,0.00054858444,0.00019325558,0.22905383,0.000027033206,0.0000284017,0.009196445],"genre_scores_gemma":[6.2486447e-9,0.81014836,0.00035178126,0.0032499454,0.000040025785,0.18472087,0.0002144299,0.000015752927,0.0012588403],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9910942,0.0016442904,0.0033353406,0.0008002082,0.002721056,0.00040492907],"domain_scores_gemma":[0.9969372,0.0004615698,0.0015645678,0.00078694936,0.000105730105,0.00014394803],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011587447,0.00039992982,0.0024685774,0.0003443698,0.00032342202,0.00019036005,0.0011537055,0.00007929653,0.03845844],"category_scores_gemma":[0.00012133005,0.00022644547,0.00050303026,0.002049146,0.000030889914,0.0004917347,0.00048084068,0.00045035523,0.0006920003],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028027887,0.000026124007,0.000006004572,0.1177319,0.000006657093,7.41305e-7,0.00014335966,8.716253e-7,5.9130906e-10,0.0000857995,0.0041646864,0.87783104],"study_design_scores_gemma":[0.00022210825,0.000059961534,0.0000021777382,0.2634913,0.000012266384,0.000015566646,0.0002449767,0.0000548492,6.3584484e-9,0.000026120588,0.73568773,0.00018293444],"about_ca_topic_score_codex":0.00009187274,"about_ca_topic_score_gemma":0.0013144277,"teacher_disagreement_score":0.8776481,"about_ca_system_score_codex":0.0007654831,"about_ca_system_score_gemma":0.0028064493,"threshold_uncertainty_score":0.9624205},"labels":[],"label_agreement":null},{"id":"W4281641218","doi":"10.1111/medu.14853","title":"When I say <i>…</i> response process validity evidence","year":2022,"lang":"en","type":"article","venue":"Medical Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; McGill University","funders":"","keywords":"Psychology; Process (computing); Equity (law); Cognition; Cognitive psychology; Social psychology; Applied psychology; Computer science; Political science; Psychiatry","score_opus":0.28645613487481736,"score_gpt":0.5686232695119959,"score_spread":0.2821671346371786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281641218","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81772786,0.00020490844,0.001229434,0.17415628,0.002500477,0.00026490228,0.0000033126937,0.00004396898,0.0038688786],"genre_scores_gemma":[0.9682976,0.000013348231,0.00021635865,0.02187605,0.0001794923,0.00026463502,0.00000906135,0.0000055434284,0.00913791],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.991674,0.0016604277,0.0004972039,0.00035680825,0.0056442386,0.00016731335],"domain_scores_gemma":[0.9966722,0.0020690474,0.00020342662,0.00047549984,0.0004040888,0.00017574476],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.023970893,0.00007728874,0.00012612544,0.00017466595,0.00041466957,0.000100766934,0.000877525,0.000038520015,0.06260707],"category_scores_gemma":[0.033688575,0.000060039372,0.000048956837,0.00071826245,0.000066102155,0.0004147874,0.00014971149,0.00028407713,0.0004933007],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038554336,0.0005810526,0.031180084,0.0000098093715,0.0000038124738,0.0000020261712,0.0075088684,0.00016375213,0.00010013017,0.0005864597,0.77792096,0.1815575],"study_design_scores_gemma":[0.00027357726,0.0002735845,0.052049063,0.00004504917,0.000009865834,0.00003037747,0.0057925205,0.00843928,0.00019873011,0.025912164,0.9068004,0.00017540698],"about_ca_topic_score_codex":0.00002766193,"about_ca_topic_score_gemma":0.000015254352,"teacher_disagreement_score":0.18138209,"about_ca_system_score_codex":0.00018400239,"about_ca_system_score_gemma":0.00763897,"threshold_uncertainty_score":0.9979868},"labels":[],"label_agreement":null},{"id":"W4281767293","doi":"10.1111/capa.12458","title":"The Canadian Impact Assessment Act and intersectional analysis: Exaggerated tensions, fierce resistance, little understanding","year":2022,"lang":"en","type":"article","venue":"Canadian Public Administration","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Guelph; Dalhousie University","funders":"","keywords":"Mainstreaming; Gender mainstreaming; Legislature; Intersectionality; Legislation; Invisibility; Political science; Resistance (ecology); Public administration; Inclusion (mineral); Legislative process; Resource (disambiguation); Sociology; Law; Gender studies; Gender equality","score_opus":0.21907985764122717,"score_gpt":0.4574565444753476,"score_spread":0.23837668683412044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281767293","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4709641,0.00038511833,0.0036354978,0.40486953,0.0022326857,0.00137627,0.0009214958,0.00009131734,0.115523994],"genre_scores_gemma":[0.9945986,0.000008915427,0.00008071024,0.0009419367,0.000052171014,0.000065079745,0.00025389434,0.000008104862,0.0039905654],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969056,0.00048951054,0.00050241547,0.00040099738,0.0012462802,0.00045515707],"domain_scores_gemma":[0.99751705,0.0005646697,0.00021385476,0.00043192646,0.00037075218,0.00090173376],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004790889,0.00014208765,0.0001737781,0.0012175326,0.0049480884,0.0018999467,0.00039111575,0.000060759372,0.0047746366],"category_scores_gemma":[0.0007050828,0.00010740614,0.00010776375,0.0026110813,0.00011126969,0.0005035976,0.000039980183,0.00032977562,0.000014671742],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000065040294,0.00004714879,0.38262087,0.0000030683802,0.00059784314,0.00004791134,0.00081958075,0.00062592636,0.000014448305,0.4190886,0.19148675,0.0045828214],"study_design_scores_gemma":[0.00025880878,0.00018146411,0.38583404,0.0000038799312,0.0000763065,0.000031057785,0.009752384,0.03438966,0.0000016410214,0.0056408676,0.563556,0.00027387106],"about_ca_topic_score_codex":0.06066706,"about_ca_topic_score_gemma":0.99629676,"teacher_disagreement_score":0.9356297,"about_ca_system_score_codex":0.004753593,"about_ca_system_score_gemma":0.019137396,"threshold_uncertainty_score":0.99913615},"labels":[],"label_agreement":null},{"id":"W4281789958","doi":"10.22329/wyaj.v37i1.7281","title":"Measuring Improvements in Access to Justice: Utilizing an A2J Measurement Framework for Comparative Justice Data Collection and Program Evaluation Across Canada","year":2022,"lang":"en","type":"article","venue":"Windsor Yearbook of Access to Justice","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université Laval; University of Windsor; Université du Québec à Montréal; Université de Montréal; University of Saskatchewan","funders":"","keywords":"Economic Justice; Data collection; Population; Computer science; Sociology; Political science; Business; Law; Social science","score_opus":0.7083547047958997,"score_gpt":0.5923293814452161,"score_spread":0.1160253233506836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281789958","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9697227,0.00018682725,0.015643125,0.0018804931,0.002374136,0.008814185,0.000323147,0.000046862464,0.0010085258],"genre_scores_gemma":[0.98746103,0.0000080873115,0.009001949,0.0013255593,0.00018427514,0.0018835323,0.000058342284,0.000024587785,0.000052647527],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99134,0.000592485,0.0011271832,0.0011020049,0.00528155,0.00055680686],"domain_scores_gemma":[0.9952344,0.00091082347,0.0005790622,0.0010534029,0.0019287637,0.00029359187],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0138134,0.00026662985,0.00048061635,0.0003249883,0.0009582746,0.00092326,0.002449122,0.00006817414,0.000272549],"category_scores_gemma":[0.003993181,0.0002651219,0.000034962788,0.0018363111,0.000043690736,0.0019803394,0.0017110957,0.00035719931,0.0000042232723],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004218328,0.0021479083,0.029305972,0.0015674069,0.0002997401,0.000008644243,0.025971455,0.40475407,0.0031726772,0.00075505505,0.028139902,0.49965882],"study_design_scores_gemma":[0.003257799,0.0013822948,0.24151628,0.00034938837,0.0013029925,0.0000037872462,0.065260254,0.6657296,0.002257893,0.00093887537,0.01714057,0.00086029543],"about_ca_topic_score_codex":0.020795321,"about_ca_topic_score_gemma":0.21246038,"teacher_disagreement_score":0.49879855,"about_ca_system_score_codex":0.0010462058,"about_ca_system_score_gemma":0.0020239707,"threshold_uncertainty_score":0.9999801},"labels":[],"label_agreement":null},{"id":"W4283209786","doi":"10.6017/ital.v41i2.15161","title":"Gathering Strength to Combat Access Inequality","year":2022,"lang":"en","type":"article","venue":"Information Technology and Libraries","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Public access; Order (exchange); Inequality; Public relations; Library science; Sociology; Political science; Computer science; Business; Mathematics","score_opus":0.11819903401280733,"score_gpt":0.42815609034218605,"score_spread":0.3099570563293787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283209786","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9622967,0.00005311688,0.008785934,0.017779661,0.0002726888,0.0002197596,0.00003573833,0.00022202125,0.010334361],"genre_scores_gemma":[0.99598384,0.0000056517506,0.0010227951,0.0025765107,0.000009081979,0.00008769025,0.000016126804,0.0000021437893,0.0002961505],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986764,0.00006526825,0.00045524744,0.000115092,0.00055908016,0.00012887508],"domain_scores_gemma":[0.9992454,0.00017167907,0.00017318605,0.00028613728,0.00008003758,0.000043544314],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00120335,0.000072616625,0.00012558978,0.0008696103,0.0005763705,0.0004695129,0.0006371866,0.00004857429,0.0021638814],"category_scores_gemma":[0.00047375902,0.000059507478,0.000017850505,0.0014910176,0.00008388413,0.0039061417,0.00094203796,0.00018228948,0.00010446868],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004153467,0.000022611444,0.09316274,0.000006351707,0.000008786087,4.0680553e-7,0.0034901397,0.0009770218,0.000017803713,0.5353218,0.007783408,0.3591674],"study_design_scores_gemma":[0.00034355855,0.00015160968,0.04598166,0.000003412679,0.0000027709345,0.000007152815,0.012283242,0.0041269003,0.0013326121,0.14021844,0.7953963,0.00015233987],"about_ca_topic_score_codex":0.000005645704,"about_ca_topic_score_gemma":0.0000036134086,"teacher_disagreement_score":0.7876129,"about_ca_system_score_codex":0.000018136705,"about_ca_system_score_gemma":0.00009230939,"threshold_uncertainty_score":0.9987483},"labels":[],"label_agreement":null},{"id":"W4283391831","doi":"10.1111/capa.12454","title":"Evaluating the evaluators: What have we learned from “neutral assessments” of the Canadian federal evaluation function?","year":2022,"lang":"en","type":"article","venue":"Canadian Public Administration","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Agency (philosophy); Function (biology); Government (linguistics); Quality (philosophy); Business; Political science; Public relations; Psychology; Sociology","score_opus":0.4379135587071296,"score_gpt":0.5156808570606097,"score_spread":0.07776729835348012,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283391831","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.735829,0.00034413635,0.00013434664,0.24900152,0.0039278893,0.001965484,0.00025604892,0.000022518829,0.008519084],"genre_scores_gemma":[0.99336,0.000008455521,0.00010858084,0.003328398,0.00022544482,0.00043736864,0.00034682787,0.000019923915,0.0021650458],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9894519,0.0032496185,0.0010424468,0.0006557315,0.0050213877,0.0005789271],"domain_scores_gemma":[0.9952975,0.0006432733,0.0007409267,0.0012080877,0.001543986,0.0005662377],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.018369792,0.00023163827,0.00024253037,0.0005134794,0.0042499234,0.0023247288,0.0013689721,0.00011821404,0.017905014],"category_scores_gemma":[0.0019139242,0.00016166562,0.0001893279,0.0013782178,0.00017221646,0.0016847678,0.00011289067,0.0005701609,0.00007516785],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018024209,0.00019051568,0.09289349,0.000009732954,0.00029120708,0.000005127541,0.0036995974,0.0132188015,0.0003634328,0.056622837,0.043021873,0.78950316],"study_design_scores_gemma":[0.0016600267,0.0011561753,0.1407456,0.000031376236,0.00020322509,0.000021461863,0.03488674,0.45844132,0.00018015348,0.0587741,0.30335188,0.0005479564],"about_ca_topic_score_codex":0.1415032,"about_ca_topic_score_gemma":0.9816308,"teacher_disagreement_score":0.8401276,"about_ca_system_score_codex":0.0027187048,"about_ca_system_score_gemma":0.04300247,"threshold_uncertainty_score":0.99871093},"labels":[],"label_agreement":null},{"id":"W4283514737","doi":"10.47678/cjhe.v52i1.189121","title":"Utilisateurs et non-utilisateurs des centres d’aide en français au postsecondaire : une étude comparative par la méthode d’appariement cas-témoin","year":2022,"lang":"fr","type":"article","venue":"Canadian Journal of Higher Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Humanities; Political science; Art","score_opus":0.1509430451506304,"score_gpt":0.4361293109957156,"score_spread":0.2851862658450852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283514737","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9140286,0.0108330725,0.00028465778,0.03825829,0.012223221,0.00046016963,0.00020536223,0.000008019116,0.023698619],"genre_scores_gemma":[0.9763915,0.00016887645,0.0012256085,0.002866406,0.00045090503,0.00003741793,0.000054937856,0.000030262336,0.018774122],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99345756,0.0025825298,0.0013819496,0.00043071358,0.0014143478,0.0007328819],"domain_scores_gemma":[0.9955249,0.00088917266,0.000936918,0.00044314592,0.00097001594,0.0012358376],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0055990326,0.00036298935,0.0005685331,0.0008577696,0.0012238821,0.0004898481,0.00097475643,0.00012933761,0.024840496],"category_scores_gemma":[0.00019936071,0.00035210376,0.0002506394,0.0012536264,0.0005320822,0.0011709597,0.000075211,0.0009476441,0.0002056056],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000114022725,0.00055632833,0.5237345,0.000058878482,0.0002278963,0.000089405905,0.20155053,0.0130261555,0.00011208688,0.007941431,0.19238071,0.060208075],"study_design_scores_gemma":[0.0004952533,0.00026106206,0.50960547,0.00010026652,0.000082097984,0.00013522687,0.025068887,0.00028138212,0.000117496274,0.0042231786,0.45940644,0.00022326734],"about_ca_topic_score_codex":0.060488712,"about_ca_topic_score_gemma":0.19717695,"teacher_disagreement_score":0.2670257,"about_ca_system_score_codex":0.002340569,"about_ca_system_score_gemma":0.025945129,"threshold_uncertainty_score":0.99989307},"labels":[],"label_agreement":null},{"id":"W4285464530","doi":"10.32920/14668881","title":"On Effect Assessment in Work Environment Interventions – A Literature Overview and Methodological Reflection","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada; Workplace Safety and Insurance Board","keywords":"Psychological intervention; Intervention (counseling); Context (archaeology); Variety (cybernetics); Quality (philosophy); Identification (biology); Work (physics); Psychology; Applied psychology; Risk analysis (engineering); Computer science; Medicine; Engineering; Epistemology","score_opus":0.5729218036102105,"score_gpt":0.628097569155461,"score_spread":0.0551757655452505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285464530","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8930478,0.008702981,0.06981248,0.0066357423,0.0021241868,0.0019491457,0.00001933507,0.00007814608,0.0176302],"genre_scores_gemma":[0.9545887,0.0037877157,0.036323983,0.00087896106,0.000086895634,0.00049393653,0.00013503154,0.000016720527,0.0036880202],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9914914,0.004593041,0.0010365534,0.001098661,0.0015602867,0.00022009367],"domain_scores_gemma":[0.9954552,0.0031537646,0.00037057346,0.000819893,0.000095211675,0.000105368505],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016097903,0.00032068865,0.0007300169,0.00048660152,0.00009952858,0.00095197995,0.00036179117,0.00038539525,0.0072171837],"category_scores_gemma":[0.0012286041,0.00020560857,0.00040856563,0.0006435988,0.00004825669,0.00017803427,0.00093547435,0.0013506985,0.000065503235],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042057308,0.0019180994,0.14277476,0.0010964175,0.00029440728,0.00013350311,0.0027843653,0.033167057,0.00022357257,0.019038279,0.00771424,0.7904347],"study_design_scores_gemma":[0.0011895283,0.0010764339,0.92860377,0.004608701,0.00008884263,0.000015296817,0.00042465198,0.007319202,0.00012378728,0.05071968,0.0051966533,0.0006334829],"about_ca_topic_score_codex":0.000012850556,"about_ca_topic_score_gemma":0.00006846415,"teacher_disagreement_score":0.78980124,"about_ca_system_score_codex":0.00031733786,"about_ca_system_score_gemma":0.0001180697,"threshold_uncertainty_score":0.9936904},"labels":[],"label_agreement":null},{"id":"W4285775844","doi":"10.29173/anserj.2019v10n2a287","title":"Caractéristiques organisationnelles qui influencent le renforcement des capacités en évaluation chez les organismes communautaires du Québec : une recension des écrits","year":2019,"lang":"en","type":"article","venue":"Canadian journal of nonprofit and social economy research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"École Nationale d'Administration Publique; University of Ottawa","funders":"","keywords":"Valuation (finance); Sociology; Humanities; Philosophy; Business","score_opus":0.19655548514452198,"score_gpt":0.43047281264361437,"score_spread":0.2339173274990924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285775844","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9836898,0.0006148883,0.00009631178,0.011319898,0.00009717434,0.0002884626,0.00000526486,0.0000053131507,0.003882881],"genre_scores_gemma":[0.9984898,0.00027881944,0.00036445557,0.0001537117,0.0001859573,0.0000072627518,0.000006055746,0.000013751615,0.000500214],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99691194,0.00097513193,0.0007619896,0.00021232499,0.000757147,0.00038144525],"domain_scores_gemma":[0.99574584,0.0008650205,0.00030309692,0.00018193776,0.0025796322,0.00032448888],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011011039,0.00013645347,0.00031882778,0.0005396083,0.0016895485,0.0005538933,0.000470814,0.0001272028,0.0018609738],"category_scores_gemma":[0.0011059028,0.000113304355,0.00007539105,0.00044335096,0.0007924375,0.0008785737,0.00006354476,0.00042346286,0.0000871051],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048865,0.0000241998,0.8069178,0.00005391957,0.000048595288,0.000005555387,0.08928829,0.0001386315,0.0010295665,0.0037965018,0.002320715,0.09632736],"study_design_scores_gemma":[0.00099438,0.00046706034,0.7320487,0.00015715424,0.000017847606,0.00003577944,0.20204559,0.00095464475,0.002000498,0.04019337,0.020825438,0.00025955928],"about_ca_topic_score_codex":0.18849258,"about_ca_topic_score_gemma":0.5030461,"teacher_disagreement_score":0.31455353,"about_ca_system_score_codex":0.00089919724,"about_ca_system_score_gemma":0.010549378,"threshold_uncertainty_score":0.9996101},"labels":[],"label_agreement":null},{"id":"W4286005457","doi":"10.4000/educationdidactique.10417","title":"Science et autorité dans le champ de la recherche en éducation au temps de l’Evidence-Based Practice and Policy","year":2022,"lang":"fr","type":"article","venue":"Éducation & didactique","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.42116737017244477,"score_gpt":0.5978993305465423,"score_spread":0.17673196037409755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286005457","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43976483,0.0011121435,0.02371585,0.48643947,0.0015958636,0.00064509164,0.000018804447,0.00006940064,0.046638552],"genre_scores_gemma":[0.95513344,0.0012325207,0.019912796,0.008927687,0.0004301678,0.00032568962,0.000012847215,0.000025073938,0.0139997685],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.97562295,0.020362278,0.0006843873,0.00080767914,0.0019122332,0.0006104725],"domain_scores_gemma":[0.9748108,0.022621945,0.0006587993,0.00074403547,0.0008014024,0.00036304374],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.111053474,0.00022943453,0.00021295907,0.0008835605,0.0015946446,0.00084995927,0.000854745,0.00023932902,0.0010934775],"category_scores_gemma":[0.07031801,0.00024505722,0.000071839815,0.0036952752,0.0005761735,0.00375376,0.00023487136,0.0013057302,0.000096232274],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00013791556,0.0018265501,0.0158449,0.00008572763,0.00003138276,0.0000053787717,0.52795476,0.009143406,0.029016146,0.31369087,0.008039735,0.09422325],"study_design_scores_gemma":[0.00062993966,0.0004194043,0.16358894,0.00016755794,0.00004075696,0.00026631393,0.121257454,0.025374297,0.00873725,0.03634197,0.64269,0.0004861282],"about_ca_topic_score_codex":0.010607573,"about_ca_topic_score_gemma":0.0004551966,"teacher_disagreement_score":0.63465023,"about_ca_system_score_codex":0.012390885,"about_ca_system_score_gemma":0.15227272,"threshold_uncertainty_score":0.99981964},"labels":[],"label_agreement":null},{"id":"W4286648530","doi":"10.3768/rtipress.2022.rr.0046.2205","title":"Integrated Governance: Achieving Governance Results and Contributing to Sector Outcomes","year":2022,"lang":"en","type":"report","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"International Development Research Centre","funders":"","keywords":"Corporate governance; Psychological intervention; Service delivery framework; Government (linguistics); Process management; Business; Public relations; Knowledge management; Service (business); Political science; Marketing; Computer science; Psychology","score_opus":0.24178214826792904,"score_gpt":0.49778326113760735,"score_spread":0.2560011128696783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286648530","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10407335,0.002613333,0.0014372756,0.028693167,0.010916354,0.0023310578,0.0061539286,0.00032119415,0.8434603],"genre_scores_gemma":[0.4664563,0.0029360186,0.0017932452,0.0027892652,0.00046097944,0.00015865632,0.00026150138,0.00006713904,0.5250769],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.987842,0.00034725547,0.0020495874,0.0012391869,0.00786935,0.0006525712],"domain_scores_gemma":[0.9928078,0.0025751677,0.0017797035,0.0010295958,0.0015610363,0.00024668392],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.020634046,0.00045151476,0.0010724964,0.00016534688,0.00055612094,0.00063868234,0.001027569,0.00020176894,0.011427505],"category_scores_gemma":[0.03185815,0.00030296267,0.00021510464,0.0011382088,0.000042262312,0.00037549358,0.001125239,0.0008211388,0.00022337587],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017731129,0.000070297756,0.20081982,0.000035328376,0.00012284811,0.000029746445,0.00062515645,0.0003603784,0.000044361263,0.0011730966,0.5860933,0.21044832],"study_design_scores_gemma":[0.0005172031,0.00009400658,0.30139506,0.00008090874,0.000019280278,0.000013904017,0.00042591212,0.0004985286,0.000021505986,0.0000669477,0.6965529,0.00031382797],"about_ca_topic_score_codex":0.0020558985,"about_ca_topic_score_gemma":0.0029250477,"teacher_disagreement_score":0.36238295,"about_ca_system_score_codex":0.0015521133,"about_ca_system_score_gemma":0.0026645812,"threshold_uncertainty_score":0.99994224},"labels":[],"label_agreement":null},{"id":"W4286808818","doi":"10.30770/2572-1852-105.1.3","title":"From the Editor","year":2019,"lang":"en","type":"article","venue":"Journal of Medical Regulation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Scrutiny; Harm; Identification (biology); Health care; Medicine; Psychology; Medical education; Family medicine; Political science; Social psychology","score_opus":0.11507485079640377,"score_gpt":0.5000901901167369,"score_spread":0.38501533932033316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286808818","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8814023,0.000112522284,0.011419126,0.091771886,0.0132361315,0.00007503202,0.000001116477,0.0000034910508,0.0019783762],"genre_scores_gemma":[0.98735416,0.000019599902,0.00025951688,0.000999621,0.010478451,3.114445e-7,0.00000113284,0.0000021437206,0.00088506826],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9926532,0.00019680156,0.00058886205,0.00006981131,0.0064295665,0.00006176763],"domain_scores_gemma":[0.99690336,0.0019197188,0.0004724709,0.00019665669,0.0004130233,0.000094771356],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009818088,0.000037393667,0.00011893264,0.00005246597,0.00003817534,0.00008826222,0.0005529788,0.00006917699,0.021932615],"category_scores_gemma":[0.0038678788,0.00001630917,0.0000761508,0.0001892188,0.000030680938,0.00030328656,0.000033832574,0.00018833326,0.00058916426],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058146634,0.000038798647,0.039550956,9.315051e-7,0.000019995887,0.0000015824965,0.0009050399,0.00057467795,0.00029765084,0.002900218,0.72572505,0.22992696],"study_design_scores_gemma":[0.00066048757,0.00008377873,0.36948958,0.000049759354,0.000008247175,0.000008495683,0.00075109914,0.035773344,0.00008576432,0.038855992,0.55419636,0.000037105783],"about_ca_topic_score_codex":0.0000075605562,"about_ca_topic_score_gemma":0.000006229943,"teacher_disagreement_score":0.32993862,"about_ca_system_score_codex":0.000028149494,"about_ca_system_score_gemma":0.00031465996,"threshold_uncertainty_score":0.97896147},"labels":[],"label_agreement":null},{"id":"W4289022587","doi":"","title":"Co-construction of knowledge through the lenses of epistemology and social inequalities","year":2019,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Social epistemology; Inequality; Sociology; Epistemology; Aesthetics; Philosophy; Social science; Mathematics","score_opus":0.11118312408102056,"score_gpt":0.39505673343805103,"score_spread":0.2838736093570305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4289022587","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8257387,0.001322046,0.035780635,0.013962024,0.0005941165,0.0005615563,0.00016358425,0.000037915786,0.12183938],"genre_scores_gemma":[0.98801947,0.0003671313,0.0056964615,0.00005915249,0.000022876124,0.000022520011,0.000083215586,0.000012120508,0.0057170386],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9891118,0.008333621,0.0010811107,0.00047010134,0.00083058485,0.00017278532],"domain_scores_gemma":[0.98784155,0.0057552154,0.0014566721,0.0013072778,0.0036085725,0.00003068621],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014162684,0.00019242536,0.0005350415,0.00018522258,0.0002691977,0.00014880723,0.0010561114,0.00022612799,0.00034162067],"category_scores_gemma":[0.001972478,0.00014136909,0.00017693674,0.00030720473,0.0010320579,0.00017353342,0.0006902269,0.00034783513,0.00002828987],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039347495,0.0003012332,0.03249197,0.00041877505,0.00011583486,2.2444571e-7,0.117648706,0.000082910694,0.0012536388,0.7563432,0.0023528484,0.08895135],"study_design_scores_gemma":[0.0033165594,0.00001099643,0.17629799,0.0028221298,0.00030714067,0.00005372632,0.039310057,0.023187358,0.18976508,0.4256156,0.13784114,0.0014722056],"about_ca_topic_score_codex":0.0004928923,"about_ca_topic_score_gemma":0.00055901404,"teacher_disagreement_score":0.33072755,"about_ca_system_score_codex":0.00004321964,"about_ca_system_score_gemma":0.0005666995,"threshold_uncertainty_score":0.57648647},"labels":[],"label_agreement":null},{"id":"W4289547999","doi":"10.33524/cjar.v19i1.377","title":"Canadian Association of Action Research in Education (CAARE) Conference 2019, June 1-5, Vancouver, British Columbia, Canada","year":2018,"lang":"en","type":"article","venue":"The Canadian Journal of Action Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Presentation (obstetrics); Library science; Action (physics); Action research; Political science; Media studies; History; Sociology; Pedagogy; Computer science; Medicine","score_opus":0.3746208688593892,"score_gpt":0.5407452346147313,"score_spread":0.16612436575534212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4289547999","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95740765,0.0001273046,0.000012841926,0.021661641,0.0053407,0.00044434983,0.000056515084,0.0000020705656,0.014946933],"genre_scores_gemma":[0.95421404,0.00013249867,0.00003649449,0.00019141319,0.00046148608,0.000010537361,0.000005322913,0.0000096335125,0.044938575],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9911528,0.0024256739,0.00087766646,0.00023685159,0.0045725317,0.0007344462],"domain_scores_gemma":[0.98326695,0.0012439461,0.00050315994,0.00039898837,0.013785994,0.0008009736],"candidate_categories":["metaresearch","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.035665154,0.00007516446,0.000237648,0.0015059107,0.0013838221,0.0011000508,0.0009877103,0.00015452935,0.0054796855],"category_scores_gemma":[0.0047788047,0.000080213766,0.000053394146,0.0029444245,0.00029713908,0.0007354067,0.000029771481,0.0012757936,0.000072267765],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000018974113,0.000021992295,0.09694314,0.0000062656504,0.000015093141,0.000007854133,0.000545899,0.000050394192,0.000108563094,0.00006822613,0.8396359,0.06257767],"study_design_scores_gemma":[0.00043276913,0.00022777719,0.3612681,0.0001600478,0.000006482785,0.000034509663,0.01406477,0.000631677,0.00028234025,0.006434502,0.61633456,0.00012244603],"about_ca_topic_score_codex":0.99976724,"about_ca_topic_score_gemma":0.9999998,"teacher_disagreement_score":0.26432496,"about_ca_system_score_codex":0.011133729,"about_ca_system_score_gemma":0.12673777,"threshold_uncertainty_score":0.9999369},"labels":[],"label_agreement":null},{"id":"W4289793429","doi":"10.2196/41424","title":"Correction: The Science of Learning Health Systems: Scoping Review of Empirical Research","year":2022,"lang":"en","type":"erratum","venue":"JMIR Medical Informatics","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Data science; Computer science; Empirical research; Knowledge management; Management science; Engineering","score_opus":0.428233754616679,"score_gpt":0.640756310504439,"score_spread":0.21252255588776003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4289793429","genre_codex":"other","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00042709406,0.11752235,0.0018515353,0.030867713,0.118947364,0.00951776,0.00005383571,0.00012784921,0.7206845],"genre_scores_gemma":[0.010430632,0.5434178,0.0009122892,0.019558579,0.0049953703,0.0025433325,0.0006039439,0.00013492514,0.41740313],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9632435,0.0022630463,0.004620761,0.00027928496,0.0290255,0.00056790264],"domain_scores_gemma":[0.98835033,0.0045123976,0.0029070105,0.0010791777,0.002815902,0.0003351833],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1111357,0.00018130887,0.0010380921,0.00086217583,0.0010080811,0.00017378038,0.0029820825,0.00020636184,0.0066638575],"category_scores_gemma":[0.02837878,0.000102921,0.00016897994,0.0055128066,0.0015688124,0.00044414963,0.0011944574,0.0037135936,0.00010369724],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037024263,0.000034362805,0.00004882391,0.013085539,0.000007426007,3.945934e-7,0.0039549726,0.000108619635,4.1341355e-8,0.00015821178,0.9684693,0.014128567],"study_design_scores_gemma":[0.00015158867,0.000481866,0.00009041579,0.12657183,0.000008954508,0.000033370157,0.023555342,0.11115143,0.0000014876628,0.00003849837,0.7377805,0.00013468594],"about_ca_topic_score_codex":0.000035935198,"about_ca_topic_score_gemma":0.00001148344,"teacher_disagreement_score":0.42589545,"about_ca_system_score_codex":0.00039831584,"about_ca_system_score_gemma":0.02841452,"threshold_uncertainty_score":0.99858487},"labels":[],"label_agreement":null},{"id":"W4290839652","doi":"10.4324/9781003309192-3","title":"Methodological Aspects","year":2022,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.8180558595572599,"score_gpt":0.6047411828071907,"score_spread":0.2133146767500692,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4290839652","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000006946248,0.0001180004,0.0018582774,0.0029808497,0.0007983447,0.00016814464,0.000012218435,0.00005944913,0.99399775],"genre_scores_gemma":[0.00077149225,0.00010688135,0.0046439315,0.0022275138,0.0001534808,0.0000121662815,0.000018239814,0.000013936043,0.9920524],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99516994,0.00024016683,0.00063824083,0.0005524777,0.0032502867,0.00014887677],"domain_scores_gemma":[0.99588704,0.0028081164,0.00031685896,0.00069455325,0.00020172988,0.000091699556],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.009380248,0.00018723324,0.00043267742,0.00027944945,0.00017110801,0.00012682266,0.00077253865,0.00015136311,0.75786334],"category_scores_gemma":[0.0009523497,0.0001164248,0.00024194016,0.00007794452,0.00006104249,0.00013078481,0.00038728476,0.00044045242,0.0081103835],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006119823,0.0000051003212,0.00001364951,6.9488857e-7,0.000010827581,0.000008355702,0.00002418331,0.000030619743,0.0000022936238,0.88500667,0.06494771,0.04994381],"study_design_scores_gemma":[0.000055913424,0.00006355062,0.00010499175,0.0000015533826,0.0000068484264,0.0000056613485,0.00002521373,0.0001285556,0.000004147884,0.3877411,0.61175764,0.00010483102],"about_ca_topic_score_codex":0.000003916514,"about_ca_topic_score_gemma":0.000021163773,"teacher_disagreement_score":0.74975294,"about_ca_system_score_codex":0.00008985798,"about_ca_system_score_gemma":0.0002574407,"threshold_uncertainty_score":0.9926619},"labels":[],"label_agreement":null},{"id":"W4291209168","doi":"10.1177/1035719x221119841","title":"Developmental evaluation during the COVID-19 pandemic: Practice-based learnings from projects in British Columbia, Canada","year":2022,"lang":"en","type":"article","venue":"Evaluation Journal of Australasia","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Centre for Advancing Health Outcomes; University of British Columbia","funders":"","keywords":"Context (archaeology); Leverage (statistics); Knowledge management; Embeddedness; Coronavirus disease 2019 (COVID-19); Pandemic; Ambidexterity; Stakeholder engagement; Public relations; Process management; Political science; Business; Sociology; Computer science","score_opus":0.21498372054834972,"score_gpt":0.4556638389750601,"score_spread":0.24068011842671036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4291209168","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99262136,0.00013966222,0.00010522997,0.0052861045,0.0006094721,0.00085116207,0.000027015885,0.0000075688695,0.00035241348],"genre_scores_gemma":[0.9966317,0.000009663759,0.0006851096,0.0018093532,0.00010913449,0.00012173714,0.000029178647,0.000011077609,0.0005930625],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9825811,0.004611411,0.0015414143,0.00034804584,0.010640408,0.00027764027],"domain_scores_gemma":[0.9939653,0.002084328,0.001756648,0.00019647877,0.0018094039,0.00018778397],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.047283057,0.0001145097,0.00026500373,0.0002239635,0.00084804447,0.0006601074,0.0006871485,0.00004665624,0.025781836],"category_scores_gemma":[0.015271136,0.00012389424,0.00008621834,0.0011050525,0.00005502074,0.00082896935,0.000090001035,0.00071140676,0.000011364208],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000098634235,0.000095578325,0.755562,0.000003474899,0.000036303485,0.00003409886,0.0023920743,0.19053322,0.0002508311,9.151627e-7,0.015503768,0.03548911],"study_design_scores_gemma":[0.004445442,0.00014405901,0.86159396,0.00002348682,0.000093604045,0.000578614,0.044354916,0.0410526,0.000023451206,0.00053001876,0.04697265,0.0001872208],"about_ca_topic_score_codex":0.34233454,"about_ca_topic_score_gemma":0.9006011,"teacher_disagreement_score":0.5582665,"about_ca_system_score_codex":0.005977111,"about_ca_system_score_gemma":0.032188762,"threshold_uncertainty_score":0.9978388},"labels":[],"label_agreement":null},{"id":"W4291746190","doi":"10.4324/9781003163954-40","title":"The Transformative Potential of Evaluation as a Policy Tool","year":2022,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Transformative learning; Political science; Psychology; Pedagogy","score_opus":0.1549965666721076,"score_gpt":0.4916493620269713,"score_spread":0.3366527953548637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4291746190","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003486109,0.00013442319,0.00050613296,0.0050062975,0.00043746748,0.00081331114,0.000050253813,0.000014445694,0.9926891],"genre_scores_gemma":[0.11853888,0.0005085785,0.00008507505,0.0006634517,0.0001772969,0.00008026039,0.00005494482,0.000018033046,0.87987345],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9915615,0.00023493571,0.001130899,0.00029133508,0.0066172704,0.00016407503],"domain_scores_gemma":[0.99689424,0.0007028156,0.0006580302,0.00062278385,0.0010766794,0.000045439174],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.010189065,0.00018770839,0.0002909611,0.00038750327,0.00043612355,0.00015058334,0.0006132639,0.000103533406,0.108757146],"category_scores_gemma":[0.000576295,0.00010565125,0.00029060987,0.00017425323,0.00013609859,0.00034513944,0.00011527826,0.0002786842,0.0008497933],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047714235,0.00000943605,0.0000015887865,0.0000024846133,0.000045045428,4.5756042e-7,0.0006949707,0.0005701286,0.0000108466265,0.6578426,0.005681658,0.3350931],"study_design_scores_gemma":[0.0003684206,0.00017559071,0.0001327693,0.000008286252,0.000053450814,0.000007568262,0.00069011404,0.008072751,0.00005137114,0.35776863,0.6325345,0.00013653113],"about_ca_topic_score_codex":0.000067256966,"about_ca_topic_score_gemma":0.00007486972,"teacher_disagreement_score":0.62685287,"about_ca_system_score_codex":0.00020109196,"about_ca_system_score_gemma":0.0021673222,"threshold_uncertainty_score":0.9999282},"labels":[],"label_agreement":null},{"id":"W4292195360","doi":"10.1016/s0197-2510(09)70118-4","title":"10.1016/s0197-2510(09)70118-4","year":2000,"lang":"en","type":"letter","venue":"Time to knit","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Medicine","score_opus":0.09229470461402309,"score_gpt":0.36265422468976094,"score_spread":0.2703595200757378,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292195360","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000024209955,0.00005289837,0.0000036626993,0.26222637,0.000018835019,0.00034749022,0.00007603231,0.00008991664,0.7371824],"genre_scores_gemma":[3.9294414e-7,8.453285e-7,0.00016110015,0.10848128,0.0025936356,0.00006297217,0.00019300076,0.000049884286,0.8884569],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9931595,0.00039739642,0.0010440937,0.00094290735,0.0038406572,0.0006154862],"domain_scores_gemma":[0.9965872,0.0008954493,0.00035440442,0.0015245359,0.00044943133,0.00018894186],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0026151575,0.00044392908,0.00066234963,0.00072188134,0.00020833123,0.0006000781,0.001796579,0.0005766532,0.99970704],"category_scores_gemma":[0.00044630637,0.00034409057,0.00027912174,0.0009011796,0.0000764382,0.00032993834,0.00019981546,0.0011283314,0.9996346],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014414438,0.000011773017,7.726694e-8,0.000003673037,0.000013640124,0.0000152521025,0.00001658587,0.00005439038,7.229865e-7,1.555504e-7,0.62964,0.37022933],"study_design_scores_gemma":[0.00022475806,0.00016632043,0.000014563222,0.000038283397,0.000032639124,0.000012928806,0.0000023166212,0.0004661532,0.000006977036,0.00009871399,0.9984707,0.0004656266],"about_ca_topic_score_codex":0.000018013729,"about_ca_topic_score_gemma":5.948658e-7,"teacher_disagreement_score":0.3697637,"about_ca_system_score_codex":0.00012772117,"about_ca_system_score_gemma":0.0005113454,"threshold_uncertainty_score":0.9999011},"labels":[],"label_agreement":null},{"id":"W4292257769","doi":"10.2352/j.imagingsci.technol.2022.66.4.040101","title":"From the Editor","year":2022,"lang":"en","type":"article","venue":"Journal of Imaging Science and Technology","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"European Space Agency; National Aeronautics and Space Administration","keywords":"Computer science","score_opus":0.05272822454534775,"score_gpt":0.44024104156273275,"score_spread":0.387512817017385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292257769","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78989726,0.0006364432,0.0006562765,0.2025373,0.0052297562,0.000051607058,0.0000035095402,0.000012675695,0.00097520096],"genre_scores_gemma":[0.99745274,0.000013639486,0.00065164344,0.0012371697,0.0005622381,0.0000019003055,5.0958377e-8,0.0000013808673,0.000079258054],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99726915,0.000055303204,0.0003241891,0.00013503939,0.002089532,0.00012675788],"domain_scores_gemma":[0.998257,0.00034589838,0.00034641026,0.00023668245,0.0007793488,0.000034664477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009413879,0.000039188846,0.000096767435,0.0004839299,0.0007355712,0.00017798143,0.0013703951,0.000009044689,0.00039209126],"category_scores_gemma":[0.0021363453,0.00002067492,0.000021168284,0.0019654047,0.0006765763,0.00047149864,0.00037297216,0.00028834856,0.000009579983],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013557076,0.00004644702,0.18796344,2.796686e-7,0.000006977782,0.000016785107,0.0013357598,0.00008710296,0.01366066,0.005345875,0.25715452,0.5343686],"study_design_scores_gemma":[0.000354718,0.00013998375,0.017777985,0.000005089116,0.000008752664,0.00028522604,0.023448545,0.0066132746,0.0012079962,0.116255745,0.83382934,0.00007335562],"about_ca_topic_score_codex":0.000008125779,"about_ca_topic_score_gemma":0.0000016394839,"teacher_disagreement_score":0.5766748,"about_ca_system_score_codex":0.000056578767,"about_ca_system_score_gemma":0.0006032899,"threshold_uncertainty_score":0.56574935},"labels":[],"label_agreement":null},{"id":"W4292508301","doi":"10.7202/1086391ar","title":"La référentialisation : une façon de modéliser l’évaluation de programme, entre théorie et pratique. Vers une comparaison des approches au Québec et en France","year":2006,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Humanities; Valuation (finance); Philosophy; Political science; Economics","score_opus":0.09559525034063282,"score_gpt":0.45102145325957216,"score_spread":0.35542620291893934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292508301","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6320381,0.0005994604,0.24047075,0.10832486,0.0012207077,0.0021096654,0.00003618749,0.00016258887,0.015037658],"genre_scores_gemma":[0.9703163,0.0002927435,0.017819827,0.0010368703,0.00049004616,0.00079943513,0.0013523547,0.00006789745,0.007824508],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9727477,0.020421969,0.0017227435,0.0010399246,0.003228552,0.000839153],"domain_scores_gemma":[0.9922721,0.0039946525,0.0012309673,0.0006942427,0.0015944941,0.00021353622],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.06593557,0.0005835616,0.000541657,0.00052025943,0.0006135182,0.0009156657,0.00053742813,0.00062425324,0.0010630622],"category_scores_gemma":[0.0039999248,0.0005873211,0.00024619908,0.0020106793,0.00035272675,0.0029518423,0.000071270624,0.00073341577,0.00031469358],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00014123094,0.0014651414,0.1367638,0.00020545423,0.0001005997,0.0000017533415,0.37780583,0.22988984,0.0032055948,0.05293696,0.0076062465,0.18987754],"study_design_scores_gemma":[0.0017394881,0.00020417321,0.71096873,0.00030249334,0.00024892305,0.000018265102,0.012642674,0.1904189,0.0018160286,0.032394264,0.04868249,0.0005635448],"about_ca_topic_score_codex":0.08421749,"about_ca_topic_score_gemma":0.161577,"teacher_disagreement_score":0.574205,"about_ca_system_score_codex":0.004118338,"about_ca_system_score_gemma":0.023351086,"threshold_uncertainty_score":0.9998501},"labels":[],"label_agreement":null},{"id":"W4292772345","doi":"10.3102/1442480","title":"Deconstructing Discipline: A Mixed-Methods Analysis of Disciplinary Policies in New York State's Capital District","year":2019,"lang":"en","type":"article","venue":"Proceedings of the 2019 AERA Annual Meeting","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Discipline; State (computer science); Capital (architecture); Public administration; Sociology; Regional science; Computer science; Political science; Social science; Geography; Archaeology","score_opus":0.04971538137891118,"score_gpt":0.4315899658800586,"score_spread":0.3818745845011474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292772345","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99417496,0.00015920443,0.0000878274,0.00068645034,0.00047994935,0.00028947956,0.000060436763,0.0000147388255,0.0040469365],"genre_scores_gemma":[0.9899326,0.000009807417,0.008403076,0.000022324715,0.00006125131,0.0000041491758,0.000003264454,0.000012316227,0.0015512372],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99633104,0.000092687784,0.0014242764,0.00045327083,0.0013392089,0.00035954322],"domain_scores_gemma":[0.99639577,0.0011750201,0.001412103,0.00029828757,0.0006239141,0.00009492092],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0065938435,0.0002060344,0.0006988219,0.00079965155,0.00013375361,0.00013940637,0.0011237749,0.000073725314,0.00014380181],"category_scores_gemma":[0.0020168254,0.00012993826,0.00033142147,0.0040538707,0.0001398417,0.000710476,0.0007428842,0.00023069089,0.000017131011],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043157983,0.00004577906,0.9530294,0.000031894015,0.0001043506,4.130691e-8,0.01802601,0.003213109,0.00642301,0.0007702052,0.0007047894,0.017608287],"study_design_scores_gemma":[0.00047858537,0.00010656988,0.906041,0.00021193644,0.00016069986,0.0000029537944,0.064745456,0.013925948,0.009082682,0.0048516956,0.0001441717,0.00024826254],"about_ca_topic_score_codex":0.0004928485,"about_ca_topic_score_gemma":0.00015254006,"teacher_disagreement_score":0.04698833,"about_ca_system_score_codex":0.00007171596,"about_ca_system_score_gemma":0.00021601321,"threshold_uncertainty_score":0.52987283},"labels":[],"label_agreement":null},{"id":"W4293180673","doi":"10.1002/ev.20490","title":"The importance of implementation: Putting evaluation policy to work","year":2022,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Work (physics); Government (linguistics); White paper; Public administration; Public relations; Early adopter; Program evaluation; Evaluation methods; Policy analysis; Business; Political science; Marketing","score_opus":0.2980319978182459,"score_gpt":0.5961758186242162,"score_spread":0.2981438208059703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293180673","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7828459,0.001607929,0.03320837,0.13422324,0.0071068397,0.016124846,0.00016824828,0.00017501465,0.024539622],"genre_scores_gemma":[0.9893297,0.000011052466,0.0031975934,0.0007444617,0.00044667287,0.0032922735,0.00011314333,0.000017273487,0.002847841],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9924928,0.00092516723,0.0010636223,0.0004202659,0.0048391996,0.0002589448],"domain_scores_gemma":[0.9951912,0.0013433011,0.0006796181,0.00059563154,0.0020966614,0.00009358202],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.032118186,0.000117078824,0.00016020292,0.00048968697,0.0018534898,0.0001744437,0.00045791568,0.00002514043,0.004750548],"category_scores_gemma":[0.0053201625,0.000093036164,0.00014039913,0.0033966824,0.000026385773,0.00032347848,0.00012327038,0.00010004611,0.000041214716],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054827553,0.00003213319,0.013882514,0.0000011670263,0.00002573282,1.2460131e-8,0.0013693314,0.03815974,0.0001446965,0.0032667504,0.05568473,0.88737833],"study_design_scores_gemma":[0.003172344,0.000496369,0.18513095,0.000009426855,0.00023120327,0.000004388635,0.010390384,0.10720741,0.0011449698,0.11851981,0.57342863,0.0002641207],"about_ca_topic_score_codex":0.000102137805,"about_ca_topic_score_gemma":0.00088735716,"teacher_disagreement_score":0.8871142,"about_ca_system_score_codex":0.00085165305,"about_ca_system_score_gemma":0.0024305116,"threshold_uncertainty_score":0.999446},"labels":[],"label_agreement":null},{"id":"W4293248311","doi":"10.5281/zenodo.4495007","title":"How the Common Impact Data Standard relates to other data standards","year":2020,"lang":"en","type":"report","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"LogicalOutcomes","funders":"","keywords":"Computer science","score_opus":0.4797793147424913,"score_gpt":0.506730900623332,"score_spread":0.026951585880840734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293248311","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00094235764,0.0010263652,0.022569818,0.0687049,0.0014612351,0.0031770545,0.15013751,0.0011068627,0.7508739],"genre_scores_gemma":[0.67994684,0.006092491,0.0027833928,0.0055469936,0.0070339367,7.549509e-7,0.19869871,0.01385447,0.08604239],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9868656,0.0014723714,0.00085534353,0.0015265662,0.008764472,0.00051566283],"domain_scores_gemma":[0.9865794,0.00032839164,0.00067243085,0.0071755373,0.0048090634,0.0004351749],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.025866047,0.00036040408,0.000574174,0.00039827146,0.0027205953,0.009021239,0.015054617,0.00016904283,0.047449328],"category_scores_gemma":[0.025854,0.00023037913,0.00010613682,0.0017165054,0.00023382844,0.0012271946,0.016433313,0.00094460126,0.007958008],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000095862335,0.000024921976,0.000025936404,0.00002078994,0.00009590333,0.0000062905124,0.00050386775,0.000056751713,0.000022539969,0.00011277057,0.81248915,0.18654522],"study_design_scores_gemma":[0.00029470577,0.0003725408,0.00056144595,0.0000709383,0.000056583245,0.00006875699,0.0007672869,0.0022997227,0.000013371174,0.0002242,0.99498254,0.00028789503],"about_ca_topic_score_codex":0.000085688866,"about_ca_topic_score_gemma":0.000023144295,"teacher_disagreement_score":0.6790045,"about_ca_system_score_codex":0.0007739824,"about_ca_system_score_gemma":0.00037093423,"threshold_uncertainty_score":0.9985777},"labels":[],"label_agreement":null},{"id":"W4293251238","doi":"10.1057/s41599-022-01157-w","title":"How can funders promote the use of research? Three converging views on relational research","year":2022,"lang":"en","type":"article","venue":"Humanities and Social Sciences Communications","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Johns Hopkins University","keywords":"Sustainability; Order (exchange); Work (physics); Political science; Public relations; Engineering ethics; Bridge (graph theory); Knowledge management; Sociology; Business; Computer science; Engineering; Medicine; Ecology","score_opus":0.9564556683276968,"score_gpt":0.6270769069684027,"score_spread":0.3293787613592941,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293251238","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5132821,0.0007991303,0.00016900073,0.40389293,0.00033026165,0.0014908342,0.00013130286,0.000038674032,0.079865746],"genre_scores_gemma":[0.99398476,0.00011740004,0.00037804124,0.0006434026,0.000038049184,0.00012460061,0.000009631211,0.0000037384089,0.0047003482],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9929388,0.0026282205,0.0003066531,0.00021876252,0.0036478415,0.00025967616],"domain_scores_gemma":[0.993008,0.0053831935,0.00017234766,0.0006836023,0.00073137257,0.00002147764],"candidate_categories":["sts"],"consensus_categories":["sts"],"category_scores_codex":[0.021342859,0.000060083545,0.00011726431,0.00038950212,0.017131979,0.00088914915,0.001863919,0.000022359054,0.00043587072],"category_scores_gemma":[0.00078208727,0.00004039194,0.000049325492,0.0013832616,0.004667633,0.00042327758,0.0012657448,0.0006158223,0.000006316594],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000057517436,0.00004736326,0.001940623,0.0000020044602,0.000005451125,8.4724235e-8,0.026311003,0.00017225037,0.000013665624,0.9560015,0.009729353,0.0057709245],"study_design_scores_gemma":[0.0001031434,0.00018326232,0.011907021,0.0000074808486,0.0000025892073,8.2831383e-7,0.1170619,0.011261837,0.000002692177,0.080039024,0.77936786,0.00006233287],"about_ca_topic_score_codex":0.0005023103,"about_ca_topic_score_gemma":0.006260766,"teacher_disagreement_score":0.8759625,"about_ca_system_score_codex":0.00012226065,"about_ca_system_score_gemma":0.0004609892,"threshold_uncertainty_score":0.9980411},"labels":[],"label_agreement":null},{"id":"W4294760705","doi":"10.4095/330521","title":"Resilient pathways report: co-creating new knowledge for understanding risk and resilience in British Columbia","year":2022,"lang":"en","type":"report","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Natural Resources Canada","funders":"","keywords":"Resilience (materials science); Environmental resource management; Geography; History; Environmental science","score_opus":0.31038545301678,"score_gpt":0.48881286520267286,"score_spread":0.17842741218589286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294760705","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09743323,0.003641866,0.02881253,0.00020870603,0.003363576,0.0035783155,0.0005291193,0.0001619103,0.8622708],"genre_scores_gemma":[0.4602207,0.0048901844,0.004458895,0.00011508057,0.00060068734,0.0004099477,0.00034002267,0.00009061975,0.52887386],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99116665,0.00044106023,0.0023508826,0.0015137792,0.0040018535,0.00052577065],"domain_scores_gemma":[0.99313766,0.0034075459,0.0016621785,0.00087642967,0.0006471179,0.0002690601],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.026703076,0.00024561776,0.00083694793,0.0004236376,0.0010839304,0.0020351757,0.0006168341,0.00024578394,0.0083934935],"category_scores_gemma":[0.013954992,0.00031641245,0.0002033281,0.0010393974,0.0001303688,0.00038205693,0.0003790052,0.00062800304,0.000017877372],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017942017,0.00008320361,0.35605654,0.000076769014,0.000023215278,0.00013805304,0.0012540141,0.00026833185,0.0000048349143,0.00019323114,0.5252922,0.11659164],"study_design_scores_gemma":[0.0017485888,0.00045638185,0.15587313,0.00055574434,0.00008781572,0.0008973655,0.030240769,0.009582104,0.00000674341,0.041801807,0.757735,0.0010145553],"about_ca_topic_score_codex":0.042344805,"about_ca_topic_score_gemma":0.5210825,"teacher_disagreement_score":0.47873768,"about_ca_system_score_codex":0.0018586707,"about_ca_system_score_gemma":0.0077665346,"threshold_uncertainty_score":0.9999288},"labels":[],"label_agreement":null},{"id":"W4295420340","doi":"10.1080/16549716.2022.2067396","title":"Building coherent monitoring and evaluation plans with the Evaluation Planning Tool for global health","year":2022,"lang":"en","type":"article","venue":"Global Health Action","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Global Affairs Canada","keywords":"Theory of change; Plan (archaeology); Data collection; Resource (disambiguation); Computer science; Value (mathematics); Process management; Public relations; Business; Management science; Knowledge management; Political science; Economics; Sociology; Management","score_opus":0.34613600032222835,"score_gpt":0.6126921370034176,"score_spread":0.26655613668118927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4295420340","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92915523,0.0011567499,0.047819648,0.015662499,0.0022175459,0.0034580391,0.00015854987,0.00005682375,0.0003149383],"genre_scores_gemma":[0.9960541,0.000024714647,0.00173678,0.0009810303,0.00027714454,0.00083613757,0.00006187008,0.0000062515273,0.000021956632],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99323124,0.001235699,0.0006305451,0.0004946408,0.003997293,0.0004105745],"domain_scores_gemma":[0.998003,0.00030300923,0.00073757314,0.00029827535,0.00052091776,0.00013719576],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.021476615,0.00015236244,0.00022482131,0.00006988835,0.0021417197,0.00022344466,0.00023043549,0.000032939643,0.000110686924],"category_scores_gemma":[0.0002453107,0.00010719203,0.000044144726,0.00068795064,0.000029942436,0.00041337498,0.00007660019,0.00016298445,0.0000046853847],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025712204,0.000039865114,0.0466952,0.00001949635,0.000015053891,1.02422256e-7,0.0004886427,0.08512921,0.0000060230022,0.0013735591,0.003719355,0.86225635],"study_design_scores_gemma":[0.0023467815,0.0013327746,0.62824386,0.000053001855,0.000043869393,0.00004953716,0.0075053866,0.32583374,0.000010462959,0.013515598,0.020875972,0.00018900735],"about_ca_topic_score_codex":0.00026855918,"about_ca_topic_score_gemma":0.00028378266,"teacher_disagreement_score":0.86206734,"about_ca_system_score_codex":0.0043806415,"about_ca_system_score_gemma":0.0025944205,"threshold_uncertainty_score":0.9994414},"labels":[],"label_agreement":null},{"id":"W4296162467","doi":"10.1002/hpm.3579","title":"Towards CR<sup>2</sup> evaluation: Culturally ‐reflexive and ‐responsive evaluation in crises times and beyond","year":2022,"lang":"en","type":"article","venue":"The International Journal of Health Planning and Management","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Centre Intégré Universitaire de Santé et de Services Sociaux du Centre-Sud-de-l'Île-de-Montréal","funders":"","keywords":"Reflexivity; Sociology; Anthropology","score_opus":0.21579762640680134,"score_gpt":0.529266080371993,"score_spread":0.31346845396519163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4296162467","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90554076,0.0073883384,0.00044162627,0.079338096,0.0006199522,0.0007306729,0.000013919012,0.0000064214237,0.005920196],"genre_scores_gemma":[0.99411535,0.00075893913,0.00074372836,0.0038940576,0.00008061633,0.000042528765,0.000009327697,0.000004291387,0.00035115765],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9943687,0.0010530947,0.00078398874,0.00020417241,0.0034514735,0.00013862598],"domain_scores_gemma":[0.9980679,0.00043164048,0.0006169519,0.000111706584,0.0007077002,0.000064083746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024909697,0.00010033704,0.00019734412,0.0004590023,0.00037431368,0.0002282614,0.00036514003,0.000015535927,0.00046305507],"category_scores_gemma":[0.00040999427,0.00006490582,0.000030375077,0.0001934331,0.000055437893,0.00034092955,0.00030370572,0.00020312298,0.0000023397865],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006446207,0.00009999012,0.00923212,0.000023080835,0.00021612071,0.000029933379,0.03600837,0.14712045,0.000009608889,0.0061551305,0.028905772,0.7715548],"study_design_scores_gemma":[0.0051024193,0.000978259,0.29777285,0.0002038104,0.00013164457,0.000385197,0.13203159,0.40800515,0.0000114572185,0.059666358,0.09545268,0.00025857688],"about_ca_topic_score_codex":0.00003066018,"about_ca_topic_score_gemma":0.000008165416,"teacher_disagreement_score":0.7712962,"about_ca_system_score_codex":0.0002571076,"about_ca_system_score_gemma":0.0003323776,"threshold_uncertainty_score":0.86332536},"labels":[],"label_agreement":null},{"id":"W4296187046","doi":"10.1787/911cc792-en","title":"Evaluation Framework and Practices: A comparative analysis of five OECD countries","year":2022,"lang":"en","type":"article","venue":"OECD Journal on Budgeting","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Institutionalisation; Quality assurance; Government (linguistics); Function (biology); Regional science; Political science; Quality (philosophy); Public administration; Economic growth; Public economics; Accounting; Business; Economics; Sociology; Operations management","score_opus":0.27895341521736694,"score_gpt":0.5586174930213613,"score_spread":0.2796640778039944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4296187046","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98675066,0.00051702594,0.0011684966,0.0028727923,0.00036069588,0.00018132257,0.00001999797,0.0000068949926,0.008122131],"genre_scores_gemma":[0.99709237,0.000079051126,0.0017039385,0.00082039693,0.00008260916,0.000016620459,0.000005989898,0.0000038931194,0.00019512561],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.992253,0.0020364837,0.0008555296,0.00026889067,0.0044205454,0.00016552575],"domain_scores_gemma":[0.9908607,0.0047367876,0.0029592102,0.00024443635,0.0011108697,0.00008798259],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.031186542,0.00011275036,0.00040696224,0.0008235444,0.0008892583,0.00033563978,0.00032450122,0.00003455047,0.012846502],"category_scores_gemma":[0.0031281789,0.00008562035,0.00013386674,0.00080490095,0.00006681443,0.00047682237,0.00011602477,0.00053523236,0.00006141159],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006931798,0.0004010312,0.19633098,0.000011050849,0.0022170166,0.000014253844,0.051761806,0.6666053,0.00033853532,0.012139141,0.006994845,0.06249286],"study_design_scores_gemma":[0.0011120727,0.00083625887,0.123992994,0.000038607475,0.0018193668,0.00004289169,0.055118926,0.7387169,0.00020658737,0.017220546,0.060597986,0.00029688142],"about_ca_topic_score_codex":0.000013810794,"about_ca_topic_score_gemma":0.000021902459,"teacher_disagreement_score":0.07233799,"about_ca_system_score_codex":0.00018242837,"about_ca_system_score_gemma":0.00040390834,"threshold_uncertainty_score":0.99759734},"labels":[],"label_agreement":null},{"id":"W4297275206","doi":"","title":"A meta-analysis of DDL research 1: Rationale, methodology and outcomes.","year":2016,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science","score_opus":0.5883216146352902,"score_gpt":0.5237753221270584,"score_spread":0.06454629250823185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297275206","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11996611,0.0047342386,0.6130203,0.14264867,0.00040187227,0.0016339271,0.0006140731,0.000112732334,0.1168681],"genre_scores_gemma":[0.8429492,0.00061782385,0.096984476,0.00032080023,0.0000172669,0.0002751585,0.00021948123,0.00003038744,0.05858541],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9520977,0.041444216,0.0016331284,0.0012277947,0.0032279976,0.00036912833],"domain_scores_gemma":[0.94165736,0.041978277,0.0012270779,0.0034042767,0.011538036,0.00019495912],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12985183,0.00029535545,0.0016320428,0.0019036537,0.0003548792,0.0004358419,0.0020042937,0.00031335175,0.0045730458],"category_scores_gemma":[0.020672858,0.00019753489,0.0010629478,0.0019950364,0.0006700763,0.00022576845,0.0023035868,0.00061254576,0.000076739285],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004995978,0.00081023056,0.055230156,0.000103617334,0.06351558,0.0000033466713,0.023469705,0.0006352053,0.0019916818,0.789603,0.004730202,0.05985729],"study_design_scores_gemma":[0.0016676892,0.0000033085337,0.25269875,0.00024823908,0.052712366,0.00000730778,0.0015323524,0.06678129,0.019892937,0.55903363,0.044078015,0.0013441052],"about_ca_topic_score_codex":0.0005359526,"about_ca_topic_score_gemma":0.0030719165,"teacher_disagreement_score":0.72298306,"about_ca_system_score_codex":0.00008415548,"about_ca_system_score_gemma":0.00070841325,"threshold_uncertainty_score":0.99633694},"labels":[],"label_agreement":null},{"id":"W4297674479","doi":"10.5281/zenodo.1179009","title":"What Does 'Evaluation' Mean For The Nime Community?","year":2015,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science","score_opus":0.18034011885843096,"score_gpt":0.4219220950226665,"score_spread":0.24158197616423552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297674479","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26170582,0.009703647,0.32795686,0.26181778,0.009768524,0.008616624,0.0004781932,0.00057170104,0.11938086],"genre_scores_gemma":[0.9479511,0.0011660458,0.012246432,0.0008977141,0.00013275216,0.00095751684,0.0008190769,0.00006493823,0.03576447],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.96670794,0.026595227,0.0014217043,0.000947073,0.003855361,0.00047271888],"domain_scores_gemma":[0.9511418,0.021205582,0.0013818642,0.0061746514,0.019833496,0.00026262004],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.15044743,0.0004349444,0.0005671851,0.0003410643,0.0016198094,0.0039614346,0.0049944394,0.00033556006,0.0013262641],"category_scores_gemma":[0.019333962,0.00027207006,0.00041812522,0.0007101581,0.0004624377,0.00088445004,0.0025326235,0.0012090856,0.00023632236],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008218992,0.0012205491,0.0028376381,0.0001399154,0.00037214556,7.637457e-7,0.14875636,0.004884667,0.00034679633,0.0877204,0.058686312,0.69495225],"study_design_scores_gemma":[0.0016877571,0.0000019300994,0.003738573,0.0011811301,0.0002657337,0.0000062078507,0.019337466,0.48352224,0.0048500374,0.29021835,0.19441628,0.0007743108],"about_ca_topic_score_codex":0.0007382005,"about_ca_topic_score_gemma":0.014781808,"teacher_disagreement_score":0.6941779,"about_ca_system_score_codex":0.00031910956,"about_ca_system_score_gemma":0.0018356787,"threshold_uncertainty_score":0.9999732},"labels":[],"label_agreement":null},{"id":"W4297846253","doi":"10.2139/ssrn.4103768","title":"Agenda for Practice Oriented Research: From Relevance versus Rigor to Relevance with Rigor","year":2022,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Center for Interuniversity Research and Analysis on Organizations; HEC Montréal","funders":"","keywords":"Relevance (law); Rigour; Engineering ethics; Political science; Sociology; Public relations; Psychology; Epistemology; Law; Engineering","score_opus":0.2658163949900732,"score_gpt":0.5305738425797831,"score_spread":0.2647574475897099,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297846253","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5969173,0.005714966,0.2503096,0.12107919,0.0068263854,0.0037496372,0.00028957796,0.00016827292,0.014945129],"genre_scores_gemma":[0.9581009,0.0013319664,0.014899699,0.0018279577,0.0010653322,0.0004502079,0.000031393454,0.00006782787,0.02222472],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9896615,0.0012826473,0.0007369392,0.0007341372,0.0051701237,0.0024146202],"domain_scores_gemma":[0.9880317,0.008529813,0.0005378585,0.00074160146,0.0019353033,0.00022370937],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.032701872,0.00019828079,0.0002959546,0.0004487564,0.0020204436,0.00030134007,0.0012889592,0.000045714554,0.0010501343],"category_scores_gemma":[0.014185758,0.0001494475,0.00011714392,0.002075001,0.000082530394,0.00094732625,0.00023997128,0.0029133377,0.0003050346],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.047171023,0.00083944254,0.0011202198,0.000008665351,0.00084326183,0.000066408094,0.0071027223,0.021731265,0.0017463188,0.29886436,0.10827207,0.5122343],"study_design_scores_gemma":[0.0031148721,0.004303324,0.0001679543,0.000012242337,0.00003445189,0.00009613002,0.023782182,0.0018943566,0.00014285327,0.07555881,0.8906698,0.00022298346],"about_ca_topic_score_codex":0.00012591104,"about_ca_topic_score_gemma":0.0022424213,"teacher_disagreement_score":0.78239775,"about_ca_system_score_codex":0.0026081246,"about_ca_system_score_gemma":0.007239278,"threshold_uncertainty_score":0.999863},"labels":[],"label_agreement":null},{"id":"W4297978706","doi":"10.7202/1086390ar","title":"La relation entre la théorie et la pratique en évaluation de programme : dialogue ET monologue","year":2006,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Valuation (finance); Humanities; Philosophy; Economics","score_opus":0.09561989389025295,"score_gpt":0.4602433589785144,"score_spread":0.3646234650882615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297978706","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5589056,0.0007577646,0.17887002,0.15314274,0.0029867475,0.0029372936,0.00009519905,0.0003221526,0.101982474],"genre_scores_gemma":[0.9662097,0.00091715384,0.018226044,0.0009911974,0.0005009253,0.00059316744,0.002519329,0.00007211622,0.009970378],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.92247546,0.07032113,0.0019993568,0.0011672666,0.0033128143,0.0007240061],"domain_scores_gemma":[0.9837034,0.012691736,0.0012455689,0.00079298724,0.0013962316,0.00017008794],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.1463729,0.0005547963,0.0005076806,0.0006796309,0.00033944868,0.0011842494,0.0005169222,0.0011625006,0.0015692897],"category_scores_gemma":[0.0104361065,0.0005444487,0.00024647274,0.0013755366,0.00020678948,0.0028536245,0.00011116965,0.0011793928,0.00078121026],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000103991595,0.0016174216,0.08179556,0.00010268424,0.00010848805,0.0000074110103,0.15845549,0.06915714,0.0015730755,0.34413853,0.015661327,0.32727888],"study_design_scores_gemma":[0.0015760306,0.00018515787,0.69596004,0.00019825278,0.00021705872,0.00005711576,0.0040667206,0.06800947,0.00053673604,0.13890031,0.08976287,0.0005302293],"about_ca_topic_score_codex":0.0008779679,"about_ca_topic_score_gemma":0.0034022008,"teacher_disagreement_score":0.6141645,"about_ca_system_score_codex":0.0013763353,"about_ca_system_score_gemma":0.011713175,"threshold_uncertainty_score":0.9999968},"labels":[],"label_agreement":null},{"id":"W4298083200","doi":"10.46692/9781447334927.012","title":"Commissions of inquiry and policy analysis","year":2018,"lang":"en","type":"other","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Policy analysis; Political science; Computer science; Data science; Public administration","score_opus":0.3347167648037691,"score_gpt":0.5951550426829958,"score_spread":0.2604382778792267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4298083200","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020916901,0.000082714374,0.0026183682,0.00084021204,0.000101446414,0.000067445224,0.000013328784,0.000020075073,0.99604726],"genre_scores_gemma":[0.010715762,0.00011514054,0.0017044393,0.00023482963,0.00020114766,0.0000021968815,0.000008140579,0.000023658627,0.9869947],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983894,0.00009625849,0.00034110635,0.00021546414,0.00087706005,0.00008068341],"domain_scores_gemma":[0.9987544,0.00018885586,0.00029820565,0.00054567336,0.00013428627,0.00007859159],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011509323,0.00009059417,0.00033477432,0.001707628,0.00003306767,0.000043024273,0.00029264993,0.000106900545,0.14465229],"category_scores_gemma":[0.0003435303,0.000053363372,0.00009261598,0.0015603979,0.00017266069,0.00003661775,0.000111223584,0.000037231617,0.0006282455],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001207626,0.000013853267,0.008985188,0.0000025435331,0.00011762008,6.779091e-8,0.0001780138,0.000002094438,0.0000025724157,0.002092792,0.977715,0.0108890245],"study_design_scores_gemma":[0.000090854766,0.000026926293,0.010734356,0.000014467651,0.00009799486,2.284415e-7,0.00038458713,0.000913669,0.000009663727,0.0011680285,0.9864866,0.00007259135],"about_ca_topic_score_codex":0.00038342678,"about_ca_topic_score_gemma":0.0009067532,"teacher_disagreement_score":0.14402406,"about_ca_system_score_codex":0.000008258029,"about_ca_system_score_gemma":0.00016759618,"threshold_uncertainty_score":0.8561296},"labels":[],"label_agreement":null},{"id":"W4298270500","doi":"10.7202/1086964ar","title":"L’activité évaluative entre cognition et réponse sociale : nouveaux défis pour les évaluateurs","year":2006,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Humanities; Philosophy; Psychology","score_opus":0.1674804283750438,"score_gpt":0.46858767860774153,"score_spread":0.30110725023269774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4298270500","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.57958317,0.0021331601,0.070009924,0.25309494,0.0073741414,0.0026954631,0.00028542467,0.00024690042,0.084576845],"genre_scores_gemma":[0.9513876,0.0007587973,0.0055206353,0.001955433,0.0011582819,0.00035990635,0.0016082232,0.0000915465,0.037159596],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.96063685,0.029805264,0.0020552205,0.0013958138,0.0052921227,0.0008147126],"domain_scores_gemma":[0.98595256,0.007353242,0.0016396578,0.0007958604,0.0040608123,0.0001979004],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.07830717,0.0007274003,0.000736279,0.00086475996,0.0008839681,0.00091396197,0.00058003515,0.00062769954,0.015026086],"category_scores_gemma":[0.007675658,0.0007346718,0.00043652716,0.0017608546,0.00029868225,0.003085101,0.00013636886,0.0008230863,0.0036271107],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003267515,0.0035914665,0.03194429,0.00013802925,0.00030666977,0.0000080715745,0.108202115,0.030917374,0.0065792315,0.049363058,0.15458971,0.6140332],"study_design_scores_gemma":[0.0033014917,0.00032977917,0.70524764,0.00034058877,0.000758601,0.00003406979,0.022122627,0.06095517,0.0050290376,0.13479917,0.06594144,0.001140406],"about_ca_topic_score_codex":0.00096578454,"about_ca_topic_score_gemma":0.0044715144,"teacher_disagreement_score":0.6733033,"about_ca_system_score_codex":0.001660711,"about_ca_system_score_gemma":0.010812152,"threshold_uncertainty_score":0.9995104},"labels":[],"label_agreement":null},{"id":"W4299357479","doi":"10.51952/9781447334927.ch011","title":"Commissions of inquiry and policy analysis","year":2018,"lang":"en","type":"book-chapter","venue":"Policy Press eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.4370931175856895,"score_gpt":0.5451051383542824,"score_spread":0.10801202076859295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4299357479","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00046409946,0.00020808335,0.00031624586,0.000572176,0.000104455416,0.00023206355,0.00015855246,0.000027164067,0.9979172],"genre_scores_gemma":[0.042499937,0.00015086663,0.00031522932,0.00065263256,0.00092813105,0.000013146199,0.000016889653,0.000027735634,0.95539546],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965056,0.00011475876,0.0010220361,0.00051145675,0.0015912799,0.0002548667],"domain_scores_gemma":[0.9964965,0.00056826556,0.00083430274,0.0012545584,0.0005874097,0.00025897322],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014483382,0.00030310315,0.0007815236,0.0021364226,0.0001607705,0.00015062059,0.000744606,0.00028360976,0.001571419],"category_scores_gemma":[0.00056507054,0.00022523638,0.000320602,0.00012660855,0.0006444822,0.000092148155,0.00051177276,0.00022803717,0.00008429201],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004003452,0.000021528256,0.00029040343,0.000034394772,0.0008018671,0.0000017113182,0.00692977,0.00004450132,0.00003557925,0.8976154,0.030124815,0.06406003],"study_design_scores_gemma":[0.00025985538,0.000084424806,0.0012328909,0.00006264279,0.00037984058,0.0000029732182,0.00006025902,0.00081955903,0.00016190209,0.12943876,0.8672327,0.00026424736],"about_ca_topic_score_codex":0.0010588911,"about_ca_topic_score_gemma":0.00022609848,"teacher_disagreement_score":0.83710784,"about_ca_system_score_codex":0.000058303005,"about_ca_system_score_gemma":0.00066584715,"threshold_uncertainty_score":0.9993413},"labels":[],"label_agreement":null},{"id":"W4299474551","doi":"10.7765/9781526111418","title":"Knowledge, democracy and action","year":2016,"lang":"en","type":"book","venue":"Manchester University Press eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Office of International Science and Engineering; Michigan Diabetes Research Center, University of Michigan; Universiti Sains Malaysia; Social Sciences and Humanities Research Council of Canada; University of Toronto; Higher Education Authority; Center for Depression Research and Clinical Care, University of Texas Southwestern Medical Center; Research Councils UK; Agency for Healthcare Research and Quality; European Commission; Université du Québec à Montréal; University of Brighton; Rijksuniversiteit Groningen; Houston Advanced Research Center; International Development Research Centre; Kırıkkale Üniversitesi; University of Victoria; University of Sussex; Harvard Business School","keywords":"Democracy; Action (physics); Political science; Law; Politics; Physics","score_opus":0.23401079150219695,"score_gpt":0.4080273506612632,"score_spread":0.17401655915906628,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4299474551","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00047771024,0.00007334606,0.0011898299,0.00019420109,0.00045623945,0.00026646268,0.000029634502,0.000057738012,0.99725485],"genre_scores_gemma":[0.0024436826,0.00010539168,0.000106482745,0.000086337364,0.00021019249,9.2412995e-7,0.0000070044493,0.000016787064,0.9970232],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979405,0.00019924295,0.00029326853,0.000590874,0.0007651613,0.00021095402],"domain_scores_gemma":[0.998041,0.0005184383,0.00034330803,0.0006244432,0.00032616823,0.00014664307],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008488549,0.00024726248,0.00033490974,0.0003300419,0.00029986852,0.00018197851,0.00059266266,0.0002789186,0.00030350202],"category_scores_gemma":[0.000040614384,0.0001937555,0.00011616725,0.000023050508,0.00018232051,0.00038855732,0.0004895352,0.00025041058,0.0002718968],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015407216,0.00003705613,0.00038058407,0.00010728545,0.00012729393,0.000032795873,0.0019539348,0.0000022951845,0.00006222119,0.07526617,0.3720838,0.54979247],"study_design_scores_gemma":[0.0005345188,0.000039460683,0.0007303668,0.00009895611,0.000060106955,0.000005793968,0.00009795938,0.000105581865,0.000076598815,0.00613369,0.9918634,0.0002535089],"about_ca_topic_score_codex":0.000003921556,"about_ca_topic_score_gemma":0.00002703593,"teacher_disagreement_score":0.61977965,"about_ca_system_score_codex":0.00024356648,"about_ca_system_score_gemma":0.00038147447,"threshold_uncertainty_score":0.790112},"labels":[],"label_agreement":null},{"id":"W4300074607","doi":"10.46692/9781447334927.003","title":"The policy analysis profession in Canada","year":2018,"lang":"en","type":"other","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.13079504763439884,"score_gpt":0.5363175659217475,"score_spread":0.40552251828734864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4300074607","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00022112497,0.000049349004,0.00010563014,0.005611193,0.00040641785,0.00014179212,0.000005413869,0.0000100876405,0.993449],"genre_scores_gemma":[0.017641755,0.00007052878,0.000076344375,0.00061684527,0.00018964143,0.000013270668,0.0000054484667,0.00002376407,0.9813624],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99729985,0.00021261873,0.00038134903,0.00023769887,0.0016940081,0.00017445545],"domain_scores_gemma":[0.99860954,0.0003421899,0.00025617075,0.0006468207,0.00009537935,0.000049895192],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0020624632,0.00009866439,0.00021561654,0.0006987449,0.00008494269,0.00008855586,0.00065202435,0.000062603125,0.057745613],"category_scores_gemma":[0.000368026,0.000042948683,0.000056487137,0.0024449192,0.000033746997,0.000029919924,0.00008305752,0.0000786524,0.0010215214],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001368596,0.0000026389505,0.029786982,4.915674e-7,0.000028963748,2.988448e-7,0.000021113628,0.0000100418865,8.9199574e-8,0.0005169424,0.9528192,0.016811842],"study_design_scores_gemma":[0.000059299644,0.000004287421,0.023779608,0.000008186852,0.000013419295,6.2762176e-8,0.0006684689,0.0029577955,0.0000016089134,0.00039085216,0.97204953,0.0000668765],"about_ca_topic_score_codex":0.9689116,"about_ca_topic_score_gemma":0.999822,"teacher_disagreement_score":0.056724094,"about_ca_system_score_codex":0.00031081348,"about_ca_system_score_gemma":0.0055685854,"threshold_uncertainty_score":0.9997563},"labels":[],"label_agreement":null},{"id":"W4300114924","doi":"10.4018/978-1-93177-741-4.ch009","title":"Culture and Anonymity in GSS Meetings","year":2003,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Anonymity; Hofstede's cultural dimensions theory; Apprehension; Social psychology; Psychology; Political science; Cognitive psychology","score_opus":0.09227089758479748,"score_gpt":0.40663782037524754,"score_spread":0.3143669227904501,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4300114924","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016232812,0.0004166975,0.000033929773,0.00025431233,0.00033662101,0.00029175807,0.000047713853,0.00002452294,0.9969712],"genre_scores_gemma":[0.16490832,0.00006028403,0.0013049934,0.0049035074,0.0001757497,0.000018583642,0.0000049487558,0.000028086743,0.8285955],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9969285,0.00007470456,0.00066617667,0.0006076447,0.0014803398,0.0002426232],"domain_scores_gemma":[0.99869883,0.00010668689,0.00032978388,0.0004615632,0.0002621421,0.00014102085],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017759036,0.0002981318,0.00045217923,0.00011699469,0.000097751974,0.00024420177,0.00037797124,0.0003710766,0.00049898727],"category_scores_gemma":[0.00021571852,0.000222972,0.000110618486,0.00005177675,0.00011603703,0.00010231095,0.00012993104,0.00030572063,0.00032739824],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018746456,0.0000067169312,0.0018706195,0.0000073506844,0.000011939923,0.000018810331,0.00019498267,0.000004589361,0.00000613778,0.962113,0.021036612,0.014710469],"study_design_scores_gemma":[0.0003772951,0.00004927351,0.0009989768,0.00007334901,0.000013378548,0.000019915302,0.00007290031,0.0000482836,0.000012310217,0.56117934,0.43690366,0.00025134647],"about_ca_topic_score_codex":0.0000348657,"about_ca_topic_score_gemma":0.00058409857,"teacher_disagreement_score":0.41586703,"about_ca_system_score_codex":0.00016041813,"about_ca_system_score_gemma":0.00024134129,"threshold_uncertainty_score":0.9092534},"labels":[],"label_agreement":null},{"id":"W4300131131","doi":"10.7202/1088238ar","title":"Une application de la théorie de la généralisabilité à la planification des enquêtes sur les acquisitions des élèves","year":2003,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.10171697274235064,"score_gpt":0.46369406361871546,"score_spread":0.3619770908763648,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4300131131","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6848228,0.002016594,0.26513493,0.010716911,0.0005255018,0.0009864228,0.000057141824,0.00014134009,0.035598364],"genre_scores_gemma":[0.9700143,0.001721525,0.024474407,0.000254063,0.0002055406,0.0005508779,0.00032119465,0.000048987087,0.0024091245],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9660477,0.029832209,0.0011901113,0.0008011182,0.0015916778,0.0005371984],"domain_scores_gemma":[0.9824446,0.014332465,0.0006789158,0.00082735636,0.0014910045,0.00022564994],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.076266296,0.00039314284,0.00035265193,0.00039006709,0.0009101513,0.00090987294,0.00047897358,0.00061766955,0.0024544308],"category_scores_gemma":[0.014189451,0.0004017232,0.00018529425,0.0016523823,0.0011061053,0.0017423806,0.000040421808,0.0004968703,0.00036256056],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050953415,0.0015188084,0.22376895,0.00020647093,0.00009152554,0.0000012368902,0.17005117,0.01865776,0.011710503,0.3897763,0.004889538,0.1792768],"study_design_scores_gemma":[0.0005914921,0.0000667059,0.6145663,0.000117525466,0.00013884137,0.000055124357,0.008184723,0.012142228,0.0027447015,0.33898854,0.022087023,0.00031679432],"about_ca_topic_score_codex":0.00094490056,"about_ca_topic_score_gemma":0.0007246065,"teacher_disagreement_score":0.39079735,"about_ca_system_score_codex":0.0013472167,"about_ca_system_score_gemma":0.0042361575,"threshold_uncertainty_score":0.9998435},"labels":[],"label_agreement":null},{"id":"W4300193344","doi":"10.7202/1086393ar","title":"L’étude du raisonnement dans les pratiques évaluatives","year":2006,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Humanities; Philosophy","score_opus":0.16084169475948157,"score_gpt":0.4873622230020045,"score_spread":0.3265205282425229,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4300193344","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6726817,0.0020973275,0.14524865,0.117980026,0.005104403,0.0016125139,0.00005686831,0.00014740965,0.055071127],"genre_scores_gemma":[0.95732456,0.00076350285,0.009207599,0.00070646504,0.0011912244,0.0002892766,0.0005231228,0.000046792054,0.02994746],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.97838867,0.013949091,0.0019349381,0.0010014083,0.004187541,0.00053836964],"domain_scores_gemma":[0.99308306,0.002775732,0.0010954253,0.00080028584,0.0021141535,0.00013134103],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.060438897,0.00049709185,0.00048177844,0.0005134139,0.00070682203,0.00074156525,0.00061574683,0.0003544505,0.015008293],"category_scores_gemma":[0.003663245,0.00045623624,0.00023967557,0.0011483424,0.00023443915,0.0019758758,0.00011245207,0.0004175766,0.0016289315],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000064403386,0.0020164852,0.18478662,0.000096081385,0.00013319208,0.0000028295171,0.39994127,0.03845291,0.005238109,0.10055432,0.09410078,0.17461301],"study_design_scores_gemma":[0.0010012109,0.00022978435,0.827322,0.00013396518,0.00015929795,0.000010390697,0.012209351,0.065682285,0.0030448232,0.01644934,0.07327937,0.00047817527],"about_ca_topic_score_codex":0.0015825514,"about_ca_topic_score_gemma":0.012835654,"teacher_disagreement_score":0.6425354,"about_ca_system_score_codex":0.0011041821,"about_ca_system_score_gemma":0.0038461841,"threshold_uncertainty_score":0.99978894},"labels":[],"label_agreement":null},{"id":"W4300594616","doi":"10.1086/721273","title":"Fact Construction and Categorization in Assessment: Cultivating Epistemic Justice and Resistance in Social Work Assessment","year":2022,"lang":"en","type":"article","venue":"Social Service Review","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Injustice; Framing (construction); Categorization; Obligation; Dignity; Epistemology; Sociology; Conversation; Conversation analysis; Accountability; Resistance (ecology); Social psychology; Psychology; Political science; Law","score_opus":0.1478025762095761,"score_gpt":0.4906335715665985,"score_spread":0.3428309953570224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4300594616","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7209033,0.03982911,0.0030042299,0.18138182,0.00136953,0.004552025,0.0000892068,0.000121100544,0.048749723],"genre_scores_gemma":[0.9867666,0.005619818,0.003754601,0.0032172543,0.0001251347,0.0002644256,0.00005809888,0.000015744981,0.00017832703],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99612486,0.0012404323,0.0008671206,0.00041643836,0.0011311535,0.00022000322],"domain_scores_gemma":[0.9987637,0.00035924232,0.00052594603,0.0001215876,0.00018840737,0.00004114404],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0058464585,0.00014515125,0.00043152453,0.0001537115,0.0009860025,0.00013076252,0.00020832162,0.000054179305,0.00050526863],"category_scores_gemma":[0.00015717179,0.00013891427,0.000038771912,0.0028008088,0.000046667425,0.00039750893,0.00018892314,0.00038041992,0.000004759163],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007087245,0.00024765937,0.41347295,0.006505496,0.00003396421,0.000011652082,0.014672609,0.00013072693,0.00032450404,0.22490776,0.0021221437,0.33749968],"study_design_scores_gemma":[0.0014420929,0.00003708253,0.90600055,0.0007685759,0.00011852647,0.000006096785,0.016998913,0.0009718395,0.0000016187214,0.038039606,0.03515906,0.00045601357],"about_ca_topic_score_codex":0.000067306675,"about_ca_topic_score_gemma":0.00059681333,"teacher_disagreement_score":0.49252763,"about_ca_system_score_codex":0.00046552243,"about_ca_system_score_gemma":0.00030901877,"threshold_uncertainty_score":0.7583633},"labels":[],"label_agreement":null},{"id":"W4300665063","doi":"","title":"Using Item Analysis to Assess Objectively the Quality of the Calgary-Cambridge OSCE Checklist","year":2011,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Checklist; Quality (philosophy); Psychology; Medical education; Medicine; Cognitive psychology","score_opus":0.8442899180310458,"score_gpt":0.7097906095390945,"score_spread":0.13449930849195135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4300665063","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9648342,0.00067400344,0.00797527,0.00030114764,0.00061013637,0.0006281427,0.000055044893,0.0000114231325,0.024910616],"genre_scores_gemma":[0.9971019,0.00019607335,0.00087737036,0.0006856673,0.000069316564,0.000025252748,0.0000018714682,0.000018812518,0.0010237129],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9908951,0.002258935,0.0021643238,0.00058762333,0.0037329388,0.00036106614],"domain_scores_gemma":[0.99167174,0.0020011258,0.002679268,0.001552324,0.0018657626,0.00022975406],"candidate_categories":["scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.020848071,0.00028810988,0.0010262919,0.0010287033,0.000623502,0.0013130059,0.0071319165,0.00009214644,0.011358153],"category_scores_gemma":[0.0039477856,0.00015522855,0.0006217174,0.0068511316,0.00027563475,0.0021454094,0.0017172465,0.00040512288,0.000027611079],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001376421,0.00020976418,0.9669328,0.000010907676,0.0004535824,0.0000013098527,0.0010110597,0.00088235247,0.019591387,0.00078392745,0.0040107286,0.00597455],"study_design_scores_gemma":[0.00021738025,0.000007893413,0.9742464,0.000053881628,0.00026503816,0.000002208089,0.00074421725,0.0023843062,0.018488642,0.0021018025,0.0012662131,0.00022202043],"about_ca_topic_score_codex":0.005667386,"about_ca_topic_score_gemma":0.0010877596,"teacher_disagreement_score":0.03226771,"about_ca_system_score_codex":0.00015795385,"about_ca_system_score_gemma":0.0006445186,"threshold_uncertainty_score":0.99972373},"labels":[],"label_agreement":null},{"id":"W4300785760","doi":"10.7202/1087032ar","title":"Évaluation de programme et recherche évaluative : des activités distinctes","year":2005,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Valuation (finance); Humanities; Philosophy; Political science; Sociology; Economics","score_opus":0.685414406203407,"score_gpt":0.6007644560936577,"score_spread":0.0846499501097493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4300785760","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62704647,0.0020466256,0.16608079,0.17653395,0.002336575,0.002095527,0.00005057805,0.00019635713,0.023613129],"genre_scores_gemma":[0.8002688,0.0014083061,0.16604075,0.002055728,0.00085359573,0.000603906,0.00048850535,0.000077424906,0.028202966],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9265145,0.06354057,0.002181463,0.0014752487,0.005074787,0.0012134025],"domain_scores_gemma":[0.98061657,0.013574327,0.0011809099,0.001006666,0.0032651112,0.00035639427],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.24873136,0.0006378046,0.0006108054,0.000668151,0.00065366086,0.0010619673,0.000721035,0.0007639036,0.010559681],"category_scores_gemma":[0.046209197,0.00061089126,0.00031798537,0.0022774187,0.00036927918,0.004227106,0.00014232825,0.0011996338,0.0028371832],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00006827463,0.0008405921,0.013701481,0.000048406564,0.00008168803,5.220289e-7,0.19923458,0.012396618,0.0017731277,0.0061741825,0.0037602913,0.7619203],"study_design_scores_gemma":[0.0016155668,0.0003916468,0.6111464,0.00032173915,0.00035584494,0.000031777243,0.0102813905,0.23106164,0.0050722444,0.0789058,0.060075246,0.0007407381],"about_ca_topic_score_codex":0.00046608367,"about_ca_topic_score_gemma":0.0046928786,"teacher_disagreement_score":0.7611795,"about_ca_system_score_codex":0.004685691,"about_ca_system_score_gemma":0.014144364,"threshold_uncertainty_score":0.999975},"labels":[],"label_agreement":null},{"id":"W4300865418","doi":"10.18666/jnel-2022-11213","title":"Social Innovation through Evaluation Science Dynamic Learning Approaches for Nonprofit Leaders Driving Social Change","year":2022,"lang":"en","type":"article","venue":"Journal of Nonprofit Education and Leadership","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact","funders":"","keywords":"Process (computing); Field (mathematics); Knowledge management; Public relations; Organizational learning; Business; Political science; Computer science","score_opus":0.769876198722961,"score_gpt":0.5556203033682248,"score_spread":0.21425589535473621,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4300865418","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9351229,0.000518468,0.005925986,0.05421256,0.0018738844,0.0010078645,0.000003509098,0.00002005431,0.001314787],"genre_scores_gemma":[0.9950594,0.00000660982,0.0012993995,0.001395085,0.00077482616,0.00022457796,0.000023865558,0.000016767926,0.0011995191],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9944856,0.00058001536,0.0010073537,0.0003813426,0.0031986062,0.00034709385],"domain_scores_gemma":[0.995828,0.00033133602,0.0015509533,0.00012923112,0.002097446,0.00006304162],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.020434875,0.00016380881,0.00029445742,0.0010316076,0.0024194259,0.00036065388,0.0005331513,0.00007281158,0.00039370285],"category_scores_gemma":[0.0016790507,0.00014752045,0.00011873766,0.002550961,0.0003490046,0.0019114526,0.00007895717,0.00055884436,0.0000071722466],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020794963,0.0004360348,0.029286236,0.000084026804,0.000050931387,3.41612e-7,0.20885643,0.0009855898,0.0013768511,0.018293455,0.0059097633,0.7345124],"study_design_scores_gemma":[0.002090231,0.00067471573,0.20904627,0.000043234395,0.00013272761,0.00006232514,0.6826897,0.05867058,0.00019648591,0.016201321,0.029723361,0.00046899208],"about_ca_topic_score_codex":0.000007112464,"about_ca_topic_score_gemma":0.000008948566,"teacher_disagreement_score":0.7340434,"about_ca_system_score_codex":0.00061006914,"about_ca_system_score_gemma":0.0023712143,"threshold_uncertainty_score":0.9988793},"labels":[],"label_agreement":null},{"id":"W4300885756","doi":"10.51952/9781447334927.ch002","title":"The policy analysis profession in Canada","year":2018,"lang":"en","type":"book-chapter","venue":"Policy Press eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.22757285867885083,"score_gpt":0.4917554903432765,"score_spread":0.2641826316644257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4300885756","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00052970427,0.00014441431,0.000023003988,0.002590733,0.0003233492,0.0004282408,0.00007996735,0.000016238457,0.99586433],"genre_scores_gemma":[0.06355401,0.000100741956,0.000023729992,0.0013415836,0.00085370895,0.00005348323,0.00001188688,0.000026999563,0.9340339],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9948465,0.0002204482,0.0011470811,0.00056592637,0.002733935,0.0004860805],"domain_scores_gemma":[0.9961774,0.0009575158,0.0007509164,0.0014737311,0.00045465791,0.00018583173],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023407235,0.00033324465,0.0005630886,0.0010651465,0.00035311587,0.0002794314,0.0014525187,0.00018866562,0.0006933103],"category_scores_gemma":[0.00062044075,0.00019506832,0.00022296041,0.00018566696,0.00018192979,0.000080403355,0.00041681674,0.0004263986,0.00012773844],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000089411726,0.000011579131,0.0014973049,0.000018230225,0.00052477606,0.00001152204,0.0026117377,0.00028867554,0.0000048588886,0.71030265,0.110258274,0.17438096],"study_design_scores_gemma":[0.00018428422,0.000019151847,0.0022453163,0.000038751452,0.00007667152,0.0000010757861,0.00009904456,0.0019192805,0.000037866306,0.05680643,0.9383265,0.00024565158],"about_ca_topic_score_codex":0.89449155,"about_ca_topic_score_gemma":0.98294663,"teacher_disagreement_score":0.8280682,"about_ca_system_score_codex":0.0010922506,"about_ca_system_score_gemma":0.011072902,"threshold_uncertainty_score":0.9945334},"labels":[],"label_agreement":null},{"id":"W4300936480","doi":"10.46692/9781847428585.008","title":"Extending research practices","year":2010,"lang":"en","type":"other","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science","score_opus":0.8027186283874751,"score_gpt":0.7379887056549993,"score_spread":0.0647299227324758,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4300936480","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003403953,0.00018518779,0.00023459017,0.0020606269,0.0011533258,0.00021989626,0.0000040069895,0.00008208552,0.9960262],"genre_scores_gemma":[0.0009306643,0.0001782273,0.0040171184,0.00017906817,0.0007178496,0.000021628024,0.000004466631,0.00009646358,0.9938545],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99399465,0.00045672074,0.00033116384,0.0004826898,0.004474486,0.00026030254],"domain_scores_gemma":[0.9959636,0.0019039173,0.00068508193,0.00095853896,0.00038929412,0.000099598314],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0191586,0.00011167132,0.00019362966,0.0011553947,0.00013806288,0.0005657635,0.0010094536,0.00028133576,0.4686663],"category_scores_gemma":[0.0071035624,0.00006752747,0.00005293608,0.0007414141,0.000108458335,0.00020195081,0.00018962873,0.0007994389,0.02835501],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016276266,0.000016700127,0.00046872205,0.0000024867336,0.000005128938,0.0000014097348,0.00003528331,1.7030013e-7,0.000045332905,0.006964748,0.92526853,0.06718989],"study_design_scores_gemma":[0.00007239009,0.000021576552,0.0003280776,0.000018844446,0.0000026120479,0.0000022014456,0.00041572918,0.00024701844,0.000030278348,0.0032133674,0.99555254,0.0000953537],"about_ca_topic_score_codex":0.00032552812,"about_ca_topic_score_gemma":0.0033895,"teacher_disagreement_score":0.44031128,"about_ca_system_score_codex":0.000020873149,"about_ca_system_score_gemma":0.00036564036,"threshold_uncertainty_score":0.9724015},"labels":[],"label_agreement":null},{"id":"W4301182923","doi":"10.4212/cjhp.3366","title":"Using Evidence to Inform Advocacy and Training Priorities","year":2022,"lang":"en","type":"article","venue":"The Canadian Journal of Hospital Pharmacy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Training (meteorology); Political science; Medical education; Public relations; Medicine; Geography","score_opus":0.44296539979724786,"score_gpt":0.5167680648059454,"score_spread":0.07380266500869753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4301182923","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97476417,0.0007616921,0.00008914838,0.022111993,0.0011191899,0.0001474553,0.0000065012264,0.0000022538454,0.0009976259],"genre_scores_gemma":[0.9970069,0.000016312497,0.0003936092,0.0021186655,0.00015296681,0.0000030583776,1.309197e-7,0.0000055479977,0.00030281587],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99789447,0.00014162742,0.0004846065,0.00009477447,0.0011580893,0.00022644608],"domain_scores_gemma":[0.998428,0.00036315818,0.000282773,0.00014582086,0.000349994,0.00043028823],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0052875965,0.00007870037,0.00014864722,0.00033813898,0.0011662114,0.00038441914,0.0006922216,0.000006849694,0.0017348075],"category_scores_gemma":[0.0008941215,0.000053259286,0.00006016952,0.0005767401,0.00008661069,0.00084177515,0.00008236584,0.00029322776,0.0000136051],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018366822,0.00003334159,0.13976069,0.000012986925,0.00011816398,0.00022203181,0.26450184,0.039415896,0.0005041571,0.0036020034,0.027390998,0.52425426],"study_design_scores_gemma":[0.0016860618,0.0016533718,0.09511764,0.00012868538,0.00009436817,0.00082942354,0.08673057,0.016428674,0.0002436272,0.012257432,0.78426856,0.00056159357],"about_ca_topic_score_codex":0.0030105584,"about_ca_topic_score_gemma":0.0031995801,"teacher_disagreement_score":0.75687754,"about_ca_system_score_codex":0.00025166286,"about_ca_system_score_gemma":0.004941091,"threshold_uncertainty_score":0.99917775},"labels":[],"label_agreement":null},{"id":"W4302011939","doi":"10.32920/ryerson.14652003.v1","title":"Seeking equity for mental health in public education in Ontario: a critical discourse analysis of four policy documents","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Athabasca University; Toronto Metropolitan University","funders":"Ministère de l’Éducation, Gouvernement de l’Ontario","keywords":"Mental health; Equity (law); Curriculum; Christian ministry; Diversity (politics); Critical discourse analysis; Mental illness; Psychology; Health policy; Education policy; Sociology; Political science; Public relations; Pedagogy; Public health; Medicine; Higher education; Nursing; Psychiatry; Law","score_opus":0.3706279421120325,"score_gpt":0.6342858908926464,"score_spread":0.26365794878061394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4302011939","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85190135,0.00008309204,0.010955138,0.10442409,0.0016974967,0.0023488256,0.00029375983,0.000020242034,0.028275982],"genre_scores_gemma":[0.99096745,0.000024828896,0.003243062,0.0014547032,0.00003368744,0.0003208494,0.00046386974,0.000007625662,0.0034838957],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9948422,0.00053036225,0.0016065614,0.0006888373,0.0019355924,0.00039646783],"domain_scores_gemma":[0.9977819,0.00057936047,0.0005596422,0.00065889827,0.0002719858,0.00014823272],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011211528,0.00018293416,0.00074250513,0.0038554932,0.00013062383,0.00030828733,0.0008457193,0.00008875114,0.008560123],"category_scores_gemma":[0.0012586281,0.00015794752,0.00029260796,0.0021145071,0.00005842753,0.0004484262,0.0013518814,0.0004547034,0.000004656049],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006668939,0.0013809497,0.8310634,0.000056515673,0.00017039345,2.821107e-7,0.008034299,0.0046524135,0.0000073099905,0.050322205,0.0032444112,0.10100111],"study_design_scores_gemma":[0.0007006801,0.00013539738,0.8368419,0.00007137536,0.00007390054,5.887956e-7,0.01211364,0.07604386,0.000002159229,0.06554722,0.008190138,0.000279166],"about_ca_topic_score_codex":0.21154666,"about_ca_topic_score_gemma":0.787776,"teacher_disagreement_score":0.57622933,"about_ca_system_score_codex":0.003697088,"about_ca_system_score_gemma":0.019702403,"threshold_uncertainty_score":0.99234617},"labels":[],"label_agreement":null},{"id":"W4302011956","doi":"10.32920/ryerson.14652003","title":"Seeking equity for mental health in public education in Ontario: a critical discourse analysis of four policy documents","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Athabasca University; Toronto Metropolitan University","funders":"","keywords":"Mental health; Equity (law); Curriculum; Critical discourse analysis; Christian ministry; Diversity (politics); Mental illness; Psychology; Health policy; Education policy; Policy analysis; Political science; Public policy; Public relations; Sociology; Pedagogy; Public health; Public administration; Medicine; Higher education; Nursing; Psychiatry; Law","score_opus":0.3706279421120325,"score_gpt":0.6342858908926464,"score_spread":0.26365794878061394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4302011956","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85190135,0.00008309204,0.010955138,0.10442409,0.0016974967,0.0023488256,0.00029375983,0.000020242034,0.028275982],"genre_scores_gemma":[0.99096745,0.000024828896,0.003243062,0.0014547032,0.00003368744,0.0003208494,0.00046386974,0.000007625662,0.0034838957],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9948422,0.00053036225,0.0016065614,0.0006888373,0.0019355924,0.00039646783],"domain_scores_gemma":[0.9977819,0.00057936047,0.0005596422,0.00065889827,0.0002719858,0.00014823272],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011211528,0.00018293416,0.00074250513,0.0038554932,0.00013062383,0.00030828733,0.0008457193,0.00008875114,0.008560123],"category_scores_gemma":[0.0012586281,0.00015794752,0.00029260796,0.0021145071,0.00005842753,0.0004484262,0.0013518814,0.0004547034,0.000004656049],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006668939,0.0013809497,0.8310634,0.000056515673,0.00017039345,2.821107e-7,0.008034299,0.0046524135,0.0000073099905,0.050322205,0.0032444112,0.10100111],"study_design_scores_gemma":[0.0007006801,0.00013539738,0.8368419,0.00007137536,0.00007390054,5.887956e-7,0.01211364,0.07604386,0.000002159229,0.06554722,0.008190138,0.000279166],"about_ca_topic_score_codex":0.21154666,"about_ca_topic_score_gemma":0.787776,"teacher_disagreement_score":0.57622933,"about_ca_system_score_codex":0.003697088,"about_ca_system_score_gemma":0.019702403,"threshold_uncertainty_score":0.99234617},"labels":[],"label_agreement":null},{"id":"W4306402948","doi":"10.33422/5th.educationconf.2022.08.10","title":"A Bi-Epistemic Community Project: Accounting for Socio-Political Realities","year":2022,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Brock University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Politics; Epistemic community; Accounting; Epistemology; Political science; Computer science; Business; Philosophy","score_opus":0.4289458845954921,"score_gpt":0.5461762982796131,"score_spread":0.11723041368412102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4306402948","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76925296,0.000024329654,0.004658191,0.01791837,0.0006324864,0.00096719613,0.00016518944,0.00014811096,0.20623316],"genre_scores_gemma":[0.98041165,0.0000011355766,0.0011154892,0.0028997674,0.0000778774,0.000347639,0.000032825094,0.0000081460785,0.015105469],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967312,0.00077559846,0.00053494057,0.0001907401,0.0014292732,0.00033819655],"domain_scores_gemma":[0.9960869,0.0029130885,0.00014729756,0.00048088466,0.0003205864,0.00005126875],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.012621242,0.00008996429,0.00018509275,0.00018795943,0.0017072706,0.00022664011,0.00070088287,0.000028964505,0.0032220013],"category_scores_gemma":[0.0012229896,0.000067973444,0.000110944486,0.00040046795,0.00008418181,0.00027763896,0.00038734014,0.00030630914,0.00005914378],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006928685,0.00022869404,0.026883306,0.00003232421,0.000022043121,5.3403596e-7,0.008633215,0.00013940393,0.00016019534,0.8303644,0.121506445,0.011960125],"study_design_scores_gemma":[0.0009542242,0.00037648762,0.0076297526,0.0000069612415,0.000016563756,0.000018370874,0.3267852,0.028986325,0.00017674013,0.29525942,0.33950207,0.00028792044],"about_ca_topic_score_codex":0.0008121134,"about_ca_topic_score_gemma":0.000167569,"teacher_disagreement_score":0.53510505,"about_ca_system_score_codex":0.00020349036,"about_ca_system_score_gemma":0.0004969931,"threshold_uncertainty_score":0.99959236},"labels":[],"label_agreement":null},{"id":"W4307053258","doi":"10.1002/ev.20514","title":"Identity as a compass when navigating uncharted equitable spaces: Our queer evaluation practices","year":2022,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan; Saskatchewan Health","funders":"","keywords":"Queer; Dialogic; Situated; Sociology; Normative; Identity (music); Epistemology; Norm (philosophy); Social psychology; Psychology; Computer science; Aesthetics; Gender studies; Pedagogy","score_opus":0.37946722076513645,"score_gpt":0.5847148136120114,"score_spread":0.20524759284687494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307053258","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80582666,0.0019333476,0.06489756,0.05557442,0.012585679,0.012019774,0.00017755994,0.0005451508,0.046439826],"genre_scores_gemma":[0.97967243,0.000016730251,0.004318316,0.0006521001,0.00052723126,0.002972892,0.00040223126,0.00003389493,0.0114041995],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9861952,0.0024654856,0.0011017299,0.0008573209,0.008921117,0.00045914954],"domain_scores_gemma":[0.99234587,0.0011687668,0.0019942794,0.00074758456,0.0035723848,0.0001711227],"candidate_categories":["metaresearch","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.051013894,0.000233402,0.00032406437,0.00045279213,0.0026006922,0.0010415043,0.00063263736,0.000080544814,0.019863738],"category_scores_gemma":[0.015418283,0.00022619047,0.00021377247,0.0018706643,0.000024309324,0.0035016218,0.00023747071,0.0004018565,0.0005076299],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003123172,0.00056424306,0.00774694,0.000022054855,0.00021558389,6.091701e-7,0.0125857955,0.17334187,0.0023594282,0.0066846665,0.18165368,0.6145128],"study_design_scores_gemma":[0.0030252028,0.00035162366,0.004598951,0.00002438069,0.00041230506,0.000016318372,0.02225355,0.6849001,0.0002623454,0.10770027,0.17615089,0.00030407615],"about_ca_topic_score_codex":0.0016499187,"about_ca_topic_score_gemma":0.002260426,"teacher_disagreement_score":0.61420876,"about_ca_system_score_codex":0.0012901152,"about_ca_system_score_gemma":0.0027114328,"threshold_uncertainty_score":0.9999955},"labels":[],"label_agreement":null},{"id":"W4307053273","doi":"10.1002/ev.20510","title":"At the intersection of co‐creation: Exploring LGBTQ2S evaluation with youth","year":2022,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Prince Edward Island; University of Winnipeg; Youth Services Bureau of Ottawa; Parks Canada","funders":"","keywords":"Intersection (aeronautics); Sociology; Context (archaeology); Public relations; Program evaluation; Positive Youth Development; Youth studies; Psychology; Political science; Gender studies; Public administration; Engineering","score_opus":0.46878928555177146,"score_gpt":0.5291504336284258,"score_spread":0.06036114807665438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307053273","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9439751,0.00021247836,0.016392145,0.0019280729,0.0020208328,0.003215263,0.00008095982,0.00006748029,0.03210769],"genre_scores_gemma":[0.99199605,0.000010455595,0.00040506473,0.00008422627,0.00019761921,0.0024963461,0.00033350487,0.000017754852,0.004459007],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9927616,0.0010505274,0.0007180612,0.000455304,0.0048330794,0.00018140055],"domain_scores_gemma":[0.9961001,0.00076261687,0.0006539192,0.0005969613,0.001825643,0.00006070901],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017694706,0.00014685771,0.0001949984,0.00036826186,0.0015129464,0.00010793516,0.0003047447,0.000032938675,0.0095843235],"category_scores_gemma":[0.0012866192,0.000102496815,0.0001411229,0.0014746861,0.00007002493,0.0006777277,0.00007830914,0.00014141627,0.00004754341],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006549892,0.00016005208,0.0070647467,0.0000062924487,0.00009764642,5.1510607e-8,0.015421011,0.2569839,0.00096890767,0.0013920321,0.01191483,0.70533556],"study_design_scores_gemma":[0.008349707,0.0019271638,0.06614615,0.000041503386,0.0011645718,0.00003235981,0.06650653,0.7054949,0.01409585,0.014211895,0.12151393,0.0005154756],"about_ca_topic_score_codex":0.00018074414,"about_ca_topic_score_gemma":0.00089106447,"teacher_disagreement_score":0.70482004,"about_ca_system_score_codex":0.0013052708,"about_ca_system_score_gemma":0.001031544,"threshold_uncertainty_score":0.999787},"labels":[],"label_agreement":null},{"id":"W4308208661","doi":"10.51744/cswp6","title":"Development project evaluations in Malawi: A Country Evaluation Map","year":2022,"lang":"en","type":"report","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact","funders":"Government of the United Kingdom","keywords":"Corporate governance; Agriculture; Program evaluation; Function (biology); Monitoring and evaluation; International development; Development aid; Impact evaluation; Agricultural development; Political science; Environmental resource management; Economic growth; Business; Geography; Public administration; Economics","score_opus":0.5874405334798818,"score_gpt":0.6210809485560724,"score_spread":0.033640415076190644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308208661","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007519192,0.0009086357,0.0005583413,0.00092498405,0.005526838,0.004813501,0.00009289909,0.000100604935,0.979555],"genre_scores_gemma":[0.100717515,0.001350188,0.023592796,0.0021845393,0.0013831923,0.018724719,0.0087465355,0.00023636839,0.8430641],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.96486294,0.0014550082,0.0028772578,0.0012688125,0.02903217,0.0005038036],"domain_scores_gemma":[0.9928729,0.00083283754,0.0011732616,0.0011774483,0.0038517758,0.00009179646],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.08702403,0.0004106585,0.00069150975,0.002048267,0.0004185018,0.0004323594,0.0010776232,0.0002763788,0.14526005],"category_scores_gemma":[0.005020999,0.0003243734,0.00015718378,0.0023857024,0.000050645256,0.00048342758,0.00044678498,0.000726434,0.001344051],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00002578016,0.00037694623,0.023288442,0.00007247792,0.00008911116,0.0000075717594,0.0026770916,0.0064585977,0.00001037498,0.00043245032,0.6403396,0.32622153],"study_design_scores_gemma":[0.0006544222,0.000049050417,0.03938132,0.00006358495,0.000060652616,0.000014990187,0.0028276218,0.020386148,0.000008659873,0.0008887624,0.935243,0.00042177297],"about_ca_topic_score_codex":0.0004967187,"about_ca_topic_score_gemma":0.008108149,"teacher_disagreement_score":0.32579973,"about_ca_system_score_codex":0.0048402958,"about_ca_system_score_gemma":0.05719966,"threshold_uncertainty_score":0.99992085},"labels":[],"label_agreement":null},{"id":"W4308614086","doi":"10.15581/004.39.39599","title":"Handbook on Measuring Equity in Education (2018). Montréal: UNESCO Institute for Statistics, 142 pp.","year":2020,"lang":"es","type":"article","venue":"Estudios sobre Educación","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Equity (law); Statistics; Library science; Mathematics education; Sociology; Regional science; Political science; Psychology; Mathematics; Computer science; Law","score_opus":0.2091034941127479,"score_gpt":0.4603794936033102,"score_spread":0.25127599949056234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308614086","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4556208,0.056262366,0.090911694,0.27043086,0.07573775,0.017727224,0.0027788237,0.0006148828,0.029915616],"genre_scores_gemma":[0.9752548,0.004902455,0.009901633,0.0052072247,0.002398794,0.0005261972,0.00015706518,0.00006946007,0.0015824],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.994806,0.0002722006,0.0012775762,0.0010565008,0.0019370342,0.0006506906],"domain_scores_gemma":[0.9968314,0.000779408,0.0005325693,0.0006587638,0.0007538398,0.0004439758],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0025638207,0.00047166125,0.0007074516,0.00028792818,0.0004935132,0.0005656968,0.000805853,0.00017773865,0.0003424127],"category_scores_gemma":[0.0033780513,0.0004254996,0.00016680548,0.0008993564,0.0001794218,0.0007859993,0.00029200246,0.00044774008,0.0012751954],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004590243,0.0014267471,0.027376777,0.0003808053,0.000100043915,0.000008209002,0.0058395537,0.0038592734,0.00022732845,0.028328275,0.3973568,0.53463715],"study_design_scores_gemma":[0.0031827837,0.0013006479,0.0719458,0.001099088,0.00015215245,0.0000057489374,0.005974626,0.011644281,0.0010800397,0.0055973106,0.8969488,0.0010686829],"about_ca_topic_score_codex":0.00039416706,"about_ca_topic_score_gemma":0.0009413469,"teacher_disagreement_score":0.53356844,"about_ca_system_score_codex":0.00056893827,"about_ca_system_score_gemma":0.004122764,"threshold_uncertainty_score":0.9998197},"labels":[],"label_agreement":null},{"id":"W4309127530","doi":"","title":"Small Steps Forward Through Critical Appraisal (Editorial)","year":2006,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Critical appraisal; Psychology; Computer science; Medicine; Alternative medicine; Pathology","score_opus":0.5939598922781602,"score_gpt":0.6876972824681955,"score_spread":0.09373739019003535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309127530","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7261095,0.008939942,0.026125945,0.0043889433,0.106417626,0.0013174706,0.00017384034,0.00016005685,0.12636669],"genre_scores_gemma":[0.9811053,0.0010056599,0.0025213074,0.000571484,0.013287695,0.000047378493,0.000019378422,0.00005342172,0.001388355],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99107033,0.0007734983,0.0021805102,0.0007704895,0.004598548,0.0006066214],"domain_scores_gemma":[0.9896391,0.0061934767,0.0010557096,0.0009522747,0.0018637351,0.00029568237],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009102526,0.00038060313,0.0009778716,0.00073461956,0.00051052583,0.004566373,0.0050131287,0.00021920803,0.031645127],"category_scores_gemma":[0.0066918638,0.0002912039,0.00035765365,0.0017932764,0.00030556988,0.0055497745,0.0011209892,0.0005725977,0.00035673965],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024580586,0.00043904426,0.19163504,0.000026790178,0.000059035527,0.000016851218,0.00024836467,0.00073722797,0.007929854,0.0041581076,0.7860415,0.008462403],"study_design_scores_gemma":[0.0010095899,0.000033905,0.29994187,0.00014153369,0.0000785496,0.000013774864,0.00040714777,0.0007639906,0.007353517,0.1207394,0.5689378,0.00057891716],"about_ca_topic_score_codex":0.0008542554,"about_ca_topic_score_gemma":0.00022074414,"teacher_disagreement_score":0.25499585,"about_ca_system_score_codex":0.00011696646,"about_ca_system_score_gemma":0.00053699757,"threshold_uncertainty_score":0.999954},"labels":[],"label_agreement":null},{"id":"W4309592929","doi":"10.1177/1035719x221139858","title":"A Culturally Adaptive Approach to First Nations evaluation consulting","year":2022,"lang":"en","type":"article","venue":"Evaluation Journal of Australasia","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Reflexivity; Context (archaeology); Corporate governance; Public relations; Cultural diversity; Work (physics); Sociology; Political science; Business; Social science; Engineering; Geography; Law","score_opus":0.28401913605717927,"score_gpt":0.4882824620841202,"score_spread":0.20426332602694092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309592929","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8740892,0.00028330748,0.019504068,0.015312221,0.0028983522,0.0034630485,0.000056057885,0.000038421746,0.08435536],"genre_scores_gemma":[0.9879614,0.0000053668027,0.010433683,0.00026935624,0.00021420179,0.00019551197,0.000022236376,0.000011312178,0.00088691106],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98499095,0.0019330255,0.001637395,0.0003609538,0.010811838,0.0002658497],"domain_scores_gemma":[0.989737,0.0011162744,0.0014360001,0.0003438887,0.007142915,0.00022395159],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04182841,0.00017413107,0.00031662942,0.0011067004,0.0011816105,0.0002719942,0.00078561914,0.000045740613,0.009048968],"category_scores_gemma":[0.010564907,0.00013825123,0.00019729121,0.0023825592,0.000045111166,0.0009522168,0.0001293889,0.00041268006,0.00014374165],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001444164,0.00030029408,0.003950591,0.0000036742804,0.00008029316,0.0000013609207,0.009229834,0.913559,0.00029420046,0.002475537,0.026881816,0.04307898],"study_design_scores_gemma":[0.004577788,0.001213417,0.11117091,0.000051340125,0.00036394515,0.00025820217,0.04228308,0.7860399,0.0002399749,0.0066941,0.046673615,0.00043371206],"about_ca_topic_score_codex":0.0000064161013,"about_ca_topic_score_gemma":0.00004165652,"teacher_disagreement_score":0.12751909,"about_ca_system_score_codex":0.0009207907,"about_ca_system_score_gemma":0.0018138336,"threshold_uncertainty_score":0.99776953},"labels":[],"label_agreement":null},{"id":"W4309691492","doi":"10.14324/rfa.06.1.24","title":"How can impact strategies be developed that better support universities to address twenty-first-century challenges?","year":2022,"lang":"en","type":"article","venue":"Research for All","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"University of Wollongong; Queen's University; Massey University","keywords":"Incentive; Typology; Promotion (chess); Public relations; Impact assessment; Business; Political science; Marketing; Sociology; Economics; Public administration","score_opus":0.5395156351694385,"score_gpt":0.5512371744834572,"score_spread":0.011721539314018758,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309691492","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73400563,0.0003857156,0.00032799356,0.23882572,0.0006408235,0.0021120484,0.0007758855,0.000072798386,0.02285338],"genre_scores_gemma":[0.98616105,0.00025385033,0.00027989244,0.0007594722,0.000093064795,0.00025608193,0.00010109022,0.0000195087,0.012075968],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.993284,0.0005798653,0.00025020816,0.00053410395,0.0045431475,0.0008086666],"domain_scores_gemma":[0.99702173,0.0011843409,0.0000976064,0.0005825559,0.0007929052,0.0003208806],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0091383075,0.00016352242,0.00024574448,0.00081381877,0.0009486293,0.00086359924,0.0013307814,0.000048918206,0.004629251],"category_scores_gemma":[0.00024188297,0.00012732917,0.00014740652,0.0006745014,0.000101296544,0.0007671649,0.00075988506,0.00037675677,0.00006314115],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011856611,0.00045992123,0.0071553923,0.00012311275,0.00038652343,0.00010108929,0.070833005,0.0037289325,0.0005017813,0.028298859,0.8183688,0.06885694],"study_design_scores_gemma":[0.0005566072,0.00075327826,0.008877909,0.0000063440043,0.0000054753186,0.0000048342226,0.13980761,0.0004751382,0.00014565482,0.0018308781,0.8473599,0.00017638034],"about_ca_topic_score_codex":0.00017128846,"about_ca_topic_score_gemma":0.0016264406,"teacher_disagreement_score":0.25215545,"about_ca_system_score_codex":0.00078086223,"about_ca_system_score_gemma":0.0022066138,"threshold_uncertainty_score":0.99628067},"labels":[],"label_agreement":null},{"id":"W4311441921","doi":"10.22329/il.v42i4.7175","title":"On Numerical Arguments in Policymaking","year":2022,"lang":"en","type":"article","venue":"Informal Logic","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Argumentation theory; Context (archaeology); Quality (philosophy); Positive economics; Epistemology; Political science; Management science; Sociology; Economics; Philosophy","score_opus":0.23758838426911483,"score_gpt":0.5060161726369339,"score_spread":0.26842778836781905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311441921","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6986826,0.000010958892,0.00042879858,0.0013580798,0.00046141254,0.00016826231,0.000007631864,0.000027882188,0.29885438],"genre_scores_gemma":[0.9906692,0.0000013541028,0.0001532212,0.0075827013,0.000024939784,0.000044686447,0.0000050773815,0.0000026327261,0.001516178],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974147,0.000115125324,0.00046082368,0.00015399104,0.0016236029,0.00023175022],"domain_scores_gemma":[0.99926555,0.0002726638,0.00014021122,0.00023522633,0.000036979454,0.000049391314],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002414275,0.000074600066,0.0001228871,0.00034255785,0.0002108587,0.00008281363,0.00046315204,0.000019736535,0.010574473],"category_scores_gemma":[0.00034364054,0.00005487846,0.0000485385,0.00078147603,0.000016747781,0.00032618546,0.00024131521,0.000230927,0.0011580792],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003104981,0.0004085515,0.16270086,0.0000036083286,0.000010776104,0.000037612703,0.004360944,0.30667087,0.000039672002,0.29657805,0.014335845,0.2145427],"study_design_scores_gemma":[0.0016177292,0.0010730415,0.39741632,0.0000067949195,0.0000026190355,0.000029406332,0.002398312,0.112995476,0.000054567823,0.061272185,0.4227914,0.0003421542],"about_ca_topic_score_codex":0.000025386033,"about_ca_topic_score_gemma":0.000008156122,"teacher_disagreement_score":0.40845555,"about_ca_system_score_codex":0.000109770845,"about_ca_system_score_gemma":0.00010833618,"threshold_uncertainty_score":0.99961966},"labels":[],"label_agreement":null},{"id":"W4311547247","doi":"10.1163/9789004322714_cclc_2019-0168-641","title":"A REPORT CARD ON CANADA’S NEW IMPACT ASSESSMENT ACT","year":2022,"lang":"en","type":"dataset","venue":"Climate Change and Law Collection","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Report card; Computer science; Psychology","score_opus":0.27320021354390167,"score_gpt":0.4952061067956948,"score_spread":0.22200589325179315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311547247","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020255651,0.00020622334,0.0000026814866,0.0027648036,0.004574946,0.0010971178,0.9759004,0.000036003545,0.013392238],"genre_scores_gemma":[0.0026359053,0.0020414582,0.000012937051,0.0028480222,0.0009021535,0.00031106672,0.986342,0.000025210982,0.004881227],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99545956,0.00029532533,0.0006940949,0.0007167574,0.0024582993,0.0003759418],"domain_scores_gemma":[0.9977556,0.00034315023,0.00067192357,0.0007916944,0.00018724636,0.00025038153],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0024953354,0.0003228853,0.000522561,0.0003441921,0.001111375,0.00040896263,0.00032207998,0.00015277836,0.044244856],"category_scores_gemma":[0.00015452677,0.00024580205,0.00014194469,0.0007484429,0.00003069013,0.00025022458,0.00020877458,0.00047991573,0.000027061771],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044802524,0.00004185469,0.0003972671,0.000016610446,0.00003165721,0.00009040425,0.00008061643,0.00002367606,7.973636e-7,0.000050273484,0.9974215,0.0018005547],"study_design_scores_gemma":[0.00036826098,0.0005999044,0.0055418345,0.000028956403,0.00005984472,0.0001143484,0.00020355033,0.0002009803,0.0000027296546,0.00011853319,0.9924898,0.00027125294],"about_ca_topic_score_codex":0.61992776,"about_ca_topic_score_gemma":0.867154,"teacher_disagreement_score":0.24722624,"about_ca_system_score_codex":0.0014632529,"about_ca_system_score_gemma":0.003197874,"threshold_uncertainty_score":0.9999994},"labels":[],"label_agreement":null},{"id":"W4312043060","doi":"10.29173/ijll22","title":"School leadership standards and graduate education: Instructional negotiations of theory, practice, and policy regulation.","year":2022,"lang":"en","type":"article","venue":"International Journal for Leadership in Learning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Negotiation; Political science; Normative; Dialogic; Educational leadership; Pedagogy; Public relations; Leadership studies; Standardization; Sociology; Leadership style","score_opus":0.40068999445996584,"score_gpt":0.5278142430992988,"score_spread":0.12712424863933297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312043060","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5290447,0.0034028857,0.044599492,0.3957002,0.008567632,0.0013697805,0.00019086574,0.00007518192,0.01704926],"genre_scores_gemma":[0.9908032,0.000072844625,0.003098381,0.0013930094,0.00042847142,0.000042002273,0.000019219475,0.000012624371,0.0041302904],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.99541396,0.00081543246,0.00075492315,0.00025624846,0.002561001,0.00019840628],"domain_scores_gemma":[0.9952208,0.0020046881,0.0007460951,0.00010861835,0.0018062652,0.000113580725],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010841747,0.00011267011,0.00017242464,0.0012140523,0.0005395085,0.00034049441,0.00036354124,0.000041409785,0.0011458247],"category_scores_gemma":[0.014453304,0.00010695151,0.000073230345,0.0005244204,0.00014093706,0.0011357812,0.00010162572,0.00066177355,0.0000035243231],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014285193,0.000310887,0.07611665,0.000044042492,0.00022277395,0.0000046979903,0.01656054,0.06491035,0.00035754792,0.44381487,0.0056960722,0.39053303],"study_design_scores_gemma":[0.003278515,0.0005087236,0.19625628,0.00015217718,0.000045104345,0.0013183913,0.31793448,0.014533419,0.00008927681,0.24381615,0.2217047,0.00036276956],"about_ca_topic_score_codex":0.000021324964,"about_ca_topic_score_gemma":0.000014439006,"teacher_disagreement_score":0.46175843,"about_ca_system_score_codex":0.00044222877,"about_ca_system_score_gemma":0.0020165178,"threshold_uncertainty_score":0.99976724},"labels":[],"label_agreement":null},{"id":"W4312844884","doi":"10.1093/oso/9780192897046.003.0001","title":"Introduction","year":2022,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Realm; Public policy; Political science; Policy learning; Public administration; Public relations; Computer science; Law","score_opus":0.24439742246252202,"score_gpt":0.4749518172713611,"score_spread":0.23055439480883907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312844884","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000052614296,0.00005271754,0.0002727331,0.011625484,0.0018329116,0.000116274095,0.000008048093,0.00003858786,0.986048],"genre_scores_gemma":[0.00026830714,0.0000849877,0.00025519263,0.00072140014,0.0010849223,0.000008207,0.00004288912,0.0000122949305,0.9975218],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99655765,0.000031610278,0.00046813246,0.00041093474,0.002446579,0.0000851201],"domain_scores_gemma":[0.9987014,0.00016166641,0.00024071475,0.0006334682,0.00021885952,0.000043883832],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0025871603,0.00011974915,0.00019002568,0.00028992954,0.00014599727,0.00010826451,0.0003849461,0.000069960486,0.82591814],"category_scores_gemma":[0.00014128737,0.00008602318,0.00011336104,0.00006186554,0.000030174659,0.00019834352,0.00015090733,0.00025456745,0.013732596],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027395567,0.0000023068965,0.0000054689563,4.0742214e-7,0.0000048851457,4.772509e-7,0.000018786885,0.000049644797,0.0000013226677,0.5305501,0.42008123,0.04928263],"study_design_scores_gemma":[0.00005108314,0.0000403082,0.000035776313,8.145044e-7,0.0000065960453,0.0000041404246,0.000033693992,0.00020291936,0.0000040557743,0.10930605,0.8902146,0.00009993747],"about_ca_topic_score_codex":0.0000031213397,"about_ca_topic_score_gemma":0.000017380435,"teacher_disagreement_score":0.8121856,"about_ca_system_score_codex":0.00009745905,"about_ca_system_score_gemma":0.00016540033,"threshold_uncertainty_score":0.98703533},"labels":[],"label_agreement":null},{"id":"W4313021641","doi":"10.7202/1091250ar","title":"Regards sur la problématique de la production des indicateurs en éducation","year":2022,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.14626773895338702,"score_gpt":0.497753458890308,"score_spread":0.35148571993692096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313021641","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8616948,0.0011561611,0.0147409905,0.08983398,0.0066581937,0.0019051326,0.00004447362,0.00016150488,0.023804765],"genre_scores_gemma":[0.94148785,0.00086979766,0.00507939,0.00060679106,0.0005255539,0.0011175246,0.0004089094,0.000060119615,0.04984409],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9367255,0.05651883,0.0014335663,0.0010591071,0.0037217007,0.0005412709],"domain_scores_gemma":[0.9914572,0.0052260263,0.001098465,0.0008152682,0.0012353328,0.00016767082],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.15843768,0.00037357473,0.0003645966,0.0008387743,0.0010306806,0.00060755777,0.00068912643,0.0003249925,0.008018505],"category_scores_gemma":[0.016668597,0.00039516808,0.00017217529,0.0019903139,0.0002864895,0.0022365542,0.00018307935,0.0010193327,0.00044119425],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00009329674,0.0017842453,0.045929305,0.00019708587,0.00010436554,0.0000023677533,0.5376398,0.06887624,0.0028331315,0.013305117,0.11336558,0.21586947],"study_design_scores_gemma":[0.0008312294,0.0002605906,0.6697962,0.00014058067,0.00018268141,0.00017719678,0.018481368,0.023868745,0.0016244262,0.04702666,0.23708133,0.00052899163],"about_ca_topic_score_codex":0.00042546025,"about_ca_topic_score_gemma":0.00042575924,"teacher_disagreement_score":0.6238669,"about_ca_system_score_codex":0.004063353,"about_ca_system_score_gemma":0.012333004,"threshold_uncertainty_score":0.99985003},"labels":[],"label_agreement":null},{"id":"W4313050016","doi":"10.29034/ijmra.v13n3editorial","title":"Editors’ Introduction to the International Journal of Multiple Research Approaches: Issue 13(3)","year":2021,"lang":"en","type":"article","venue":"International Journal of Multiple Research Approaches","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Publishing; Volume (thermodynamics); Engineering ethics; Library science; Political science; Sociology; Management science; Computer science; Engineering; Law; Physics","score_opus":0.6327362013188447,"score_gpt":0.5587839951350285,"score_spread":0.07395220618381615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313050016","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41901603,0.0016155788,0.024795424,0.5033206,0.044882465,0.0011632974,0.00011780893,0.000025299754,0.00506355],"genre_scores_gemma":[0.9332646,0.00029097212,0.00785117,0.00021218619,0.056102138,0.00003314003,0.000019940098,0.000030890253,0.0021949224],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97236896,0.0032236227,0.00234253,0.00058765174,0.02083141,0.00064583175],"domain_scores_gemma":[0.96228284,0.0070798667,0.001078028,0.0007662161,0.02834479,0.00044825533],"candidate_categories":["metaresearch","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06453306,0.00023676388,0.00050085154,0.0025638023,0.00042792453,0.0017977945,0.00591691,0.00017189827,0.0014937393],"category_scores_gemma":[0.06112211,0.00015208045,0.000441305,0.0018888601,0.0004600854,0.0015217877,0.0012552097,0.002324044,0.00040215516],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020103124,0.0016099985,0.026940027,0.000015401194,0.00094342744,0.00020965279,0.008384402,0.024967171,0.0057805283,0.00093309785,0.7116383,0.21656772],"study_design_scores_gemma":[0.0025769752,0.0005242693,0.011949509,0.00012871665,0.000017804507,0.00064216356,0.031226126,0.031221986,0.018525971,0.0028732992,0.90009177,0.00022140144],"about_ca_topic_score_codex":0.0000662873,"about_ca_topic_score_gemma":0.00024572553,"teacher_disagreement_score":0.5142486,"about_ca_system_score_codex":0.0009031963,"about_ca_system_score_gemma":0.002572076,"threshold_uncertainty_score":0.99997765},"labels":[],"label_agreement":null},{"id":"W4313065918","doi":"10.2139/ssrn.4250104","title":"Implementing and Evaluating Knowledge Exchange: Insights from Practitioners at the Canadian Forest Service","year":2022,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa; Dalhousie University; Natural Resources Canada; Carleton University","funders":"","keywords":"Business; Service (business); Knowledge management; Computer science; Marketing","score_opus":0.11815311729831779,"score_gpt":0.4512549562701454,"score_spread":0.3331018389718276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313065918","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9736157,0.0038919586,0.000186799,0.013896437,0.00040117695,0.00022677438,0.0000152580715,0.000009184502,0.0077567007],"genre_scores_gemma":[0.99503744,0.00021130036,0.00004753193,0.0011324984,0.00028856535,0.000038645507,0.000027315138,0.000011310622,0.0032054107],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99568367,0.00083524873,0.0004484369,0.00026940487,0.0014571655,0.0013061018],"domain_scores_gemma":[0.99824965,0.00059430685,0.00039406068,0.0002499294,0.00036959996,0.00014242977],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016418112,0.00011410068,0.00012686658,0.0002355722,0.0053559826,0.0004345053,0.00050600845,0.000026888763,0.003556045],"category_scores_gemma":[0.00028267925,0.00007690661,0.000052062744,0.0006490041,0.000029781913,0.00040565737,0.00036886727,0.0011912425,0.00011802286],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019441299,0.000109071996,0.10205566,0.00000929034,0.0005023031,0.00001032822,0.053281758,0.007395946,0.0012090853,0.11697063,0.012260227,0.7060013],"study_design_scores_gemma":[0.0013428528,0.00033602546,0.020896126,0.0000085915,0.00006841106,0.00029104276,0.083956935,0.03840361,0.00002091998,0.27741897,0.5769827,0.00027385287],"about_ca_topic_score_codex":0.037480712,"about_ca_topic_score_gemma":0.97468764,"teacher_disagreement_score":0.9372069,"about_ca_system_score_codex":0.0027226573,"about_ca_system_score_gemma":0.007406087,"threshold_uncertainty_score":0.998221},"labels":[],"label_agreement":null},{"id":"W4313124775","doi":"10.1007/978-3-030-85124-8_11","title":"The Future of Qualitative Research","year":2022,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; St. Francis Xavier University","funders":"","keywords":"Qualitative research; Point (geometry); Order (exchange); Epistemology; Computer science; Sociology; Mathematics; Philosophy; Social science; Geometry","score_opus":0.7374526792072426,"score_gpt":0.693087168342885,"score_spread":0.04436551086435758,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313124775","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000023891202,0.001143402,0.00002724702,0.010305982,0.0006147989,0.00023923573,0.000029858249,0.0000069051966,0.9876087],"genre_scores_gemma":[0.0018342129,0.0010632727,0.00013200303,0.00015482632,0.00019442773,0.000020207332,0.000009150412,0.000010104041,0.9965818],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9904266,0.000940721,0.00074713485,0.0003193876,0.0073949955,0.00017118029],"domain_scores_gemma":[0.9889767,0.008350212,0.00032556534,0.0008080997,0.0014936047,0.000045825625],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.04215723,0.00010406343,0.00022460816,0.00028707704,0.0005779681,0.00011014635,0.001132586,0.00008900318,0.105429344],"category_scores_gemma":[0.00049571105,0.000050515406,0.00013997519,0.00018992336,0.00030208734,0.000104700004,0.00037326073,0.0006583156,0.0010322558],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001423056,0.0000033985912,0.000002489628,0.0000013424666,0.000012418027,3.4514304e-7,0.0029992783,0.0000031818167,8.7029326e-7,0.78731054,0.15553184,0.054120064],"study_design_scores_gemma":[0.00004357535,0.00007476052,0.000016783059,0.0000033267172,0.0000018074943,3.1961568e-7,0.017059568,0.000034586683,0.000003429844,0.34952828,0.6331919,0.000041676834],"about_ca_topic_score_codex":0.000013599987,"about_ca_topic_score_gemma":0.0002540172,"teacher_disagreement_score":0.47766003,"about_ca_system_score_codex":0.000076915974,"about_ca_system_score_gemma":0.0005870859,"threshold_uncertainty_score":0.99974555},"labels":[],"label_agreement":null},{"id":"W4313250641","doi":"10.1177/10982140221106991","title":"Laying a Solid Foundation for the Next Generation of Evaluation Capacity Building: Findings from an Integrative Review","year":2022,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of Ottawa","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Scholarship; Foundation (evidence); Capacity building; Engineering ethics; Political science; Management science; Sociology; Public relations; Economics; Engineering; Law","score_opus":0.5281446215139854,"score_gpt":0.552257622583783,"score_spread":0.024113001069797524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313250641","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9015306,0.0010050958,0.091588184,0.004145938,0.00058545027,0.0010573332,0.000018860452,0.0000041551,0.000064366504],"genre_scores_gemma":[0.9906204,0.00035422455,0.0072691115,0.0011984244,0.00025343217,0.00021709272,0.000065730135,0.0000100610305,0.000011526881],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9903591,0.0032482874,0.0014041963,0.00025772,0.0045760903,0.00015458134],"domain_scores_gemma":[0.99026376,0.001888515,0.0028500063,0.0003619502,0.004568974,0.00006678513],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.053027164,0.0001311702,0.00040036225,0.00028917496,0.0005215689,0.00014869412,0.0004154313,0.000020804539,0.0024085203],"category_scores_gemma":[0.007583005,0.00008701489,0.00019574142,0.00095813203,0.00011778886,0.0011637158,0.000045877347,0.00023967409,0.000003464331],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016091141,0.00013380888,0.0024619761,0.000009684613,0.000107082764,1.5612969e-7,0.007180661,0.06890283,0.03453159,0.0005519745,0.0024434708,0.88351583],"study_design_scores_gemma":[0.0008514303,0.0014067297,0.011631107,0.00012776762,0.0005299873,0.00001784637,0.011140413,0.95993745,0.0017130144,0.010845466,0.0016759424,0.00012285398],"about_ca_topic_score_codex":0.00010360429,"about_ca_topic_score_gemma":0.00004166746,"teacher_disagreement_score":0.8910346,"about_ca_system_score_codex":0.00069016573,"about_ca_system_score_gemma":0.0013960135,"threshold_uncertainty_score":0.9985034},"labels":[],"label_agreement":null},{"id":"W4313445929","doi":"10.1007/978-3-031-04394-9_72","title":"Thematic Analysis","year":2023,"lang":"en","type":"book-chapter","venue":"Springer texts in education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":92,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Thematic analysis; Qualitative research; Psychology; Qualitative analysis; Interpretative phenomenological analysis; Mental health; Grounded theory; Sociology; Social science; Psychotherapist","score_opus":0.18122605750582277,"score_gpt":0.4845566908164057,"score_spread":0.3033306333105829,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313445929","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043393504,0.0002446414,0.0001965759,0.001023987,0.0019872552,0.0003450625,0.000006463512,0.000055430795,0.99180126],"genre_scores_gemma":[0.07570235,0.00016923147,0.000508773,0.00021365058,0.00022997812,0.000050088285,0.000045153793,0.00002843241,0.9230524],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9967429,0.00005328567,0.0008938926,0.00052934804,0.0016150767,0.00016552051],"domain_scores_gemma":[0.9976322,0.00051570154,0.0005050103,0.00096190587,0.00031734692,0.000067810244],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0032930574,0.00020005865,0.00042503135,0.0023636883,0.00006718739,0.00018564217,0.0005536397,0.00017557954,0.009304828],"category_scores_gemma":[0.0004974852,0.00016330635,0.00022709862,0.0008355771,0.00004234153,0.00018970862,0.000091522656,0.00026203663,0.008374113],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006235067,0.00011509338,0.0098071,0.000036513975,0.00021379277,0.0000016345527,0.0020886275,0.001112892,0.0000063663,0.33286595,0.014201352,0.6395444],"study_design_scores_gemma":[0.00016195534,0.00002870909,0.076644704,0.0002691894,0.00040347845,0.0000011501314,0.0010251149,0.0031434747,0.000013976962,0.6999518,0.21779425,0.00056218327],"about_ca_topic_score_codex":0.000019453002,"about_ca_topic_score_gemma":0.0005300784,"teacher_disagreement_score":0.63898224,"about_ca_system_score_codex":0.000214847,"about_ca_system_score_gemma":0.000711125,"threshold_uncertainty_score":0.99239796},"labels":[],"label_agreement":null},{"id":"W4313446218","doi":"10.1007/978-3-031-04394-9_76","title":"Conclusions","year":2023,"lang":"en","type":"book-chapter","venue":"Springer texts in education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Scholarship; Variety (cybernetics); Context (archaeology); Interrogation; Set (abstract data type); Engineering ethics; Indigenous; Computer science; Sociology; Political science; Engineering; History; Artificial intelligence","score_opus":0.18372751329248987,"score_gpt":0.48864675616828135,"score_spread":0.3049192428757915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313446218","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001338674,0.00027019545,0.000034741694,0.002348284,0.005232349,0.00036149024,0.0000097633865,0.00006330399,0.9903412],"genre_scores_gemma":[0.025444718,0.0003210867,0.0003488214,0.0005188189,0.00047048155,0.000047486796,0.000041475552,0.00003833419,0.9727688],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99701524,0.000045124467,0.00076773914,0.0005206227,0.001469563,0.0001816938],"domain_scores_gemma":[0.9979188,0.0004875667,0.00036457545,0.0007753379,0.00036636507,0.000087349305],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0024553274,0.0001962911,0.00028334185,0.0009346986,0.00011832456,0.00014508408,0.0005531243,0.00022124579,0.009047737],"category_scores_gemma":[0.0005875422,0.0001696873,0.00010384717,0.00023039148,0.000061062514,0.00020217137,0.00019858032,0.00035477022,0.014069365],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000048109373,0.000057600046,0.0019143575,0.000010654205,0.000008608082,0.0000016153258,0.00093918253,0.00008947621,0.0000161488,0.4700164,0.054696232,0.47224492],"study_design_scores_gemma":[0.0000808446,0.000015493724,0.0108076,0.00013052006,0.000007788047,0.000001105612,0.00021214965,0.00013022743,0.0000078032845,0.2907403,0.69768476,0.00018139163],"about_ca_topic_score_codex":0.000020032296,"about_ca_topic_score_gemma":0.00029009342,"teacher_disagreement_score":0.64298856,"about_ca_system_score_codex":0.00025643338,"about_ca_system_score_gemma":0.0015044237,"threshold_uncertainty_score":0.9918581},"labels":[],"label_agreement":null},{"id":"W4313466224","doi":"10.1177/10982140221079837","title":"Translating Evaluation Policy Into Practice in Government Organizations","year":2022,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Government (linguistics); Policy analysis; Program evaluation; Key (lock); Public policy; Public relations; Evaluation methods; Process management; Business; Public administration; Management science; Political science; Computer science; Economics; Engineering; Computer security","score_opus":0.09400042012462564,"score_gpt":0.5279233762509515,"score_spread":0.4339229561263259,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313466224","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9314688,0.00041277302,0.013296736,0.034870066,0.0007694929,0.00094148115,0.000008784366,0.00001104278,0.018220866],"genre_scores_gemma":[0.9923508,0.000025554054,0.006435518,0.00094679795,0.00013041295,0.00004843658,0.000006740344,0.000011838256,0.000043864016],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9837594,0.004192274,0.0014390487,0.00023535646,0.010200328,0.00017361563],"domain_scores_gemma":[0.99285966,0.0011798219,0.0022917863,0.0002898601,0.003293045,0.00008583108],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.047903053,0.00010933651,0.00026165403,0.0006095027,0.00028858028,0.00008953561,0.0003813397,0.000016148193,0.004845102],"category_scores_gemma":[0.021136971,0.00009665039,0.0000745884,0.0044887555,0.00006463617,0.0010613967,0.00006947502,0.00029845658,0.000025305146],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010941513,0.00021265438,0.007536105,7.48746e-7,0.000024920484,0.0000018660446,0.021180239,0.16030169,0.00053743785,0.00071653136,0.00028031258,0.80909806],"study_design_scores_gemma":[0.004807677,0.0032193826,0.11871657,0.000036161142,0.0004126973,0.00027090378,0.19723642,0.61028856,0.0003141711,0.039136793,0.025105545,0.000455151],"about_ca_topic_score_codex":0.00017893511,"about_ca_topic_score_gemma":0.00011838045,"teacher_disagreement_score":0.8086429,"about_ca_system_score_codex":0.0019494032,"about_ca_system_score_gemma":0.0035748784,"threshold_uncertainty_score":0.9960646},"labels":[],"label_agreement":null},{"id":"W4315649348","doi":"10.29173/cjnser614","title":"Mixed Methods for Complex Programmes: The Use of the DOME Model for the Evaluation of Public-Private Partnerships Against Educational Poverty in Italy","year":2023,"lang":"en","type":"article","venue":"Canadian journal of nonprofit and social economy research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Poverty; Citizen journalism; Poverty reduction; Dome (geology); Political science; Program evaluation; Economic growth; Engineering; Public administration; Economics","score_opus":0.9108393480948866,"score_gpt":0.6341949302725147,"score_spread":0.2766444178223719,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4315649348","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.788662,0.00021187098,0.004147476,0.20285082,0.00037433385,0.002946425,0.00010820316,0.0000016921712,0.00069715775],"genre_scores_gemma":[0.99726605,0.000014230924,0.0017730362,0.00029779717,0.000113500246,0.00017480612,0.000008169874,0.0000063190896,0.0003461057],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996778,0.0013215999,0.00069064606,0.00013199211,0.000761666,0.0003160717],"domain_scores_gemma":[0.98987454,0.006339458,0.0003960128,0.0002041078,0.0030634883,0.00012236756],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.054108456,0.00006644091,0.00020859601,0.00038574467,0.00069394946,0.0003032528,0.0006968555,0.000058071517,0.00007329373],"category_scores_gemma":[0.00655107,0.00003391548,0.00015720898,0.0007881902,0.00043912916,0.00036681342,0.000046724534,0.00021303917,0.0000012093856],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014090171,0.000064351014,0.058322612,0.00006702889,0.00019989716,1.5141416e-7,0.016751017,0.009654314,0.00013852006,0.109741725,0.0707827,0.73413676],"study_design_scores_gemma":[0.000823991,0.000058653808,0.085703604,0.00001357984,0.00002012197,7.508933e-7,0.00886091,0.7466876,0.000031393032,0.10489308,0.052848823,0.000057502704],"about_ca_topic_score_codex":0.00021081796,"about_ca_topic_score_gemma":0.01867459,"teacher_disagreement_score":0.73703325,"about_ca_system_score_codex":0.00020568506,"about_ca_system_score_gemma":0.0070981598,"threshold_uncertainty_score":0.99923205},"labels":[],"label_agreement":null},{"id":"W4317036961","doi":"10.3389/frsus.2022.992939","title":"Altering regional development for sustainability: Lessons learned from strategic communications of RCE Saskatchewan (Canada) with government","year":2023,"lang":"en","type":"article","venue":"Frontiers in Sustainability","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Regina","funders":"Government of Canada; University of Regina","keywords":"Sustainable development; Government (linguistics); Sustainability; Business; Public administration; Psychological intervention; Political science; Environmental planning; Economic growth; Economics; Geography","score_opus":0.2218294401030793,"score_gpt":0.4368710600117737,"score_spread":0.21504161990869441,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317036961","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94016397,0.000078304874,0.01980003,0.0374444,0.0002127383,0.0015150598,0.000092673145,0.000042910142,0.0006499405],"genre_scores_gemma":[0.97826713,0.0000145420745,0.019980848,0.000099052304,0.00001641249,0.00035715275,0.00006572685,0.000014167442,0.0011849698],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99537903,0.00040849636,0.0009867775,0.0006436124,0.0021126808,0.00046938955],"domain_scores_gemma":[0.9947613,0.0012864069,0.00038215818,0.0020765946,0.0013663145,0.00012725125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0055614035,0.00020000088,0.00046166088,0.00015890763,0.00030090322,0.00007953062,0.001434517,0.000078836296,0.000038347363],"category_scores_gemma":[0.0017770549,0.00016591781,0.00007689864,0.0011812599,0.00033909664,0.00023638524,0.00044414404,0.00020407733,9.473407e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00090494344,0.00045906557,0.77119654,0.00028103398,0.000120365956,0.0000078967905,0.013281803,0.015217709,0.000026327214,0.0072981585,0.010079598,0.18112655],"study_design_scores_gemma":[0.00096617517,0.00009870534,0.18782254,0.000025535855,0.000014295653,2.9193245e-7,0.44359908,0.024168253,0.00014881801,0.30627075,0.036632515,0.00025308234],"about_ca_topic_score_codex":0.015583993,"about_ca_topic_score_gemma":0.2819631,"teacher_disagreement_score":0.583374,"about_ca_system_score_codex":0.003858037,"about_ca_system_score_gemma":0.010594733,"threshold_uncertainty_score":0.99996597},"labels":[],"label_agreement":null},{"id":"W4317356924","doi":"10.3138/cjpe.74693","title":"Listening with the Heart: A Reflection on Relationality and Ceremony","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Indigenous; Ceremony; Active listening; Reflection (computer programming); Sociology; Process (computing); Psychology; History; Computer science; Communication; Archaeology; Ecology","score_opus":0.4173002021624416,"score_gpt":0.531349183556716,"score_spread":0.11404898139427438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317356924","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95948625,0.00024404131,0.0003611167,0.032678872,0.00040914933,0.00080929586,0.000004976629,0.000006581483,0.005999711],"genre_scores_gemma":[0.99800456,0.0000011049946,0.0008118231,0.00070407265,0.00008462736,0.00006724385,0.000004667255,0.0000049205487,0.00031697846],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9962193,0.0009213158,0.0003729689,0.0001394106,0.0022172886,0.00012972702],"domain_scores_gemma":[0.99795693,0.00031651816,0.0004172306,0.00016851469,0.0009788102,0.00016197472],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016023112,0.00006504151,0.00010449167,0.00031044212,0.0009058045,0.00026729118,0.00018291842,0.000019974274,0.0013156261],"category_scores_gemma":[0.0006854555,0.000038974675,0.000044296172,0.00066255435,0.000074799376,0.00027716873,0.0000116998135,0.00029549928,0.0000083938385],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018477428,0.00006091594,0.08500864,0.000002873303,0.00004642622,0.0000060613306,0.0051773586,0.0664101,0.0000531813,0.0042711087,0.01678733,0.8219912],"study_design_scores_gemma":[0.0012278024,0.002603944,0.5099091,0.000022248083,0.00008555178,0.0003240172,0.00538108,0.07941684,0.000025452377,0.013846726,0.3870061,0.00015112798],"about_ca_topic_score_codex":0.00026467448,"about_ca_topic_score_gemma":0.0073011694,"teacher_disagreement_score":0.8218401,"about_ca_system_score_codex":0.00037685345,"about_ca_system_score_gemma":0.002180333,"threshold_uncertainty_score":0.9995973},"labels":[],"label_agreement":null},{"id":"W4317381160","doi":"10.3138/cjpe.66908","title":"Making Relationships Count: Measuring Trust in Relationships Between a Catholic Development Agency and Māori Communities","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Aotearoa; Indigenous; Centrality; Agency (philosophy); Foundation (evidence); Sociology; Affect (linguistics); Cultural values; Public relations; Social psychology; Psychology; Political science; Social science; Gender studies","score_opus":0.7823290008155973,"score_gpt":0.5171308822180672,"score_spread":0.26519811859753006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317381160","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9952139,0.00075840513,0.00038646787,0.0010170788,0.0002736776,0.0007206733,0.0000079981255,0.000008054678,0.0016137481],"genre_scores_gemma":[0.9957646,0.000006425411,0.0038553963,0.000042344374,0.000062928804,0.00015962585,0.000027402695,0.000010714169,0.00007054156],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99323225,0.0028843684,0.0012364949,0.00015404478,0.00222854,0.00026430076],"domain_scores_gemma":[0.9971275,0.0007463592,0.0007139652,0.00024152298,0.00093271985,0.00023795906],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.044799767,0.00012062852,0.00023413336,0.001499301,0.0017448092,0.0003421432,0.0004220697,0.00006029647,0.00077270524],"category_scores_gemma":[0.0023554473,0.0001171158,0.000049950486,0.0011390907,0.000077127945,0.0006554511,0.000048039667,0.00092116604,0.000013072799],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000057569255,0.000017424603,0.74354804,0.000003948924,0.000012269778,0.0000032594014,0.044378024,0.005727601,0.0000012040476,0.00034538514,0.000064344196,0.20589276],"study_design_scores_gemma":[0.0005619199,0.00010248851,0.9291764,0.000053566197,0.000038651462,0.0000421003,0.023980796,0.0146553125,0.0000029831197,0.006044241,0.025204787,0.00013676641],"about_ca_topic_score_codex":0.00057776074,"about_ca_topic_score_gemma":0.05893753,"teacher_disagreement_score":0.20575598,"about_ca_system_score_codex":0.0012358942,"about_ca_system_score_gemma":0.004931012,"threshold_uncertainty_score":0.9995548},"labels":[],"label_agreement":null},{"id":"W4317381171","doi":"10.3138/cjpe.74487","title":"New Insights for Tracking and Reporting Milestones","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Tracking (education); Reflection (computer programming); Process (computing); Metric (unit); Developmental Milestone; Key (lock); Critical reflection; Psychology; Computer science; Operations management; Pedagogy; Engineering; Computer security; Developmental psychology","score_opus":0.6188240831545975,"score_gpt":0.573439920067952,"score_spread":0.0453841630866455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317381171","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98512375,0.0015906617,0.0060144383,0.0036401341,0.0014010302,0.0013319968,0.000004348239,0.000007735525,0.0008859148],"genre_scores_gemma":[0.9890606,0.0000034436152,0.010234126,0.00016169205,0.0001870245,0.00007516749,0.000006886398,0.0000067955743,0.00026431005],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99659663,0.00027211083,0.0013221313,0.00015631493,0.0014895478,0.00016324432],"domain_scores_gemma":[0.99580663,0.000245248,0.0021182583,0.00013816828,0.0013595377,0.00033216222],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01736877,0.00006892241,0.00018665439,0.0005065588,0.0005494458,0.00030625574,0.00021564303,0.000024439334,0.0011172834],"category_scores_gemma":[0.0054823407,0.00005648795,0.00008680702,0.00044394174,0.00002491884,0.00042919288,0.00001382826,0.00014062907,0.0000022249312],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000108548975,0.000008527662,0.013615856,0.0000021277515,0.000010343813,0.0000041460653,0.0022364974,0.0027937633,0.000055163015,0.00046923666,0.0038537902,0.9769397],"study_design_scores_gemma":[0.0021703304,0.0015421249,0.16668889,0.000039281837,0.00015444435,0.00042203668,0.010231323,0.10609517,0.00021004336,0.07818985,0.63398755,0.00026896296],"about_ca_topic_score_codex":0.000294796,"about_ca_topic_score_gemma":0.0057733557,"teacher_disagreement_score":0.97667074,"about_ca_system_score_codex":0.00024104008,"about_ca_system_score_gemma":0.005292828,"threshold_uncertainty_score":0.99979585},"labels":[],"label_agreement":null},{"id":"W4317381207","doi":"10.3138/cjpe.73987","title":"Involving Youth in Empowerment Evaluation: Evaluators’ Perspectives","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa; University of Winnipeg","funders":"","keywords":"Youth empowerment; Empowerment; Positive Youth Development; Psychology; Applied psychology; Developmental psychology; Political science","score_opus":0.41873982061622445,"score_gpt":0.5321663351437933,"score_spread":0.11342651452756886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317381207","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9842958,0.004111406,0.000089654044,0.0027998267,0.0017849274,0.0024301722,0.000019791063,0.000010367381,0.004458076],"genre_scores_gemma":[0.9983367,0.0000140487155,0.00074121845,0.00019464582,0.00018451465,0.0003856089,0.000030152325,0.00001562993,0.000097484975],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.98578304,0.0035318807,0.0015375402,0.00041308257,0.008299016,0.00043543387],"domain_scores_gemma":[0.9932643,0.00025622666,0.0010525582,0.0004485754,0.0045397384,0.00043859737],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.07362724,0.000182141,0.00033710332,0.0020013321,0.0005890861,0.00041340565,0.0008202611,0.000057942507,0.020896576],"category_scores_gemma":[0.005051852,0.00016368182,0.00018980446,0.0021420347,0.000100073295,0.0008150669,0.000059121234,0.0005182731,0.000043045402],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000071259004,0.00030363674,0.12749267,0.000004935279,0.00006015881,0.000018042956,0.07497705,0.0919096,0.000034901743,0.0011623055,0.0031523886,0.70081306],"study_design_scores_gemma":[0.0050701774,0.0018784199,0.22326659,0.00006741191,0.00036305285,0.000070195085,0.37197798,0.3507553,0.000033792574,0.026017688,0.020003272,0.00049610995],"about_ca_topic_score_codex":0.00076630997,"about_ca_topic_score_gemma":0.017636098,"teacher_disagreement_score":0.7003169,"about_ca_system_score_codex":0.0039842674,"about_ca_system_score_gemma":0.016126284,"threshold_uncertainty_score":0.99983925},"labels":[],"label_agreement":null},{"id":"W4317381228","doi":"10.3138/cjpe.72343","title":"The Evaluation Marketplace in Canada: What Qualifications Do Employers Demand?","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Waterloo; University of Guelph","funders":"","keywords":"Business; Profit (economics); Public relations; Marketing; Private sector; Political science; Economics; Economic growth","score_opus":0.37366454585497816,"score_gpt":0.5216791308618242,"score_spread":0.148014585006846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317381228","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9573012,0.007336563,0.00020942886,0.025296593,0.004341485,0.0032915156,0.000020017873,0.0000068625045,0.0021963338],"genre_scores_gemma":[0.99857986,0.000084168816,0.00020917789,0.00031579475,0.00007670581,0.00057685946,0.000021485575,0.0000104379205,0.00012549765],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9873052,0.0041801594,0.0014342013,0.00026187248,0.006427395,0.00039117207],"domain_scores_gemma":[0.9941158,0.0011285718,0.0010018803,0.0004720586,0.002933291,0.0003483982],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.06987932,0.00012549282,0.00020392815,0.0006033633,0.00110766,0.00092057127,0.00090976874,0.000032323205,0.00522633],"category_scores_gemma":[0.0047617164,0.000093721974,0.00009300272,0.0016163555,0.00006908027,0.0009642404,0.00003100021,0.00039440306,0.000016284506],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000028055136,0.000023087905,0.041128088,0.0000011290252,0.000019858782,0.0000038862377,0.0013977461,0.0696343,0.0000041275753,0.00038731625,0.0155045,0.8718679],"study_design_scores_gemma":[0.0016597398,0.00028084515,0.35904816,0.000037239955,0.00011225466,0.00006837895,0.0826673,0.3267503,0.000011708983,0.01241859,0.21670029,0.00024519555],"about_ca_topic_score_codex":0.25882727,"about_ca_topic_score_gemma":0.9875174,"teacher_disagreement_score":0.8716227,"about_ca_system_score_codex":0.006138984,"about_ca_system_score_gemma":0.05846519,"threshold_uncertainty_score":0.99767625},"labels":[],"label_agreement":null},{"id":"W4317381695","doi":"10.3138/cjpe.74582","title":"Fostering an Evaluative Culture by Addressing a Breakdown in the Policy Development Cycle","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Accountability; Corporate governance; Function (biology); Process (computing); Citizen journalism; Participatory evaluation; Process management; Political science; Public relations; Public administration; Business; Management; Economics; Computer science; Law","score_opus":0.4732297645571751,"score_gpt":0.5733556647379928,"score_spread":0.10012590018081774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317381695","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9809259,0.0011005427,0.00048122418,0.007594812,0.0005778534,0.002876265,0.000025113346,0.000010312747,0.006407946],"genre_scores_gemma":[0.996736,0.00000442471,0.0016685083,0.0008939194,0.00012359314,0.00043934453,0.000039510047,0.000008626414,0.00008607125],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9925865,0.0023436619,0.0008942783,0.00022225104,0.0036318272,0.0003215132],"domain_scores_gemma":[0.99763674,0.00015344755,0.00063515594,0.00026476034,0.0010461869,0.00026373673],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.030251922,0.00012488168,0.00018710598,0.00074203825,0.00078292825,0.0005820196,0.0008868488,0.00003978303,0.0015953489],"category_scores_gemma":[0.0013352222,0.00008517215,0.00006813429,0.0014649624,0.000057348552,0.00075344177,0.00006572332,0.0003822946,0.000013486996],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016259033,0.00007198569,0.0026774597,0.000001984707,0.000010931433,0.0000056932017,0.039834894,0.00911664,0.00007942525,0.00009043364,0.0032441535,0.94485015],"study_design_scores_gemma":[0.0041908096,0.0023975987,0.13778444,0.00012275341,0.0001044531,0.000426786,0.10204167,0.18852764,0.00023091331,0.026370855,0.537186,0.0006160518],"about_ca_topic_score_codex":0.0008079827,"about_ca_topic_score_gemma":0.019134898,"teacher_disagreement_score":0.9442341,"about_ca_system_score_codex":0.0012473877,"about_ca_system_score_gemma":0.009316388,"threshold_uncertainty_score":0.99931735},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"qualitative","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"design_other","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W4317381706","doi":"10.3138/cjpe.73451","title":"Validation du questionnaire sur la capacité évaluative des organisations et ses déterminants (QCEOD)","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal; Université du Québec à Montréal","funders":"","keywords":"Internal consistency; Confirmatory factor analysis; Psychology; Reliability (semiconductor); Applied psychology; Consistency (knowledge bases); Social psychology; Structural equation modeling; Psychometrics; Statistics; Clinical psychology; Computer science; Mathematics","score_opus":0.3059432813083428,"score_gpt":0.5062255374256022,"score_spread":0.20028225611725936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317381706","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9877031,0.00026729767,0.0030060702,0.004014036,0.00093893404,0.0010178614,0.00003790226,0.000021188896,0.0029936444],"genre_scores_gemma":[0.9968752,0.00001794547,0.0021838841,0.0002586028,0.00012800776,0.00020666345,0.000045778932,0.000017602495,0.00026628672],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9922253,0.00303823,0.0010194884,0.00025920436,0.0031784733,0.00027932794],"domain_scores_gemma":[0.9936284,0.0006153193,0.00073785987,0.0002862803,0.004366316,0.00036583922],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.029391808,0.00016045225,0.0002486382,0.0009042191,0.0010659859,0.0005735658,0.0005226761,0.000060336286,0.005671295],"category_scores_gemma":[0.007942067,0.0001407003,0.00013619904,0.0012605718,0.0001850489,0.0014526506,0.00003711379,0.00035026405,0.000050939463],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003682178,0.00023352171,0.15777284,0.000009587097,0.00007279469,0.000026698339,0.023834134,0.05839053,0.0002722692,0.0025054566,0.011286219,0.7455591],"study_design_scores_gemma":[0.0030201867,0.0018194038,0.68994516,0.00014270506,0.00034601951,0.00077924354,0.014395236,0.1311972,0.0007795685,0.06422792,0.09276739,0.0005799692],"about_ca_topic_score_codex":0.0013156909,"about_ca_topic_score_gemma":0.011454686,"teacher_disagreement_score":0.74497914,"about_ca_system_score_codex":0.0011309515,"about_ca_system_score_gemma":0.010821815,"threshold_uncertainty_score":0.9994454},"labels":[],"label_agreement":null},{"id":"W4317548846","doi":"10.1016/j.evalprogplan.2023.102242","title":"Examining the competencies required by evaluation capacity builders in community-based organizations","year":2023,"lang":"en","type":"article","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Capacity building; Business; Knowledge management; Perception; Public relations; Psychology; Political science; Computer science","score_opus":0.5356546001196051,"score_gpt":0.5285005507770261,"score_spread":0.007154049342579016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317548846","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99113506,0.00018819928,0.0017528833,0.0025925331,0.0002456178,0.0014624584,0.000011733717,0.00016791816,0.0024436205],"genre_scores_gemma":[0.997037,0.00001078997,0.0012345588,0.00065497454,0.000030230061,0.00040752185,0.0004922808,0.000012600895,0.0001200583],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99221736,0.003725441,0.00066637556,0.00031698906,0.0027908182,0.00028300696],"domain_scores_gemma":[0.9957982,0.002469336,0.00028816782,0.00046485793,0.0009070186,0.00007247602],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.037811197,0.00015665872,0.00019458855,0.00042930737,0.0010800078,0.00051604124,0.00039113534,0.000083998624,0.0004391393],"category_scores_gemma":[0.004620292,0.00011269211,0.000027764125,0.0033151526,0.00016927042,0.000450724,0.00008086028,0.00034865038,0.000075742944],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032656804,0.00018284416,0.34515,0.000021812342,0.000027531296,6.9908543e-7,0.026985934,0.122379825,0.0018762086,0.00032904,0.0099931,0.49302036],"study_design_scores_gemma":[0.0010079428,0.00012668701,0.21679984,0.00005721904,0.000032338015,0.0000013597066,0.014922617,0.75987214,0.00015054789,0.00243394,0.0044527757,0.00014261168],"about_ca_topic_score_codex":0.000058382684,"about_ca_topic_score_gemma":0.00010151403,"teacher_disagreement_score":0.6374923,"about_ca_system_score_codex":0.0000894857,"about_ca_system_score_gemma":0.00036610695,"threshold_uncertainty_score":0.9907759},"labels":[],"label_agreement":null},{"id":"W4318062718","doi":"10.1163/9789004524545_015","title":"Training for Settlement Organizations, English Learners, and Graduate Education","year":2022,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Settlement (finance); Process (computing); Training (meteorology); Graduate students; Pedagogy; Political science; Medical education; Mathematics education; Psychology; Sociology; Business; Computer science; Geography; Medicine","score_opus":0.32784707917562667,"score_gpt":0.4698042839769078,"score_spread":0.14195720480128116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318062718","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015002351,0.0001898536,0.0019127788,0.002735847,0.0015892298,0.00084429566,0.00016051231,0.00006384212,0.9923536],"genre_scores_gemma":[0.007927008,0.00034497195,0.0032470864,0.0016274048,0.00039483389,0.000105702726,0.0007978299,0.000040446605,0.9855147],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99742794,0.000042622047,0.0005886706,0.0004779686,0.0013216787,0.0001411045],"domain_scores_gemma":[0.99772555,0.0004751347,0.00033701875,0.00035027397,0.0010240761,0.000087940774],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0025849133,0.00018153517,0.0002498606,0.00032684417,0.00036070187,0.000251263,0.00026854986,0.00007745927,0.03400893],"category_scores_gemma":[0.0008345344,0.00015094157,0.00006329795,0.00012899925,0.000039620423,0.00025677844,0.00011717678,0.00018485381,0.00008110922],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000071434843,0.000016616603,0.00006755436,0.000009857825,0.000026092428,1.1972442e-7,0.0054159495,0.00006651479,0.0000020333125,0.63258594,0.11402166,0.24778053],"study_design_scores_gemma":[0.00018823428,0.000079416786,0.00009925943,0.000011685733,0.00003282373,0.0000016028771,0.007833887,0.0005281003,0.0000039700294,0.05678884,0.93424237,0.00018978819],"about_ca_topic_score_codex":0.000004767313,"about_ca_topic_score_gemma":0.000029863302,"teacher_disagreement_score":0.8202207,"about_ca_system_score_codex":0.00010632089,"about_ca_system_score_gemma":0.0011599768,"threshold_uncertainty_score":0.9668741},"labels":[],"label_agreement":null},{"id":"W4319310321","doi":"10.7202/1095696ar","title":"Pratiques de soutien au cours d’un groupe d’intégration sociale et professionnelle : retombées sur les capabilités de personnes réfugiées dans leur parcours d’apprentissage","year":2023,"lang":"fr","type":"article","venue":"Nouveaux cahiers de la recherche en éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université du Québec à Montréal; Université de Sherbrooke","funders":"","keywords":"Humanities; Political science; Sociology; Philosophy","score_opus":0.21403412264264535,"score_gpt":0.4771197069686794,"score_spread":0.263085584326034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319310321","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93720174,0.00060078135,0.014509912,0.039189674,0.0015965697,0.0008875378,0.000049420705,0.00028230756,0.005682043],"genre_scores_gemma":[0.9598685,0.0021085793,0.015467623,0.0006149294,0.000589686,0.00043236336,0.00019698098,0.000080903905,0.02064044],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9689085,0.026624857,0.0010260419,0.00090821774,0.0014533029,0.001079067],"domain_scores_gemma":[0.9821255,0.015327978,0.0006172578,0.00069017184,0.0008747353,0.0003643434],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.06405125,0.00048693837,0.0005043544,0.00046970075,0.0011666847,0.0005788433,0.00083074236,0.0022054745,0.0011063623],"category_scores_gemma":[0.021890806,0.0004705432,0.0002877984,0.0017233749,0.0008292619,0.001398078,0.0001221267,0.002428154,0.00026837992],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000063049636,0.00046857644,0.09567416,0.00021027001,0.00008624602,0.0000072045964,0.81403166,0.0009932523,0.009010009,0.009573335,0.011671174,0.058211073],"study_design_scores_gemma":[0.00060066686,0.00019523643,0.20397168,0.00034888388,0.00016543413,0.000030077557,0.6993369,0.036807623,0.0064695943,0.045827743,0.0056707393,0.0005754517],"about_ca_topic_score_codex":0.002908709,"about_ca_topic_score_gemma":0.009830539,"teacher_disagreement_score":0.11469478,"about_ca_system_score_codex":0.00792045,"about_ca_system_score_gemma":0.013874297,"threshold_uncertainty_score":0.9998733},"labels":[],"label_agreement":null},{"id":"W4319662944","doi":"10.1016/j.evalprogplan.2023.102257","title":"Learning from experiences of evaluators implementing theory-driven evaluations in diverse settings: Building on the contributions of John Mayne","year":2023,"lang":"en","type":"review","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Honor; Theory of change; Set (abstract data type); Sociology; Engineering ethics; Work (physics); Epistemology; Management science; Psychology; Computer science; Engineering; Philosophy","score_opus":0.3687882346319569,"score_gpt":0.6091828399366908,"score_spread":0.24039460530473383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319662944","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20009363,0.78542155,0.0008106215,0.0003412154,0.0009476532,0.009305432,0.0002416178,0.00017077917,0.002667499],"genre_scores_gemma":[0.5956558,0.39540258,0.0022731386,0.00009644897,0.000323214,0.0050063212,0.0009798184,0.00009291028,0.00016975195],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98640764,0.006005603,0.0024765332,0.0007502797,0.0039122635,0.00044765696],"domain_scores_gemma":[0.9831658,0.012257532,0.0031119005,0.00050718937,0.0008726526,0.000084927575],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.043404438,0.00036870636,0.0012078269,0.000994964,0.00059874856,0.00026294723,0.00066815916,0.00017628427,0.001515902],"category_scores_gemma":[0.01865708,0.00023923558,0.0003104505,0.0022404946,0.0002244147,0.00028278094,0.00029047174,0.0005708483,0.000035200683],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015171151,0.000058676476,0.0009223409,0.00017377177,0.00012951296,7.6590453e-7,0.019637996,0.00393559,0.000012267238,0.0016586469,0.00013013935,0.97332513],"study_design_scores_gemma":[0.0036629087,0.0011889236,0.0025330663,0.033828493,0.002916228,0.0000067989863,0.3734897,0.4225227,0.00019017157,0.014537689,0.14380535,0.0013179472],"about_ca_topic_score_codex":0.00003253707,"about_ca_topic_score_gemma":0.000013403718,"teacher_disagreement_score":0.97200716,"about_ca_system_score_codex":0.00011220244,"about_ca_system_score_gemma":0.0008803715,"threshold_uncertainty_score":0.99939686},"labels":[],"label_agreement":null},{"id":"W4319794051","doi":"10.21810/jicw.v5i3.5206","title":"LESSONS LEARNED AS A NEW POLICE FORCE","year":2023,"lang":"en","type":"article","venue":"The Journal of Intelligence Conflict and Warfare","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Presentation (obstetrics); Police department; Service (business); Period (music); Public relations; Sociology; Political science; Criminology; Management; Medicine; Business; Art; Marketing","score_opus":0.44662653809182873,"score_gpt":0.5473337675089248,"score_spread":0.10070722941709609,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319794051","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82994014,0.0017012614,0.014813428,0.13795747,0.000927181,0.0002671282,0.000007278491,0.000047708127,0.014338384],"genre_scores_gemma":[0.96666074,0.0051345862,0.00008488595,0.0017143696,0.00022036354,8.902183e-7,6.8602793e-7,0.000008003411,0.02617548],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976763,0.00018366011,0.00065013435,0.00011831118,0.0011647578,0.00020680565],"domain_scores_gemma":[0.9972032,0.0013063488,0.0004258467,0.00029534404,0.0005361535,0.00023312886],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005276539,0.000107916305,0.00021937508,0.00026698923,0.00023485384,0.000182763,0.00078623026,0.0000484965,0.0011082443],"category_scores_gemma":[0.0014948569,0.000056040724,0.00009552826,0.000871423,0.00010090884,0.00032161752,0.000114502225,0.000251474,0.00076670334],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026192868,0.000025730413,0.0027858657,0.0000075127796,0.00006702001,0.000009437972,0.051741894,0.0043510636,0.0015472455,0.010792071,0.06254514,0.8658651],"study_design_scores_gemma":[0.00060085964,0.0010458375,0.016978784,0.00017677322,0.00010085658,0.00048699699,0.09862156,0.018117402,0.012372028,0.09747903,0.75362664,0.00039319493],"about_ca_topic_score_codex":0.00019257312,"about_ca_topic_score_gemma":0.000065056105,"teacher_disagreement_score":0.8654719,"about_ca_system_score_codex":0.00001832043,"about_ca_system_score_gemma":0.00042190173,"threshold_uncertainty_score":0.99980485},"labels":[],"label_agreement":null},{"id":"W4319945850","doi":"10.4324/9781003376316-3","title":"COVID Crisis","year":2023,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"World Bank Group","keywords":"Coronavirus disease 2019 (COVID-19); Virology; Medicine; Infectious disease (medical specialty); Internal medicine","score_opus":0.4624869458733234,"score_gpt":0.5338481548770213,"score_spread":0.07136120900369791,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319945850","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000026915777,0.000026514257,0.0007630929,0.0071372264,0.00092742586,0.00013896784,0.000027239674,0.00013638688,0.99084044],"genre_scores_gemma":[0.00059344206,0.00015705333,0.00024837616,0.0047385916,0.0001764934,0.0000071751497,0.000023533303,0.000026452888,0.99402887],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9959126,0.000025560059,0.0006472601,0.0004753818,0.0027914292,0.00014778457],"domain_scores_gemma":[0.99771535,0.00069257134,0.00024692234,0.0007662743,0.00038858518,0.0001902732],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0030833266,0.00018047843,0.00030783922,0.0004341204,0.0001091739,0.00021851902,0.00061476347,0.00019162666,0.1908255],"category_scores_gemma":[0.0005116779,0.00011955956,0.00019365786,0.00010547473,0.000039947063,0.00013443148,0.00016732757,0.00019437638,0.10533662],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021836777,0.0000017721683,0.000017794257,0.0000018387593,0.000011166911,0.000003533875,0.00004909168,0.0000195863,4.0128361e-7,0.34697443,0.63903815,0.013880075],"study_design_scores_gemma":[0.00006616201,0.000021657872,0.000053060583,0.0000058880532,0.000008846913,0.0000010897526,0.000105366664,0.00029461877,0.0000027850695,0.2857563,0.71356136,0.0001229062],"about_ca_topic_score_codex":0.000012628736,"about_ca_topic_score_gemma":0.00016687722,"teacher_disagreement_score":0.085488886,"about_ca_system_score_codex":0.000065134365,"about_ca_system_score_gemma":0.0005108741,"threshold_uncertainty_score":0.89536},"labels":[],"label_agreement":null},{"id":"W4319986326","doi":"10.4324/9781003376316","title":"Policy Evaluation in the Era of COVID-19","year":2023,"lang":"en","type":"book","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University","funders":"International Fund for Agricultural Development; United Nations Development Programme; Public Health Agency of Canada; European Commission; Johns Hopkins University; George Washington University; World Bank Group","keywords":"Coronavirus disease 2019 (COVID-19); 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Political science; Virology; Medicine; Infectious disease (medical specialty); Outbreak","score_opus":0.47537042383470646,"score_gpt":0.6048653696546793,"score_spread":0.12949494581997284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319986326","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003320113,0.00005381666,0.00034552568,0.024746902,0.00029207664,0.00079748716,0.000026476991,0.000021723068,0.97338396],"genre_scores_gemma":[0.011355747,0.000119407356,0.00006525872,0.0064014248,0.00023999983,0.00008059782,0.00009089843,0.000011844232,0.9816348],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9920246,0.00074423145,0.0009532595,0.0003386142,0.005786568,0.0001527039],"domain_scores_gemma":[0.99479234,0.0033769931,0.0004561195,0.0007983023,0.0005134509,0.00006278683],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.030000733,0.00013506282,0.00028504687,0.0007300519,0.000072310075,0.00010868383,0.0010097866,0.0001522327,0.010687362],"category_scores_gemma":[0.0077586523,0.00007252289,0.00012206058,0.0010875476,0.00008179612,0.00013802256,0.00009281668,0.00030516938,0.0024062255],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014066077,0.0000346902,0.00056924106,0.000024485704,0.000014245811,0.0000016903525,0.0041174423,0.0035331543,0.0000025089096,0.12942378,0.76115084,0.101113856],"study_design_scores_gemma":[0.0004973503,0.000063505366,0.0059991544,0.00002987157,0.00001992606,0.0000018909901,0.0013956048,0.013664119,0.000002539255,0.62573624,0.35245875,0.00013109825],"about_ca_topic_score_codex":0.00016440153,"about_ca_topic_score_gemma":0.0014489999,"teacher_disagreement_score":0.49631244,"about_ca_system_score_codex":0.00040016635,"about_ca_system_score_gemma":0.011916433,"threshold_uncertainty_score":0.9988184},"labels":[],"label_agreement":null},{"id":"W4320490525","doi":"10.1111/gove.12765","title":"Measuring accountability in interlocal agreements between Indigenous and local governments","year":2023,"lang":"en","type":"article","venue":"Governance","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Western University; York University","funders":"","keywords":"Accountability; Indigenous; Public administration; Political science; State (computer science); Law","score_opus":0.23564995107971679,"score_gpt":0.44405444420824214,"score_spread":0.20840449312852535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320490525","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99640363,0.000070823466,0.0007466266,0.0002940222,0.00022844959,0.0002098462,0.000043259177,0.00003992721,0.001963433],"genre_scores_gemma":[0.9985694,0.00007444703,0.000050776493,0.000119299664,0.00004792284,0.00002090875,0.0000039866904,0.000007076334,0.0011061616],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99630547,0.00013515526,0.0005446433,0.00043717824,0.0022615513,0.0003160349],"domain_scores_gemma":[0.99888253,0.00040164657,0.00020800074,0.00035978714,0.000065600376,0.0000824461],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038978322,0.00012794563,0.00024112509,0.00007148703,0.00010003966,0.00011894669,0.00044279493,0.000059810318,0.00024555152],"category_scores_gemma":[0.00047203057,0.000102131235,0.000037912956,0.0005913563,0.00008631804,0.0005085589,0.0002797427,0.0001642522,0.0007363685],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023633631,0.000014615634,0.8187901,0.00000583812,0.0000042611046,0.000003009234,0.0017905298,0.00016973901,0.00001786194,0.000018843826,0.00037313392,0.17878847],"study_design_scores_gemma":[0.00058230443,0.000054098906,0.98682415,0.000033562024,0.0000031941984,7.9577404e-7,0.0008412643,0.0046330886,0.0002321653,0.00086117396,0.0058211773,0.00011299211],"about_ca_topic_score_codex":0.00043265967,"about_ca_topic_score_gemma":0.0010281923,"teacher_disagreement_score":0.17867547,"about_ca_system_score_codex":0.00037388408,"about_ca_system_score_gemma":0.000088082124,"threshold_uncertainty_score":0.94647735},"labels":[],"label_agreement":null},{"id":"W4320894712","doi":"10.4300/jgme-d-22-00397.1","title":"Program Evaluation Use in Graduate Medical Education","year":2023,"lang":"en","type":"article","venue":"Journal of Graduate Medical Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"University of Ottawa","keywords":"Timeline; Process (computing); Publication; Curriculum; Medical education; Program evaluation; Graduate medical education; Computer science; Psychology; Accreditation; Medicine; Political science; Pedagogy","score_opus":0.5342027688137225,"score_gpt":0.6158367903650068,"score_spread":0.0816340215512843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320894712","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91897345,0.00013598551,0.00020964595,0.07240203,0.00630579,0.00074593263,9.92443e-7,0.000039792234,0.0011863734],"genre_scores_gemma":[0.9932703,0.00066714454,0.0010250915,0.002702394,0.0010079416,0.00021027142,0.000062915286,0.000018847306,0.0010351221],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98092175,0.0012994609,0.0022259976,0.0003606392,0.014837511,0.00035467325],"domain_scores_gemma":[0.9929926,0.0010655855,0.0011115002,0.00042242327,0.0036256919,0.00078222],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.038518123,0.00018891269,0.00041364992,0.0016318266,0.00012857061,0.00031126055,0.00085752824,0.00021343563,0.0032804238],"category_scores_gemma":[0.07346608,0.00013472296,0.00017948089,0.0032135244,0.00014508,0.0013556005,0.00008053934,0.0008217715,0.0005038967],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003658381,0.0011473756,0.022413984,0.000010729828,0.00001294275,0.000005633181,0.0009934905,0.00009367017,0.0000067206097,0.0006004098,0.12095672,0.85372174],"study_design_scores_gemma":[0.0019156999,0.00045354603,0.7155604,0.00071341573,0.00007204721,0.00020902569,0.0053167273,0.16427805,0.0000474905,0.04476999,0.066350676,0.00031298315],"about_ca_topic_score_codex":0.00010939537,"about_ca_topic_score_gemma":0.00032984588,"teacher_disagreement_score":0.85340875,"about_ca_system_score_codex":0.00037390128,"about_ca_system_score_gemma":0.027351322,"threshold_uncertainty_score":0.9976307},"labels":[],"label_agreement":null},{"id":"W4321268861","doi":"10.3138/9781487545154-008","title":"5 What Counts in Research? Dysfunction in Knowledge Creation and Moving Beyond","year":2021,"lang":"en","type":"book-chapter","venue":"University of Toronto Press eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Knowledge creation; Knowledge management; Computer science; Engineering; Operations management","score_opus":0.24191341634814362,"score_gpt":0.43061795244234663,"score_spread":0.188704536094203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321268861","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007335186,0.0029350258,0.000024919524,0.000024827848,0.00023328248,0.00015611714,0.000005331148,0.0000043785276,0.9958826],"genre_scores_gemma":[0.007765283,0.0022651886,0.00007123686,0.000008304146,0.00002559411,2.9772332e-7,0.000008886063,0.000005166502,0.98985004],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986836,0.00012049256,0.00018936602,0.000264464,0.00064872205,0.00009336294],"domain_scores_gemma":[0.99899054,0.0002678357,0.000112507034,0.00022441123,0.00036752858,0.00003716298],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015825332,0.00007862798,0.00018733105,0.00013798816,0.00006123701,0.00007948315,0.00018440768,0.0001475873,0.0019157719],"category_scores_gemma":[0.000053668122,0.00008452674,0.000032365646,0.000005382447,0.00010466256,0.0004241818,0.00017563866,0.00016565614,0.00002251362],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019449412,0.00006435147,0.00076202827,0.00010392742,0.00004237144,0.000037923422,0.029235318,0.000062626255,0.00008336969,0.2516313,0.01300601,0.7047763],"study_design_scores_gemma":[0.00044061022,0.000038434355,0.0021723565,0.00033169414,0.000008743156,6.539082e-7,0.0015653165,0.0012785533,0.000016355132,0.003431187,0.9906118,0.00010428218],"about_ca_topic_score_codex":0.0049558706,"about_ca_topic_score_gemma":0.07828085,"teacher_disagreement_score":0.9776058,"about_ca_system_score_codex":0.00031507385,"about_ca_system_score_gemma":0.00018577692,"threshold_uncertainty_score":0.9989966},"labels":[],"label_agreement":null},{"id":"W4321766392","doi":"10.1016/j.ijnss.2023.02.002","title":"Corrigendum to “Exploring social movement concepts and actions in a knowledge uptake and sustainability context: A concept analysis” [Int J Nurs Sci 9/4 (2022) 411–421]","year":2023,"lang":"en","type":"erratum","venue":"International Journal of Nursing Sciences","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Public Health; Université Laval; Queensway-Carleton Hospital; Research Institute for Aging; Alberta Health Services; Women's College Hospital; University of Toronto; CARE Canada; Ottawa Hospital; University of Ottawa; Registered Nurses' Association of Ontario","funders":"","keywords":"INT; Context (archaeology); Movement (music); Sustainability; Sociology; Psychology; Computer science; Philosophy; Geography","score_opus":0.3790037481634055,"score_gpt":0.5651515388565397,"score_spread":0.1861477906931342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321766392","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60357535,0.008295036,0.0048971116,0.12511809,0.23735327,0.0018014233,0.00035968667,0.00009840827,0.018501624],"genre_scores_gemma":[0.97951585,0.00053656084,0.00020330737,0.000544687,0.0014629982,0.000031899224,0.0000116897045,0.000016824413,0.017676184],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99280924,0.00039520572,0.0016456121,0.00072093384,0.004003255,0.0004257376],"domain_scores_gemma":[0.9950543,0.00060126465,0.0011893879,0.00016818967,0.0027261472,0.0002607073],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.008225149,0.00029277356,0.00079482375,0.0035533844,0.000525595,0.001154105,0.0013268169,0.00016012871,0.00025452656],"category_scores_gemma":[0.0024763658,0.00023440008,0.0002645289,0.0030485757,0.0010994925,0.0011165382,0.00020313778,0.0007291649,0.000012081174],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019922563,0.00052286603,0.014933259,0.000016995184,0.0006925373,0.00005213859,0.0601149,0.0018678763,0.000045314122,0.010115003,0.45565382,0.45578608],"study_design_scores_gemma":[0.0017193907,0.0008837991,0.53903943,0.0011489046,0.0004410332,0.00006244948,0.17860541,0.021717161,0.000042514483,0.03832359,0.2172061,0.00081020803],"about_ca_topic_score_codex":0.00011892857,"about_ca_topic_score_gemma":0.001006691,"teacher_disagreement_score":0.5241062,"about_ca_system_score_codex":0.0013389948,"about_ca_system_score_gemma":0.0020847511,"threshold_uncertainty_score":0.9998828},"labels":[],"label_agreement":null},{"id":"W4322744890","doi":"10.1177/13563890231156954","title":"How can climate change and its interaction with other compounding risks be considered in evaluation? Experiences from Vietnam","year":2023,"lang":"en","type":"article","venue":"Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of Alberta; University of Guelph","funders":"Australian Centre for International Agricultural Research; Canadian Institutes of Health Research; Consortium of International Agricultural Research Centers","keywords":"Climate change; Context (archaeology); Environmental resource management; Environmental planning; Public relations; Political science; Business; Psychology; Geography; Environmental science; Ecology","score_opus":0.6069973684791174,"score_gpt":0.5550850423223465,"score_spread":0.051912326156770994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4322744890","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98864734,0.00021124794,0.00006017375,0.008013335,0.0006210676,0.0013147092,0.000025868892,0.000050128667,0.001056123],"genre_scores_gemma":[0.9979693,0.000059622038,0.00016088401,0.00041839213,0.00013970585,0.001066888,0.00010029376,0.000013297775,0.00007157778],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9942534,0.0010937816,0.00047277985,0.0005499427,0.0033711542,0.00025895282],"domain_scores_gemma":[0.9976649,0.00077997963,0.00039332622,0.0002911684,0.00079598324,0.0000746429],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.012224016,0.00016667346,0.00023838088,0.00054199743,0.0002643324,0.0005525851,0.0001716471,0.000071229595,0.0017989558],"category_scores_gemma":[0.0014324833,0.00012541586,0.000030339063,0.0010773874,0.00005479471,0.0013700718,0.000063193,0.00012861073,0.000101135876],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034267554,0.00016150929,0.42566052,0.000023309529,0.000073409195,0.000005096957,0.20220369,0.007643127,0.004074518,0.00093844725,0.0012696432,0.35760403],"study_design_scores_gemma":[0.0013632437,0.00008871122,0.29396734,0.00007427349,0.000038131624,0.0000021937772,0.06110349,0.64018095,0.00041135814,0.0018695529,0.00073482445,0.00016592156],"about_ca_topic_score_codex":0.00019236241,"about_ca_topic_score_gemma":0.004061178,"teacher_disagreement_score":0.63253784,"about_ca_system_score_codex":0.0002063037,"about_ca_system_score_gemma":0.00020057004,"threshold_uncertainty_score":0.99911356},"labels":[],"label_agreement":null},{"id":"W4323314054","doi":"10.1177/14767503231160960","title":"How long-term emancipatory programming facilitates participatory evaluation: Building a methodology of participation through research with youth in Honduras","year":2023,"lang":"en","type":"article","venue":"Action Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; University of Waterloo","funders":"Global Affairs Canada; Social Sciences and Humanities Research Council of Canada; Centro Internacional de Agricultura Tropical","keywords":"Participatory action research; Empowerment; Action research; General partnership; Transformative learning; Participatory evaluation; Insider; Sociology; Citizen journalism; Public relations; Framing (construction); Political science; Pedagogy; Social science","score_opus":0.9576394455500017,"score_gpt":0.7315822924670258,"score_spread":0.22605715308297591,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323314054","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99262965,0.00014623332,0.0022806318,0.0029981725,0.00020761498,0.0013098946,0.000006756644,0.00005516969,0.00036590846],"genre_scores_gemma":[0.996611,0.000075140044,0.0010621194,0.000016834165,0.000087611705,0.0011129137,0.000026872145,0.000018761013,0.0009887544],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97614944,0.011959418,0.00090774725,0.0007582554,0.009127046,0.0010980865],"domain_scores_gemma":[0.98725045,0.007063418,0.00024523947,0.00081654533,0.004473056,0.00015129281],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10829718,0.0001587852,0.00037985254,0.002014131,0.0005073425,0.0003449211,0.00057635264,0.00016038753,0.00043360068],"category_scores_gemma":[0.0137747405,0.0001198078,0.000071193936,0.007441114,0.00066149235,0.001335569,0.0002345183,0.000822124,0.00018469316],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00053674617,0.00032621238,0.65887076,0.0001601991,0.00006208644,0.000016016029,0.04707901,0.0037948638,0.008865719,0.0016108106,0.00080557354,0.277872],"study_design_scores_gemma":[0.001755616,0.0011095019,0.7972857,0.00019654502,0.000035530793,0.0000028501322,0.14921607,0.016819285,0.022430614,0.008643611,0.0022166797,0.0002879948],"about_ca_topic_score_codex":0.00029487532,"about_ca_topic_score_gemma":0.0019374151,"teacher_disagreement_score":0.27758402,"about_ca_system_score_codex":0.00040008678,"about_ca_system_score_gemma":0.0010400381,"threshold_uncertainty_score":0.99453264},"labels":[],"label_agreement":null},{"id":"W4353055378","doi":"10.3138/cjpe.75448","title":"John Mayne and Rules of Thumb for Contribution Analysis: A Comparison With Two Related Approaches","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Rule of thumb; Manifesto; Thumb; Epistemology; Work (physics); Sociology; Computer science; Political science; Law; Philosophy; Medicine; Engineering; Algorithm; Surgery","score_opus":0.4678585488688824,"score_gpt":0.5302059008889366,"score_spread":0.0623473520200542,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055378","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99035895,0.0005304466,0.0058180713,0.001656896,0.00013179917,0.0011529941,0.000045889305,0.000010331382,0.0002946065],"genre_scores_gemma":[0.99602515,0.000009009951,0.0036314763,0.000014725181,0.00003654241,0.00005028772,0.00017807905,0.000005853359,0.000048880887],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99700975,0.00036602197,0.00092343974,0.00020477318,0.0012955364,0.00020045589],"domain_scores_gemma":[0.99580115,0.0003965314,0.0010033937,0.00028240096,0.0022937944,0.00022274218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0187302,0.0000923242,0.00037395238,0.0011364669,0.00016077656,0.00018897708,0.00031049026,0.000056267894,0.00013645954],"category_scores_gemma":[0.0016503269,0.000063698244,0.00009178544,0.001681784,0.00011764126,0.00041321918,0.0000131788265,0.00010047608,0.0000073023402],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001272462,0.00006576826,0.2647713,0.000014208235,0.00073690945,0.0000019680201,0.0025042712,0.039624188,0.000040242136,0.002901427,0.0013184445,0.687894],"study_design_scores_gemma":[0.0016194995,0.0005151323,0.21675566,0.000031299573,0.0008841282,0.000007642675,0.0018659047,0.7692501,0.00005472162,0.006607699,0.002325412,0.00008282906],"about_ca_topic_score_codex":0.00021491873,"about_ca_topic_score_gemma":0.01351109,"teacher_disagreement_score":0.7296259,"about_ca_system_score_codex":0.000103028,"about_ca_system_score_gemma":0.0016509243,"threshold_uncertainty_score":0.75395054},"labels":[],"label_agreement":null},{"id":"W4353055384","doi":"10.3138/cjpe.75515","title":"Remembering John Mayne—A Practical Thinker and a Thinking Practitioner","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Ontario Stroke Network","funders":"","keywords":"Psychoanalysis; Psychology; Epistemology; Philosophy","score_opus":0.4904664904135886,"score_gpt":0.5735784858630458,"score_spread":0.08311199544945724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055384","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9210034,0.0004307254,0.0028486904,0.050624818,0.0026487224,0.0017682888,0.0000074069703,0.000078055156,0.02058988],"genre_scores_gemma":[0.98850065,0.00003965697,0.010276212,0.00041870723,0.0002712975,0.000042654032,0.000010487821,0.000012429974,0.0004278936],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956469,0.00052894844,0.00074895006,0.00020637907,0.0025869526,0.00028189356],"domain_scores_gemma":[0.99616265,0.0005689892,0.00061932486,0.00021886104,0.001997458,0.00043272108],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.025636477,0.00010372759,0.0001852663,0.00082684174,0.0003828657,0.0008589659,0.00021514164,0.000084299856,0.0018438477],"category_scores_gemma":[0.00843999,0.00007973721,0.00007516478,0.001090363,0.000078110905,0.0014794471,0.000025112053,0.00029213383,0.0002328866],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003308573,0.00004379826,0.02980915,0.000012172598,0.00007092299,0.00008755224,0.005841572,0.003266818,0.00018245095,0.0059483354,0.046809334,0.9078948],"study_design_scores_gemma":[0.0015817065,0.00058218325,0.27750462,0.0001508337,0.00019847623,0.00062139216,0.0078944145,0.21895744,0.000090458125,0.077694535,0.41438448,0.0003394599],"about_ca_topic_score_codex":0.00019027307,"about_ca_topic_score_gemma":0.0059579005,"teacher_disagreement_score":0.90755534,"about_ca_system_score_codex":0.00021658152,"about_ca_system_score_gemma":0.003544823,"threshold_uncertainty_score":0.9999123},"labels":[],"label_agreement":null},{"id":"W4353055391","doi":"10.3138/cjpe.75444","title":"Using Evaluative Information Sensibly: The Enduring Contributions of John Mayne","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Ontario Stroke Network","funders":"MetroWest Health Foundation; Hartford Foundation for Public Giving","keywords":"Causation; Audit; Accountability; Discipline; Bridge (graph theory); Work (physics); Knowledge management; Sociology; Engineering ethics; Epistemology; Computer science; Political science; Social science; Accounting; Engineering; Medicine; Business; Law","score_opus":0.47197470653963447,"score_gpt":0.5711621102531929,"score_spread":0.09918740371355839,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055391","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9846249,0.00021139582,0.00478111,0.004298168,0.001349868,0.0017431269,0.000063457876,0.000018486196,0.002909494],"genre_scores_gemma":[0.99846494,0.000012776565,0.0011888852,0.00009841069,0.00012767344,0.000030733776,0.000028623917,0.0000055865466,0.000042343807],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9945276,0.00088651007,0.0013176386,0.0001094071,0.0028665264,0.00029231168],"domain_scores_gemma":[0.9897987,0.0005650801,0.0013217032,0.00029889448,0.00777217,0.00024344811],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.028679764,0.000109641136,0.00023939906,0.0012211953,0.0004174108,0.00031186786,0.00040432898,0.000073932686,0.00089069013],"category_scores_gemma":[0.008966826,0.00007256842,0.0001517296,0.0024235395,0.00015097213,0.0013623735,0.000023308712,0.00020989684,0.00012445672],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038679576,0.00003666825,0.0122142695,0.000013716735,0.00012639065,0.000004306047,0.008158214,0.14734825,0.0009713076,0.0029570877,0.008098386,0.8200327],"study_design_scores_gemma":[0.0014882,0.0003884603,0.11509988,0.00010560851,0.00022808556,0.00006030012,0.010879092,0.83022666,0.0014596437,0.012949068,0.026944742,0.0001702811],"about_ca_topic_score_codex":0.00041972546,"about_ca_topic_score_gemma":0.002198187,"teacher_disagreement_score":0.8198624,"about_ca_system_score_codex":0.00039102402,"about_ca_system_score_gemma":0.0064977994,"threshold_uncertainty_score":0.99938107},"labels":[],"label_agreement":null},{"id":"W4353055426","doi":"10.3138/cjpe.75451","title":"John Mayne and the Origins of Evaluation in the Public Sector in Canada: A Shaping of Both Evaluation and the Evaluator","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Test (biology); Public sector; Public administration; Political science; Sociology; Management; Public relations; Economics; Law; Philosophy; Geology","score_opus":0.37158747526533276,"score_gpt":0.48774464836179726,"score_spread":0.1161571730964645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055426","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9766919,0.0022472444,0.00003675037,0.01615367,0.0004294204,0.004004699,0.000010685831,0.0000022987317,0.00042332086],"genre_scores_gemma":[0.99906635,0.00011857902,0.00008904139,0.0002485306,0.00007252637,0.00037641398,0.00001288551,0.000008947046,0.000006730184],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9825772,0.007646695,0.0019724176,0.00029496488,0.0071237376,0.00038495375],"domain_scores_gemma":[0.99206847,0.0026368261,0.0013310511,0.00042186156,0.0033922496,0.00014951854],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.16078137,0.00015832736,0.0004487634,0.0009772494,0.0002192174,0.0002598263,0.0005597079,0.000067415596,0.0004702977],"category_scores_gemma":[0.014689999,0.00008004488,0.00009145456,0.0026743417,0.00043820674,0.00053726096,0.000032075364,0.00030841999,0.0000025203442],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002686929,0.00004608861,0.10597804,0.000032548287,0.00008728667,0.0000037874581,0.016573137,0.0120452745,0.000045212983,0.0100857355,0.0012814454,0.85355276],"study_design_scores_gemma":[0.0060614487,0.00009820517,0.36397165,0.00007485624,0.00015949293,0.00002113067,0.007833255,0.6106292,0.000009118127,0.009844811,0.0012230133,0.00007380592],"about_ca_topic_score_codex":0.2899152,"about_ca_topic_score_gemma":0.96185267,"teacher_disagreement_score":0.85347897,"about_ca_system_score_codex":0.0015257866,"about_ca_system_score_gemma":0.02524637,"threshold_uncertainty_score":0.99360967},"labels":[],"label_agreement":null},{"id":"W4353055441","doi":"10.3138/cjpe.37.3.ed-en","title":"Editor’s Remarks","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Psychology","score_opus":0.3016607384097375,"score_gpt":0.5419447489581198,"score_spread":0.24028401054838233,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055441","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83711743,0.00097156427,0.002445411,0.03685035,0.06468003,0.0036134229,0.000029206036,0.00013233752,0.05416026],"genre_scores_gemma":[0.9940449,0.000013220605,0.0014438768,0.00020563856,0.0031648087,0.000045330296,0.00001773646,0.000009942429,0.0010545491],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9955053,0.000415694,0.0007865304,0.00015167915,0.002868767,0.0002720561],"domain_scores_gemma":[0.9953159,0.00028554566,0.0004931246,0.0002655536,0.0031687526,0.0004710908],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.024627816,0.000083011575,0.00016917981,0.0010701319,0.00019822734,0.0003929544,0.0004595897,0.00007228107,0.0038903803],"category_scores_gemma":[0.005499139,0.00006263263,0.00011801692,0.0016472327,0.00006102372,0.0005616982,0.000011080702,0.00017529621,0.00091196224],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004549832,0.000008382617,0.0116367815,0.000001386721,0.000010852067,0.0000064418723,0.00047632185,0.0016546788,0.000018128467,0.00019120304,0.28842306,0.69756824],"study_design_scores_gemma":[0.0006104685,0.0003107812,0.13341339,0.00003110775,0.000040280895,0.000023838049,0.0013397733,0.07667341,0.000042513147,0.016967505,0.7704299,0.00011702141],"about_ca_topic_score_codex":0.0001839598,"about_ca_topic_score_gemma":0.008594621,"teacher_disagreement_score":0.6974512,"about_ca_system_score_codex":0.00025826498,"about_ca_system_score_gemma":0.0053484077,"threshold_uncertainty_score":0.99986595},"labels":[],"label_agreement":null},{"id":"W4353055504","doi":"10.3138/cjpe.75430","title":"Causality and Complexity in Evaluating Equity Interventions: Conceptual Issues That Need to Be Addressed in Theory-Driven Evaluation Approaches","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto","funders":"","keywords":"Causality (physics); Variety (cybernetics); Psychological intervention; Equity (law); Management science; Causal model; Conceptual framework; Risk analysis (engineering); Positive economics; Psychology; Computer science; Sociology; Economics; Political science; Business; Medicine; Social science","score_opus":0.921309918994153,"score_gpt":0.6511159997897381,"score_spread":0.27019391920441493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055504","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9866945,0.00061955536,0.00044118156,0.007808607,0.00045970856,0.0030938115,0.000025385658,0.000017992475,0.0008392673],"genre_scores_gemma":[0.99669397,0.000013904525,0.0024813092,0.00019321575,0.00008304773,0.0003709172,0.00007556356,0.000013161999,0.000074930445],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98853093,0.0048682257,0.0016825474,0.00046148914,0.0039542895,0.00050249],"domain_scores_gemma":[0.9956864,0.0008232879,0.00077206426,0.00035920864,0.0019115558,0.0004475013],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09844063,0.00019984314,0.00046809332,0.0019735503,0.00021952525,0.00052699697,0.0005483606,0.00012333576,0.0017816039],"category_scores_gemma":[0.014224714,0.00017474595,0.00014034042,0.0023267458,0.00027780602,0.0009436707,0.000100698206,0.0003474602,0.000040607723],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000947511,0.000114589035,0.14119618,0.000030088577,0.000036644546,0.0000067873334,0.019164206,0.03206704,0.00007355578,0.0043197433,0.0013146211,0.8015818],"study_design_scores_gemma":[0.001892026,0.00049186643,0.5385117,0.00024054127,0.000071401984,0.0000068193835,0.025557417,0.38283092,0.000043343756,0.04963478,0.0005388537,0.00018035003],"about_ca_topic_score_codex":0.0016824801,"about_ca_topic_score_gemma":0.16618764,"teacher_disagreement_score":0.80140144,"about_ca_system_score_codex":0.00095736614,"about_ca_system_score_gemma":0.003084084,"threshold_uncertainty_score":0.9991309},"labels":[],"label_agreement":null},{"id":"W4353055508","doi":"10.3138/cjpe.75467","title":"John Mayne’s Contribution to Performance Audit","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Carleton University","funders":"","keywords":"Audit; Government (linguistics); Service (business); Public service; Business; Accounting; Public administration; Political science; Philosophy; Marketing","score_opus":0.3441610320995043,"score_gpt":0.528996299099539,"score_spread":0.18483526700003472,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055508","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98598784,0.00008504031,0.0006832591,0.007916707,0.0017978908,0.0011509322,0.0000109819575,0.000028262077,0.0023390802],"genre_scores_gemma":[0.9978024,0.00001598916,0.00069295155,0.0003779117,0.00029200115,0.00009361082,0.000026284393,0.000009384194,0.00068951986],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9954164,0.00035389408,0.00092094846,0.00020857553,0.0026944932,0.00040568202],"domain_scores_gemma":[0.9939035,0.00020025743,0.0004899483,0.00029670438,0.0044148252,0.0006947373],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.02122548,0.00011672165,0.00022702584,0.0014030781,0.00031010757,0.00041319587,0.0005087196,0.000075720665,0.0025384875],"category_scores_gemma":[0.004966496,0.00009275142,0.00011064636,0.0025010402,0.000048945243,0.0007051433,0.000018641202,0.00017142645,0.0022771521],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021681868,0.0000155456,0.03882633,0.0000030317708,0.000018145449,0.00000653601,0.00059652154,0.011763633,0.0001555637,0.00043551796,0.03864247,0.909515],"study_design_scores_gemma":[0.0008127224,0.0007137563,0.50682807,0.000055414625,0.00004474881,0.00002936009,0.00047201457,0.095139466,0.00031420344,0.0023064103,0.39312485,0.00015896978],"about_ca_topic_score_codex":0.0001198295,"about_ca_topic_score_gemma":0.005362593,"teacher_disagreement_score":0.90935606,"about_ca_system_score_codex":0.00053728133,"about_ca_system_score_gemma":0.0044759014,"threshold_uncertainty_score":0.9984997},"labels":[],"label_agreement":null},{"id":"W4353055537","doi":"10.3138/cjpe.75431","title":"Building Evaluation Culture—The Missing Link","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Sociology; Knowledge management; Psychology; Epistemology; Computer science; Philosophy","score_opus":0.5208539717794183,"score_gpt":0.5865932421472865,"score_spread":0.0657392703678682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055537","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8144254,0.004027716,0.011062529,0.1356717,0.010375078,0.007065487,0.000018014936,0.00012802676,0.01722601],"genre_scores_gemma":[0.9940717,0.000017431012,0.0043542664,0.0004222477,0.00070020405,0.00009730976,0.000018147057,0.000013142458,0.0003055332],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99242246,0.0012359023,0.0010439067,0.00022761324,0.0047103143,0.0003598027],"domain_scores_gemma":[0.99254125,0.00041509993,0.00082254503,0.00038251976,0.005448218,0.00039036118],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05735271,0.0001314581,0.00020116502,0.0008599142,0.0006382905,0.0009247136,0.000674629,0.000094607865,0.0018211184],"category_scores_gemma":[0.010421291,0.000082493236,0.0001671914,0.0023532289,0.000101280006,0.0007337571,0.000018313582,0.00029571741,0.00030338805],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000046499877,0.000006583839,0.0026067628,0.0000019037814,0.000019111727,0.0000026601108,0.0014186067,0.010633542,0.00014020059,0.0005200926,0.013712593,0.9709333],"study_design_scores_gemma":[0.0008529485,0.00023776163,0.06726978,0.000068410125,0.00016998181,0.00004499004,0.0014202937,0.6034538,0.00017267934,0.07539648,0.25075975,0.00015311589],"about_ca_topic_score_codex":0.00017751264,"about_ca_topic_score_gemma":0.003225833,"teacher_disagreement_score":0.9707802,"about_ca_system_score_codex":0.00053978106,"about_ca_system_score_gemma":0.006295008,"threshold_uncertainty_score":0.9993384},"labels":[],"label_agreement":null},{"id":"W4353055566","doi":"10.3138/cjpe.75441","title":"Mapping the Contributions of John Mayne: Bridging the Gaps Between Evaluation, Auditing, and Performance Monitoring","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Audit; Citation; Bridging (networking); Field (mathematics); Library science; Data science; Computer science; Accounting; Business","score_opus":0.36971123944452877,"score_gpt":0.5041761856590817,"score_spread":0.13446494621455296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055566","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9887963,0.0009021795,0.00044641295,0.0074141547,0.0007014889,0.0011337185,0.000015619964,0.000011130092,0.0005789776],"genre_scores_gemma":[0.99892324,0.00007905726,0.0001992012,0.000042715714,0.0005675952,0.00009639588,0.000013816036,0.000008270334,0.00006968634],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99457127,0.0009383209,0.0010786209,0.00017669427,0.0029090678,0.00032603266],"domain_scores_gemma":[0.99265146,0.00097549555,0.0010910012,0.0003311767,0.00473712,0.00021373932],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.049873527,0.00011858243,0.00022822041,0.0006429794,0.0009363149,0.00040039976,0.00053983997,0.000058834583,0.0002986035],"category_scores_gemma":[0.00681114,0.000070114365,0.00009837245,0.0019264793,0.00021169221,0.00055016385,0.00003438331,0.0002835635,0.000031692394],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003049859,0.0000042486768,0.30430388,0.000006122753,0.00003749699,4.7462888e-7,0.002107484,0.0043916656,0.00006161742,0.00006233117,0.002015983,0.68700564],"study_design_scores_gemma":[0.00052256905,0.000121068406,0.8387907,0.0001222366,0.000119306664,0.00001616207,0.0050122985,0.14499968,0.000374473,0.001655146,0.008183329,0.00008304469],"about_ca_topic_score_codex":0.00019068459,"about_ca_topic_score_gemma":0.00047351595,"teacher_disagreement_score":0.6869226,"about_ca_system_score_codex":0.00025552648,"about_ca_system_score_gemma":0.003226933,"threshold_uncertainty_score":0.97835517},"labels":[],"label_agreement":null},{"id":"W4353055592","doi":"10.3138/cjpe.37.3.addendum-fr","title":"Addendum","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Addendum; Philosophy; Linguistics","score_opus":0.642089777734816,"score_gpt":0.5990496877794452,"score_spread":0.043040089955370786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055592","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9540916,0.00043606546,0.0006610809,0.012670758,0.0046380693,0.0013814108,0.000013304841,0.000052672887,0.026055051],"genre_scores_gemma":[0.99746716,0.000008909568,0.0008860703,0.00017324988,0.00034030667,0.000035940233,0.000012235989,0.000007058447,0.0010690439],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99615,0.0003575139,0.0007025887,0.00013286926,0.0024045184,0.00025249607],"domain_scores_gemma":[0.996134,0.00020753607,0.00042654618,0.00023272597,0.002569188,0.00043000194],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.019818896,0.00007338626,0.00015013629,0.0010854412,0.00017640422,0.00035183533,0.00043078838,0.000053238673,0.0057088393],"category_scores_gemma":[0.0039079995,0.000055008473,0.000108579545,0.0017535926,0.00005347931,0.0005079353,0.000009701136,0.00014022966,0.0013377728],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000035498335,0.000008186101,0.015335971,0.0000010713674,0.000011100746,0.000008956075,0.00058021606,0.0017007942,0.000023370401,0.00047397587,0.07176863,0.9100842],"study_design_scores_gemma":[0.00088556076,0.00044394648,0.25132003,0.000032330274,0.000056172234,0.000037142803,0.0023367624,0.11563147,0.00010049322,0.031403188,0.5975973,0.00015560775],"about_ca_topic_score_codex":0.0001781861,"about_ca_topic_score_gemma":0.009452958,"teacher_disagreement_score":0.90992856,"about_ca_system_score_codex":0.00019560097,"about_ca_system_score_gemma":0.004715324,"threshold_uncertainty_score":0.9994398},"labels":[],"label_agreement":null},{"id":"W4353055595","doi":"10.3138/cjpe.37.3.addendum-en","title":"Addendum","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Addendum; Philosophy; Linguistics","score_opus":0.642089777734816,"score_gpt":0.5990496877794452,"score_spread":0.043040089955370786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055595","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9540916,0.00043606546,0.0006610809,0.012670758,0.0046380693,0.0013814108,0.000013304841,0.000052672887,0.026055051],"genre_scores_gemma":[0.99746716,0.000008909568,0.0008860703,0.00017324988,0.00034030667,0.000035940233,0.000012235989,0.000007058447,0.0010690439],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99615,0.0003575139,0.0007025887,0.00013286926,0.0024045184,0.00025249607],"domain_scores_gemma":[0.996134,0.00020753607,0.00042654618,0.00023272597,0.002569188,0.00043000194],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.019818896,0.00007338626,0.00015013629,0.0010854412,0.00017640422,0.00035183533,0.00043078838,0.000053238673,0.0057088393],"category_scores_gemma":[0.0039079995,0.000055008473,0.000108579545,0.0017535926,0.00005347931,0.0005079353,0.000009701136,0.00014022966,0.0013377728],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000035498335,0.000008186101,0.015335971,0.0000010713674,0.000011100746,0.000008956075,0.00058021606,0.0017007942,0.000023370401,0.00047397587,0.07176863,0.9100842],"study_design_scores_gemma":[0.00088556076,0.00044394648,0.25132003,0.000032330274,0.000056172234,0.000037142803,0.0023367624,0.11563147,0.00010049322,0.031403188,0.5975973,0.00015560775],"about_ca_topic_score_codex":0.0001781861,"about_ca_topic_score_gemma":0.009452958,"teacher_disagreement_score":0.90992856,"about_ca_system_score_codex":0.00019560097,"about_ca_system_score_gemma":0.004715324,"threshold_uncertainty_score":0.9994398},"labels":[],"label_agreement":null},{"id":"W4353055654","doi":"10.3138/cjpe.75428","title":"Causal Claims in Contribution Analysis","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Counterfactual thinking; Causality (physics); Causation; Relevance (law); Epistemology; Causal analysis; Counterfactual conditional; Generative grammar; Probabilistic logic; Computer science; Positive economics; Psychology; Sociology; Econometrics; Philosophy; Artificial intelligence; Economics; Political science; Law","score_opus":0.4173134303158473,"score_gpt":0.5774615920977317,"score_spread":0.16014816178188446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055654","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99369323,0.00012365221,0.0010822137,0.003255388,0.00063187175,0.000596357,0.000008983438,0.0000121522235,0.00059615343],"genre_scores_gemma":[0.9992996,0.000010986737,0.0002776369,0.00008889131,0.00009570678,0.000042555483,0.000054344837,0.0000043555006,0.00012591996],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9958046,0.00062353734,0.0009811239,0.0001716958,0.0021209598,0.0002980918],"domain_scores_gemma":[0.9961322,0.00027665118,0.0004912705,0.00021873532,0.0025483463,0.00033278693],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.026240636,0.00008046794,0.00026938439,0.0032622819,0.00012252547,0.00029069558,0.00031517533,0.00007741166,0.0016899792],"category_scores_gemma":[0.002684498,0.0000669835,0.00016813693,0.0067898184,0.000050014627,0.0005031266,0.000008600842,0.00017585952,0.00024824962],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014157892,0.000024405,0.40862143,0.0000012078931,0.00009387408,0.000021289767,0.0007356543,0.044790983,0.000030735642,0.00093538093,0.0032190424,0.54151183],"study_design_scores_gemma":[0.0006366847,0.00014150837,0.6970087,0.000010099759,0.00015748403,0.000005241214,0.0005071957,0.27787903,0.000024009234,0.0118117295,0.011745176,0.00007311533],"about_ca_topic_score_codex":0.0007143109,"about_ca_topic_score_gemma":0.12745304,"teacher_disagreement_score":0.54143876,"about_ca_system_score_codex":0.00050000014,"about_ca_system_score_gemma":0.0032608567,"threshold_uncertainty_score":0.99922264},"labels":[],"label_agreement":null},{"id":"W4353055688","doi":"10.3138/cjpe.75457","title":"Bridging Evaluation Theory and Practice: The Contributions of John Mayne to Canadian Federal Evaluation","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Bridging (networking); Thematic analysis; Function (biology); Government (linguistics); Conceptual framework; Sociology; Qualitative research; Computer science; Social science; Philosophy","score_opus":0.3228660608706075,"score_gpt":0.5747000820470364,"score_spread":0.2518340211764289,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055688","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87996596,0.0019778193,0.003365531,0.09280909,0.0025876372,0.008613405,0.00012582056,0.000028886183,0.010525852],"genre_scores_gemma":[0.99781984,0.000025171103,0.0005740177,0.0008621635,0.00024161045,0.00027934747,0.000070474525,0.000014286463,0.00011311616],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9868277,0.005697487,0.0013462972,0.00032646616,0.0052808058,0.0005212678],"domain_scores_gemma":[0.97947073,0.0020775006,0.0009793128,0.00044086904,0.016184555,0.0008470409],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.16893819,0.00017143167,0.00029573176,0.0017312695,0.00084787083,0.00067647535,0.00048194148,0.0001130932,0.0019278515],"category_scores_gemma":[0.07724181,0.0001257896,0.000121177254,0.0024590986,0.00016215212,0.0010140538,0.000026656066,0.00026779991,0.00011875319],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060651288,0.000020962736,0.0027572077,0.0000039839415,0.000073058975,0.0000030462813,0.0034749617,0.02000812,0.00021261157,0.002833807,0.016165065,0.95438653],"study_design_scores_gemma":[0.0027390907,0.000775858,0.27729595,0.00014959893,0.000908626,0.00016873398,0.016695004,0.6002636,0.00028990788,0.04142255,0.058935553,0.00035554077],"about_ca_topic_score_codex":0.016771773,"about_ca_topic_score_gemma":0.29755536,"teacher_disagreement_score":0.954031,"about_ca_system_score_codex":0.0013372877,"about_ca_system_score_gemma":0.02151677,"threshold_uncertainty_score":0.9989845},"labels":[],"label_agreement":null},{"id":"W4353055711","doi":"10.3138/cjpe.75429","title":"Enduring Themes in John Mayne’s Work: Implications for Evaluation Practice","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Sophistication; Checklist; Work (physics); Elaboration; Accountability; Field (mathematics); Causality (physics); Sociology; Psychology; Engineering ethics; Political science; Social science; Engineering; Cognitive psychology","score_opus":0.5854453128611484,"score_gpt":0.6102911840352087,"score_spread":0.02484587117406023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055711","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88561356,0.001573196,0.0032382314,0.083452865,0.0029347253,0.009873807,0.000040279447,0.00006606989,0.013207276],"genre_scores_gemma":[0.9942446,0.000030256719,0.0041701095,0.00023024288,0.0002179809,0.00084547733,0.00005180038,0.000015223684,0.00019432868],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9952069,0.0008258319,0.0011972279,0.00027650656,0.0020934085,0.00040013422],"domain_scores_gemma":[0.9911466,0.0014283418,0.0008885919,0.00036293326,0.005868492,0.00030500357],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.044765096,0.00012662027,0.00022409689,0.001628307,0.0002815622,0.00045052226,0.0004895403,0.000093550945,0.00068472145],"category_scores_gemma":[0.021236487,0.00010741412,0.00013405657,0.0027659356,0.000052232037,0.0012248317,0.000015985763,0.00018878185,0.00011503267],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031113592,0.000040542698,0.028187193,0.00000414862,0.000022843426,0.0000011725665,0.0015609208,0.016917948,0.00004756416,0.0011210503,0.00817898,0.9438865],"study_design_scores_gemma":[0.0026729566,0.0003038603,0.6936453,0.00009154642,0.00018870943,0.000027426824,0.0046955124,0.10970281,0.00006152578,0.039484233,0.14890315,0.00022294786],"about_ca_topic_score_codex":0.00018476204,"about_ca_topic_score_gemma":0.009194592,"teacher_disagreement_score":0.9436636,"about_ca_system_score_codex":0.0007706328,"about_ca_system_score_gemma":0.0061575915,"threshold_uncertainty_score":0.99947655},"labels":[],"label_agreement":null},{"id":"W4360842424","doi":"10.5206/cie-eci.v51i2.14370","title":"Correspondance entre des caractéristiques sociodémographiques de professeur·e·s universitaires canadiens sur la collaboration et la coécriture de publications avec des collègues internationaux","year":2023,"lang":"fr","type":"article","venue":"Comparative and International Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Toronto; Université de Montréal","funders":"","keywords":"Humanities; Political science; Art","score_opus":0.1629600782766062,"score_gpt":0.5180188671478668,"score_spread":0.35505878887126063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4360842424","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91700053,0.0028714961,0.0022716187,0.035336632,0.00148989,0.00044615616,0.00034493618,0.00011056946,0.040128186],"genre_scores_gemma":[0.85288393,0.0046225637,0.0018437485,0.00062730786,0.00019602498,0.00013900339,0.0005042415,0.000015122332,0.13916807],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99666494,0.001417585,0.00050117145,0.0004649259,0.00061686814,0.00033452932],"domain_scores_gemma":[0.9929333,0.0020526526,0.00038665757,0.00021147075,0.0041787187,0.00023724561],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0025360503,0.0002541827,0.00025280815,0.0008309477,0.0005782724,0.0010795373,0.0004976032,0.00018750255,0.0006269724],"category_scores_gemma":[0.0017587891,0.00026327983,0.00008589341,0.0013989396,0.0008672649,0.0026886603,0.00011899114,0.0003250389,0.00007126678],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000118118995,0.0005526246,0.258677,0.00006755823,0.0001908829,0.000005522773,0.13514182,0.00085645256,0.00037184422,0.2177767,0.34158543,0.044656042],"study_design_scores_gemma":[0.0003692582,0.000086332584,0.4882267,0.00031187225,0.000043810436,0.00003976434,0.044277355,0.027347974,0.00026976177,0.040890306,0.3978814,0.0002554727],"about_ca_topic_score_codex":0.0017312896,"about_ca_topic_score_gemma":0.015361503,"teacher_disagreement_score":0.2295497,"about_ca_system_score_codex":0.0009940533,"about_ca_system_score_gemma":0.006113101,"threshold_uncertainty_score":0.99998194},"labels":[],"label_agreement":null},{"id":"W4362503601","doi":"10.56645/jmde.v18i42.721","title":"Competitive champions versus cooperative advocates","year":2022,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Advancing Health Outcomes","funders":"","keywords":"Interview; Nonprobability sampling; Enthusiasm; Public relations; Extant taxon; Data collection; Sociology; Psychology; Knowledge management; Social psychology; Political science; Social science; Computer science","score_opus":0.2869313256836769,"score_gpt":0.5289861200793462,"score_spread":0.2420547943956693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362503601","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9710362,0.0004134076,0.0012521454,0.008196087,0.0039056032,0.00055841747,0.000034675464,0.00001261296,0.014590878],"genre_scores_gemma":[0.9979879,0.000028331962,0.0010046555,0.00007594457,0.00022706685,0.000051021965,0.000025977644,0.000009452207,0.0005896095],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99126565,0.0018549076,0.0011412522,0.00024710203,0.005313955,0.00017713121],"domain_scores_gemma":[0.9936605,0.0017761617,0.0012352099,0.00029534654,0.0029200113,0.00011274487],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.019955589,0.00013504164,0.00029997382,0.0005233706,0.0008899349,0.00010354823,0.0005844239,0.0000312115,0.009895207],"category_scores_gemma":[0.0021730533,0.000101375495,0.00018268873,0.0008998308,0.00007742024,0.00078257103,0.0003049395,0.00039781115,0.0001272857],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0042171753,0.0016309915,0.013382383,0.000006884534,0.00028431547,0.0000360195,0.040511973,0.7991644,0.0060691275,0.016854702,0.016333938,0.10150809],"study_design_scores_gemma":[0.014273812,0.006804482,0.1786221,0.000044581087,0.0002770003,0.00017980079,0.16448338,0.57801706,0.001802838,0.013945556,0.041016795,0.0005326016],"about_ca_topic_score_codex":0.0000027976998,"about_ca_topic_score_gemma":0.000030071264,"teacher_disagreement_score":0.22114736,"about_ca_system_score_codex":0.00051113527,"about_ca_system_score_gemma":0.0012950251,"threshold_uncertainty_score":0.9910099},"labels":[],"label_agreement":null},{"id":"W4362503613","doi":"10.56645/jmde.v18i42.711","title":"Empowerment Evaluation of Programs Involving Youth","year":2022,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; University of Winnipeg","funders":"","keywords":"Empowerment; Participatory evaluation; Program evaluation; Youth empowerment; Citizen journalism; Psychology; Participatory action research; Intervention (counseling); Positive Youth Development; Set (abstract data type); Medical education; Applied psychology; Sociology; Computer science; Political science; Medicine; Social science; Developmental psychology","score_opus":0.39650484374405937,"score_gpt":0.526744258074393,"score_spread":0.1302394143303336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362503613","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99378353,0.000773647,0.0005276538,0.00084155577,0.0015732676,0.0009886493,0.000011918129,0.0000075762205,0.0014922076],"genre_scores_gemma":[0.99828947,0.000020852543,0.001275581,0.000027207743,0.0001494126,0.0000740598,0.000041547533,0.0000127032645,0.000109175104],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97514635,0.0037042464,0.0023683913,0.0003218361,0.018233227,0.00022593202],"domain_scores_gemma":[0.9894966,0.00038802737,0.0031301172,0.00047837663,0.006398164,0.00010873606],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.10131924,0.0001582994,0.0003915739,0.0007876208,0.0004493439,0.000088386114,0.00071529904,0.000047241287,0.0038870394],"category_scores_gemma":[0.0021979162,0.00012233981,0.0002765446,0.0011261263,0.00006567212,0.0008668402,0.0003327267,0.0003268559,0.000017943998],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005280332,0.0015719543,0.096870266,0.000015420088,0.00012219006,0.000002854831,0.04659998,0.44026068,0.0048614973,0.00020987079,0.00086917495,0.40808806],"study_design_scores_gemma":[0.0042999336,0.0018352941,0.16526648,0.00006335345,0.0005017038,0.000040033745,0.07099652,0.74232435,0.0006566264,0.013475291,0.00033912784,0.00020125664],"about_ca_topic_score_codex":0.0000072806356,"about_ca_topic_score_gemma":0.000016669794,"teacher_disagreement_score":0.4078868,"about_ca_system_score_codex":0.00087455765,"about_ca_system_score_gemma":0.0020811493,"threshold_uncertainty_score":0.9970235},"labels":[],"label_agreement":null},{"id":"W4362504882","doi":"10.56645/jmde.v3i5.54","title":"Collaborative Evaluation","year":2006,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Psychology","score_opus":0.14730919225055178,"score_gpt":0.5253125317131393,"score_spread":0.3780033394625875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362504882","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9748165,0.00078670494,0.004213102,0.003441431,0.0015172232,0.0007939289,0.000009881122,0.000010581687,0.0144106485],"genre_scores_gemma":[0.9947186,0.000020512321,0.0040534763,0.000037516947,0.0006436118,0.000031475887,0.000030766772,0.000010845931,0.00045319134],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9861593,0.0019169484,0.0019087093,0.0002860645,0.009528342,0.0002006361],"domain_scores_gemma":[0.9838074,0.00086416793,0.0021487952,0.00038257072,0.012706706,0.00009034848],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.050346162,0.00016773789,0.0003466404,0.0006963146,0.00028478322,0.00022288364,0.00045942658,0.000095017,0.003099008],"category_scores_gemma":[0.0032558606,0.00011708064,0.0001845056,0.0013098383,0.000073304305,0.0015584317,0.00006950708,0.00020440893,0.00020232965],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00059586135,0.0009724667,0.09187198,0.000009473781,0.00009194232,0.0000099545405,0.0044530164,0.48171347,0.011499148,0.0021916085,0.042911854,0.36367923],"study_design_scores_gemma":[0.0028174652,0.000371452,0.43439582,0.00003401565,0.00017842236,0.000032848708,0.003101407,0.4888171,0.0014434598,0.06587128,0.0027742062,0.00016251742],"about_ca_topic_score_codex":0.000008795309,"about_ca_topic_score_gemma":0.00009838622,"teacher_disagreement_score":0.3635167,"about_ca_system_score_codex":0.0005028403,"about_ca_system_score_gemma":0.0019577865,"threshold_uncertainty_score":0.9978123},"labels":[],"label_agreement":null},{"id":"W4362504947","doi":"10.56645/jmde.v3i4.83","title":"American Evaluation Association","year":2006,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Association (psychology); Psychology; Psychotherapist","score_opus":0.16413093304957194,"score_gpt":0.5246990005505626,"score_spread":0.3605680675009907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362504947","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98136115,0.00022863332,0.003196411,0.0051011024,0.0013491809,0.00052379136,0.0000049289947,0.0000131064635,0.008221703],"genre_scores_gemma":[0.9952995,0.000019324525,0.002866098,0.00005681981,0.0008128215,0.000024620927,0.000024965873,0.000012241907,0.0008836084],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9835074,0.0020900518,0.0019788647,0.00029298855,0.011877532,0.00025315574],"domain_scores_gemma":[0.98515934,0.0012795589,0.004204542,0.00036813618,0.008896633,0.00009180347],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.066769734,0.0001657123,0.000396558,0.00071319315,0.00025795688,0.00023585696,0.00044741778,0.000083482286,0.001732419],"category_scores_gemma":[0.005915922,0.00012271844,0.000252252,0.0011895497,0.000054649827,0.0013578676,0.00006503518,0.00024917352,0.00025531513],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002062987,0.00051003974,0.40755993,0.0000040589957,0.00006624311,0.0000026836988,0.0011819277,0.16504379,0.0050277035,0.00035176397,0.023917213,0.39612836],"study_design_scores_gemma":[0.0015656418,0.0002873642,0.63077784,0.000017159771,0.00016942392,0.000013170086,0.0010981803,0.34245884,0.00050572044,0.020980109,0.0020020287,0.00012455412],"about_ca_topic_score_codex":0.00003373453,"about_ca_topic_score_gemma":0.00016762369,"teacher_disagreement_score":0.3960038,"about_ca_system_score_codex":0.0015328007,"about_ca_system_score_gemma":0.0011451944,"threshold_uncertainty_score":0.99918014},"labels":[],"label_agreement":null},{"id":"W4362633354","doi":"10.30770/2572-1852-109.1.3","title":"From the Editor","year":2023,"lang":"en","type":"article","venue":"Journal of Medical Regulation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.2099891392803344,"score_gpt":0.5388659843097385,"score_spread":0.3288768450294041,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362633354","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67547137,0.00009192415,0.01657592,0.29003412,0.016661333,0.00007336411,0.000002838523,0.000017287515,0.0010718352],"genre_scores_gemma":[0.9789784,0.00006393012,0.00016572156,0.0008603153,0.019000947,8.204401e-7,0.0000033947777,0.0000029997552,0.00092344766],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99222386,0.00021039642,0.0005952431,0.000066162764,0.006830561,0.00007378513],"domain_scores_gemma":[0.9963636,0.0026077242,0.00037909602,0.00016249096,0.0003806771,0.00010641525],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.013888214,0.0000355819,0.000103529914,0.00009497182,0.00007593752,0.000092480615,0.0005400397,0.00006495454,0.006192244],"category_scores_gemma":[0.00929523,0.000015887357,0.00007431546,0.00053602335,0.0000443681,0.00024051948,0.000043929296,0.00016926801,0.0005643674],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012869027,0.000008543088,0.00331745,2.6810523e-7,0.000007069513,0.0000024961278,0.00048495538,0.00033090322,0.000058905396,0.00073026004,0.85221994,0.14282635],"study_design_scores_gemma":[0.0003767065,0.000040769482,0.37667987,0.000033152206,0.0000071686695,0.000005503913,0.0009229216,0.059745632,0.000050707833,0.06629692,0.4958122,0.000028436338],"about_ca_topic_score_codex":0.000007080429,"about_ca_topic_score_gemma":0.000009786508,"teacher_disagreement_score":0.37336242,"about_ca_system_score_codex":0.000022983117,"about_ca_system_score_gemma":0.00029547513,"threshold_uncertainty_score":0.9990499},"labels":[],"label_agreement":null},{"id":"W4362681378","doi":"10.3138/cjpe.18.001","title":"Evaluation and Research: Differences and Similarities","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Generalization; Similarity (geometry); Relevance (law); Causality (physics); Psychology; Management science; Computer science; Knowledge management; Epistemology; Artificial intelligence; Political science","score_opus":0.7713106731453503,"score_gpt":0.617815743068949,"score_spread":0.15349493007640125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362681378","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9844016,0.00381466,0.00014528737,0.0020574243,0.00042547498,0.0010164215,0.0000030095123,0.0000038579474,0.008132269],"genre_scores_gemma":[0.99806005,0.00008386681,0.0015337277,0.00007177858,0.00006955137,0.000060993905,0.0000016297314,0.000005473414,0.00011294165],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9910994,0.0030733766,0.0006434766,0.0002176959,0.004689834,0.0002762164],"domain_scores_gemma":[0.9909535,0.00068525743,0.00030426294,0.00018408304,0.007424066,0.00044883115],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08505214,0.0000954722,0.00018930787,0.0009065759,0.00043490867,0.0008093224,0.00019029075,0.00007599516,0.0016136573],"category_scores_gemma":[0.017424863,0.00007102668,0.00003748609,0.0006272737,0.00029546625,0.00068457256,0.000010928867,0.00024829633,0.0000116165675],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000053831495,0.000018394889,0.07548368,0.0000039467272,0.000019205441,0.0000015763649,0.0021206224,0.00008591494,0.00001783085,0.0035500245,0.0010547277,0.9176387],"study_design_scores_gemma":[0.0016731175,0.0010282922,0.57746077,0.00008341578,0.00017597666,0.00011013792,0.012340396,0.071233734,0.000094366194,0.28318226,0.052406553,0.00021099592],"about_ca_topic_score_codex":0.00025552302,"about_ca_topic_score_gemma":0.011736539,"teacher_disagreement_score":0.9174277,"about_ca_system_score_codex":0.00023385437,"about_ca_system_score_gemma":0.0052477377,"threshold_uncertainty_score":0.999299},"labels":[],"label_agreement":null},{"id":"W4362683297","doi":"10.3138/cjpe.18.006","title":"Creating Logic Models Using Grounded Theory: A Case Example Demonstrating a Unique Approach to Logic Model Development","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Saskatchewan Health; University of Regina; York University","funders":"","keywords":"Grounded theory; Logic model; Parallels; Computer science; Process (computing); Context (archaeology); Theory; Management science; Sociology; Qualitative research; Engineering; Programming language","score_opus":0.7082610594770602,"score_gpt":0.5253019207443822,"score_spread":0.182959138732678,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362683297","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30181333,0.00011602683,0.6816635,0.00008456192,0.00012226493,0.0011809538,0.0000025206975,0.000011317328,0.015005538],"genre_scores_gemma":[0.62965894,6.562184e-7,0.3699659,0.00021267709,0.000027787566,0.00006851188,0.0000041377953,0.000010630881,0.000050750394],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9945899,0.0014632939,0.00131956,0.0003645955,0.0017879684,0.00047468176],"domain_scores_gemma":[0.99522233,0.00031470222,0.0007872159,0.000308201,0.0026359165,0.0007316361],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.032538123,0.00021330996,0.000332524,0.0007966804,0.00076130405,0.00068918,0.00036075845,0.00011414633,0.000226161],"category_scores_gemma":[0.003184243,0.00016814722,0.000108490676,0.0010712212,0.00006584022,0.00088217686,0.000017745893,0.00026690259,0.0000082747265],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011039259,0.000065883105,0.00061164494,0.0000058819624,0.000027640706,0.00003148451,0.0060218954,0.75925046,0.000047336584,0.06421748,0.000036135716,0.16967314],"study_design_scores_gemma":[0.00042494407,0.00012811202,0.00015276916,0.000038643215,0.00005301087,0.0008545106,0.0058831605,0.8255775,0.00006713719,0.16645424,0.00018153041,0.0001844195],"about_ca_topic_score_codex":0.000646872,"about_ca_topic_score_gemma":0.00750663,"teacher_disagreement_score":0.3278456,"about_ca_system_score_codex":0.0010024618,"about_ca_system_score_gemma":0.0111301085,"threshold_uncertainty_score":0.99620557},"labels":[],"label_agreement":null},{"id":"W4362683298","doi":"10.3138/cjpe.18.005","title":"Theory-Driven Approach for Facilitation of Planning Health Promotion or Other Programs","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Plan (archaeology); Theory of change; Promotion (chess); Computer science; Process management; Management science; Chen; Development theory; Facilitation; Program Design Language; Program evaluation; Knowledge management; Business; Political science; Software engineering; Management; Engineering; Economic growth; Economics","score_opus":0.6171863065840855,"score_gpt":0.5681104673795182,"score_spread":0.04907583920456726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362683298","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2739828,0.00093733193,0.7072621,0.0015223895,0.0010555977,0.010287403,0.00004612441,0.00002667373,0.0048795748],"genre_scores_gemma":[0.9244789,0.0000021980588,0.07481214,0.00007280456,0.00006228559,0.00024997938,0.00003701311,0.000012316959,0.00027236465],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955315,0.0012374566,0.0011805331,0.00021195936,0.0015475574,0.00029097765],"domain_scores_gemma":[0.99514776,0.00026377055,0.0013065953,0.00021795776,0.0027465175,0.00031736938],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026848048,0.00012178065,0.00030138882,0.0005609995,0.00020615573,0.00018011787,0.00026375864,0.000076729964,0.00051602634],"category_scores_gemma":[0.003919819,0.00008395931,0.00013801038,0.00069534546,0.0000956927,0.00049093796,0.000003270157,0.00012121721,0.0000050695667],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007747474,0.00020237862,0.013548168,0.00004203663,0.000042346946,3.379833e-7,0.0054621943,0.013586673,0.000023324137,0.0058019822,0.00061728247,0.9605958],"study_design_scores_gemma":[0.009235308,0.020836566,0.02638343,0.0005898032,0.0003240769,0.00013893595,0.037180733,0.6533473,0.00065769104,0.11861812,0.13191381,0.0007742297],"about_ca_topic_score_codex":0.00007410995,"about_ca_topic_score_gemma":0.0012749764,"teacher_disagreement_score":0.9598216,"about_ca_system_score_codex":0.00031816805,"about_ca_system_score_gemma":0.0059718234,"threshold_uncertainty_score":0.9996634},"labels":[],"label_agreement":null},{"id":"W4362683301","doi":"10.3138/cjpe.18.002","title":"The Language of Evaluation Theory: Insights Gained from an Empirical Study of Evaluation Theory and Practice","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Terminology; Ambiguity; Confusion; Epistemology; Field (mathematics); Vernacular; Empirical research; Psychology; Linguistics; Sociology; Computer science; Philosophy","score_opus":0.28713025319252194,"score_gpt":0.573348207363572,"score_spread":0.28621795417105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362683301","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99082917,0.002529248,0.0006522984,0.00064329896,0.00050752814,0.0027933298,0.0000063550738,0.000004693772,0.002034072],"genre_scores_gemma":[0.99867654,0.000018277988,0.000896304,0.00012345577,0.00010621905,0.000116894225,0.000019598985,0.000012766227,0.000029933095],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.96107405,0.029510027,0.0019053805,0.0003949662,0.006831573,0.0002839711],"domain_scores_gemma":[0.9824272,0.0054181195,0.0020024588,0.00060945103,0.009228049,0.0003147326],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14912175,0.00017197564,0.00034845047,0.0005437812,0.0003601666,0.0002875756,0.00034234495,0.000105205385,0.0011111647],"category_scores_gemma":[0.058101732,0.00010999613,0.000088328656,0.00088903145,0.00020951922,0.001153712,0.000015920818,0.00023668857,0.0000067504807],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004898968,0.0005716317,0.014977594,0.0000042381134,0.00021140769,0.0000038678136,0.06494115,0.0036191726,0.00034135638,0.0035388607,0.00032152343,0.9109793],"study_design_scores_gemma":[0.007901782,0.0051505384,0.2847515,0.00008693657,0.0023592599,0.00006159814,0.31856167,0.14750025,0.00068157626,0.22762607,0.004966112,0.0003527231],"about_ca_topic_score_codex":0.0005401118,"about_ca_topic_score_gemma":0.015662538,"teacher_disagreement_score":0.9106266,"about_ca_system_score_codex":0.0003327773,"about_ca_system_score_gemma":0.0058983997,"threshold_uncertainty_score":0.99980193},"labels":[],"label_agreement":null},{"id":"W4362683309","doi":"10.3138/cjpe.18.004","title":"User-Friendly Evaluation in Community-Based Projects","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Perspective (graphical); User Friendly; Evaluation methods; Program evaluation; Process management; User group; Computer science; Psychology; Knowledge management; Management science; Business; Political science; Multimedia; Engineering","score_opus":0.4381303297538949,"score_gpt":0.5384420399654519,"score_spread":0.10031171021155705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362683309","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9795924,0.0004311537,0.0017802537,0.0012256767,0.001111118,0.002829241,0.0000052464497,0.000010656135,0.013014254],"genre_scores_gemma":[0.9932124,0.0000023417424,0.006118928,0.00031352916,0.000049832037,0.00018431534,0.000023800623,0.000012030699,0.000082811755],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9876653,0.006523764,0.0013058477,0.00020187613,0.0039306204,0.00037259702],"domain_scores_gemma":[0.9926142,0.00056501303,0.0008216046,0.0005032487,0.0051001883,0.00039575036],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.080191724,0.000156272,0.00028376767,0.0015911781,0.000338777,0.00043058998,0.00055975735,0.0001143518,0.0025135258],"category_scores_gemma":[0.012645561,0.00012914008,0.0001235947,0.0018361423,0.000098672346,0.0008162135,0.000007129977,0.00053990004,0.00007816242],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041374737,0.00034127824,0.18425815,0.000018455381,0.000027384816,0.000009138679,0.003447199,0.045194414,0.000083566694,0.001726729,0.0063309846,0.7585213],"study_design_scores_gemma":[0.009504683,0.0029088908,0.29900858,0.00029958625,0.00026144358,0.00007841825,0.01220201,0.31170353,0.001010256,0.026072847,0.3363188,0.0006309707],"about_ca_topic_score_codex":0.001030756,"about_ca_topic_score_gemma":0.07812917,"teacher_disagreement_score":0.75789034,"about_ca_system_score_codex":0.001077034,"about_ca_system_score_gemma":0.017883226,"threshold_uncertainty_score":0.9983983},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W4362688871","doi":"10.3138/cjpe.015.001","title":"Answering the <i>Why</i> Question in Evaluation: The Causal-Model Approach","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Casual; Terminology; Causal model; Outcome (game theory); Test (biology); Intervention (counseling); Contrast (vision); Computer science; Psychology; Management science; Artificial intelligence; Economics; Political science; Linguistics; Medicine; Microeconomics","score_opus":0.38287591332918275,"score_gpt":0.5196684715095707,"score_spread":0.136792558180388,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362688871","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.906102,0.0025357064,0.006609394,0.02818028,0.0011475924,0.0055377213,0.000008982188,0.00002108655,0.049857225],"genre_scores_gemma":[0.9968178,0.000030855164,0.0014897139,0.00087939616,0.00021766034,0.00024814764,0.0000116185665,0.000010404752,0.0002943481],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9927259,0.0019036739,0.001070485,0.00023899598,0.0037383107,0.0003226342],"domain_scores_gemma":[0.9963578,0.00029864506,0.00047141113,0.0004943398,0.002158007,0.00021978957],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.055985577,0.00014307412,0.00019689578,0.00036936963,0.00043829705,0.00061008986,0.0007941889,0.00008256025,0.0028639208],"category_scores_gemma":[0.0017450028,0.00007757838,0.000116386705,0.0012524283,0.00015370749,0.00077631744,0.000009864898,0.00039245005,0.00006454406],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010162721,0.000025899697,0.0033982128,0.0000012228181,0.000008603717,7.460006e-7,0.0018037264,0.33691776,0.0000062827453,0.0004205022,0.0026007437,0.65480614],"study_design_scores_gemma":[0.00067431823,0.00010631445,0.038360965,0.000028688277,0.00007482855,0.000036540525,0.0011534067,0.9199799,0.000011081626,0.012149879,0.027322758,0.0001013732],"about_ca_topic_score_codex":0.0008463787,"about_ca_topic_score_gemma":0.028681673,"teacher_disagreement_score":0.65470475,"about_ca_system_score_codex":0.0005451822,"about_ca_system_score_gemma":0.0051731127,"threshold_uncertainty_score":0.9980476},"labels":[],"label_agreement":null},{"id":"W4362688961","doi":"10.3138/cjpe.015.002","title":"Towards Sustainability of Human Services: Assessing Community Self-Determination and Self-Reliance","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sustainability; Negotiation; Dependency (UML); Process (computing); Accountability; Process management; Relevance (law); Knowledge management; Human resources; Environmental resource management; Business; Psychology; Computer science; Political science; Ecology; Economics","score_opus":0.21373330538929033,"score_gpt":0.5275247607142796,"score_spread":0.3137914553249892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362688961","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9955047,0.00018897082,0.00009034753,0.00064046605,0.00013342645,0.0007077557,0.0000037996895,0.00002146449,0.0027090719],"genre_scores_gemma":[0.9947963,0.000019205252,0.004966537,0.00007627901,0.000057295016,0.00002248732,0.000009205914,0.000007662326,0.00004506275],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99528587,0.0016323125,0.0010582114,0.00016017698,0.0016352248,0.00022819801],"domain_scores_gemma":[0.993378,0.00022100205,0.00080801186,0.00037687164,0.004901634,0.00031451715],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.021769814,0.0001270793,0.00028134466,0.00045447185,0.000532294,0.0004734396,0.00047158342,0.00009518245,0.0010439781],"category_scores_gemma":[0.0007016078,0.00010610817,0.00008533845,0.0007080653,0.00011327541,0.0013891844,0.000015868452,0.00030555,0.000006088695],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000069345615,0.00017228718,0.04694076,0.00007873279,0.000019895817,0.0000018541263,0.007855395,0.0005829181,0.0000252687,0.0000747511,0.00006976557,0.9441714],"study_design_scores_gemma":[0.0012197276,0.0009657405,0.77202207,0.00014702736,0.00016472409,0.000038212496,0.008438433,0.18621986,0.00014238062,0.022892667,0.0075490237,0.00020014787],"about_ca_topic_score_codex":0.002617416,"about_ca_topic_score_gemma":0.014656929,"teacher_disagreement_score":0.9439713,"about_ca_system_score_codex":0.00060681056,"about_ca_system_score_gemma":0.004048246,"threshold_uncertainty_score":0.9998692},"labels":[],"label_agreement":null},{"id":"W4362689123","doi":"10.3138/cjpe.015.005","title":"The Redesign of Advanced Patrol Training for Police Constables in Ontario: Making Use of Evaluation to Maximize Organizational Effectiveness and Efficiency","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Nipissing University","funders":"","keywords":"Training (meteorology); Curriculum; Operations management; Business; Medical education; Engineering management; Psychology; Engineering; Medicine; Pedagogy","score_opus":0.31680565738729644,"score_gpt":0.48073747035389924,"score_spread":0.1639318129666028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362689123","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99300396,0.00012520044,0.0037145182,0.00027753168,0.00017102533,0.0024288425,0.000011003679,0.0000019185125,0.00026602065],"genre_scores_gemma":[0.99198645,0.000005172301,0.0077991593,0.00003988863,0.000019298292,0.000114979244,0.0000059578188,0.000007468163,0.000021612987],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99628586,0.0008294433,0.00097507157,0.00017601116,0.0015035659,0.00023006475],"domain_scores_gemma":[0.99387634,0.0017704676,0.00060130196,0.00016621906,0.0034543118,0.00013138301],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022331176,0.000098894765,0.00026175077,0.00046052574,0.0002064184,0.00016540936,0.000196065,0.000051594256,0.0004931854],"category_scores_gemma":[0.004553163,0.00007318303,0.000057383626,0.000783266,0.00010143036,0.00054651557,0.000006838059,0.000096938435,0.0000011045432],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022216265,0.000029199276,0.03297231,0.0000072066055,0.000016783972,2.2229499e-7,0.0057278415,0.090294905,0.0003624554,0.00040312335,0.000026886923,0.8699369],"study_design_scores_gemma":[0.00394412,0.0012573169,0.80906373,0.00037126942,0.00014499672,0.000021049356,0.004784106,0.16701293,0.000534329,0.009233293,0.0034422132,0.00019067236],"about_ca_topic_score_codex":0.005986917,"about_ca_topic_score_gemma":0.33350575,"teacher_disagreement_score":0.8697462,"about_ca_system_score_codex":0.00048066917,"about_ca_system_score_gemma":0.0068638874,"threshold_uncertainty_score":0.99876624},"labels":[],"label_agreement":null},{"id":"W4362689223","doi":"10.3138/cjpe.015.008","title":"Focusing on Inputs, Outputs, and Outcomes: Are International Approaches to Performance Management Really so Different?","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Logic model; Process (computing); Service (business); Focus (optics); Key (lock); Performance measurement; Process management; Performance management; Business; Public relations; Knowledge management; Computer science; Political science; Public administration; Marketing; Computer security","score_opus":0.45225536612016,"score_gpt":0.4616739906963755,"score_spread":0.009418624576215506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362689223","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9738167,0.000079568184,0.00044482815,0.013404128,0.0006354857,0.000942429,0.000007574315,0.0000104063865,0.01065886],"genre_scores_gemma":[0.9952449,0.000043310127,0.0024801618,0.00095521315,0.00015077698,0.000062080544,0.000010306852,0.000011201316,0.0010420338],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9961743,0.00022621163,0.0007882351,0.00028594548,0.002253811,0.0002715188],"domain_scores_gemma":[0.99813396,0.000095475785,0.00040248453,0.00027931502,0.00061419606,0.00047459124],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005137632,0.00017081505,0.00025816515,0.00085177185,0.0002836425,0.00084743684,0.0004923974,0.000059467297,0.001605435],"category_scores_gemma":[0.0003240404,0.00012288042,0.000086238484,0.00038001256,0.0000689055,0.00057471247,0.000021484235,0.00018052352,0.00011408843],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034892808,0.000049524628,0.09814749,0.0000052499317,0.00004415366,0.0000043637683,0.00079351617,0.0022722369,0.0000017309324,0.00039764386,0.0007631455,0.89748603],"study_design_scores_gemma":[0.0010714835,0.00046925203,0.9030715,0.00014581757,0.000062072686,0.000020528758,0.0006967255,0.02006915,0.00004521054,0.0015044288,0.07265265,0.00019112925],"about_ca_topic_score_codex":0.00005889707,"about_ca_topic_score_gemma":0.002872105,"teacher_disagreement_score":0.89729494,"about_ca_system_score_codex":0.00040058402,"about_ca_system_score_gemma":0.00048797447,"threshold_uncertainty_score":0.9993072},"labels":[],"label_agreement":null},{"id":"W4362689327","doi":"10.3138/cjpe.16.001","title":"Using the Right Tools to Answer the Right Questions: The Importance of Evaluative Research Techniques for Health Services Evaluation Research in the 21st Century","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Rubric; Causal inference; Affect (linguistics); Accountability; Health care; Psychology; Causal model; Inference; Health policy; Health services research; Applied psychology; Public relations; Social psychology; Management science; Political science; Computer science; Medicine; Economics; Mathematics education; Econometrics","score_opus":0.6435564373162587,"score_gpt":0.6614983899363868,"score_spread":0.0179419526201281,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362689327","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6673424,0.014679478,0.0016839638,0.2576538,0.0018850473,0.04564247,0.00008708846,0.000020246403,0.011005496],"genre_scores_gemma":[0.9934181,0.00023138867,0.0021387085,0.0017882604,0.00052093837,0.0018239459,0.00001858901,0.000015935875,0.000044126446],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9695797,0.017033111,0.0018994437,0.00038677393,0.010301925,0.00079907366],"domain_scores_gemma":[0.97614807,0.004652134,0.0010318585,0.0010433125,0.016884169,0.00024043408],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.2995536,0.0001744248,0.00030055482,0.0011506716,0.0021329995,0.0010351166,0.002263509,0.00010440617,0.000532556],"category_scores_gemma":[0.006347903,0.00007342146,0.00015309884,0.0047508557,0.0005245109,0.00085591816,0.000057253812,0.0008740616,0.000011352426],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000120367265,0.00016515511,0.008165993,0.00002636781,0.00003808595,0.000001594023,0.027062943,0.0033206597,0.000048245114,0.010918362,0.00568143,0.9444508],"study_design_scores_gemma":[0.0012017466,0.002169,0.09937133,0.00092176395,0.00016365583,0.00011224467,0.14931108,0.1386855,0.00018859802,0.16225943,0.4453416,0.00027406687],"about_ca_topic_score_codex":0.0025920072,"about_ca_topic_score_gemma":0.12625095,"teacher_disagreement_score":0.94417673,"about_ca_system_score_codex":0.0014834844,"about_ca_system_score_gemma":0.016393794,"threshold_uncertainty_score":0.9991661},"labels":[],"label_agreement":null},{"id":"W4362689335","doi":"10.3138/cjpe.16.004","title":"Accountability, Rationality, and New Structures of Governance: Making Room for Political Rationality","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Accountability; Rationality; Agency (philosophy); Politics; Bureaucracy; Law and economics; Corporate governance; Technocracy; Parliament; Mandate; Political science; Sociology; Economics; Public relations; Public administration; Positive economics; Law; Social science; Finance","score_opus":0.518764035540208,"score_gpt":0.5838040393902938,"score_spread":0.06504000385008579,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362689335","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9587135,0.00075046043,0.017425885,0.018275108,0.0008805572,0.0018801435,0.000075839016,0.00000711474,0.001991415],"genre_scores_gemma":[0.99005574,0.0000061068536,0.009176132,0.00029610493,0.00033884545,0.000023163393,0.000017431232,0.0000057841676,0.000080692414],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99622977,0.00029233968,0.0010486916,0.00019855537,0.0019860158,0.00024465693],"domain_scores_gemma":[0.99484307,0.00051295763,0.0007537269,0.00020709138,0.0033144292,0.00036874964],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009857579,0.000105565596,0.00024902902,0.00019730497,0.00016745194,0.00029628226,0.00028831873,0.00007965692,0.0014891978],"category_scores_gemma":[0.0051947,0.00008441537,0.00011163592,0.0003666541,0.00009871594,0.00070448144,0.00001528975,0.00011485701,0.0000026391867],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000098642566,0.000048626145,0.290163,0.00001837983,0.000042580617,9.494343e-7,0.00061955,0.001679335,0.000059460916,0.14609443,0.0046635508,0.5565115],"study_design_scores_gemma":[0.0010180863,0.00023773861,0.59559566,0.000028350856,0.000060504022,0.00004140383,0.0005493758,0.018194448,0.00007139096,0.36096105,0.023145935,0.00009605137],"about_ca_topic_score_codex":0.0008202045,"about_ca_topic_score_gemma":0.020923853,"teacher_disagreement_score":0.55641544,"about_ca_system_score_codex":0.00035210367,"about_ca_system_score_gemma":0.0064886487,"threshold_uncertainty_score":0.99942356},"labels":[],"label_agreement":null},{"id":"W4362689338","doi":"10.3138/cjpe.015.006","title":"Contributions of Evaluation Research to the Development of Community Policing in a Canadian City","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Windsor; Service (business); Community service; Population; Sociology; Political science; Business; Demography; Public relations; Marketing","score_opus":0.6536296981549493,"score_gpt":0.636219151212957,"score_spread":0.01741054694199229,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362689338","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.988159,0.00010697722,0.00010066715,0.005388503,0.00014564348,0.001745166,0.000023157094,0.000001445147,0.0043294528],"genre_scores_gemma":[0.99864787,0.000002943628,0.0010105851,0.00011459867,0.000048698195,0.00010490252,0.000016963759,0.0000049387218,0.00004849549],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.989585,0.0044071106,0.0015901558,0.000118819,0.0038173643,0.00048156016],"domain_scores_gemma":[0.9885776,0.00068961625,0.0004167686,0.0004337726,0.009257699,0.0006245098],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1334795,0.00009090618,0.0002555288,0.0018229575,0.000640917,0.00012314023,0.00068127975,0.000079326346,0.0033177678],"category_scores_gemma":[0.009964478,0.00006673517,0.00007037597,0.0026962669,0.00014311478,0.00029361848,0.000016536,0.0005015467,0.00003748664],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002111918,0.000061865285,0.033197436,0.0000037597504,0.000018401422,4.2022145e-7,0.02147956,0.012250973,0.00007444043,0.00019558136,0.0011731385,0.9315233],"study_design_scores_gemma":[0.0010089594,0.00039111316,0.9188525,0.00014264627,0.00003966269,0.000009025708,0.0074231825,0.031827457,0.00080336374,0.0051801926,0.03421356,0.000108327324],"about_ca_topic_score_codex":0.44661522,"about_ca_topic_score_gemma":0.9896937,"teacher_disagreement_score":0.93141496,"about_ca_system_score_codex":0.002256378,"about_ca_system_score_gemma":0.035862356,"threshold_uncertainty_score":0.998375},"labels":[],"label_agreement":null},{"id":"W4363676449","doi":"10.21203/rs.3.rs-2564918/v1","title":"The use of evidence to guide decision-making during the COVID-19 pandemic: Divergent perspectives from a qualitative case study in British Columbia, Canada","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia; University of Waterloo","funders":"Canadian Institutes of Health Research; University of British Columbia","keywords":"Pandemic; Coronavirus disease 2019 (COVID-19); 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Geography; History; Virology; Biology; Medicine; Infectious disease (medical specialty)","score_opus":0.7879678719046316,"score_gpt":0.6658567601695009,"score_spread":0.12211111173513067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4363676449","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9916443,0.0007354908,0.00033811573,0.0027773182,0.0003974788,0.0034215692,0.00065117725,0.000023394576,0.000011110672],"genre_scores_gemma":[0.99575657,0.0007093064,0.00027738346,0.00012066873,0.00008295164,0.0007493702,0.0000038824537,0.000023174583,0.002276673],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.97623086,0.009930036,0.0016836565,0.0013828521,0.010078521,0.0006940969],"domain_scores_gemma":[0.8886569,0.105627656,0.00042293785,0.0017948018,0.0031752756,0.00032240056],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.043498013,0.00019406072,0.0005276697,0.00037351775,0.0018211569,0.0029238893,0.002375352,0.00011269754,0.00072821963],"category_scores_gemma":[0.1705955,0.00014665256,0.00015131765,0.0023019693,0.00031805248,0.0003099729,0.0048262184,0.0013208833,0.000030270408],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00010239169,0.00010055205,0.7956855,0.00004000378,0.0000774215,0.0015473111,0.14966524,0.021024404,0.000003089264,0.000003915575,0.020513088,0.011237027],"study_design_scores_gemma":[0.00022841281,0.000089572924,0.40943065,0.0007581988,0.0000071430063,0.000026797661,0.5826227,0.001587347,2.8518167e-7,0.0020571204,0.0030419424,0.00014984059],"about_ca_topic_score_codex":0.99404037,"about_ca_topic_score_gemma":0.99981487,"teacher_disagreement_score":0.43295744,"about_ca_system_score_codex":0.0039059988,"about_ca_system_score_gemma":0.009962166,"threshold_uncertainty_score":0.9999178},"labels":[],"label_agreement":null},{"id":"W4366382532","doi":"10.3138/cjpe.31132","title":"Moving Beyond the Buzzword: A Framework for Teaching Culturally Responsive Approaches to Evaluation","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Conceptual framework; Competence (human resources); Cultural competence; Sociology; Domain (mathematical analysis); Knowledge management; Computer science; Engineering ethics; Psychology; Pedagogy; Social psychology; Social science; Engineering","score_opus":0.6407724104552023,"score_gpt":0.5597165071488638,"score_spread":0.0810559033063385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366382532","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7964171,0.0006996965,0.06172205,0.11679335,0.0039230823,0.010497101,0.000029389254,0.00001937502,0.009898834],"genre_scores_gemma":[0.9442305,0.0000020867046,0.053669736,0.0006807805,0.00062992965,0.0005111801,0.000010829728,0.000014514366,0.00025042123],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99375,0.0012998708,0.0009640276,0.00032071312,0.0032831854,0.00038220125],"domain_scores_gemma":[0.9916731,0.001200062,0.0015481611,0.00085052446,0.0042589023,0.0004692256],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06413532,0.00017211442,0.00027153068,0.00047589108,0.0025056505,0.002436947,0.0014618158,0.000120825745,0.00044665832],"category_scores_gemma":[0.05975384,0.00010669613,0.00021011101,0.00027187346,0.00015377066,0.0012010831,0.000033656175,0.00042033644,0.000043056185],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000063470805,0.000021310096,0.0030200302,0.0000031741024,0.00004120647,8.601991e-7,0.0076990915,0.0064308494,0.000034300905,0.012181978,0.0043913624,0.9661124],"study_design_scores_gemma":[0.0017336969,0.001117979,0.1500711,0.0002102308,0.0004454044,0.000045278404,0.01645248,0.3153688,0.00016640026,0.42197177,0.092011586,0.00040529348],"about_ca_topic_score_codex":0.00029378763,"about_ca_topic_score_gemma":0.012848757,"teacher_disagreement_score":0.96570706,"about_ca_system_score_codex":0.00061139866,"about_ca_system_score_gemma":0.005132222,"threshold_uncertainty_score":0.99879295},"labels":[],"label_agreement":null},{"id":"W4366383480","doi":"10.3138/cjpe.20.008","title":"Certification, Credentialing, Licensure, Competencies, and the Like: Issues Confronting the Field of Evaluation","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Credentialing; Accreditation; Licensure; Certification; Competence (human resources); Engineering ethics; Medical education; Professional certification (computer technology); Framing (construction); Certification and Accreditation; Professional association; Psychology; Political science; Medicine; Public relations; Engineering; Law; Social psychology","score_opus":0.2723915791832564,"score_gpt":0.5250140899096121,"score_spread":0.25262251072635566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366383480","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8244046,0.021209618,0.0029290023,0.13813572,0.0021279568,0.004691288,0.000009240871,0.000015408616,0.006477189],"genre_scores_gemma":[0.9967683,0.000082372215,0.001855139,0.000705869,0.00030977477,0.00005960799,0.000006462632,0.000005838889,0.00020661255],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.994516,0.0013542504,0.001154233,0.00016055521,0.0026330575,0.00018186166],"domain_scores_gemma":[0.99185896,0.0010577325,0.0012241112,0.00036020926,0.005356948,0.00014206761],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03997838,0.00010218194,0.00022630607,0.0002618588,0.00042943726,0.00047157385,0.0004467758,0.00006298137,0.0015731286],"category_scores_gemma":[0.0076117963,0.00005508857,0.00010463037,0.00049164117,0.0002844933,0.00047590444,0.0000173508,0.00019388313,0.000015672573],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039603885,0.000022825463,0.007507359,0.0000039874835,0.000048282353,2.1112133e-7,0.0058557703,0.0037924263,0.000053966734,0.0019443509,0.016343147,0.9643881],"study_design_scores_gemma":[0.0024821816,0.0002587298,0.07593752,0.00007048294,0.00040191546,0.00003739935,0.0061757355,0.57144344,0.0005000144,0.008750696,0.33379665,0.000145262],"about_ca_topic_score_codex":0.0014878527,"about_ca_topic_score_gemma":0.024798421,"teacher_disagreement_score":0.9642428,"about_ca_system_score_codex":0.00012728287,"about_ca_system_score_gemma":0.0022657458,"threshold_uncertainty_score":0.9993396},"labels":[],"label_agreement":null},{"id":"W4366383880","doi":"10.3138/cjpe.026.005","title":"Evaluation-Capacity Building: The Three Sides of the Coin","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Gautama Buddha; Metaphor; Context (archaeology); Field (mathematics); Intervention (counseling); Process (computing); Computer science; Psychology; Linguistics; Mathematics; History; Philosophy; Buddhism; Archaeology","score_opus":0.6801887921330342,"score_gpt":0.5042779477622058,"score_spread":0.17591084437082838,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366383880","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98361266,0.00050078414,0.0012146707,0.0027541795,0.001448625,0.0018623952,0.0000071673626,0.0000047655426,0.00859474],"genre_scores_gemma":[0.9969236,0.0000035731566,0.0026648482,0.00016913988,0.00012386947,0.00006805711,9.645311e-7,0.0000076008537,0.000038322887],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99191195,0.0015387897,0.0011193379,0.00017313682,0.005012187,0.00024461903],"domain_scores_gemma":[0.98971075,0.00040139828,0.0013879434,0.0006073003,0.0076686232,0.00022399498],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.052748356,0.00012366741,0.00021537775,0.00031581274,0.00039260933,0.00018192171,0.0011853719,0.00007413497,0.0043214606],"category_scores_gemma":[0.009290858,0.00006218052,0.00022315515,0.0010248885,0.00034287278,0.00049777026,0.000027412529,0.00026774805,0.000029466826],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014671591,0.000060486756,0.108337305,0.0000033427202,0.00007606901,5.210546e-7,0.0040113735,0.0020295605,0.00014072249,0.004089684,0.002350601,0.8788857],"study_design_scores_gemma":[0.00078568404,0.0003252918,0.73602027,0.00006129213,0.0003721656,0.000033124954,0.0014848546,0.090533406,0.0013248635,0.16018963,0.008746546,0.00012289232],"about_ca_topic_score_codex":0.0015430005,"about_ca_topic_score_gemma":0.06333101,"teacher_disagreement_score":0.8787628,"about_ca_system_score_codex":0.00033430333,"about_ca_system_score_gemma":0.007134706,"threshold_uncertainty_score":0.9990543},"labels":[],"label_agreement":null},{"id":"W4366384040","doi":"10.3138/cjpe.0024.004","title":"Utilité de l’évaluation de l’évaluabilité des politiques gouvernementales de lutte contre le tabagisme : l’expérience québécoise des centres d’abandon du tabagisme","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Valuation (finance); Government (linguistics); Welfare economics; Political science; Humanities; Psychology; Economics; Philosophy; Accounting","score_opus":0.14670026669426978,"score_gpt":0.4436251216368626,"score_spread":0.2969248549425928,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384040","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9902577,0.0005518048,0.002287714,0.0024249828,0.000499632,0.0010445545,0.000025286694,0.000034729645,0.0028736363],"genre_scores_gemma":[0.9855101,0.00009501058,0.013290312,0.00039868263,0.00036784462,0.00013631348,0.000020581729,0.000025710195,0.0001554338],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99360067,0.0015742475,0.0013032123,0.00040221133,0.0021850131,0.00093464134],"domain_scores_gemma":[0.9929193,0.00066159037,0.0008758289,0.00045501452,0.003918949,0.0011692663],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.027978051,0.0002868877,0.0003894897,0.0006319111,0.0008831175,0.00078793016,0.00079787895,0.00019679221,0.0019185279],"category_scores_gemma":[0.010647361,0.00024536406,0.00026743178,0.0007134197,0.00081000815,0.0015011964,0.0000332779,0.0004929825,0.00002813773],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049985072,0.00014801866,0.4964407,0.000016098349,0.000037310747,0.000015336962,0.019264705,0.0011475626,0.0026411356,0.0023023395,0.00086853374,0.47706828],"study_design_scores_gemma":[0.0019440652,0.00049349695,0.778329,0.00011773545,0.0001652065,0.00033950093,0.014158482,0.09807688,0.0032947222,0.09102852,0.011718732,0.00033360964],"about_ca_topic_score_codex":0.0397154,"about_ca_topic_score_gemma":0.41797534,"teacher_disagreement_score":0.47673467,"about_ca_system_score_codex":0.001485949,"about_ca_system_score_gemma":0.018263398,"threshold_uncertainty_score":0.9999999},"labels":[],"label_agreement":null},{"id":"W4366384054","doi":"10.3138/cjpe.0021.005","title":"Evaluation Can Cross the Boundaries: The Case of Transport Canada","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Transport Canada","funders":"","keywords":"Champion; Coaching; Unit (ring theory); Work (physics); Service (business); Function (biology); Resource (disambiguation); Government (linguistics); Independence (probability theory); Computer science; Process management; Operations management; Business; Public relations; Psychology; Political science; Management; Marketing; Engineering; Economics; Mathematics education","score_opus":0.29431312733175025,"score_gpt":0.5310447804049384,"score_spread":0.23673165307318816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384054","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98612195,0.0006557619,0.0007478885,0.006722981,0.0017190161,0.0015562251,0.000028939303,0.0000029826892,0.0024442498],"genre_scores_gemma":[0.9989744,0.0000029813698,0.00021028102,0.00045130786,0.00020478539,0.000037861933,0.000010079322,0.000008537822,0.00009977701],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99225247,0.00092489034,0.0015096385,0.00018040322,0.0047735,0.00035909784],"domain_scores_gemma":[0.9873845,0.0007944243,0.0011779527,0.0004897701,0.009855563,0.00029778725],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.09317276,0.00013438164,0.00021794591,0.0002767006,0.0010045595,0.00045070806,0.0006905874,0.00006769253,0.0015958486],"category_scores_gemma":[0.0051573324,0.000071977556,0.0001337288,0.0010593954,0.00048202256,0.00034176465,0.000007717608,0.00028958,0.000003632746],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028258097,0.000023077451,0.030321103,0.000004259544,0.00007093389,0.00008051695,0.0053213225,0.008177948,0.000012481866,0.00065141334,0.0043482236,0.95096046],"study_design_scores_gemma":[0.0026153661,0.0006748299,0.5667385,0.000068480236,0.0008968642,0.001996605,0.028129306,0.09082799,0.0006009841,0.01429833,0.29279155,0.00036125272],"about_ca_topic_score_codex":0.604967,"about_ca_topic_score_gemma":0.9982539,"teacher_disagreement_score":0.9505992,"about_ca_system_score_codex":0.0011463522,"about_ca_system_score_gemma":0.054257307,"threshold_uncertainty_score":0.9993168},"labels":[],"label_agreement":null},{"id":"W4366384066","doi":"10.3138/cjpe.022.004","title":"Conceptualizing Research Impact: The Case of Education Research","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Social Sciences and Humanities Research Council; University of Ottawa","funders":"","keywords":"Interdependence; Educational research; Conceptual framework; Task (project management); Field (mathematics); Subject (documents); Sociology; Process (computing); Qualitative research; Grounded theory; Research methodology; Management science; Psychology; Epistemology; Computer science; Pedagogy; Social science; Management","score_opus":0.8198728471732565,"score_gpt":0.7382456792202653,"score_spread":0.08162716795299119,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384066","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98511773,0.0013001775,0.0003527487,0.0020263293,0.0007065446,0.0012539653,0.0000035797495,0.000002511769,0.009236391],"genre_scores_gemma":[0.99848205,0.000009572531,0.0008480491,0.000049526985,0.00034386868,0.000033507553,0.000003724175,0.000007830843,0.00022188184],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99062663,0.0030850773,0.0012159203,0.0001921264,0.0043466394,0.00053360773],"domain_scores_gemma":[0.97355336,0.0026942817,0.00055441645,0.00046931228,0.022199819,0.00052881544],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.22608447,0.00008099514,0.0001756403,0.0019005467,0.0007034097,0.00040644102,0.0006827635,0.00008640378,0.002035838],"category_scores_gemma":[0.01661185,0.00004871923,0.000120365774,0.0031792196,0.00056793157,0.0005338523,0.000025396817,0.0006578428,0.000057304802],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023462053,0.00005650416,0.0092983395,0.0000034509492,0.00001558454,0.000027843656,0.006868469,0.0003807237,0.00010694053,0.0034972236,0.010969504,0.96875197],"study_design_scores_gemma":[0.0021994659,0.0044011963,0.24227458,0.0003637121,0.00012586062,0.0034067368,0.36882576,0.042484377,0.0022028112,0.16799235,0.16532993,0.00039322476],"about_ca_topic_score_codex":0.007916379,"about_ca_topic_score_gemma":0.07659635,"teacher_disagreement_score":0.96835876,"about_ca_system_score_codex":0.0009653412,"about_ca_system_score_gemma":0.021847008,"threshold_uncertainty_score":0.99887645},"labels":[],"label_agreement":null},{"id":"W4366384075","doi":"10.3138/cjpe.021.005","title":"Discours qui résistent à l’objectivation : que peut-on en tirer pour l’évaluation?","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Meaning (existential); Sympathy; Politics; Political science; Context (archaeology); Sociology; Welfare economics; Social psychology; Psychology; Public relations; Epistemology; Philosophy; Law; Economics; Geography","score_opus":0.2866063764522911,"score_gpt":0.5192156027950292,"score_spread":0.23260922634273812,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384075","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9466943,0.00024304763,0.0031946276,0.025243111,0.0017304268,0.0018296684,0.000013637995,0.00002549816,0.021025691],"genre_scores_gemma":[0.9956453,0.000005895136,0.002195191,0.00028498887,0.00071530277,0.00010717243,0.00004522849,0.000019140329,0.0009817807],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99287075,0.0012149231,0.0013554929,0.0003261841,0.0038610718,0.00037158967],"domain_scores_gemma":[0.9940565,0.00051680184,0.0010551844,0.00039677363,0.0036274611,0.00034727165],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.019056115,0.00020596995,0.00029762494,0.0011532848,0.0003787196,0.00059217785,0.0004897079,0.00012946222,0.002460211],"category_scores_gemma":[0.002786931,0.0001584345,0.00022436562,0.0009615048,0.000080969956,0.0008344098,0.000012113687,0.00029451208,0.00027675246],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051116986,0.00023020562,0.069561385,0.0000060646266,0.000049768023,0.000008506884,0.0014879936,0.05363563,0.00028271254,0.009592043,0.021754535,0.84334004],"study_design_scores_gemma":[0.0023662604,0.0010968017,0.7351185,0.00012342601,0.00020474412,0.000062895364,0.0042682006,0.11926798,0.0005942376,0.09480292,0.04168377,0.000410251],"about_ca_topic_score_codex":0.0016943304,"about_ca_topic_score_gemma":0.024113974,"teacher_disagreement_score":0.8429298,"about_ca_system_score_codex":0.0010399222,"about_ca_system_score_gemma":0.0076495185,"threshold_uncertainty_score":0.99845165},"labels":[],"label_agreement":null},{"id":"W4366384079","doi":"10.3138/cjpe.021.007","title":"Participatory Needs Assessment","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Credibility; Participatory evaluation; Citizen journalism; Needs assessment; Relevance (law); Quality (philosophy); Process (computing); Process management; Business; Program evaluation; Knowledge management; Computer science; Sociology; Political science","score_opus":0.497564820203374,"score_gpt":0.5742346745312081,"score_spread":0.07666985432783413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384079","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9536883,0.00052039506,0.0035838818,0.0039182967,0.0016764601,0.0009392741,0.000005634104,0.000014981336,0.035652727],"genre_scores_gemma":[0.99521124,0.0000021097803,0.0037150558,0.00018265964,0.00035379393,0.000059661266,0.000009638691,0.000008153902,0.00045767843],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99516284,0.0005896442,0.0010844563,0.00013577884,0.002722702,0.0003045683],"domain_scores_gemma":[0.9955565,0.00018570366,0.0006986608,0.0002773539,0.0028868255,0.0003949583],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.018478857,0.0001077817,0.00020975975,0.0009498888,0.00021317584,0.000474227,0.0003944825,0.00006622345,0.0044497056],"category_scores_gemma":[0.00081469194,0.00008233226,0.00013396009,0.0009882016,0.0000888572,0.00061351963,0.0000085317015,0.00018649049,0.00012332946],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000067378874,0.00008196205,0.21806926,0.000002511991,0.00002056998,0.000008406315,0.00045413597,0.008901226,0.00008793112,0.0057178424,0.022609858,0.74403954],"study_design_scores_gemma":[0.0010712304,0.00047400832,0.62328565,0.00002677739,0.00010506735,0.000034747292,0.0014084314,0.07748473,0.00012522878,0.032309126,0.2634955,0.00017949371],"about_ca_topic_score_codex":0.00080841297,"about_ca_topic_score_gemma":0.016559925,"teacher_disagreement_score":0.74386007,"about_ca_system_score_codex":0.00051100005,"about_ca_system_score_gemma":0.007290182,"threshold_uncertainty_score":0.99833757},"labels":[],"label_agreement":null},{"id":"W4366384147","doi":"10.3138/cjpe.26.005","title":"Using Evaluation to Shape and Direct Comprehensive Community Initiatives: Evaluation, Reflective Practice, and Interventions Dealing with Complexity","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Regional Municipality of Waterloo; Wilfrid Laurier University; Centre for Community Based Research","funders":"","keywords":"Citizen journalism; Participatory action research; Experiential learning; Experiential knowledge; Psychological intervention; Value (mathematics); Reflective practice; Action (physics); Sociology; Engineering ethics; Knowledge management; Psychology; Computer science; Pedagogy; Epistemology; Engineering","score_opus":0.8567416364459937,"score_gpt":0.631227536497771,"score_spread":0.2255140999482227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384147","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98096496,0.0009874278,0.0040801866,0.0006598071,0.0002515844,0.0032517947,0.000017696222,0.000011255449,0.009775275],"genre_scores_gemma":[0.9567327,0.000016432494,0.042772334,0.00027950987,0.000048803075,0.00011544071,0.000017258388,0.000013823665,0.0000037247064],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.990506,0.0051858686,0.0010440155,0.00029283966,0.0026876342,0.00028362297],"domain_scores_gemma":[0.9802481,0.0008291129,0.001219279,0.0003194292,0.016851624,0.0005324716],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.039546747,0.00019577795,0.0003567759,0.0009809297,0.0009649922,0.00041285378,0.0002711274,0.00007464553,0.0011407239],"category_scores_gemma":[0.008975552,0.00015906307,0.00007966048,0.0009079338,0.00029899544,0.0022041244,0.00004790155,0.00039085172,0.00000779551],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030263668,0.00024827983,0.02544828,0.00003259796,0.0003170501,0.0000048227844,0.04249009,0.004703097,0.0001405039,0.0016393267,0.00011706374,0.92455626],"study_design_scores_gemma":[0.002506036,0.0024560916,0.58566487,0.00046461055,0.0012269558,0.00018327532,0.036746547,0.3491762,0.00009176386,0.02031888,0.0008452677,0.00031952988],"about_ca_topic_score_codex":0.0023677659,"about_ca_topic_score_gemma":0.03642814,"teacher_disagreement_score":0.9242367,"about_ca_system_score_codex":0.0006575838,"about_ca_system_score_gemma":0.0032631832,"threshold_uncertainty_score":0.99977237},"labels":[],"label_agreement":null},{"id":"W4366384160","doi":"10.3138/cjpe.22.004","title":"Using Public Databases to Study Relative Program Impact","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Impact assessment; Database; Computer science; Control (management); Impact evaluation; Statistics; Political science; Artificial intelligence; Mathematics","score_opus":0.7796421792303019,"score_gpt":0.6674537745782021,"score_spread":0.11218840465209978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384160","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98172134,0.00015459246,0.011932047,0.0006884004,0.00063914363,0.0034238196,0.00001044089,0.000016728234,0.0014134716],"genre_scores_gemma":[0.9676183,7.942863e-7,0.031952973,0.000109580295,0.00021254295,0.00004775395,0.0000113491915,0.000013240179,0.000033469525],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99373335,0.00077419804,0.0013200481,0.0002912941,0.0033513035,0.00052978884],"domain_scores_gemma":[0.99206424,0.0003718588,0.0008163736,0.00042765733,0.005060794,0.0012591004],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.042586878,0.0001707963,0.00029235793,0.0017038023,0.00037592082,0.00070283655,0.00054330676,0.000051337283,0.0022812593],"category_scores_gemma":[0.0073068673,0.00012324264,0.00015568218,0.0024167167,0.000066767505,0.0017328428,0.000028219685,0.00026673943,0.00008255824],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020761561,0.00023568062,0.22376633,7.137686e-7,0.0000580831,0.00001677117,0.0017987413,0.0010605259,0.000021591466,0.00014771438,0.0004263151,0.77244675],"study_design_scores_gemma":[0.0017647748,0.003935724,0.9071324,0.000046402984,0.00020648612,0.00011096797,0.011237666,0.034835365,0.0000737013,0.0021189204,0.038220257,0.00031733024],"about_ca_topic_score_codex":0.001525843,"about_ca_topic_score_gemma":0.049713615,"teacher_disagreement_score":0.7721294,"about_ca_system_score_codex":0.0010121913,"about_ca_system_score_gemma":0.008199334,"threshold_uncertainty_score":0.99863076},"labels":[],"label_agreement":null},{"id":"W4366384164","doi":"10.3138/cjpe.027.008","title":"DeMars, C. (2010). <i>Item Response Theory.</i> Oxford, UK: Oxford University Press. 137 Pages.","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Item response theory; Media studies; Political science; Economic history; Library science; Economics; Sociology; Computer science; Law","score_opus":0.29078747149008427,"score_gpt":0.43684040231959376,"score_spread":0.1460529308295095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384164","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.961349,0.002761361,0.0047892695,0.004362343,0.0034769576,0.0019183956,0.00004053598,0.000033330743,0.021268792],"genre_scores_gemma":[0.9934893,0.00011995051,0.002633894,0.00030986848,0.0002777804,0.000012039394,0.000012800299,0.000014477944,0.0031298527],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9933485,0.0026377747,0.00083812024,0.00022489885,0.0023786523,0.00057207677],"domain_scores_gemma":[0.99408484,0.0011431535,0.00088525703,0.00047178185,0.0023421582,0.0010728285],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.04634388,0.00018158955,0.00029039296,0.0007254572,0.0003924487,0.00033633306,0.0007499513,0.00014462057,0.0031836147],"category_scores_gemma":[0.0057933154,0.0001471977,0.00019834936,0.0007961469,0.00015340392,0.001478871,0.000034225777,0.000330295,0.0000428782],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000605115,0.00010717055,0.09931136,0.0000060334205,0.00008295233,0.000016746135,0.002116507,0.0008315641,0.000057616056,0.003974797,0.045773517,0.84711665],"study_design_scores_gemma":[0.0010386518,0.00035557878,0.18604569,0.000030730407,0.00011430205,0.00005992337,0.001947274,0.0040247696,0.00010430245,0.001919418,0.8041753,0.00018405702],"about_ca_topic_score_codex":0.0001485702,"about_ca_topic_score_gemma":0.002137612,"teacher_disagreement_score":0.8469326,"about_ca_system_score_codex":0.0007189188,"about_ca_system_score_gemma":0.0043380046,"threshold_uncertainty_score":0.99772763},"labels":[],"label_agreement":null},{"id":"W4366384165","doi":"10.3138/cjpe.21.001","title":"Suggestions d’améliorations d’un cadre conceptuel de l’évaluation participative","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Participatory evaluation; Empowerment; Stakeholder; Citizen journalism; Relevance (law); Valuation (finance); Sociology; Knowledge management; Management science; Process management; Business; Political science; Computer science; Public relations; Social science; Engineering; Accounting","score_opus":0.3522063354619847,"score_gpt":0.5249077562850959,"score_spread":0.17270142082311118,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384165","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9610089,0.0005563038,0.019721702,0.006071924,0.0008718071,0.001475194,0.000030262925,0.000025886782,0.010237997],"genre_scores_gemma":[0.98992616,0.0000057995467,0.0089163445,0.0001772879,0.00035348174,0.00018245871,0.000052972915,0.000012038005,0.0003734587],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9945997,0.001228601,0.0012423052,0.0002236655,0.002317746,0.0003879626],"domain_scores_gemma":[0.99258685,0.00043091763,0.0009025907,0.00029675558,0.0053524603,0.00043043157],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01660161,0.000148748,0.0002432948,0.00074208935,0.00053383136,0.0005301964,0.0003798437,0.000113418035,0.00446357],"category_scores_gemma":[0.003993693,0.00012541348,0.00015252939,0.00126438,0.00017576334,0.0008772354,0.000009483308,0.00024893376,0.0001461224],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018953036,0.00017421169,0.10015462,0.0000033201036,0.000047724985,0.000011362216,0.004176653,0.08557067,0.00044010472,0.010497415,0.016817708,0.78208727],"study_design_scores_gemma":[0.0017191214,0.0006039254,0.6223053,0.00005045508,0.00029629437,0.000076090946,0.0035984549,0.21812914,0.0009140578,0.1075364,0.04447358,0.00029720244],"about_ca_topic_score_codex":0.00188833,"about_ca_topic_score_gemma":0.03895649,"teacher_disagreement_score":0.78179,"about_ca_system_score_codex":0.0006453629,"about_ca_system_score_gemma":0.008704844,"threshold_uncertainty_score":0.99691486},"labels":[],"label_agreement":null},{"id":"W4366384172","doi":"10.3138/cjpe.0024.005","title":"Rigour and Feasibility in Tobacco Control Evaluation: Toward a Successful Reconciliation","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Communications and Information Technology Ontario; Heart and Stroke Foundation; University of Waterloo; Public Health Ontario; University of Toronto","funders":"","keywords":"Rigour; Stakeholder; Relevance (law); Context (archaeology); Tobacco control; Control (management); Plan (archaeology); Management science; Program evaluation; Process management; Political science; Engineering ethics; Public relations; Computer science; Business; Public administration; Engineering; Medicine; Public health; Epistemology; Nursing; Law; Geography","score_opus":0.37313234694188385,"score_gpt":0.5320879190308285,"score_spread":0.15895557208894467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384172","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9891412,0.00028643722,0.00030339696,0.005145354,0.0013281248,0.002073204,0.0000088797715,0.0000065427803,0.0017068554],"genre_scores_gemma":[0.9978325,0.000006655799,0.0015518485,0.00021967375,0.00022016437,0.00012203827,0.000009854979,0.0000075204457,0.000029788976],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9934024,0.0017805285,0.0013331604,0.0003279183,0.00285614,0.00029981267],"domain_scores_gemma":[0.99232656,0.00060288055,0.00084140495,0.000349631,0.0053927344,0.00048677818],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07160067,0.00014694757,0.0003180493,0.0008249185,0.0002218369,0.0005462925,0.0003851185,0.00015045279,0.0042349803],"category_scores_gemma":[0.016914625,0.00011910437,0.000095614494,0.0008217563,0.00012246043,0.0012192744,0.000010256778,0.00063199794,0.000042938125],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023974068,0.00002849496,0.4936072,0.0000020551763,0.000007763319,0.0000015455843,0.0008486235,0.00052015873,0.000059895807,0.00012834684,0.0002606644,0.5045113],"study_design_scores_gemma":[0.003238206,0.00025778174,0.84857404,0.000024111161,0.00007724069,0.000038437778,0.0013563512,0.1252883,0.000039765488,0.0157944,0.0051650214,0.00014634946],"about_ca_topic_score_codex":0.0009988707,"about_ca_topic_score_gemma":0.18166767,"teacher_disagreement_score":0.5043649,"about_ca_system_score_codex":0.00054977246,"about_ca_system_score_gemma":0.0075788377,"threshold_uncertainty_score":0.9980473},"labels":[],"label_agreement":null},{"id":"W4366384175","doi":"10.3138/cjpe.23.017","title":"R. Pawson. (2006). <i>Evidence-based Policy: A Realist Perspective.</i> Thousand Oaks, CA: Sage. 209 pages.","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Perspective (graphical); SAGE; Sociology; Philosophy; Political science; Epistemology; Regional science; Art; Physics; Visual arts; Quantum mechanics","score_opus":0.3443396687424581,"score_gpt":0.4951481816256015,"score_spread":0.1508085128831434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384175","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.657566,0.038133673,0.020112224,0.23198123,0.00660885,0.009093144,0.00025409032,0.00016441953,0.03608637],"genre_scores_gemma":[0.99257696,0.00041400248,0.003310403,0.0016256184,0.0007424489,0.00008012181,0.000014813794,0.00002226518,0.001213373],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99298465,0.0011460591,0.001209685,0.00038450622,0.003743501,0.0005315986],"domain_scores_gemma":[0.9914111,0.00057269196,0.0010416192,0.00053932285,0.0054948735,0.00094042206],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.014876123,0.00023353346,0.0004106598,0.0013266002,0.0006600296,0.00050374336,0.00071636995,0.00013406284,0.002781709],"category_scores_gemma":[0.009568143,0.00018276717,0.0002644656,0.0018777762,0.00032007493,0.0012394843,0.000015717595,0.00037827773,0.00016492215],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001412407,0.00019736914,0.066849336,0.000013800783,0.000089478846,0.00016527531,0.004356773,0.012546573,0.00013699959,0.0013756211,0.1977672,0.71636033],"study_design_scores_gemma":[0.0048979656,0.002264339,0.39768738,0.0005847221,0.0003246415,0.0007129553,0.005303364,0.068970114,0.00054142834,0.019385034,0.49843794,0.0008901233],"about_ca_topic_score_codex":0.009111389,"about_ca_topic_score_gemma":0.052051786,"teacher_disagreement_score":0.7154702,"about_ca_system_score_codex":0.0017363442,"about_ca_system_score_gemma":0.027101418,"threshold_uncertainty_score":0.9987747},"labels":[],"label_agreement":null},{"id":"W4366384176","doi":"10.3138/cjpe.21.002","title":"Challenges of Participatory Evaluation within a Community-Based Health Promotion Partnership: Mujer Sana, Comunidad Sana—Healthy Women, Healthy Communities","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"General partnership; Citizen journalism; Participatory action research; Community-based participatory research; Participatory evaluation; Promotion (chess); Sociology; Public relations; Nursing; Medicine; Political science; Social science","score_opus":0.7114160732550165,"score_gpt":0.5663836151296869,"score_spread":0.1450324581253296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384176","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97991896,0.0027511003,0.000413304,0.011962513,0.00066617155,0.002683601,0.000020454416,0.00002574266,0.001558182],"genre_scores_gemma":[0.996739,0.000047713103,0.001341658,0.0010419842,0.00015654867,0.00046172185,0.00016417925,0.000027041102,0.000020187183],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.97514385,0.015917672,0.0030896803,0.0002281717,0.0048535126,0.00076711795],"domain_scores_gemma":[0.98741335,0.00093803636,0.0035650202,0.0009650173,0.0062890626,0.00082951586],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.10788584,0.0002906319,0.0007475109,0.0015210053,0.0010504451,0.00027008157,0.0008495457,0.00017556807,0.0008559491],"category_scores_gemma":[0.0014232639,0.00025516681,0.00018464803,0.0011213582,0.0003980392,0.00079379126,0.000020735146,0.0008481647,0.000025752475],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044139213,0.002059455,0.081304796,0.00043415537,0.0001135617,0.0000023082337,0.06531169,0.060067613,0.000024421839,0.004443939,0.004694976,0.7811017],"study_design_scores_gemma":[0.01022975,0.021342123,0.38107774,0.0010616679,0.00031636423,0.000041838957,0.1646568,0.35505587,0.00017635436,0.047900848,0.017302146,0.0008384845],"about_ca_topic_score_codex":0.012303684,"about_ca_topic_score_gemma":0.36469564,"teacher_disagreement_score":0.7802632,"about_ca_system_score_codex":0.0024872217,"about_ca_system_score_gemma":0.020535868,"threshold_uncertainty_score":0.99999005},"labels":[],"label_agreement":null},{"id":"W4366384241","doi":"10.3138/cjpe.21.006","title":"Development of a Framework for Comprehensive Evaluation of Client Outcomes in Community Mental Health Services","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Western University; Riverview Hospital; University of British Columbia","funders":"","keywords":"Operationalization; Assertive community treatment; Mental health; Conceptualization; Stakeholder; Psychology; Inclusion (mineral); Mental illness; Applied psychology; Process management; Psychiatry; Public relations; Social psychology; Business; Computer science","score_opus":0.46199264417842795,"score_gpt":0.5765774015422332,"score_spread":0.1145847573638053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384241","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99425006,0.0004643644,0.0015066881,0.0008527099,0.00042074372,0.0023291581,0.000028480938,0.0000033146866,0.00014449607],"genre_scores_gemma":[0.9446337,0.0000036731954,0.0550537,0.00010381031,0.000027062737,0.00009877094,0.000067575456,0.000006863718,0.0000048456186],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9929539,0.0014380341,0.0021346842,0.0001364799,0.0030929307,0.00024395683],"domain_scores_gemma":[0.99185306,0.0005008559,0.0021119711,0.00027264078,0.005092013,0.00016946663],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.031386834,0.00012654076,0.00046183425,0.0008131309,0.0002479021,0.00007161492,0.00042356676,0.00007705681,0.00019554223],"category_scores_gemma":[0.0006480303,0.00010295472,0.00012670887,0.0006226366,0.000076569784,0.00031450365,0.000018418412,0.00020178701,0.0000029463797],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006422149,0.00047543747,0.16545223,0.000097909,0.000058718528,1.3956345e-7,0.02006756,0.013671346,0.000104721876,0.0010657794,0.0002842805,0.79865766],"study_design_scores_gemma":[0.0027183315,0.00061975024,0.8813681,0.0004080878,0.000060495153,0.0000031971056,0.017552538,0.06406259,0.00039729464,0.02910006,0.0035798533,0.00012970928],"about_ca_topic_score_codex":0.0026180723,"about_ca_topic_score_gemma":0.12973092,"teacher_disagreement_score":0.79852796,"about_ca_system_score_codex":0.0008860047,"about_ca_system_score_gemma":0.0076221703,"threshold_uncertainty_score":0.99800366},"labels":[],"label_agreement":null},{"id":"W4366384242","doi":"10.3138/cjpe.0023.008","title":"Insights into Evaluation Capacity Building: Motivations, Strategies, Outcomes, and Lessons Learned","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Variety (cybernetics); Capacity building; Accountability; Face (sociological concept); Public relations; Business; Psychology; Process management; Knowledge management; Political science; Sociology; Computer science","score_opus":0.536890060585536,"score_gpt":0.5401212105282374,"score_spread":0.00323114994270135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384242","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97717315,0.00083537295,0.0036009275,0.0142057305,0.00052734156,0.0012199333,0.0000027607134,0.000015393829,0.0024193688],"genre_scores_gemma":[0.99173206,0.000026702288,0.0076521295,0.00035116615,0.000116593976,0.000041648458,0.00001762846,0.000008058163,0.000054027165],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9938912,0.0010419987,0.0011347256,0.0003255178,0.003329569,0.00027701736],"domain_scores_gemma":[0.99318695,0.0002812643,0.0008867626,0.00036000082,0.0047391346,0.0005458742],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015174372,0.00018985014,0.00033268647,0.0010538633,0.0004900606,0.0009908496,0.00041137775,0.00013256073,0.0005911456],"category_scores_gemma":[0.005554219,0.00014624203,0.00011164167,0.0009687603,0.000120594465,0.0018059745,0.000010829596,0.00031365402,0.000020536068],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009682146,0.000059652062,0.014953587,0.0000027618826,0.000028330682,0.0000018001508,0.0022115756,0.0044333255,0.00036345056,0.015815735,0.00075832586,0.96136177],"study_design_scores_gemma":[0.0013085816,0.00045035264,0.5793656,0.00004037739,0.00013104484,0.000012014356,0.001792088,0.0814666,0.000096767864,0.3186343,0.016510535,0.00019174427],"about_ca_topic_score_codex":0.00073628547,"about_ca_topic_score_gemma":0.016562002,"teacher_disagreement_score":0.96117,"about_ca_system_score_codex":0.0006728097,"about_ca_system_score_gemma":0.0071945894,"threshold_uncertainty_score":0.9984337},"labels":[],"label_agreement":null},{"id":"W4366384248","doi":"10.3138/cjpe.026.006","title":"J. Fitzpatrick, C. Christie, &amp; M. M. Mark. (2009). <i>Evaluation in Action: Interviews with Expert Evaluators</i> . Thousand Oaks, CA: Sage. xiv + 456 pages.","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"SAGE; Action (physics); Psychology; Sociology; Physics","score_opus":0.3641684196792167,"score_gpt":0.47772110415375324,"score_spread":0.11355268447453654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384248","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9293127,0.017051077,0.009984993,0.004627008,0.0064280387,0.009063288,0.000051749725,0.00006718653,0.023413982],"genre_scores_gemma":[0.9891888,0.0004303301,0.007911993,0.00051946,0.000446215,0.0004934626,0.000061421975,0.000041949505,0.00090636057],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9890019,0.002568539,0.0021007776,0.00058487704,0.0051065255,0.00063736126],"domain_scores_gemma":[0.9917103,0.00028594985,0.0016357206,0.000763234,0.004844266,0.0007605417],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.040738348,0.00037557798,0.0006054776,0.0017447225,0.00031737724,0.0004899637,0.00082718243,0.00021785246,0.017610447],"category_scores_gemma":[0.0029169626,0.0002791596,0.00021927232,0.0021811333,0.00018305639,0.0016413591,0.00003248651,0.00056222046,0.00032639134],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016510944,0.00018267483,0.028036604,0.000012579505,0.00006066099,0.000018283672,0.0052371756,0.0012780866,0.000033098946,0.000031608102,0.039513167,0.92543095],"study_design_scores_gemma":[0.00807724,0.0018241998,0.27006137,0.0006187036,0.0005913967,0.0003633595,0.006529498,0.07318255,0.0003379863,0.0062306914,0.63111156,0.0010714221],"about_ca_topic_score_codex":0.0019076646,"about_ca_topic_score_gemma":0.18559937,"teacher_disagreement_score":0.92435956,"about_ca_system_score_codex":0.0013857904,"about_ca_system_score_gemma":0.008647293,"threshold_uncertainty_score":0.9999661},"labels":[],"label_agreement":null},{"id":"W4366384250","doi":"10.3138/cjpe.27.005","title":"The Key Functions of Collaborative Logic Modelling: Insights from the British Columbia Early Childhood Dental Programs","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Documentation; General partnership; Key (lock); Logic model; Government (linguistics); Knowledge management; Computer science; Process management; Public relations; Political science; Psychology; Business; Public administration","score_opus":0.21203274369979694,"score_gpt":0.40990725897507363,"score_spread":0.1978745152752767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384250","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9897834,0.0038878303,0.0013870632,0.00080021436,0.0012972075,0.0015499736,0.000030446381,0.0000070074216,0.0012568553],"genre_scores_gemma":[0.99786836,0.000041580468,0.0012293317,0.00009579834,0.0003524162,0.00011065983,0.000028681538,0.000009536059,0.0002636531],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9954444,0.0009125912,0.0009520268,0.00015717126,0.0022211988,0.00031256635],"domain_scores_gemma":[0.9941746,0.0005433342,0.00096807315,0.00031507493,0.0036104969,0.00038842185],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.006398575,0.00010042607,0.0002112036,0.00008179085,0.001472804,0.0029386224,0.0005196907,0.00008304356,0.0005159218],"category_scores_gemma":[0.0010991032,0.00007259355,0.00014543752,0.0010818916,0.00027391553,0.0008607192,0.000018968887,0.0002707753,0.000041712377],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013536142,0.00019071369,0.21848427,9.153167e-7,0.000120307945,0.0000018742664,0.009175833,0.002685331,0.000007270763,0.00026526226,0.006990548,0.76206416],"study_design_scores_gemma":[0.00116329,0.0008284012,0.8450762,0.00008966461,0.0002427623,0.000045665645,0.018333683,0.025069753,0.000014835202,0.018070757,0.09086806,0.00019694761],"about_ca_topic_score_codex":0.020511515,"about_ca_topic_score_gemma":0.60070926,"teacher_disagreement_score":0.76186717,"about_ca_system_score_codex":0.0002182644,"about_ca_system_score_gemma":0.002934671,"threshold_uncertainty_score":0.99982715},"labels":[],"label_agreement":null},{"id":"W4366384275","doi":"10.3138/cjpe.027.006","title":"Ryan, K. E., &amp; Cousins, J. B. (Eds.). (2009). <i>The Sage International Handbook of Educational Evaluation.</i> Thousand Oaks, CA: Sage. 608 Pages.","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"SAGE; Sociology; Psychology; Gerontology; Library science; Medicine; Computer science; Physics","score_opus":0.17755472847929304,"score_gpt":0.4727750580837578,"score_spread":0.29522032960446476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384275","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62938523,0.16491692,0.01734778,0.08940604,0.039802715,0.0130556105,0.000595395,0.000055965575,0.04543436],"genre_scores_gemma":[0.9898535,0.0005569011,0.004204648,0.0007224767,0.0014862027,0.00020912205,0.0001740039,0.000026443244,0.0027666795],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9906725,0.0012724423,0.0017014944,0.00027376553,0.0055801054,0.0004996918],"domain_scores_gemma":[0.99031264,0.0009117057,0.0017220034,0.0005662253,0.0058605084,0.00062693394],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.032235708,0.00023668852,0.0003586858,0.00079966563,0.0004426348,0.0004390875,0.0009801697,0.00013677921,0.022426955],"category_scores_gemma":[0.006382394,0.00016852183,0.00024355699,0.00091021485,0.00028765277,0.0013730157,0.00003787424,0.00036316417,0.00029243354],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036386697,0.000222272,0.062126674,0.000007914618,0.00012523515,6.5905135e-7,0.0022452148,0.003505039,0.0001950994,0.00031964516,0.107829735,0.82338613],"study_design_scores_gemma":[0.002003869,0.00019087736,0.1399945,0.00021354543,0.00040913545,0.00012448945,0.0008521978,0.019607043,0.00026276388,0.0067654047,0.8292551,0.00032107273],"about_ca_topic_score_codex":0.00045531002,"about_ca_topic_score_gemma":0.015040838,"teacher_disagreement_score":0.82306504,"about_ca_system_score_codex":0.00074975024,"about_ca_system_score_gemma":0.009834842,"threshold_uncertainty_score":0.996517},"labels":[],"label_agreement":null},{"id":"W4366384291","doi":"10.3138/cjpe.0027.008","title":"Meta-evaluation: Evaluating the Evaluation of the Paris Declaration","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Declaration; Evaluation methods; Meta-analysis; Strengths and weaknesses; Quality (philosophy); Psychology; Computer science; Management science; Political science; Medicine; Engineering; Social psychology; Law; Reliability engineering","score_opus":0.7957816232407139,"score_gpt":0.5870236538267359,"score_spread":0.20875796941397795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384291","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96098644,0.004065051,0.0007365009,0.016335307,0.002346641,0.009341846,0.000009715868,0.000010815894,0.0061676796],"genre_scores_gemma":[0.99622387,0.0000124762555,0.0016438719,0.00036576472,0.00027523696,0.0012547144,0.00001518066,0.00001707606,0.00019178685],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9732264,0.008540806,0.0024578976,0.0003717549,0.014992796,0.0004103212],"domain_scores_gemma":[0.9641123,0.0010375741,0.003087276,0.00107267,0.030381324,0.0003088746],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14050691,0.0002561096,0.0004972088,0.000548324,0.00078080606,0.0007824051,0.0013134441,0.00015122445,0.020378957],"category_scores_gemma":[0.016130183,0.00012968751,0.0005753705,0.0019734094,0.00028431488,0.0014929724,0.00004636222,0.00042079517,0.00014415798],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010064508,0.00005282935,0.008378584,0.000004432981,0.0004205836,1.05890216e-7,0.0019893844,0.06408812,0.00025197296,0.0003605446,0.0068642166,0.9175792],"study_design_scores_gemma":[0.0013521746,0.00043032708,0.18385406,0.000036939076,0.00564792,0.000024897552,0.0020164358,0.76085836,0.0004697795,0.04103515,0.004106369,0.00016759669],"about_ca_topic_score_codex":0.0014933308,"about_ca_topic_score_gemma":0.011145987,"teacher_disagreement_score":0.91741157,"about_ca_system_score_codex":0.0008810804,"about_ca_system_score_gemma":0.015448592,"threshold_uncertainty_score":0.9921574},"labels":[],"label_agreement":null},{"id":"W4366384338","doi":"10.3138/cjpe.0025.011","title":"Je me souviens … de t’avoir trop longtemps cherché","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Logic program; Set (abstract data type); Computer science; Process (computing); Expression (computer science); Epistemology; Artificial intelligence; Programming language; Philosophy; Logic programming","score_opus":0.6896710628632848,"score_gpt":0.5555406698966722,"score_spread":0.13413039296661267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384338","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9661593,0.0004970395,0.0032816306,0.002097455,0.001167533,0.0009854111,0.0000071256527,0.00001858179,0.025785968],"genre_scores_gemma":[0.9876087,0.000012501293,0.011457461,0.00028843293,0.00021852218,0.000042645115,0.0000045327934,0.000012635259,0.0003546225],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9956443,0.0007981136,0.0009626057,0.00020495965,0.0019801299,0.0004098969],"domain_scores_gemma":[0.99505013,0.00018979122,0.00066948484,0.00034651498,0.0029587753,0.0007853063],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.021191187,0.00013527718,0.00024552934,0.00067528826,0.00022069407,0.00028123366,0.00063310127,0.00011082458,0.008359505],"category_scores_gemma":[0.003850304,0.000103799524,0.00017149642,0.0007334507,0.00011802802,0.000692828,0.000012340149,0.00028421474,0.0003065675],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026813841,0.000073106174,0.08025526,0.000003941398,0.000040795116,0.000017984941,0.0069417763,0.0004001202,0.00009499033,0.0010337849,0.004892967,0.90621847],"study_design_scores_gemma":[0.0027924255,0.002663075,0.6696998,0.00011933875,0.00033478966,0.0003306539,0.008012687,0.07386107,0.0013239667,0.083013356,0.15728307,0.00056578673],"about_ca_topic_score_codex":0.00070376426,"about_ca_topic_score_gemma":0.020627595,"teacher_disagreement_score":0.9056527,"about_ca_system_score_codex":0.0006121915,"about_ca_system_score_gemma":0.007694202,"threshold_uncertainty_score":0.99793124},"labels":[],"label_agreement":null},{"id":"W4366384352","doi":"10.3138/cjpe.024.008","title":"Valéry Ridde &amp; Christian Dagenais (Éds.). (2009). <i>Approches et pratiques en évaluation de programme.</i> Montréal : Les Presses de l’Université de Montréal. 358 pages.","year":2009,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Art; Sociology","score_opus":0.14445123495851397,"score_gpt":0.4024079413428465,"score_spread":0.25795670638433255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384352","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66751605,0.18622242,0.038846083,0.09326714,0.0014490763,0.005497358,0.0001390927,0.0001352743,0.006927518],"genre_scores_gemma":[0.8774948,0.016257878,0.1004861,0.0015814318,0.0009815079,0.00019360674,0.00027661698,0.00006931189,0.002658724],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98950875,0.0042522037,0.0015659729,0.000559724,0.002797572,0.0013158015],"domain_scores_gemma":[0.99223834,0.00067474536,0.0015743439,0.00056887657,0.003310523,0.001633148],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.031810906,0.00049825263,0.0006010933,0.0008986872,0.00094816973,0.0011652162,0.0009168722,0.00053610926,0.0034790959],"category_scores_gemma":[0.0058931503,0.00048224707,0.00037364455,0.0010423097,0.00027499162,0.0016324748,0.000048655627,0.00085082726,0.00010704198],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00012274248,0.00030660923,0.014432008,0.00004411143,0.00012468577,0.000062506035,0.021587636,0.01630046,0.0005416778,0.00028850898,0.08764335,0.8585457],"study_design_scores_gemma":[0.0024785988,0.0019274977,0.26970285,0.00054800574,0.0010221179,0.0006553725,0.008527149,0.09847045,0.0011796652,0.012027348,0.60276586,0.00069506106],"about_ca_topic_score_codex":0.033725668,"about_ca_topic_score_gemma":0.3491635,"teacher_disagreement_score":0.8578507,"about_ca_system_score_codex":0.0043890355,"about_ca_system_score_gemma":0.02066079,"threshold_uncertainty_score":0.9998717},"labels":[],"label_agreement":null},{"id":"W4366384398","doi":"10.3138/cjpe.0025.004","title":"L’influence de l’évaluation sur les suites des projets d’expérimentation : l’exemple des projets d’informatisation au Québec","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Montréal; Université Laval","funders":"","keywords":"Formative assessment; Valuation (finance); Political science; Action plan; Knowledge management; Business; Sociology; Pedagogy; Management; Computer science; Economics; Accounting","score_opus":0.3539878063192124,"score_gpt":0.47094040675696225,"score_spread":0.11695260043774985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384398","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9927232,0.00036539562,0.0022793151,0.00026757742,0.0001703708,0.0015717234,0.0000072101566,0.000027066342,0.0025880886],"genre_scores_gemma":[0.9844763,0.00004275402,0.01491718,0.00008907969,0.000106331005,0.0002205346,0.000030083835,0.000018200893,0.00009948126],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99431187,0.00091980695,0.001523277,0.00026344167,0.0024509141,0.00053071696],"domain_scores_gemma":[0.99081844,0.00038965407,0.0013599376,0.0003196925,0.0065915594,0.00052071066],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016868737,0.0002280652,0.00028563463,0.0010090168,0.0009833279,0.00036842696,0.0005439035,0.00013485475,0.000954941],"category_scores_gemma":[0.008411306,0.00018860404,0.00014885807,0.000998452,0.00040415506,0.003561389,0.000019783665,0.00022604647,0.00008897913],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029247976,0.000057615587,0.38320822,0.000016019294,0.00002468795,0.0000026959258,0.06335707,0.0020132235,0.00022040778,0.000100684156,0.00029419168,0.5506759],"study_design_scores_gemma":[0.000979164,0.0007229464,0.95150065,0.00011954698,0.0001026165,0.00012081856,0.0053761993,0.030204805,0.002090236,0.0063047605,0.0022512854,0.00022694173],"about_ca_topic_score_codex":0.15701804,"about_ca_topic_score_gemma":0.5986734,"teacher_disagreement_score":0.5682925,"about_ca_system_score_codex":0.0024974572,"about_ca_system_score_gemma":0.022152748,"threshold_uncertainty_score":0.99995834},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":true,"confidence":"low"}],"label_agreement":"split"},{"id":"W4366384407","doi":"10.3138/cjpe.0025.015","title":"Réflexions autour des 25 ans de la <i>Revue canadienne d’évaluation de programme</i> : l’évaluation au passé, au présent, et au futur","year":2011,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Economics; Humanities; Philosophy","score_opus":0.3511264130259222,"score_gpt":0.4670286099850321,"score_spread":0.11590219695910992,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384407","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93144196,0.001262691,0.018643826,0.0195165,0.005306934,0.0035193102,0.00008155064,0.00005522534,0.020172024],"genre_scores_gemma":[0.9371318,0.00020472295,0.058691736,0.0006395547,0.0015292097,0.000479144,0.00010444517,0.00007312847,0.0011462233],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9843196,0.007984751,0.0023804798,0.0006951127,0.0022890575,0.002330984],"domain_scores_gemma":[0.9879731,0.0009823996,0.0020175693,0.00071159087,0.00537217,0.0029431614],"candidate_categories":["metaresearch","metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08701528,0.00057745527,0.0006823147,0.0015702151,0.0013880274,0.00093939295,0.0010233207,0.00062722625,0.0043994067],"category_scores_gemma":[0.00918734,0.00057259016,0.0004979591,0.0021649476,0.0009685875,0.0023947386,0.00004865199,0.0010308612,0.00014818305],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000053945798,0.00036733825,0.17766392,0.00007392025,0.0001463509,0.00004565362,0.11106018,0.005224754,0.00008282027,0.0058604493,0.0011797799,0.6982409],"study_design_scores_gemma":[0.0026349942,0.0021138757,0.6431869,0.00085175555,0.001259248,0.0008824984,0.017745117,0.18897116,0.00019940201,0.09370403,0.047738932,0.00071208127],"about_ca_topic_score_codex":0.30575317,"about_ca_topic_score_gemma":0.9079721,"teacher_disagreement_score":0.6975288,"about_ca_system_score_codex":0.014018771,"about_ca_system_score_gemma":0.12133292,"threshold_uncertainty_score":0.999912},"labels":[],"label_agreement":null},{"id":"W4366384488","doi":"10.3138/cjpe.0025.006","title":"Chronique d’une évaluation ratée","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Charter; Confusion; Transparency (behavior); Pluralism (philosophy); Valuation (finance); Management science; Engineering ethics; Political science; Arbitration; Public relations; Sociology; Law and economics; Epistemology; Business; Psychology; Law; Accounting; Economics; Engineering","score_opus":0.6502887605764812,"score_gpt":0.5430176093994878,"score_spread":0.10727115117699337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384488","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8935444,0.00084652175,0.013067436,0.0051350184,0.0033299832,0.0027886585,0.000008347454,0.000034925033,0.08124476],"genre_scores_gemma":[0.9883535,0.0000122812935,0.010697971,0.00022819887,0.00022380774,0.00007113505,0.000009473922,0.000011460957,0.00039220482],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9950197,0.00079285575,0.0011405223,0.00021139723,0.0025418177,0.00029373163],"domain_scores_gemma":[0.99367017,0.00014215155,0.00088814844,0.00035402415,0.004444869,0.0005006256],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.023800347,0.00013291463,0.00023765898,0.0008252805,0.00022954273,0.00026576186,0.0005366179,0.00009926945,0.011271434],"category_scores_gemma":[0.0026565166,0.00010262055,0.00015138682,0.0010776499,0.000109473425,0.0009565235,0.000010320622,0.00021636974,0.00029355646],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001898837,0.000049869897,0.018650042,0.0000023490459,0.00002415693,0.0000070270335,0.004517838,0.0004951057,0.000065365566,0.0012082695,0.0053834417,0.96957755],"study_design_scores_gemma":[0.0024752268,0.001967605,0.6582496,0.00009075103,0.0002436959,0.00016503205,0.0036682987,0.10537877,0.0014647237,0.11889352,0.10697034,0.00043242608],"about_ca_topic_score_codex":0.0016190053,"about_ca_topic_score_gemma":0.029167535,"teacher_disagreement_score":0.9691451,"about_ca_system_score_codex":0.00042073702,"about_ca_system_score_gemma":0.008149194,"threshold_uncertainty_score":0.99747366},"labels":[],"label_agreement":null},{"id":"W4366384492","doi":"10.3138/cjpe.0025.001","title":"Guest Editor’s Remarks: As I Recall—or How to take Advantage of Less-Than-Successful Evaluation Experiences","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Recall; Psychology; Cognitive psychology","score_opus":0.3693533046613303,"score_gpt":0.5143513771140032,"score_spread":0.14499807245267293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384492","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96599096,0.00059270125,0.0017402376,0.002872818,0.014851342,0.0031371352,0.00001689469,0.000018827744,0.01077911],"genre_scores_gemma":[0.98985374,0.000018544912,0.007176994,0.00017328386,0.002005881,0.00034110862,0.000016593414,0.000018397175,0.00039546908],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.990565,0.0012577509,0.0015365392,0.0004254547,0.0057732086,0.0004420552],"domain_scores_gemma":[0.988177,0.0003132763,0.001657329,0.0005817862,0.00840089,0.0008696899],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.027689371,0.00023812543,0.00046745734,0.001234518,0.00025356113,0.00041900552,0.0010792192,0.0001617174,0.0075989803],"category_scores_gemma":[0.011703657,0.00017279817,0.00018946294,0.0014896902,0.00023310709,0.0017238023,0.0000323687,0.00023977198,0.00009789646],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026795382,0.00016716571,0.025206354,0.000016729444,0.00006266917,0.000014707496,0.03195287,0.000337325,0.00021990415,0.00020262747,0.026700173,0.91485155],"study_design_scores_gemma":[0.0065136277,0.013552928,0.2091686,0.0010314867,0.0009292806,0.0002816917,0.38628814,0.051724404,0.010947675,0.014391521,0.30355367,0.0016169975],"about_ca_topic_score_codex":0.00095092686,"about_ca_topic_score_gemma":0.03613507,"teacher_disagreement_score":0.91323453,"about_ca_system_score_codex":0.0005020298,"about_ca_system_score_gemma":0.008927947,"threshold_uncertainty_score":0.9966905},"labels":[],"label_agreement":null},{"id":"W4366384499","doi":"10.3138/cjpe.0025.013","title":"Learning from Evaluation Misadventures: The Importance of Good Communication","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Variety (cybernetics); Relevance (law); Key (lock); Order (exchange); Quality (philosophy); Government (linguistics); Knowledge management; Process management; Management science; Computer science; Business; Psychology; Risk analysis (engineering); Engineering ethics; Political science; Engineering; Epistemology; Artificial intelligence; Computer security","score_opus":0.48907842534633805,"score_gpt":0.5126845869829371,"score_spread":0.02360616163659901,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384499","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98349124,0.0025646926,0.0005850393,0.0012642194,0.0005171812,0.0013148063,0.0000054768793,0.0000072129137,0.010250123],"genre_scores_gemma":[0.9965019,0.000036823123,0.003092759,0.00011166276,0.000082904095,0.00007113209,0.000033622448,0.000008825474,0.000060360253],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9934087,0.0020265,0.0012603165,0.0001719098,0.0029415176,0.00019107682],"domain_scores_gemma":[0.99181134,0.0004937689,0.0019261243,0.0005817923,0.0049822126,0.00020475488],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.030684248,0.00011319663,0.000223231,0.0003335026,0.00030044228,0.00014657735,0.00087194913,0.00008327534,0.006040428],"category_scores_gemma":[0.005285184,0.00007468922,0.00014619941,0.0006598761,0.00013360394,0.0006088484,0.000020293972,0.0003222617,0.000036457866],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027685037,0.00005768621,0.2747269,0.0000022461184,0.00006027301,7.164481e-7,0.011284951,0.003020111,0.00005550102,0.00077290856,0.0009532202,0.7090378],"study_design_scores_gemma":[0.0014042839,0.00064076704,0.76617485,0.0001024008,0.00037007313,0.000013253682,0.01257116,0.13405116,0.00048473835,0.06894502,0.015067846,0.00017444162],"about_ca_topic_score_codex":0.0016906819,"about_ca_topic_score_gemma":0.032220334,"teacher_disagreement_score":0.7088634,"about_ca_system_score_codex":0.0002780368,"about_ca_system_score_gemma":0.0035901815,"threshold_uncertainty_score":0.9981145},"labels":[],"label_agreement":null},{"id":"W4366384617","doi":"10.3138/cjpe.0025.003","title":"Evaluation, Valuation, Negotiation: Some Reflections Towards a Culture of Evaluation","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Negotiation; Valuation (finance); Consolidation (business); Contingent valuation; Program evaluation; Management science; Political science; Process management; Business; Knowledge management; Computer science; Economics; Public administration; Willingness to pay; Accounting","score_opus":0.6159822124301794,"score_gpt":0.5735759694267458,"score_spread":0.04240624300343354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384617","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7571459,0.013092341,0.0255772,0.0061448347,0.015654394,0.022472931,0.00012999165,0.00013604909,0.15964638],"genre_scores_gemma":[0.98851514,0.00004180587,0.010029952,0.00019061402,0.000492281,0.00044803473,0.00008195639,0.000025001678,0.00017523066],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98073864,0.0037310813,0.0027534482,0.0004962781,0.011823661,0.00045687507],"domain_scores_gemma":[0.952684,0.00018241446,0.0027084446,0.00074367144,0.043093164,0.000588345],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.084139585,0.0002980059,0.0005269877,0.0018469035,0.00048239797,0.00030166726,0.0007405121,0.00025791215,0.013526122],"category_scores_gemma":[0.017272515,0.00024422017,0.00035541272,0.0025193298,0.00022097465,0.0024763579,0.000026486015,0.0003747576,0.00012852564],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050102288,0.00025008636,0.007004163,0.000011327901,0.00021077014,0.0000018447244,0.019618278,0.009565724,0.00022206994,0.0029501845,0.0055449395,0.95457053],"study_design_scores_gemma":[0.0050906944,0.0022925148,0.2550907,0.00016989544,0.00279909,0.00012905415,0.009465184,0.36409116,0.0020537106,0.3386957,0.0195192,0.0006030861],"about_ca_topic_score_codex":0.0011059708,"about_ca_topic_score_gemma":0.011632577,"teacher_disagreement_score":0.95396745,"about_ca_system_score_codex":0.0015798485,"about_ca_system_score_gemma":0.025886485,"threshold_uncertainty_score":0.9959009},"labels":[],"label_agreement":null},{"id":"W4366384635","doi":"10.3138/cjpe.0025.014","title":"Reflections Over 25 Years: Evaluation Then, Now, and Into the Future","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Political science","score_opus":0.390329876993874,"score_gpt":0.5523569994362977,"score_spread":0.16202712244242368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384635","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9777834,0.0024265065,0.00039012806,0.0044446685,0.0023291882,0.0016430827,0.0000034436996,0.000011891012,0.010967724],"genre_scores_gemma":[0.9960481,0.000062631356,0.0028075576,0.00035817543,0.00047841747,0.00008940808,0.0000054825705,0.000009188659,0.0001410713],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99573195,0.00089868746,0.0006725783,0.00019751543,0.0022947558,0.00020448738],"domain_scores_gemma":[0.99584407,0.00014339578,0.0005617092,0.00034085737,0.0028146305,0.0002953543],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.021562753,0.00011052439,0.00015385001,0.0005075449,0.00037114622,0.00036264912,0.00039681574,0.00008925428,0.0043801377],"category_scores_gemma":[0.0011892116,0.00006999607,0.000092359754,0.0007801391,0.00013503843,0.00072832586,0.000016060825,0.00025247628,0.00007182585],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012778564,0.00002482437,0.016900415,0.0000013679336,0.000027401305,0.0000013801549,0.013927299,0.00010255013,0.000026614523,0.00080100907,0.004039551,0.9641348],"study_design_scores_gemma":[0.00084608333,0.0004277351,0.7497673,0.000025108931,0.00020213812,0.000043633005,0.0068784496,0.023637976,0.000034849894,0.051822532,0.16618027,0.00013390533],"about_ca_topic_score_codex":0.00062795356,"about_ca_topic_score_gemma":0.08852159,"teacher_disagreement_score":0.9640009,"about_ca_system_score_codex":0.000316314,"about_ca_system_score_gemma":0.0032836727,"threshold_uncertainty_score":0.99653},"labels":[],"label_agreement":null},{"id":"W4366384698","doi":"10.3138/cjpe.0025.005","title":"Successful Evaluation Management: Engaging Mind and Spirit","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Outcome (game theory); Quality (philosophy); Affect (linguistics); Psychology; Key (lock); Evaluation methods; Engineering ethics; Business; Process management; Public relations; Computer science; Political science; Epistemology; Engineering; Philosophy; Economics","score_opus":0.5238099666472505,"score_gpt":0.5252574195694363,"score_spread":0.0014474529221857324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384698","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94864225,0.0010190253,0.0011883726,0.0010639961,0.0009906779,0.0017417334,0.0000038020132,0.000007345458,0.045342803],"genre_scores_gemma":[0.990713,0.00002124864,0.008821833,0.0001159107,0.00011244835,0.00006720421,0.000007328913,0.000009397293,0.00013163085],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9949167,0.00079630874,0.0009348377,0.00026305995,0.0028062174,0.0002828804],"domain_scores_gemma":[0.99545974,0.0001189463,0.00069718354,0.0002906614,0.0029792439,0.00045420136],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.031249056,0.0001352096,0.00020522413,0.0010376524,0.0002877122,0.00040984538,0.00040416172,0.00006920767,0.007722329],"category_scores_gemma":[0.0013045293,0.00011036064,0.000083074425,0.00070881046,0.00010995297,0.001061169,0.000020376203,0.00019239313,0.00009293137],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011326739,0.000025531308,0.055941585,0.000004552759,0.000031895855,0.0000065947606,0.0023895504,0.00013846744,0.0000065183635,0.00048175242,0.00048376634,0.94047844],"study_design_scores_gemma":[0.0031388227,0.0007003672,0.723285,0.00014295791,0.00064918376,0.00012143422,0.011445577,0.15508203,0.0002752786,0.046666272,0.05810463,0.0003884111],"about_ca_topic_score_codex":0.00031433234,"about_ca_topic_score_gemma":0.0067791953,"teacher_disagreement_score":0.94009006,"about_ca_system_score_codex":0.0002800931,"about_ca_system_score_gemma":0.0017502793,"threshold_uncertainty_score":0.99753296},"labels":[],"label_agreement":null},{"id":"W4366384728","doi":"10.3138/cjpe.0025.009","title":"Navigating Expectations, Values and Context: A Canadian Evaluator Abroad","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Politics; Political science; Psychology; Public relations; Sociology; History; Law; Archaeology","score_opus":0.3205900033941147,"score_gpt":0.530989583284331,"score_spread":0.2103995798902163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384728","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9874447,0.0028605787,0.0002278511,0.0016681186,0.0009523461,0.0012189492,0.000015620048,0.000012816902,0.0055990284],"genre_scores_gemma":[0.99327075,0.00001467131,0.0060396637,0.0003456643,0.00014284928,0.00008025703,0.000009846634,0.000014039881,0.00008226998],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.995653,0.00071004237,0.0010906088,0.00026697386,0.0018717363,0.00040767086],"domain_scores_gemma":[0.9936472,0.00022053043,0.0007116297,0.0002950145,0.0038179809,0.0013075995],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.013024749,0.00016441217,0.00027770226,0.0005661823,0.00049653376,0.00044517982,0.0004304566,0.00010286165,0.0044950154],"category_scores_gemma":[0.004216396,0.00013539844,0.00010761699,0.00069884537,0.00017052445,0.0009318901,0.000011174412,0.00032902227,0.00012051237],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000087161425,0.000016922211,0.055688,0.0000026273533,0.000028976536,0.000009616746,0.017410642,0.00003589058,0.000009383557,0.00035530922,0.001770074,0.92466384],"study_design_scores_gemma":[0.0040832893,0.0022009523,0.64523643,0.00046204164,0.00049607205,0.00045366012,0.1087494,0.11248974,0.00051332556,0.08099003,0.043389127,0.0009359333],"about_ca_topic_score_codex":0.07461027,"about_ca_topic_score_gemma":0.63902986,"teacher_disagreement_score":0.9237279,"about_ca_system_score_codex":0.00055274664,"about_ca_system_score_gemma":0.009426222,"threshold_uncertainty_score":0.996415},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"design_other","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W4366446537","doi":"10.3138/cjpe.24.009","title":"Michael Quinn Patton. (2008). <i>Utilization-Focused Evaluation</i> (4 <sup>e</sup> éd.). Thousand Oaks, CA: Sage. 667 Pages.","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"SAGE; Gerontology; Physics; Nuclear physics; Medicine","score_opus":0.20132387130639365,"score_gpt":0.45162505319901114,"score_spread":0.2503011818926175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366446537","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8824575,0.022665333,0.020506913,0.037071336,0.005220027,0.011583896,0.00016435553,0.00015495805,0.020175677],"genre_scores_gemma":[0.9931004,0.00024524887,0.0036346042,0.001420443,0.000624635,0.0001297323,0.00014666343,0.000032255655,0.0006659854],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98778033,0.0019061469,0.0022799196,0.0006041366,0.0066646575,0.00076477823],"domain_scores_gemma":[0.98788613,0.00044159405,0.001530346,0.0008137083,0.008239373,0.0010888225],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03191987,0.00039595205,0.00060690666,0.0014356202,0.00069326,0.0010990578,0.001013333,0.00026598322,0.00915054],"category_scores_gemma":[0.0060430756,0.00032776254,0.00031539428,0.002177897,0.0001805763,0.001683839,0.000022069748,0.00049634086,0.00033214752],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035248187,0.0001258872,0.0063682115,0.0000051705547,0.000050064977,0.000011687961,0.0019941726,0.041204456,0.00004698317,0.00015424102,0.04980158,0.9002023],"study_design_scores_gemma":[0.0046261833,0.0012286681,0.09148887,0.00018307047,0.0005108892,0.000121605604,0.0024361294,0.6637795,0.000236296,0.017164534,0.2175931,0.00063115545],"about_ca_topic_score_codex":0.00029313672,"about_ca_topic_score_gemma":0.008708686,"teacher_disagreement_score":0.8995711,"about_ca_system_score_codex":0.0010547637,"about_ca_system_score_gemma":0.011894179,"threshold_uncertainty_score":0.9999379},"labels":[],"label_agreement":null},{"id":"W4366446575","doi":"10.3138/cjpe.023.007","title":"Reconnecting Knowledge Utilization and Evaluation Utilization Domains of Inquiry","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa; Social Sciences and Humanities Research Council","funders":"","keywords":"Situated; Variety (cybernetics); Context (archaeology); Domain (mathematical analysis); Knowledge management; Epistemology; Cognate; Thematic analysis; Sociology; Psychology; Computer science; Qualitative research; Social science; Geography; Artificial intelligence; Philosophy; Mathematics","score_opus":0.7789619921436738,"score_gpt":0.5916862318486936,"score_spread":0.18727576029498016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366446575","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98786736,0.0022629471,0.003974179,0.0003226426,0.0010889069,0.0012686136,0.000003991852,0.000009402376,0.003201985],"genre_scores_gemma":[0.9968048,0.00013134125,0.0026757193,0.000040081955,0.00020710376,0.00004632295,0.00003024204,0.000012361341,0.00005203797],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9945815,0.001236237,0.0014098736,0.00026086968,0.0022785775,0.00023292513],"domain_scores_gemma":[0.98985136,0.00042428923,0.0013451007,0.00027348552,0.00777777,0.00032800497],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.023362968,0.00014344169,0.0003056074,0.0011452074,0.00037940734,0.00015196898,0.00026402684,0.00012198122,0.0011540637],"category_scores_gemma":[0.007597326,0.00012314481,0.00009824011,0.0013004254,0.00020838852,0.0010347051,0.000016170174,0.00015774976,0.000018207824],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019136538,0.000056130284,0.053160414,0.000010776373,0.000023803457,0.0000012755816,0.008010616,0.0020364812,0.00009891672,0.00049832417,0.0007450093,0.9353391],"study_design_scores_gemma":[0.0024854962,0.0007956948,0.43190527,0.00014558849,0.00022373065,0.00017913748,0.005467159,0.5316531,0.0008522536,0.010611736,0.015435747,0.00024507853],"about_ca_topic_score_codex":0.00015042388,"about_ca_topic_score_gemma":0.0053326604,"teacher_disagreement_score":0.93509406,"about_ca_system_score_codex":0.0003975362,"about_ca_system_score_gemma":0.005771321,"threshold_uncertainty_score":0.99986506},"labels":[],"label_agreement":null},{"id":"W4366446952","doi":"10.3138/cjpe.28.008","title":"Barbier, J. C., &amp; Hawkins, P. (Eds.). (2012). <i>Evaluation Cultures: Sense-making in Complex Times.</i>","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sense (electronics); Psychology; Sociology; Chemistry; Physical chemistry","score_opus":0.3467359600038095,"score_gpt":0.5222283353461814,"score_spread":0.1754923753423719,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366446952","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.890911,0.009044093,0.0036325187,0.018225538,0.0037250437,0.011682485,0.000033817938,0.00006953339,0.06267596],"genre_scores_gemma":[0.99037856,0.000047226138,0.0074820463,0.0009476631,0.00030047266,0.00023431328,0.00008366287,0.000021101829,0.00050497736],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99110854,0.0016446877,0.0017813782,0.0003853763,0.004520143,0.00055989815],"domain_scores_gemma":[0.99094945,0.000329469,0.0011702903,0.00051850436,0.0064795995,0.00055267854],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.025100403,0.00024684813,0.00042468886,0.0013299672,0.0003297133,0.001008863,0.0005671851,0.00016810292,0.03015934],"category_scores_gemma":[0.004422703,0.00019553713,0.00018462173,0.0014355406,0.00012875973,0.0019604736,0.000025206105,0.0004255268,0.001113294],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012662311,0.00006953298,0.01051447,0.0000061548058,0.00002768305,0.000004403989,0.0017406514,0.0076662735,0.00023276,0.00023381296,0.08814576,0.89134586],"study_design_scores_gemma":[0.0024912476,0.0002987219,0.22042426,0.00014774279,0.00013894273,0.0001242078,0.0016217364,0.23508134,0.00004077086,0.02743776,0.5117676,0.00042564413],"about_ca_topic_score_codex":0.0016681252,"about_ca_topic_score_gemma":0.07341417,"teacher_disagreement_score":0.89092016,"about_ca_system_score_codex":0.00089136517,"about_ca_system_score_gemma":0.005445173,"threshold_uncertainty_score":0.9996644},"labels":[],"label_agreement":null},{"id":"W4366447009","doi":"10.3138/cjpe.022.007","title":"Considérations théoriques et méthodologiques lors de l’évaluation de programmes d’intervention de crise","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Confusion; Valuation (finance); Psychology; Intervention (counseling); Crisis intervention; Applied psychology; Social psychology; Business; Psychoanalysis; Psychiatry; Finance","score_opus":0.4661128635653234,"score_gpt":0.5942212119329685,"score_spread":0.12810834836764512,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366447009","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7502248,0.00046878294,0.24016541,0.004241486,0.00047388845,0.0011887127,0.0000058589994,0.000041591935,0.0031894124],"genre_scores_gemma":[0.8910345,0.000048838538,0.10784513,0.0005338902,0.00023311595,0.00009420695,0.000025195415,0.000014805191,0.00017032838],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9923487,0.0036522497,0.0013958295,0.00024546753,0.0017631202,0.00059465057],"domain_scores_gemma":[0.9931828,0.0010182912,0.0010430568,0.00027545152,0.0038338862,0.0006465645],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12513782,0.00016945865,0.00026157586,0.000986108,0.00028954627,0.0007051828,0.0004180031,0.00018950799,0.0009236758],"category_scores_gemma":[0.013854074,0.00014499466,0.00024234153,0.0007409345,0.00015803573,0.00097084953,0.000014304237,0.0003748124,0.00002582193],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046726334,0.0001235778,0.09658396,0.000008436649,0.00003951263,0.000014727149,0.0058071627,0.0030167173,0.00028987633,0.0031931628,0.003267374,0.88760877],"study_design_scores_gemma":[0.0023685468,0.002356587,0.5491494,0.00024788541,0.00035685138,0.000474902,0.015881876,0.11557038,0.0048331786,0.2619573,0.046317715,0.00048540148],"about_ca_topic_score_codex":0.0015374384,"about_ca_topic_score_gemma":0.07232608,"teacher_disagreement_score":0.88712335,"about_ca_system_score_codex":0.0013150093,"about_ca_system_score_gemma":0.011105989,"threshold_uncertainty_score":0.9999896},"labels":[],"label_agreement":null},{"id":"W4366447032","doi":"10.3138/cjpe.0022.009","title":"La comparabilité des échantillons dans les enquêtes de l’international association for the evaluation of educational achievement","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Association (psychology); Perspective (graphical); Educational research; Student achievement; Psychology; Pedagogy; Mathematics education; Sociology; Academic achievement; Political science; Mathematics","score_opus":0.4409650328077531,"score_gpt":0.5430028838125461,"score_spread":0.10203785100479301,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366447032","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98274577,0.000656489,0.0040312954,0.0068218973,0.00078081194,0.0016272947,0.00003777118,0.0000039365823,0.0032947408],"genre_scores_gemma":[0.9951145,0.000047563302,0.0039399615,0.00005147524,0.00023527768,0.0003163211,0.000033055552,0.00000831917,0.00025349317],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9939507,0.0011455546,0.0009798344,0.0001681464,0.0035243265,0.00023142743],"domain_scores_gemma":[0.986644,0.0026251895,0.0012203977,0.00021128192,0.009122533,0.00017654683],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03810959,0.000110980465,0.00018871558,0.00040046315,0.00053160253,0.00015047964,0.00054584537,0.000088683,0.0013503319],"category_scores_gemma":[0.013222459,0.00007917223,0.0001953795,0.00042619833,0.0002155907,0.0004167692,0.000011673389,0.00015309358,0.000008525287],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032792723,0.000179202,0.6268654,0.0000069415114,0.00014492197,2.1572475e-7,0.0069275666,0.029002216,0.0002094722,0.00158445,0.0026207382,0.33242607],"study_design_scores_gemma":[0.0011200599,0.00016384572,0.7661241,0.000030743555,0.00022040858,0.00003034867,0.0023019288,0.19517687,0.00029191785,0.013985945,0.020471377,0.00008240715],"about_ca_topic_score_codex":0.00073913834,"about_ca_topic_score_gemma":0.018809289,"teacher_disagreement_score":0.33234367,"about_ca_system_score_codex":0.0018120845,"about_ca_system_score_gemma":0.008648986,"threshold_uncertainty_score":0.99956256},"labels":[],"label_agreement":null},{"id":"W4366447033","doi":"10.3138/cjpe.020.001","title":"Un état des lieux théoriques de l’évaluation: une discipline à la remorque d’une révolution scientifique qui n’en finit pas","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"École Nationale d'Administration Publique","funders":"","keywords":"Schism; Epistemology; Sociology; Acknowledgement; Scientific revolution; Valuation (finance); Humanities; Philosophy; Political science; Law; Economics","score_opus":0.2405922775106585,"score_gpt":0.48362414033165124,"score_spread":0.24303186282099273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366447033","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93495184,0.0013585632,0.018778054,0.031574532,0.0007581407,0.0013564056,0.00001652226,0.000040365336,0.01116558],"genre_scores_gemma":[0.96491325,0.00013783242,0.032994382,0.00029223974,0.0006395678,0.00009330681,0.000038687453,0.00002050412,0.00087025255],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9929368,0.001980242,0.0013899991,0.00036784736,0.0028217009,0.0005034014],"domain_scores_gemma":[0.99297756,0.0006503906,0.0009064129,0.00043289573,0.0043586227,0.00067410874],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03915531,0.00022130311,0.0003235284,0.00089420547,0.0006642426,0.0008538562,0.00066774135,0.00017922895,0.0017802184],"category_scores_gemma":[0.005149105,0.00017879924,0.00019988368,0.0020973163,0.0003391494,0.0013825836,0.000031037776,0.00038529208,0.000111399815],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025836218,0.00009012124,0.014190555,0.0000080819855,0.00003055092,0.000008060877,0.006084208,0.016877573,0.0002086561,0.001254176,0.003478124,0.95774406],"study_design_scores_gemma":[0.0022369358,0.00066463463,0.32789552,0.0002889699,0.00024548318,0.00031733664,0.004164377,0.3402348,0.0012951802,0.1379523,0.18422927,0.0004752057],"about_ca_topic_score_codex":0.0010323654,"about_ca_topic_score_gemma":0.0756707,"teacher_disagreement_score":0.95726883,"about_ca_system_score_codex":0.001263826,"about_ca_system_score_gemma":0.0077701504,"threshold_uncertainty_score":0.9991323},"labels":[],"label_agreement":null},{"id":"W4366447375","doi":"10.3138/cjpe.021.008","title":"Impacts du pirs en milieu scolaire","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Psychology; Reading (process); Scale (ratio); Medical education; Mathematics education; Pedagogy; Geography; Political science; Medicine; Cartography","score_opus":0.18663340726645056,"score_gpt":0.48755375552323066,"score_spread":0.3009203482567801,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366447375","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98582083,0.0007738388,0.00056280626,0.0049668597,0.00096331927,0.0007553344,0.000005617515,0.000010859326,0.006140509],"genre_scores_gemma":[0.996891,0.00000863511,0.0021549996,0.00021544598,0.0005306771,0.00002711967,0.00001183283,0.000009630752,0.00015061993],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9955572,0.0005637048,0.0009708445,0.00017502479,0.0024245153,0.00030870998],"domain_scores_gemma":[0.99587786,0.00023630737,0.0006440374,0.00025581458,0.002523218,0.0004627605],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01610037,0.0001227152,0.00021557084,0.0007321568,0.00024566875,0.0005024636,0.00046145674,0.00008613459,0.0026376273],"category_scores_gemma":[0.002480204,0.00009275004,0.00014508964,0.00079132064,0.00007664936,0.0007993436,0.000009565932,0.00018424145,0.0001913195],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015300146,0.000059138274,0.23766205,0.0000038510398,0.00001855533,0.00001624497,0.0011222839,0.006032993,0.00010479349,0.00059428,0.024625493,0.72974503],"study_design_scores_gemma":[0.0011908778,0.0005031454,0.855973,0.0000518567,0.00007542063,0.00010528341,0.0010574494,0.035196174,0.00021191961,0.012529869,0.09292638,0.00017860248],"about_ca_topic_score_codex":0.0034381656,"about_ca_topic_score_gemma":0.12478558,"teacher_disagreement_score":0.7295664,"about_ca_system_score_codex":0.00051958725,"about_ca_system_score_gemma":0.0061470866,"threshold_uncertainty_score":0.99948716},"labels":[],"label_agreement":null},{"id":"W4366447855","doi":"10.3138/cjpe.20.009","title":"How Can Information About the Competencies Required for Evaluation Be Useful?","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Accreditation; Certification; Medical education; Psychology; Thematic analysis; Knowledge management; Engineering ethics; Computer science; Political science; Medicine; Sociology; Engineering; Qualitative research","score_opus":0.407391146677462,"score_gpt":0.4961895575741692,"score_spread":0.0887984108967072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366447855","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69728875,0.0018489175,0.01582069,0.26389745,0.003857742,0.011784176,0.00013278083,0.00004498548,0.0053245397],"genre_scores_gemma":[0.9919239,0.000014576266,0.0053978823,0.001403885,0.0005026566,0.00040411906,0.000092220536,0.000009385327,0.00025132377],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9938718,0.00070240686,0.0011495911,0.00016770305,0.0037492248,0.0003592789],"domain_scores_gemma":[0.9897866,0.0004757538,0.00137183,0.00041049384,0.007614833,0.00034048432],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.026919512,0.00016209397,0.00024189326,0.00067919894,0.0006229107,0.0017699337,0.0006925385,0.00009899083,0.0006325649],"category_scores_gemma":[0.0070977705,0.00010441929,0.00019578543,0.00074900774,0.00014527369,0.002969915,0.000013002199,0.00018972933,0.000022814751],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022191141,0.000015836522,0.0022079414,0.0000040593222,0.000028374237,1.3106181e-7,0.0035174964,0.0077982517,0.000024982804,0.0012448564,0.009809147,0.9753267],"study_design_scores_gemma":[0.0018014271,0.00036949004,0.032022696,0.000028321794,0.00017210706,0.000022612492,0.004931949,0.35170645,0.00016741609,0.0055781677,0.60305125,0.00014815206],"about_ca_topic_score_codex":0.00013714534,"about_ca_topic_score_gemma":0.026750227,"teacher_disagreement_score":0.9751786,"about_ca_system_score_codex":0.0006899135,"about_ca_system_score_gemma":0.006721322,"threshold_uncertainty_score":0.9992663},"labels":[],"label_agreement":null},{"id":"W4366448017","doi":"10.3138/cjpe.22.002","title":"Collaborative Evaluation in a Community Change Initiative: Dilemmas of Control Over Technical Decision Making","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Control (management); Process (computing); Dimension (graph theory); Work (physics); Meaning (existential); Process management; Knowledge management; Management science; Computer science; Sociology; Public relations; Political science; Psychology; Business; Engineering","score_opus":0.3796100750810484,"score_gpt":0.568284039236673,"score_spread":0.18867396415562465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366448017","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98446304,0.0006512589,0.00805053,0.000495675,0.0005645411,0.0030920687,0.000025558566,0.000006605586,0.002650707],"genre_scores_gemma":[0.9951327,0.00000829743,0.004318028,0.00026387585,0.00012547283,0.00012629699,0.000012371552,0.000010551272,0.000002435352],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9903293,0.002917317,0.0019855993,0.0001980279,0.0042132386,0.000356515],"domain_scores_gemma":[0.9873325,0.0024564792,0.0016269127,0.00038006096,0.007923323,0.00028067175],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09480893,0.00016198223,0.00043719937,0.0018065335,0.00023105215,0.00016362696,0.0005502667,0.00017497323,0.0014002124],"category_scores_gemma":[0.014924889,0.00013261542,0.00012425538,0.0024774082,0.00017918134,0.0010774138,0.000023734394,0.0005835519,0.0000118651915],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019070909,0.00014220795,0.13732606,0.000005194037,0.000019423582,0.000005534035,0.004216906,0.0012076118,0.00010154469,0.0002887101,0.00029549163,0.85620064],"study_design_scores_gemma":[0.0033066943,0.0008663366,0.93432635,0.00031205203,0.000095551666,0.000016201802,0.0037793608,0.04055121,0.00008369236,0.014774297,0.0017426804,0.00014559703],"about_ca_topic_score_codex":0.00062424195,"about_ca_topic_score_gemma":0.146796,"teacher_disagreement_score":0.856055,"about_ca_system_score_codex":0.0012261871,"about_ca_system_score_gemma":0.0049884254,"threshold_uncertainty_score":0.9995127},"labels":[],"label_agreement":null},{"id":"W4366448066","doi":"10.3138/cjpe.026.007","title":"Stake, R. E. (2010). <i>Qualitative Research: Studying How Things Work.</i> New York, NY: Guilford Press. 244 pages.","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sociology; Work (physics); Media studies; Engineering; Mechanical engineering","score_opus":0.9420309666332343,"score_gpt":0.5946086491900977,"score_spread":0.34742231744313656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366448066","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6655935,0.03326553,0.024495166,0.072200365,0.016077714,0.020529706,0.00007102297,0.00022733344,0.16753964],"genre_scores_gemma":[0.9724773,0.000086737855,0.020590203,0.0004444065,0.0004422494,0.00012214975,0.000012034285,0.000033572407,0.0057913535],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98793954,0.003571084,0.0012968077,0.00043826734,0.0059971116,0.0007572009],"domain_scores_gemma":[0.98901784,0.000992142,0.0011957573,0.0006442399,0.006907349,0.001242693],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07296109,0.00022942669,0.00041806087,0.001186101,0.00054623745,0.0012344558,0.001291025,0.00015369545,0.00280443],"category_scores_gemma":[0.011022671,0.00017577002,0.00019539145,0.001870133,0.00027942672,0.0020911426,0.000052071886,0.00082420884,0.0001554745],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056181736,0.00006455366,0.0033407356,0.000005376372,0.00006198808,0.000011603741,0.07592668,0.00009117483,0.000009840199,0.0005728257,0.2060902,0.71376884],"study_design_scores_gemma":[0.0032753171,0.0026612196,0.039209977,0.0003692451,0.0002399041,0.000043369542,0.10835056,0.0052697198,0.00037931552,0.06086,0.77868474,0.00065666443],"about_ca_topic_score_codex":0.0030411493,"about_ca_topic_score_gemma":0.014746446,"teacher_disagreement_score":0.7131122,"about_ca_system_score_codex":0.00061057415,"about_ca_system_score_gemma":0.008502355,"threshold_uncertainty_score":0.99980235},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"opus","categories":["metaresearch"],"domain":"methods","study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W4366448126","doi":"10.3138/cjpe.0027.005","title":"The Paris Declaration Evaluation Process and Methods","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Declaration; Process (computing); Process management; Engineering ethics; Corporate governance; Quality (philosophy); Perspective (graphical); Management science; Political science; Computer science; Business; Engineering; Epistemology; Law","score_opus":0.42934184573180173,"score_gpt":0.6085040427500894,"score_spread":0.17916219701828767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366448126","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.950446,0.0050000614,0.01291034,0.01733658,0.0017945153,0.0057053566,0.0000022623208,0.000016158212,0.006788692],"genre_scores_gemma":[0.9897284,0.000046567468,0.00934705,0.00017106657,0.00015084012,0.00041668522,0.0000065580593,0.00000819201,0.00012464901],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9937469,0.0020278068,0.0010002991,0.00020121073,0.0027631328,0.00026065484],"domain_scores_gemma":[0.98896545,0.00076119584,0.00085853075,0.00028207563,0.008744044,0.00038871696],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.051660173,0.00011662649,0.00017835958,0.00037005957,0.00063965167,0.0014448732,0.00037007724,0.00008340405,0.0018569787],"category_scores_gemma":[0.008005951,0.000069990536,0.00007067515,0.00069412106,0.00013955767,0.001312132,0.000010351428,0.00020131063,0.00007098776],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000044124627,0.000009814838,0.010643428,0.0000017143999,0.000016341683,1.5584607e-7,0.0008978848,0.000979886,0.00004133323,0.0002456071,0.0026659644,0.98449343],"study_design_scores_gemma":[0.0008162277,0.00035241127,0.20226845,0.000024779374,0.00014489579,0.000035598685,0.0037700376,0.64684963,0.00023753478,0.106069684,0.039284926,0.00014579513],"about_ca_topic_score_codex":0.00042549727,"about_ca_topic_score_gemma":0.0068227253,"teacher_disagreement_score":0.98434764,"about_ca_system_score_codex":0.00027755141,"about_ca_system_score_gemma":0.0046030646,"threshold_uncertainty_score":0.9995917},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W4366448430","doi":"10.3138/cjpe.23.013","title":"M.J. Bamberger, J. Rugh, and L. Mabry. (2006). <i>RealWorld Evaluation: Working Under Budget, Time, Data, and Political Constraints.</i> Thousand Oaks, CA: Sage.","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"SAGE; Politics; Psychology; Gerontology; Political science; Medicine; Physics; Law","score_opus":0.21413066728362704,"score_gpt":0.45988540608889716,"score_spread":0.24575473880527013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366448430","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.904419,0.01873856,0.0060462425,0.028508164,0.0038837784,0.005995408,0.0003782584,0.00012619724,0.03190436],"genre_scores_gemma":[0.9943982,0.00011285202,0.003618263,0.00082815107,0.00039705096,0.000037103004,0.0000793087,0.000029496314,0.0004996059],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9933903,0.0011360955,0.0012069136,0.0004994839,0.003186394,0.00058080285],"domain_scores_gemma":[0.99488896,0.00072804256,0.0006336538,0.00057744543,0.0020690127,0.0011028607],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.021674497,0.00023774376,0.00041862464,0.0006490992,0.00060012675,0.0006167089,0.000491778,0.00013826256,0.002856594],"category_scores_gemma":[0.0026188337,0.00019714773,0.000073229996,0.0006974121,0.00071756623,0.0009914035,0.00006577424,0.00036124076,0.00008281536],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033879074,0.0000680417,0.050255366,0.000008051599,0.00009349023,0.00003512925,0.0005966114,0.00059747056,0.000028822516,0.0015762132,0.03242318,0.91428375],"study_design_scores_gemma":[0.0062636477,0.0006836988,0.18898977,0.00030442997,0.0008470583,0.0028013305,0.0035561733,0.46360582,0.000040305236,0.021893978,0.31013852,0.00087526644],"about_ca_topic_score_codex":0.00047936424,"about_ca_topic_score_gemma":0.006397446,"teacher_disagreement_score":0.91340846,"about_ca_system_score_codex":0.00042797092,"about_ca_system_score_gemma":0.007168343,"threshold_uncertainty_score":0.9984601},"labels":[{"model":"gpt","categories":["insufficient_payload"],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W4366448437","doi":"10.3138/cjpe.027.007","title":"Hesse-Biber, S. N. (2010). <i>Mixed Methods Research: Merging Theory with Practice.</i> New York, NY: Guilford. 242 Pages.","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Sociology","score_opus":0.7423552584982398,"score_gpt":0.6234861653502343,"score_spread":0.11886909314800553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366448437","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21720637,0.07417683,0.3241494,0.1129106,0.02761862,0.015184668,0.000037120255,0.00022601202,0.22849037],"genre_scores_gemma":[0.7572712,0.00010750014,0.23758951,0.00086002157,0.001276803,0.00012135512,0.000015969648,0.000049463968,0.002708213],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9839431,0.008096215,0.00129091,0.00034197338,0.0053501315,0.0009776425],"domain_scores_gemma":[0.9866231,0.003602004,0.0012592193,0.00073006627,0.00605758,0.0017280371],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1709859,0.00023078558,0.00040510483,0.0015161204,0.0005942101,0.00093280274,0.00092561514,0.00014769468,0.0034832638],"category_scores_gemma":[0.021923333,0.00015808671,0.00015393611,0.0023810267,0.0002552706,0.002885966,0.00004034897,0.0008345735,0.00023434343],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000089345966,0.00007486258,0.0035684227,0.0000044154804,0.00007971633,0.000005899375,0.003390273,0.00054397597,0.00006252079,0.0027584375,0.06667337,0.92274874],"study_design_scores_gemma":[0.001570656,0.0009150644,0.017183194,0.00011470898,0.00029202868,0.0002433921,0.014458935,0.004676933,0.00062802614,0.022082848,0.9375132,0.00032104683],"about_ca_topic_score_codex":0.0009806114,"about_ca_topic_score_gemma":0.007979186,"teacher_disagreement_score":0.9224277,"about_ca_system_score_codex":0.00070522743,"about_ca_system_score_gemma":0.012174797,"threshold_uncertainty_score":0.9974277},"labels":[],"label_agreement":null},{"id":"W4366448452","doi":"10.3138/cjpe.0021.017","title":"Les dispositifs de la participation aux étapes stratégiques de l’évaluation","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Deliberation; Participatory evaluation; Valuation (finance); Citizen journalism; Relevance (law); Knowledge management; Rationality; Process management; Sociology; Management science; Psychology; Business; Computer science; Political science; Engineering; Social science; Accounting","score_opus":0.4004949898556033,"score_gpt":0.5989514537971734,"score_spread":0.19845646394157013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366448452","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95347667,0.00024419662,0.035724,0.0010035201,0.0002574892,0.0005340303,0.0000030243684,0.000015063128,0.008741991],"genre_scores_gemma":[0.98895985,0.000013683033,0.010466863,0.00015486224,0.00022590489,0.00003867309,0.000012155456,0.000010750235,0.00011726812],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9950023,0.0014733023,0.0009981783,0.00017133405,0.0019508287,0.00040401582],"domain_scores_gemma":[0.9951497,0.00087730616,0.00065272156,0.0001965551,0.0025805756,0.00054315233],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.052756462,0.00012178185,0.00018057968,0.00065778644,0.0003202434,0.0005958475,0.00032031382,0.00014798272,0.0012107735],"category_scores_gemma":[0.00549432,0.00010141644,0.00011721548,0.0006023719,0.00013339247,0.0006866785,0.000007027856,0.00025137136,0.000023919178],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023594208,0.00004764537,0.122630484,0.0000030419394,0.000017395074,0.0000074049094,0.0033590868,0.0050287833,0.0003903994,0.0020173215,0.00050456135,0.86597025],"study_design_scores_gemma":[0.0006256153,0.00041823206,0.8728573,0.000046220368,0.0001159749,0.000052760846,0.0018230482,0.0803071,0.0013272121,0.0242128,0.018073505,0.00014024862],"about_ca_topic_score_codex":0.0018487063,"about_ca_topic_score_gemma":0.03816045,"teacher_disagreement_score":0.86583,"about_ca_system_score_codex":0.0009059088,"about_ca_system_score_gemma":0.0072425455,"threshold_uncertainty_score":0.9997023},"labels":[],"label_agreement":null},{"id":"W4366448482","doi":"10.3138/cjpe.020.005","title":"The Delphi Technique as a Method for Increasing Inclusion in the Evaluation Process","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":80,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Delphi method; Delphi; Compromise; Inclusion (mineral); Process (computing); Set (abstract data type); Evaluation methods; Psychology; Economic Justice; Representation (politics); Public relations; Management science; Sociology; Engineering ethics; Computer science; Social psychology; Political science; Engineering; Social science; Artificial intelligence; Law","score_opus":0.3689523270921288,"score_gpt":0.6178187315297932,"score_spread":0.2488664044376644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366448482","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7846106,0.003387119,0.07454904,0.103009254,0.0011375145,0.02417315,0.00001156022,0.000026485151,0.009095257],"genre_scores_gemma":[0.9740414,0.000011867147,0.023542747,0.000714045,0.0002856642,0.0013635232,0.000009716074,0.000010026166,0.000020979674],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9898994,0.003581483,0.0012876746,0.00023571022,0.0046421387,0.00035359806],"domain_scores_gemma":[0.991171,0.0021832504,0.0009108325,0.00034639132,0.0052075614,0.00018096682],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.18912262,0.00013084718,0.00018777214,0.00058867433,0.0012203808,0.0006664667,0.0010673276,0.00009939401,0.00026235828],"category_scores_gemma":[0.018750962,0.00007047594,0.00012574122,0.0011808376,0.00007494464,0.0007575926,0.000042325064,0.00028641446,0.000013384752],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052819392,0.000032205357,0.0008700857,0.0000027269846,0.000007951707,5.3794565e-7,0.0051557957,0.00598011,0.000082322214,0.0005739133,0.0005906152,0.98665094],"study_design_scores_gemma":[0.0015486518,0.00059616595,0.014405023,0.000093474795,0.00014049154,0.0001616433,0.0071220137,0.7008614,0.0004952725,0.18245977,0.09194803,0.00016806836],"about_ca_topic_score_codex":0.0006280525,"about_ca_topic_score_gemma":0.052134223,"teacher_disagreement_score":0.98648286,"about_ca_system_score_codex":0.0007672923,"about_ca_system_score_gemma":0.007992775,"threshold_uncertainty_score":0.997631},"labels":[],"label_agreement":null},{"id":"W4366448488","doi":"10.3138/cjpe.26.009","title":"M. Q. Patton. (2011). <i>Developmental Evaluation: Applying Complexity Concepts to Enhance Innovation and Use.</i> New York, NY: Guilford Press. 373 pages.","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Cognitive science; Psychology; Management; Economics","score_opus":0.692320291059202,"score_gpt":0.5156360293542,"score_spread":0.17668426170500195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366448488","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96868014,0.0012271354,0.009549137,0.002249229,0.0018825426,0.0062376442,0.000028145128,0.000036942933,0.010109069],"genre_scores_gemma":[0.9533579,0.000017868048,0.044813894,0.00077705923,0.00022396835,0.00026559414,0.000042973094,0.000018963523,0.00048180632],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99348074,0.0006549112,0.0016453872,0.0004538812,0.0033372063,0.0004278612],"domain_scores_gemma":[0.9921696,0.00020258164,0.0011366975,0.00035986063,0.005401112,0.0007301383],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017990474,0.0002441997,0.00036545872,0.0008254603,0.0003728295,0.00069144065,0.0005586009,0.000120846045,0.005665628],"category_scores_gemma":[0.003157468,0.00021283558,0.00007485494,0.001080999,0.00016575227,0.001549919,0.000047731653,0.00027389923,0.00014349728],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004337492,0.00004077497,0.01977017,0.000005437481,0.00003662194,0.0000023820987,0.005284006,0.0002387213,0.00013841985,0.000868277,0.02828813,0.9452837],"study_design_scores_gemma":[0.003319258,0.0014591237,0.49840778,0.00023838875,0.00032146022,0.00014811929,0.0058883284,0.034322795,0.003234188,0.026773646,0.42489854,0.0009883866],"about_ca_topic_score_codex":0.00241706,"about_ca_topic_score_gemma":0.018375183,"teacher_disagreement_score":0.9442953,"about_ca_system_score_codex":0.0007145877,"about_ca_system_score_gemma":0.007132832,"threshold_uncertainty_score":0.99953693},"labels":[],"label_agreement":null},{"id":"W4366448611","doi":"10.3138/cjpe.0028.010","title":"M&amp;E Competencies in Support of the AIDS Response: A Sector-Specific Example","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Human immunodeficiency virus (HIV); Service delivery framework; Process (computing); Business; Psychology; Service (business); Knowledge management; Nursing; Medical education; Public relations; Medicine; Political science; Marketing; Computer science; Family medicine","score_opus":0.4760414459172037,"score_gpt":0.4932620036647494,"score_spread":0.017220557747545717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366448611","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9942073,0.00014293655,0.0008660119,0.0020856322,0.0007786487,0.000570178,0.000005807888,0.0000032096966,0.0013402387],"genre_scores_gemma":[0.99632907,0.0000039372253,0.0030894116,0.0002114751,0.000083404564,0.00002199111,0.0000034001464,0.0000066392663,0.0002506496],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9944065,0.0018803481,0.00106552,0.00015844022,0.0022574388,0.00023171448],"domain_scores_gemma":[0.9959723,0.00070612814,0.00075694156,0.00043910637,0.0019107409,0.00021478995],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03626521,0.00009637344,0.000247046,0.00068157766,0.00012947278,0.00016226765,0.0006497186,0.00006209517,0.0030438309],"category_scores_gemma":[0.003958457,0.00006192355,0.00013147354,0.0011571392,0.00015707675,0.00031971576,0.000017524988,0.00020047453,0.00004373369],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001776641,0.000090296744,0.3135061,0.000008437475,0.000022228909,0.0000020260882,0.006921491,0.0052737026,0.0017072238,0.0035097508,0.016211884,0.6525692],"study_design_scores_gemma":[0.00074657775,0.00045813082,0.4774944,0.000030018462,0.000014938683,0.000021057638,0.00065434095,0.002585146,0.00017425662,0.0069126943,0.5108309,0.00007756926],"about_ca_topic_score_codex":0.00079256797,"about_ca_topic_score_gemma":0.050491903,"teacher_disagreement_score":0.6524916,"about_ca_system_score_codex":0.00030586417,"about_ca_system_score_gemma":0.0040325737,"threshold_uncertainty_score":0.9978675},"labels":[],"label_agreement":null},{"id":"W4366449208","doi":"10.3138/cjpe.23.011","title":"L’examen de la qualité des évaluations fédérales: une méta-évaluation réussie?","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université Laval","funders":"","keywords":"Credibility; Treasury; Valuation (finance); Quality (philosophy); Relevance (law); Political science; Psychology; Accounting; Business; Philosophy; Epistemology","score_opus":0.5449930809225783,"score_gpt":0.5670762013901169,"score_spread":0.022083120467538686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366449208","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97703487,0.0006864899,0.007699292,0.0020453508,0.0005022644,0.0010500642,0.000009870124,0.000026093589,0.010945709],"genre_scores_gemma":[0.9767848,0.0000854379,0.021909982,0.0002509445,0.00028621996,0.0001339614,0.000026651285,0.000020947255,0.00050101464],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99028695,0.0035844739,0.0015474121,0.0003034954,0.0037885157,0.0004891738],"domain_scores_gemma":[0.9924003,0.0011759577,0.0010394352,0.0004453339,0.004199058,0.0007398976],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04576758,0.00020679508,0.0003572161,0.0011258154,0.0008639415,0.0004803896,0.00063743803,0.00017297608,0.0028593522],"category_scores_gemma":[0.009944887,0.00017123614,0.0002373949,0.0018912675,0.0005705472,0.0011663187,0.000016936967,0.00035247664,0.0001788303],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022625592,0.000111475085,0.15262681,0.0000062310605,0.000057140274,0.000018702209,0.012367698,0.01413113,0.00014584317,0.0010799483,0.006209887,0.8132225],"study_design_scores_gemma":[0.0017461365,0.00055038463,0.78610677,0.00008264019,0.00018796697,0.000457292,0.003573942,0.097239666,0.0001757377,0.07249853,0.03709116,0.00028978937],"about_ca_topic_score_codex":0.0016626847,"about_ca_topic_score_gemma":0.013037832,"teacher_disagreement_score":0.8129327,"about_ca_system_score_codex":0.0010829445,"about_ca_system_score_gemma":0.01522051,"threshold_uncertainty_score":0.9983948},"labels":[],"label_agreement":null},{"id":"W4366449571","doi":"10.3138/cjpe.0022.005","title":"Design and Development Issues in Provincial Large-Scale Assessments: Designing Assessments to Inform Policy and Practice","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Accountability; Scale (ratio); Quality (philosophy); Key (lock); Management science; Engineering ethics; Political science; Psychology; Public relations; Computer science; Engineering","score_opus":0.4087057107089686,"score_gpt":0.5695313585263149,"score_spread":0.16082564781734626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366449571","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81436086,0.0006595979,0.1690318,0.0076364246,0.00049530435,0.0045701056,0.0000052085275,0.000019184437,0.003221522],"genre_scores_gemma":[0.621602,0.000046654535,0.3771822,0.0007204772,0.000119329416,0.00012922603,0.0000055584637,0.000011855274,0.00018273246],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9952442,0.000879843,0.00104136,0.00025872161,0.0021776666,0.0003982183],"domain_scores_gemma":[0.9960716,0.00059876236,0.00057806424,0.0001629941,0.0019803126,0.00060828077],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024467463,0.00015918746,0.00027754676,0.0013296533,0.00045440492,0.00046571982,0.0002554074,0.00008495163,0.00015613758],"category_scores_gemma":[0.0055237007,0.00013446283,0.000024519277,0.0010233357,0.000064510816,0.0019010013,0.000038620256,0.0002112392,0.000021489006],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011047111,0.00010889753,0.052884147,0.0000074442173,0.00003120242,0.00002623957,0.014529834,0.0023237835,0.00007129442,0.00012818647,0.000939897,0.9288386],"study_design_scores_gemma":[0.005258287,0.0029972505,0.5591237,0.000249765,0.00008926293,0.0006682501,0.018214123,0.074183196,0.0005553088,0.0019053782,0.33607885,0.00067663623],"about_ca_topic_score_codex":0.0006427153,"about_ca_topic_score_gemma":0.0094253635,"teacher_disagreement_score":0.928162,"about_ca_system_score_codex":0.000845706,"about_ca_system_score_gemma":0.013948,"threshold_uncertainty_score":0.991642},"labels":[],"label_agreement":null},{"id":"W4366449572","doi":"10.3138/cjpe.0021.004","title":"Will Evaluation Prosper in the Future?","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Professionalization; Accountability; Audit; Public sector; Public relations; Professional standards; Business; Political science; Accounting; Public administration; Sociology; Engineering ethics; Engineering; Law","score_opus":0.2834746849839425,"score_gpt":0.5446628427125925,"score_spread":0.26118815772864995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366449572","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9687702,0.0016732259,0.0014438792,0.011278585,0.0023290638,0.0031429587,0.000002553174,0.0000063701063,0.011353142],"genre_scores_gemma":[0.9971578,0.000009196498,0.001399246,0.00056762696,0.0007210475,0.00007129558,0.000009730231,0.000006992642,0.00005704399],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9916764,0.0011137711,0.0012524682,0.0002046903,0.005386578,0.00036609586],"domain_scores_gemma":[0.9943455,0.00035940556,0.00066826364,0.00035635135,0.0040091146,0.00026136075],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.11714514,0.0001185937,0.00018211913,0.00092324684,0.00020268478,0.000436083,0.00067307864,0.000094292525,0.002379502],"category_scores_gemma":[0.0029751614,0.000071731505,0.00011327069,0.0015456368,0.00007748537,0.0012468583,0.000006936251,0.00031129693,0.00006900783],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015853464,0.000042151627,0.06645361,0.0000013149817,0.0000072036523,0.000005767629,0.0027168037,0.0010149529,0.000013492368,0.0010845064,0.0021873643,0.926457],"study_design_scores_gemma":[0.0014098473,0.0003867812,0.7832654,0.000029043595,0.000076528704,0.0000784437,0.006737735,0.034609206,0.00003567822,0.026040548,0.14719115,0.00013959964],"about_ca_topic_score_codex":0.00022612646,"about_ca_topic_score_gemma":0.09114942,"teacher_disagreement_score":0.9263174,"about_ca_system_score_codex":0.00063521654,"about_ca_system_score_gemma":0.0048015546,"threshold_uncertainty_score":0.9985325},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W4366449591","doi":"10.3138/cjpe.023.006","title":"La méthode de cartographie conceptuelle pour identifier les priorités de recherche sur le transfert des connaissances en santé des populations : quelques enjeux méthodologiques","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"The Quebec Population Health Research Network; Université de Montréal","funders":"","keywords":"Identifier; Computer science","score_opus":0.9068279838512547,"score_gpt":0.6204096034709966,"score_spread":0.28641838038025813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366449591","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8815304,0.005372169,0.109715514,0.0009193147,0.00017146686,0.00058864267,0.000011282588,0.000036572612,0.0016546517],"genre_scores_gemma":[0.8179191,0.0006373817,0.18091984,0.00010286844,0.00013628723,0.00006832678,0.000008473242,0.000016261125,0.0001914708],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9843362,0.01271199,0.0010233617,0.00027496164,0.0011791354,0.00047437623],"domain_scores_gemma":[0.99320126,0.0023571465,0.00043031047,0.00025682192,0.0032329394,0.00052154064],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.054259103,0.00020185222,0.00035951962,0.00069342006,0.00080051355,0.00036039855,0.00056239683,0.00033361226,0.0010202867],"category_scores_gemma":[0.014397008,0.00016995834,0.00024909855,0.0009024695,0.00090804545,0.0010599027,0.00001198491,0.00057090685,0.000010733031],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029131248,0.00007929098,0.34200144,0.000015355628,0.00004599181,0.00002436864,0.0150999315,0.001489278,0.000768716,0.0025250013,0.0021020374,0.63581944],"study_design_scores_gemma":[0.0010533277,0.00036403607,0.68683904,0.0001675922,0.00012162423,0.00043288147,0.01015325,0.00913715,0.0023233038,0.2820655,0.0070633315,0.00027894863],"about_ca_topic_score_codex":0.00638996,"about_ca_topic_score_gemma":0.107361734,"teacher_disagreement_score":0.6355405,"about_ca_system_score_codex":0.0007861748,"about_ca_system_score_gemma":0.012733182,"threshold_uncertainty_score":0.9998929},"labels":[],"label_agreement":null},{"id":"W4366449610","doi":"10.3138/cjpe.22.001","title":"Methodological and Conceptual Challenges in Studying Evaluation Process Use","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Operationalization; Process (computing); Construct (python library); Context (archaeology); Exploratory research; Process management; Quality (philosophy); Knowledge management; Management science; Computer science; Qualitative research; Conceptual model; Scale (ratio); Psychology; Sociology; Epistemology; Business; Engineering","score_opus":0.9321012710267086,"score_gpt":0.6602703593788898,"score_spread":0.2718309116478188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366449610","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9922889,0.0023612245,0.0011440008,0.0013014884,0.0004129914,0.0013463072,0.0000013080796,0.0000058889173,0.0011379258],"genre_scores_gemma":[0.99450266,0.000069716974,0.005143095,0.00009718464,0.00011512822,0.00004966801,0.000003686429,0.000006676995,0.000012164578],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99299234,0.0020617822,0.0011976735,0.000296294,0.0031133401,0.00033857537],"domain_scores_gemma":[0.99331766,0.0016797344,0.00067315367,0.00018660966,0.0037433165,0.00039950287],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1153398,0.00012716404,0.0003065356,0.000967785,0.00014298837,0.0002896587,0.0002718073,0.000117433985,0.000612001],"category_scores_gemma":[0.02073213,0.00009567966,0.000058646554,0.0007021486,0.00016607191,0.0010996584,0.000012403335,0.00027349358,0.000008953082],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026070347,0.00003696245,0.12535278,0.00000308702,0.000010770671,0.000005326743,0.00569647,0.0014916984,0.000019214316,0.00053361204,0.000035670226,0.8667883],"study_design_scores_gemma":[0.0016850107,0.00062302273,0.915161,0.00006250143,0.00007230428,0.00004261631,0.024897318,0.03975852,0.00006410205,0.01413625,0.0033413768,0.00015599145],"about_ca_topic_score_codex":0.00017491577,"about_ca_topic_score_gemma":0.036528412,"teacher_disagreement_score":0.86663234,"about_ca_system_score_codex":0.00040178513,"about_ca_system_score_gemma":0.00268061,"threshold_uncertainty_score":0.98751664},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"},{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W4366449629","doi":"10.3138/cjpe.0021.006","title":"Studies Are Not Enough: The Necessary Transformation of Evaluation","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"GRASP; Public sector; Business; Knowledge management; Profit (economics); Public relations; Not for profit; Political science; Economics; Computer science","score_opus":0.55640313541793,"score_gpt":0.5856812041578379,"score_spread":0.029278068739907903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366449629","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9739197,0.0031039552,0.0030927449,0.011172095,0.0017764173,0.002412696,0.000011040485,0.000008873436,0.004502467],"genre_scores_gemma":[0.9985262,0.00004516835,0.00082273234,0.0002820731,0.00020944429,0.00004655704,0.000010278144,0.000007774967,0.000049726463],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9918206,0.0009551927,0.0017961583,0.00017002498,0.0049647833,0.0002932744],"domain_scores_gemma":[0.98659676,0.00080693053,0.0017969861,0.0003287498,0.010240123,0.00023044278],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07960297,0.00013694513,0.00031149221,0.0007803059,0.00033141143,0.0001714244,0.00044548552,0.00008525326,0.0007678888],"category_scores_gemma":[0.0060374034,0.00008464888,0.0001728983,0.0011624171,0.0001931782,0.001029379,0.000009335649,0.00022783503,0.00002801048],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004888551,0.000043949898,0.0063183536,0.000012620621,0.00007524605,0.0000018930687,0.009665096,0.0058789467,0.00012671581,0.0007180395,0.001822944,0.9752873],"study_design_scores_gemma":[0.0042729382,0.0014983607,0.6412517,0.00035166473,0.0009702812,0.00012723127,0.09883677,0.14982268,0.0063404455,0.030367712,0.065709606,0.00045062165],"about_ca_topic_score_codex":0.00018450181,"about_ca_topic_score_gemma":0.024377735,"teacher_disagreement_score":0.9748367,"about_ca_system_score_codex":0.00052793534,"about_ca_system_score_gemma":0.003415695,"threshold_uncertainty_score":0.99342483},"labels":[],"label_agreement":null},{"id":"W4366449951","doi":"10.3138/cjpe.0023.003","title":"Perceptions of Evaluation Capacity Building in the United States: A Descriptive Study of American Evaluation Association Members","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Perception; Association (psychology); Descriptive research; Psychology; Organizational change; Descriptive statistics; Organizational learning; Capacity building; Political science; Public relations; Social psychology; Medical education; Sociology; Management; Economics; Medicine; Social science; Law; Statistics","score_opus":0.40916432990698465,"score_gpt":0.5208469713431527,"score_spread":0.11168264143616807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366449951","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99388105,0.000059469698,0.00045738835,0.0013372361,0.00026871587,0.003535574,0.0000118768485,0.0000044706208,0.00044422058],"genre_scores_gemma":[0.99843776,0.000010867204,0.0011520927,0.0001357206,0.000061976,0.00014244133,0.00004499428,0.000007190676,0.0000069674647],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9827407,0.00660236,0.0020085182,0.0002808867,0.008044859,0.00032269515],"domain_scores_gemma":[0.9829806,0.00073848746,0.00307496,0.00039813606,0.012629001,0.00017878652],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.081975855,0.00017240584,0.00043673927,0.002075916,0.00021276806,0.00019868815,0.00050535664,0.00008240029,0.00063624466],"category_scores_gemma":[0.010504852,0.00012830913,0.00014699451,0.0040010195,0.00011636127,0.0007837272,0.000008167492,0.00034093426,0.000003986513],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006319961,0.0007831089,0.19484866,0.000004541963,0.00008956449,0.0000011099423,0.0908198,0.20633921,0.00026290378,0.00012883217,0.00060059543,0.5060585],"study_design_scores_gemma":[0.0016827097,0.001954551,0.5453241,0.000045832418,0.000372205,0.000004823621,0.09351583,0.35247222,0.00003130089,0.0043054037,0.00019354091,0.00009749578],"about_ca_topic_score_codex":0.01058646,"about_ca_topic_score_gemma":0.075181395,"teacher_disagreement_score":0.505961,"about_ca_system_score_codex":0.0026587306,"about_ca_system_score_gemma":0.0037868167,"threshold_uncertainty_score":0.9978301},"labels":[],"label_agreement":null},{"id":"W4366449986","doi":"10.3138/cjpe.0021.002","title":"Evaluation Practice in Canada: Results of a National Survey","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Merck Canada Inc. (Canada); Environment and Climate Change Canada","funders":"","keywords":"Certification; Workforce; Professionalization; Public relations; Work (physics); Psychology; Accountability; Population; Medical education; Action (physics); Position (finance); Professional certification (computer technology); Political science; Business; Sociology; Medicine; Engineering; Law","score_opus":0.5394801885554342,"score_gpt":0.5848590900140788,"score_spread":0.04537890145864454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366449986","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9628789,0.00094969774,0.00068707607,0.003282418,0.0017954491,0.0020779318,0.00008577148,0.0000034328268,0.02823935],"genre_scores_gemma":[0.99783146,0.000007593165,0.0017816945,0.00018734393,0.00009253799,0.00001784685,0.000045164434,0.0000063613606,0.00003000462],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98204696,0.0028032681,0.0026291492,0.00025934778,0.011899378,0.00036186865],"domain_scores_gemma":[0.9681452,0.0030611458,0.0019084433,0.00022680454,0.026309745,0.00034864474],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.23255762,0.00011029548,0.0002580688,0.0011307102,0.00008436247,0.000102031976,0.00041449844,0.000070509705,0.00062068907],"category_scores_gemma":[0.103612065,0.000094465635,0.00006141485,0.001801026,0.000055135995,0.0008494453,0.0000097003685,0.00023817974,0.00001138275],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00017490133,0.00006898066,0.07484857,0.0000021423646,0.000033375276,0.000007589738,0.00114151,0.019479757,0.000017871065,0.00011487176,0.005365419,0.898745],"study_design_scores_gemma":[0.0023479452,0.00024582012,0.91322356,0.000040829644,0.00005382737,0.000030584248,0.0024219449,0.06383089,0.00010568088,0.0027729927,0.01481097,0.00011497939],"about_ca_topic_score_codex":0.8062789,"about_ca_topic_score_gemma":0.99895996,"teacher_disagreement_score":0.89863,"about_ca_system_score_codex":0.0042181704,"about_ca_system_score_gemma":0.10595804,"threshold_uncertainty_score":0.99960446},"labels":[],"label_agreement":null},{"id":"W4366450235","doi":"10.3138/cjpe.0024.001","title":"Challenges and Approaches to Evaluating Comprehensive Complex Tobacco Control Strategies","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Ontario Tobacco Research Unit; Public Health Ontario; University of Toronto","funders":"","keywords":"Variety (cybernetics); Management science; Computer science; Control (management); Risk analysis (engineering); Ideal (ethics); Intervention (counseling); Attribution; Psychological intervention; Process management; Psychology; Epistemology; Artificial intelligence; Business; Economics; Social psychology","score_opus":0.8095393556398636,"score_gpt":0.5490757212984705,"score_spread":0.2604636343413931,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366450235","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9803233,0.0011681063,0.0007751385,0.008372535,0.00076931267,0.0016174306,0.000007014783,0.000011799211,0.0069553712],"genre_scores_gemma":[0.9864987,0.000015290685,0.012831307,0.0002881205,0.0002513874,0.00007907355,0.000004918741,0.000010246714,0.00002091595],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9959336,0.0006225259,0.0008480906,0.0002867991,0.002000146,0.0003088249],"domain_scores_gemma":[0.995116,0.0005269552,0.0005588367,0.00031462393,0.0028109076,0.0006726652],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013429469,0.00016008427,0.0003339999,0.000618965,0.00025445863,0.0007372664,0.00042269868,0.00009156838,0.00079869747],"category_scores_gemma":[0.0021612744,0.00012368095,0.000083020146,0.0003392222,0.00013864983,0.0007563839,0.000018088012,0.0003197666,0.000046157667],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002043953,0.0000213677,0.004853634,0.000004331269,0.000027183847,0.0000018646936,0.0022611888,0.0024836115,0.0005510495,0.004683302,0.00027195408,0.98482007],"study_design_scores_gemma":[0.0020371454,0.0013450389,0.8192794,0.000041795425,0.000117108204,0.000109858534,0.018003814,0.10573103,0.000039802177,0.023224022,0.029789524,0.00028148454],"about_ca_topic_score_codex":0.00017127728,"about_ca_topic_score_gemma":0.05176646,"teacher_disagreement_score":0.9845386,"about_ca_system_score_codex":0.000094276016,"about_ca_system_score_gemma":0.0030429035,"threshold_uncertainty_score":0.96553636},"labels":[],"label_agreement":null},{"id":"W4366450277","doi":"10.3138/cjpe.022.008","title":"Navigating Uncharted Waters: Project Monitoring at Cida","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Monitoring and evaluation; Agency (philosophy); Citizen journalism; Interpretation (philosophy); Participatory evaluation; Set (abstract data type); Process management; Relation (database); International development; Knowledge management; Computer science; Public relations; Business; Sociology; Political science; Public administration","score_opus":0.49079338051818244,"score_gpt":0.592320400631158,"score_spread":0.10152702011297554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366450277","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9941261,0.00024753035,0.0007570098,0.00083080103,0.0015748012,0.00083082676,0.0000024314038,0.000013059367,0.0016174418],"genre_scores_gemma":[0.9940707,0.0000047345475,0.0051884507,0.00006746641,0.00047426965,0.000023478902,0.000008901531,0.000011309207,0.00015069192],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9951634,0.00032762048,0.0011526169,0.00020597842,0.0027261304,0.00042428044],"domain_scores_gemma":[0.99521166,0.00028414873,0.0008000101,0.0002524441,0.003000038,0.000451715],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.029178454,0.0001289341,0.00020780766,0.0003966908,0.00037197795,0.00039102655,0.00040300674,0.000084461426,0.0007433026],"category_scores_gemma":[0.002326097,0.000097186414,0.0001231926,0.0009556574,0.000068455556,0.00070563966,0.000017840328,0.00031807245,0.00010710418],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017286004,0.0000150651185,0.1531457,0.0000027371916,0.000017357526,0.000012940746,0.0032638754,0.00059643324,0.0003374784,0.000015311323,0.0006377941,0.841938],"study_design_scores_gemma":[0.00453661,0.0020830785,0.7269671,0.0006993108,0.00027440593,0.000439135,0.02597302,0.054929234,0.015366461,0.0049078125,0.1629781,0.00084573554],"about_ca_topic_score_codex":0.00067915465,"about_ca_topic_score_gemma":0.007882214,"teacher_disagreement_score":0.8410923,"about_ca_system_score_codex":0.0010076044,"about_ca_system_score_gemma":0.002566126,"threshold_uncertainty_score":0.9996651},"labels":[],"label_agreement":null},{"id":"W4366450581","doi":"10.3138/cjpe.0021.011","title":"Un outil d’évaluation de <i>l’empowerment</i> : une tentative en haïti","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Empowerment; Valuation (finance); Sociology; Psychology; Promotion (chess); Management science; Epistemology; Political science; Business; Economics; Philosophy","score_opus":0.2649696778036359,"score_gpt":0.5361563451404582,"score_spread":0.2711866673368223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366450581","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9276348,0.0004678373,0.0466601,0.0066586607,0.0015680242,0.0015927928,0.000009378342,0.00002031545,0.015388121],"genre_scores_gemma":[0.98268694,0.000014064859,0.016074954,0.0005965257,0.00027976712,0.000033046585,0.000019051848,0.000014165099,0.0002814924],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9935391,0.0010181803,0.0013737928,0.00025294398,0.0033203403,0.0004956758],"domain_scores_gemma":[0.9937952,0.0006379415,0.0009951753,0.00029181316,0.0035776226,0.0007022561],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.056212872,0.00016768386,0.00026441916,0.00093596865,0.0003035433,0.00037297423,0.0005274259,0.00012467902,0.0024090314],"category_scores_gemma":[0.0041465038,0.0001354727,0.00017106949,0.001382048,0.00011684463,0.0007373668,0.000014500316,0.00030560783,0.00014571274],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034832887,0.000059385202,0.03880226,0.0000021261696,0.000039406284,0.000014725691,0.0071565914,0.0015840717,0.00037215665,0.0005074251,0.0018444911,0.9495825],"study_design_scores_gemma":[0.0033283217,0.0013320266,0.7876799,0.000080261154,0.000281823,0.00017873476,0.015160476,0.045725316,0.0032416326,0.052707337,0.08988912,0.00039507213],"about_ca_topic_score_codex":0.00078666344,"about_ca_topic_score_gemma":0.016307246,"teacher_disagreement_score":0.94918746,"about_ca_system_score_codex":0.0010772394,"about_ca_system_score_gemma":0.006800991,"threshold_uncertainty_score":0.99882954},"labels":[],"label_agreement":null},{"id":"W4366451079","doi":"10.3138/cjpe.23.010","title":"A Journey Through Five Evaluation Projects with the Same Analysis Framework","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Strengths and weaknesses; Accountability; Process (computing); Interpretation (philosophy); Process management; Principal (computer security); Context (archaeology); Field (mathematics); Management science; Computer science; Knowledge management; Business; Political science; Psychology; Engineering; Social psychology; Computer security; Law","score_opus":0.46380024285771465,"score_gpt":0.5339974314860121,"score_spread":0.07019718862829744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366451079","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9623138,0.0010996086,0.016608292,0.012247009,0.00059631525,0.0028192196,0.000009246373,0.00001509733,0.0042914473],"genre_scores_gemma":[0.98807395,0.000029515082,0.010380981,0.0007273756,0.00029215173,0.00018722216,0.000017809723,0.000013065504,0.00027792537],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99021894,0.0017280146,0.0010178664,0.000322662,0.006320398,0.00039214926],"domain_scores_gemma":[0.98824567,0.0006962408,0.001417343,0.000603152,0.008665842,0.0003717386],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.023375375,0.00019946722,0.00040782196,0.000979442,0.00083257,0.00051352184,0.0007563584,0.00012408005,0.003429533],"category_scores_gemma":[0.0051635895,0.000110002366,0.00028659886,0.0045707054,0.00028160028,0.001127916,0.000014566508,0.0004875935,0.000074900905],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015905633,0.00019133285,0.14798598,0.0000068833583,0.0014662417,0.000045444263,0.0808295,0.16093746,0.000011906868,0.0015514971,0.025418213,0.58139646],"study_design_scores_gemma":[0.002662925,0.0020276827,0.48864514,0.0001237824,0.0042250655,0.00041720804,0.025754513,0.40738901,0.000079331374,0.026802534,0.041335497,0.00053732283],"about_ca_topic_score_codex":0.0010178047,"about_ca_topic_score_gemma":0.03441466,"teacher_disagreement_score":0.5808591,"about_ca_system_score_codex":0.0006467789,"about_ca_system_score_gemma":0.012360037,"threshold_uncertainty_score":0.99748147},"labels":[],"label_agreement":null},{"id":"W4366451139","doi":"10.3138/cjpe.0024.008","title":"Advocacy Evaluation Theory as a Tool for Strategic Conversation: A 25-Year Review of Tobacco Control Advocacy at the Canadian Cancer Society","year":2010,"lang":"en","type":"review","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Circumstantial evidence; Conversation; Tobacco control; Control (management); Key (lock); Public relations; Political science; Policy advocacy; Sociology; Medicine; Management; Nursing; Law; Public health; Computer science; Economics","score_opus":0.3649842729698006,"score_gpt":0.551830417055927,"score_spread":0.18684614408612632,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366451139","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004198205,0.9777974,0.00008221772,0.0036306423,0.0019498772,0.014467658,0.0002441522,0.0000075550533,0.0014006759],"genre_scores_gemma":[0.0051467223,0.98701733,0.00068443955,0.0016665079,0.0008551723,0.0036362237,0.00044663344,0.000065236236,0.00048174133],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9874939,0.0032757558,0.003231166,0.0005656444,0.0047888746,0.0006447159],"domain_scores_gemma":[0.97778285,0.0018608267,0.005034089,0.00096960674,0.013563036,0.00078957464],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07461086,0.00050961913,0.0016973107,0.00069901143,0.0006728804,0.0005299328,0.0013713919,0.0005308716,0.0146449],"category_scores_gemma":[0.008797126,0.0003271608,0.0015853589,0.0013714144,0.00036159612,0.0005465247,0.000024626745,0.00086107,0.00013337002],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000012981954,0.000020985257,0.00019004758,0.0016685032,0.00025666965,9.428984e-7,0.00066036335,0.00010284922,2.6659063e-7,0.0005994269,0.007725628,0.9887613],"study_design_scores_gemma":[0.0016784578,0.0003587983,0.00022041898,0.011603451,0.004664811,0.00004690022,0.0007920481,0.0027265812,8.3507297e-7,0.005402865,0.9721281,0.0003767473],"about_ca_topic_score_codex":0.01724536,"about_ca_topic_score_gemma":0.42430502,"teacher_disagreement_score":0.9883846,"about_ca_system_score_codex":0.0040260074,"about_ca_system_score_gemma":0.17273363,"threshold_uncertainty_score":0.99991804},"labels":[],"label_agreement":null},{"id":"W4366451145","doi":"10.3138/cjpe.031.1.v","title":"Editor’s Remarks","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Philosophy","score_opus":0.2352312171100758,"score_gpt":0.5173110315008186,"score_spread":0.2820798143907428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366451145","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70734173,0.0021938912,0.03592408,0.09790035,0.07559558,0.004779668,0.000048293296,0.00007085258,0.07614554],"genre_scores_gemma":[0.9935613,0.000010244632,0.0025691402,0.00019054784,0.0027680278,0.000027874888,0.0000017814228,0.0000072550424,0.0008637827],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9958554,0.0004423026,0.0008024528,0.00015376564,0.0025077513,0.00023831196],"domain_scores_gemma":[0.9944455,0.00035156467,0.00060138653,0.00028514204,0.0038056388,0.0005107857],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017838495,0.000085654596,0.00016609985,0.00057251786,0.00013777999,0.00024997292,0.00045657804,0.000071138784,0.008335228],"category_scores_gemma":[0.0062385886,0.00004694643,0.000113905895,0.00047170804,0.00008704193,0.0007777386,0.000008196827,0.00010031377,0.0003532674],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000069854896,0.000011265409,0.015546544,6.105932e-7,0.000009550195,0.0000023351624,0.00015865812,0.000045067194,0.00008708281,0.00029007465,0.09130763,0.8925342],"study_design_scores_gemma":[0.0011292034,0.00045871342,0.082593635,0.00007258218,0.000044628698,0.00003873236,0.0003466939,0.0030456726,0.00019578553,0.021925647,0.89001626,0.00013245881],"about_ca_topic_score_codex":0.00011594232,"about_ca_topic_score_gemma":0.008389437,"teacher_disagreement_score":0.89240175,"about_ca_system_score_codex":0.00040046746,"about_ca_system_score_gemma":0.0055036694,"threshold_uncertainty_score":0.9925713},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W4366451365","doi":"10.3138/cjpe.021.006","title":"Pragmatism or Transformation? Participatory Evaluation of a Humanitarian Education Project in Sierra Leone","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Sierra leone; Transformative learning; Citizen journalism; Participatory evaluation; Stakeholder; Humanitarian aid; Sociology; Context (archaeology); Humanitarian intervention; Political science; Public relations; Pedagogy; Public administration; Socioeconomics; Law","score_opus":0.4904049515913237,"score_gpt":0.5642115556092092,"score_spread":0.07380660401788552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366451365","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.984796,0.0006557947,0.00062677235,0.0011645516,0.0007666255,0.0032872597,0.000009718397,0.000007682317,0.008685635],"genre_scores_gemma":[0.99774873,0.000006356279,0.0014607538,0.000059461374,0.0001591822,0.0004030536,0.000047825743,0.000011194683,0.00010345964],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99181306,0.0016292334,0.0021027098,0.00018853761,0.0039658975,0.00030057042],"domain_scores_gemma":[0.99209607,0.00020645114,0.0013225607,0.00030476044,0.005896973,0.00017318633],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.035647385,0.00015402687,0.00032932233,0.0018071097,0.00015256686,0.00022598688,0.00036520863,0.000112917594,0.002031639],"category_scores_gemma":[0.0027093142,0.00012017972,0.000114154915,0.0015299619,0.000099622666,0.0014449953,0.0000056423996,0.00020546914,0.000024325886],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055761324,0.00035848387,0.021645376,0.00002455482,0.00002190161,0.0000012577034,0.008245746,0.012342844,0.00009717346,0.002390056,0.0024106528,0.95240617],"study_design_scores_gemma":[0.0044796714,0.0011203288,0.66356665,0.00034313832,0.00043746716,0.00005674243,0.014766334,0.24786822,0.00040685813,0.047946304,0.018647403,0.0003608769],"about_ca_topic_score_codex":0.005383559,"about_ca_topic_score_gemma":0.24671665,"teacher_disagreement_score":0.9520453,"about_ca_system_score_codex":0.00094594073,"about_ca_system_score_gemma":0.028632052,"threshold_uncertainty_score":0.9988806},"labels":[],"label_agreement":null},{"id":"W4366451556","doi":"10.3138/cjpe.020.004","title":"The Changing Role of the Evaluator in the Process of Organizational Learning","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Facilitator; Organizational learning; Knowledge management; Process (computing); Context (archaeology); Organization development; Participatory evaluation; Psychology; Computer science; Process management; Social psychology; Business; Sociology","score_opus":0.12489349374341881,"score_gpt":0.4789306428987973,"score_spread":0.3540371491553785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366451556","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99018663,0.0008010201,0.000091156,0.006295251,0.0002226553,0.00082896964,0.000001931295,0.0000018217239,0.0015705867],"genre_scores_gemma":[0.9994642,0.000008655445,0.00019009545,0.00010415214,0.00013159555,0.000028457718,0.0000017722856,0.000005482169,0.0000656007],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9950241,0.0010114897,0.00086283375,0.00009579852,0.0028092514,0.00019654767],"domain_scores_gemma":[0.9951274,0.000504825,0.0010198676,0.00022254983,0.0030521376,0.00007322464],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027491428,0.0000729309,0.00013549362,0.0003266529,0.00036407847,0.00014221611,0.0008414163,0.00004069064,0.00046547456],"category_scores_gemma":[0.0057150633,0.000033947934,0.00008156299,0.0017627856,0.00012828298,0.00028427475,0.000014673839,0.00023419547,0.000007354482],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016141634,0.000054124303,0.16663218,0.0000056138997,0.000022899883,2.44755e-7,0.025953611,0.05829283,0.00015385795,0.0027834028,0.00021394649,0.7458711],"study_design_scores_gemma":[0.001372018,0.0004221712,0.32722405,0.00016349353,0.00012831755,0.00004698502,0.06734931,0.5433532,0.0019832398,0.026021134,0.031769328,0.0001667857],"about_ca_topic_score_codex":0.00006835081,"about_ca_topic_score_gemma":0.008206646,"teacher_disagreement_score":0.74570435,"about_ca_system_score_codex":0.00015782901,"about_ca_system_score_gemma":0.004251224,"threshold_uncertainty_score":0.9528035},"labels":[],"label_agreement":null},{"id":"W4366452033","doi":"10.3138/cjpe.0027.009","title":"Lessons Learned and the Contributions of the Paris Declaration Evaluation to Evaluation Theory and Practice","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Declaration; General partnership; Stakeholder; Declaration of independence; Political science; Management; Public relations; Engineering ethics; Sociology; Law; Engineering; Economics","score_opus":0.4365949081454484,"score_gpt":0.5688416158670923,"score_spread":0.13224670772164387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366452033","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7865028,0.0037472358,0.008980947,0.18310039,0.0010858136,0.012156845,0.00002316706,0.000009125709,0.0043937275],"genre_scores_gemma":[0.9975872,0.000059535698,0.0009702207,0.0006963794,0.000093958944,0.00050919334,0.000009705867,0.000007523215,0.000066264365],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9843504,0.010072556,0.0011265905,0.00025901836,0.00393211,0.00025931833],"domain_scores_gemma":[0.9801468,0.0035276418,0.0013199919,0.0004395283,0.014266276,0.00029972132],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1322017,0.00013445289,0.0002588102,0.0003670478,0.0006519375,0.00062404247,0.0003596601,0.00009888516,0.0010431936],"category_scores_gemma":[0.0739798,0.00007441109,0.00009791045,0.000906574,0.00035681878,0.001417658,0.00004021361,0.00024771714,0.000025493411],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011470826,0.00003294366,0.001416131,0.0000028605668,0.000058514182,8.96656e-8,0.0039309906,0.004441598,0.00031824462,0.01845139,0.0019433798,0.9692891],"study_design_scores_gemma":[0.006006219,0.00048752656,0.23891471,0.0001036852,0.0014885752,0.00008453905,0.012935339,0.39597058,0.0004971705,0.3278815,0.015406488,0.00022367446],"about_ca_topic_score_codex":0.0009844056,"about_ca_topic_score_gemma":0.0045406884,"teacher_disagreement_score":0.9690655,"about_ca_system_score_codex":0.0003891121,"about_ca_system_score_gemma":0.0047939783,"threshold_uncertainty_score":0.99987},"labels":[],"label_agreement":null},{"id":"W4366452150","doi":"10.3138/cjpe.0021.001","title":"Special Edition / Edition Speciale Crossing Borders / Crossing Boundaries Editors’ Remarks","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Philosophy","score_opus":0.1617430004729702,"score_gpt":0.49414516120917895,"score_spread":0.33240216073620876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366452150","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6190321,0.0006788787,0.11612828,0.015366707,0.19910944,0.0033302428,0.00006470352,0.000081422084,0.046208236],"genre_scores_gemma":[0.8611904,0.0000034522532,0.009470173,0.00047415486,0.12848793,0.000018649971,0.00007890925,0.000026168895,0.0002501652],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9928471,0.00039718335,0.0016790567,0.00032425232,0.0041598156,0.00059258775],"domain_scores_gemma":[0.9919553,0.00038143765,0.0014046328,0.00031032786,0.005291217,0.00065707834],"candidate_categories":["metaresearch","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.030562721,0.00020939833,0.00032671753,0.001197374,0.0033236481,0.010866922,0.00044144978,0.00020712915,0.005321485],"category_scores_gemma":[0.005864068,0.00018589875,0.00021222811,0.0012067311,0.0013162462,0.0024311242,0.000016629027,0.00044617895,0.00008213129],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007111848,0.00005065466,0.006951703,0.0000053536614,0.000021362228,0.00001867303,0.00334998,0.0005793231,0.00007606256,0.00052496855,0.2150825,0.7732683],"study_design_scores_gemma":[0.0010440814,0.0003589519,0.07368757,0.00009263828,0.00006783751,0.0000621053,0.002536295,0.003996861,0.00039488848,0.013790071,0.90374386,0.00022482593],"about_ca_topic_score_codex":0.00068171724,"about_ca_topic_score_gemma":0.052149765,"teacher_disagreement_score":0.77304345,"about_ca_system_score_codex":0.0013342409,"about_ca_system_score_gemma":0.021751272,"threshold_uncertainty_score":0.9982397},"labels":[],"label_agreement":null},{"id":"W4366452167","doi":"10.3138/cjpe.23.014","title":"Carl F. Brun. (2005). <i>A Practical Guide to Social Service Evaluation.</i> Chicago: Lyceum Books. 204 pages, plus preface, appendices, glossary, references, and index.","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Glossary; Index (typography); Library science; Gerontology; Medicine; Computer science; Philosophy; World Wide Web; Linguistics","score_opus":0.36228510341394915,"score_gpt":0.5103163508900976,"score_spread":0.1480312474761485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366452167","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8424137,0.004558499,0.0031898173,0.07947901,0.0033296235,0.009281473,0.00013122303,0.00008787953,0.057528764],"genre_scores_gemma":[0.9878877,0.00013269183,0.0073876423,0.0024238068,0.0006836837,0.00022943655,0.0000764978,0.000027570706,0.0011509648],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9885263,0.001566633,0.0017672698,0.00058967207,0.0068372195,0.000712945],"domain_scores_gemma":[0.98947257,0.00037368856,0.0012329055,0.0004614711,0.007095484,0.0013638785],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.026040895,0.0003181742,0.00054804044,0.00092521793,0.0010104778,0.0007070873,0.00071410026,0.00026954204,0.0025436082],"category_scores_gemma":[0.0039790086,0.00026812023,0.00013376698,0.0012462294,0.00021251533,0.0014283898,0.0000715013,0.0006242152,0.00021023458],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023261509,0.00016569559,0.03409702,0.000027254548,0.00016850517,0.00005433457,0.007327041,0.00415617,0.000064013395,0.0005478699,0.2954055,0.65775394],"study_design_scores_gemma":[0.003062343,0.0005844365,0.17869328,0.00007674282,0.0002716735,0.0004940462,0.00249956,0.057655595,0.0000314047,0.0018251338,0.7543748,0.00043095785],"about_ca_topic_score_codex":0.0031069147,"about_ca_topic_score_gemma":0.108584285,"teacher_disagreement_score":0.657323,"about_ca_system_score_codex":0.0011351827,"about_ca_system_score_gemma":0.026524203,"threshold_uncertainty_score":0.9999771},"labels":[],"label_agreement":null},{"id":"W4366452169","doi":"10.3138/cjpe.20.007","title":"Preparing School Evaluators: Hiroshima Pilot Test of the Japan Evaluation Society’s Accreditation Project","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Toronto Public Health","funders":"","keywords":"Accreditation; Certification; Certification and Accreditation; Test (biology); Context (archaeology); Medical education; Sustainability; Program evaluation; Government (linguistics); Political science; Quality (philosophy); Public relations; Psychology; Medicine; Public administration","score_opus":0.3502415788863397,"score_gpt":0.5226132347110275,"score_spread":0.17237165582468778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366452169","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9841619,0.00076113327,0.0003891916,0.0035913028,0.0014188705,0.0047020637,0.00002095376,0.000018559225,0.004936033],"genre_scores_gemma":[0.9929133,0.000012511953,0.0056686373,0.00023596865,0.0006810112,0.00025141405,0.000021625945,0.000019887653,0.00019560858],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9892831,0.0013354825,0.0018962985,0.00035651794,0.00673305,0.00039557077],"domain_scores_gemma":[0.98738813,0.0006271991,0.0022227764,0.00066163164,0.008734359,0.00036592752],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04267324,0.00022079,0.00034623788,0.0006034301,0.00044195366,0.0004879745,0.000979954,0.00012238992,0.001677089],"category_scores_gemma":[0.018634915,0.0001522946,0.00035037994,0.001679314,0.0001878203,0.0016541448,0.000041208463,0.00037256142,0.00006432168],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031354997,0.00018478662,0.08682996,0.000013658993,0.000067968715,1.3022934e-7,0.0029663832,0.019439561,0.0010070107,0.000091718124,0.023228027,0.8661395],"study_design_scores_gemma":[0.0028889521,0.0013957503,0.36206108,0.00020369019,0.0005332331,0.000037090485,0.0032437192,0.59556854,0.0016653576,0.0039145583,0.028202182,0.00028582485],"about_ca_topic_score_codex":0.0004803687,"about_ca_topic_score_gemma":0.016572587,"teacher_disagreement_score":0.8658536,"about_ca_system_score_codex":0.0016281845,"about_ca_system_score_gemma":0.021868998,"threshold_uncertainty_score":0.9992355},"labels":[],"label_agreement":null},{"id":"W4366452402","doi":"10.3138/cjpe.22.005","title":"Thickening the Plot: Combining Objectives- and Methods-Oriented Approaches in the Evaluation of a Provincial Superintendents’ Qualification Program","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University","funders":"","keywords":"Commensurability (mathematics); Legislature; Evaluation methods; Program evaluation; Plot (graphics); Computer science; Management science; Political science; Public administration; Mathematics; Engineering; Statistics","score_opus":0.5865720125219641,"score_gpt":0.5866314486560237,"score_spread":0.00005943613405956505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366452402","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98243713,0.000620006,0.00888208,0.0015733138,0.0004270785,0.0042112684,0.0000027998876,0.000008440259,0.0018378798],"genre_scores_gemma":[0.98802847,0.000005022293,0.011494473,0.00007028268,0.000101880054,0.00027195542,0.000011106961,0.000009454495,0.0000073328424],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98829865,0.0051694503,0.0015985644,0.00029063903,0.004297716,0.00034496028],"domain_scores_gemma":[0.99339914,0.0012855821,0.0011562783,0.00035517945,0.0036441614,0.00015965273],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.17891058,0.00014754085,0.0002654702,0.00073974126,0.00032640973,0.0003325697,0.00055635424,0.00009985803,0.00008676052],"category_scores_gemma":[0.009842666,0.000085117674,0.000105286934,0.001496029,0.0002854053,0.0006055042,0.000020783431,0.00040946473,0.0000024392386],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000455361,0.00010632855,0.0400851,0.000006091957,0.000025847206,7.1148355e-7,0.025304122,0.000854888,0.00007566638,0.0019226973,0.000029594548,0.9315434],"study_design_scores_gemma":[0.0016317294,0.00076846615,0.6679095,0.00007404151,0.00021854349,0.000045738092,0.07555797,0.24258983,0.0002796846,0.008477227,0.0023052758,0.00014197508],"about_ca_topic_score_codex":0.00081666023,"about_ca_topic_score_gemma":0.026028495,"teacher_disagreement_score":0.93140143,"about_ca_system_score_codex":0.00039122815,"about_ca_system_score_gemma":0.0033089544,"threshold_uncertainty_score":0.99849784},"labels":[],"label_agreement":null},{"id":"W4366452409","doi":"10.3138/cjpe.022.001","title":"Value-for-Money Analysis of Active Labour Market Programs","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec; Employment and Social Development Canada; University of Manitoba","funders":"","keywords":"Value for money; Value (mathematics); Time value of money; Context (archaeology); Accountability; Disadvantaged; Relevance (law); Economics; Government (linguistics); Money measurement concept; Business; Microeconomics; Actuarial science; Public economics; Endogenous money; Finance; Computer science; Monetary policy; Macroeconomics; Economic growth; Velocity of money; Political science","score_opus":0.29403001195915573,"score_gpt":0.5330757016348798,"score_spread":0.2390456896757241,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366452409","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9684392,0.0003297965,0.01888452,0.0009813785,0.0008659956,0.0022246386,0.000051667663,0.000010779046,0.008212028],"genre_scores_gemma":[0.99030685,0.000006029974,0.008958234,0.00010777879,0.0001282461,0.00004683225,0.000035348145,0.000009722461,0.0004009648],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9948673,0.0004132785,0.0014581615,0.00023219004,0.0026460318,0.0003830282],"domain_scores_gemma":[0.990964,0.0006014423,0.0015202774,0.0003325051,0.006041188,0.0005405786],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03733911,0.00013791413,0.00045918225,0.0022827885,0.00016370312,0.00021093008,0.0005140954,0.00010952381,0.0018219317],"category_scores_gemma":[0.003593438,0.00010814518,0.0004162251,0.0035002227,0.000119444245,0.0005257817,0.000010321054,0.00016197348,0.000008138562],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009159558,0.000070388196,0.056770746,0.000005181917,0.00042065146,0.000002062063,0.0010858943,0.0018220567,0.00003687181,0.0012630248,0.00067028916,0.93776125],"study_design_scores_gemma":[0.0013641806,0.0010483472,0.8256498,0.00004106652,0.0016104257,0.000009543438,0.00367457,0.10171395,0.0006065803,0.0069348565,0.05714495,0.00020171772],"about_ca_topic_score_codex":0.0007873904,"about_ca_topic_score_gemma":0.038794536,"teacher_disagreement_score":0.93755955,"about_ca_system_score_codex":0.00042659728,"about_ca_system_score_gemma":0.0035853158,"threshold_uncertainty_score":0.99909055},"labels":[],"label_agreement":null},{"id":"W4366452424","doi":"10.3138/cjpe.28.010","title":"King, J. A., &amp; Stevahn, L. (2013). <i>Interactive Evaluation Practice: Mastering the Interpersonal Dynamics of Program Evaluation.</i>","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Interpersonal communication; Dynamics (music); Psychology; Interpersonal relationship; Sociology; Applied psychology; Social psychology; Pedagogy","score_opus":0.3003669884072015,"score_gpt":0.5346756791914403,"score_spread":0.23430869078423883,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366452424","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88839346,0.0022234337,0.009775876,0.042321876,0.006473302,0.02765401,0.000051283794,0.000059454545,0.02304729],"genre_scores_gemma":[0.98638314,0.000024105508,0.010828592,0.0003938513,0.00031966722,0.0017174009,0.00011289594,0.000030515179,0.00018982349],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9847866,0.0035775509,0.0022437284,0.00046932994,0.0083728405,0.00054989144],"domain_scores_gemma":[0.9673536,0.0014714848,0.003297125,0.0007561121,0.02662628,0.0004954308],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.051099855,0.0003203756,0.00047222487,0.000956614,0.00043013974,0.0014824409,0.0010924897,0.00016807759,0.013618639],"category_scores_gemma":[0.018832989,0.00022260583,0.00031109664,0.0013437745,0.0002938432,0.0038490046,0.00006275623,0.0006303937,0.00033701074],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053552798,0.00017688467,0.0037489617,0.000009154544,0.00014738506,8.812497e-7,0.0036179624,0.009698751,0.000055203174,0.00016402801,0.006000682,0.9763265],"study_design_scores_gemma":[0.0018214165,0.0009368428,0.032463934,0.00022165525,0.0006998175,0.00012286102,0.0139291035,0.8900659,0.000055098455,0.0067937127,0.052605778,0.00028387358],"about_ca_topic_score_codex":0.0029364203,"about_ca_topic_score_gemma":0.047876187,"teacher_disagreement_score":0.9760427,"about_ca_system_score_codex":0.0019544715,"about_ca_system_score_gemma":0.008580472,"threshold_uncertainty_score":0.9995541},"labels":[],"label_agreement":null},{"id":"W4366452622","doi":"10.3138/cjpe.0026.005","title":"L’approche <i>Realist</i> à l’épreuve du réel de l’évaluation des programmes","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; Université de Montréal","funders":"","keywords":"Epistemology; Context (archaeology); Valuation (finance); Psychological intervention; Outcome (game theory); Sociology; Psychology; GRASP; Mechanism (biology); Philosophy; Computer science; Economics; History","score_opus":0.4946108818232891,"score_gpt":0.5147343735641988,"score_spread":0.020123491740909716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366452622","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9705555,0.0014464353,0.011910757,0.003403249,0.0012832982,0.0017583914,0.000008951802,0.000032269865,0.009601187],"genre_scores_gemma":[0.97286177,0.000030992876,0.025520813,0.00039381743,0.0007195025,0.00017698713,0.000025725267,0.00001896087,0.00025145625],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9937447,0.0013712643,0.0011391782,0.00021058261,0.002817339,0.00071696716],"domain_scores_gemma":[0.9933913,0.00039078057,0.00088187173,0.00034431068,0.0039122095,0.0010795635],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.047357675,0.000192258,0.0002899536,0.0006935721,0.00043539575,0.00062600797,0.0005697161,0.00016777006,0.0013883599],"category_scores_gemma":[0.007978791,0.00015029217,0.00020263939,0.0010959326,0.00021304029,0.0016894074,0.00001892493,0.00032042235,0.00011805171],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014047397,0.00009640321,0.23180704,0.000006305317,0.000028078424,0.0000016496614,0.008050774,0.00077630545,0.000060523595,0.000417196,0.0066518015,0.75208986],"study_design_scores_gemma":[0.0019892808,0.0008937028,0.63328785,0.00010094865,0.00038266944,0.00037793122,0.008991606,0.05536036,0.00048820587,0.04106676,0.25660837,0.00045234367],"about_ca_topic_score_codex":0.0008721581,"about_ca_topic_score_gemma":0.010221943,"teacher_disagreement_score":0.7516375,"about_ca_system_score_codex":0.000876735,"about_ca_system_score_gemma":0.005596429,"threshold_uncertainty_score":0.99952453},"labels":[],"label_agreement":null},{"id":"W4366452662","doi":"10.3138/cjpe.22.006","title":"Developing a Special Education Accountability Framework Using Program Evaluation","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Accountability; Bureaucracy; Context (archaeology); Citizen journalism; Public administration; Public relations; Political science; Business; Politics; Geography","score_opus":0.5571351357964983,"score_gpt":0.6246417530511743,"score_spread":0.067506617254676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366452662","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9530271,0.0005240141,0.028949987,0.0012890443,0.005953388,0.005478737,0.0000038902494,0.00002508241,0.0047487346],"genre_scores_gemma":[0.8791885,0.000005070065,0.11763718,0.0002740025,0.002664022,0.00016350207,0.000024338433,0.000017317452,0.000026073314],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99097395,0.0009076966,0.0019290977,0.00039972208,0.0052427244,0.0005468156],"domain_scores_gemma":[0.98488694,0.00048915594,0.0014947541,0.00047525455,0.0120447865,0.0006090918],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.065369956,0.00022143,0.00033984098,0.001312916,0.0004918073,0.0008865869,0.0006204667,0.00023069796,0.00370354],"category_scores_gemma":[0.010727579,0.00019047766,0.0001921672,0.0021375422,0.00014869329,0.0014270778,0.000021716916,0.00043372673,0.00007368723],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029118453,0.00011577373,0.032827497,0.0000062208564,0.000021699356,0.0000011426729,0.0016968191,0.0011269774,0.000018504968,0.0012577722,0.000514385,0.9623841],"study_design_scores_gemma":[0.0016403039,0.0008261994,0.4946539,0.00040578117,0.00046555558,0.00015194353,0.012406186,0.1493244,0.0003397163,0.16632807,0.1727775,0.00068043254],"about_ca_topic_score_codex":0.0006546345,"about_ca_topic_score_gemma":0.02555283,"teacher_disagreement_score":0.96170366,"about_ca_system_score_codex":0.0036061956,"about_ca_system_score_gemma":0.036656246,"threshold_uncertainty_score":0.9976055},"labels":[],"label_agreement":null},{"id":"W4366453107","doi":"10.3138/cjpe.023.004","title":"L’utilisation de l’évaluation fondée sur la théorie du programme comme stratégie d’application des connaissances issues de la recherche","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; Centre intégré universitaire de santé et de services sociaux de la Mauricie-et-du-Centre-du-Québec; Université du Québec à Trois-Rivières; Université du Québec à Montréal","funders":"","keywords":"Knowledge management; Tacit knowledge; Valuation (finance); Sociology; Psychology; Business; Computer science","score_opus":0.8056653558025793,"score_gpt":0.5756305185019046,"score_spread":0.23003483730067464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366453107","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9580388,0.0016212736,0.023694,0.006598135,0.00026954888,0.0016308039,0.000008019139,0.00005019516,0.008089212],"genre_scores_gemma":[0.9721085,0.00030322987,0.026598394,0.00017393482,0.00034418597,0.0002565693,0.000036010024,0.000020762991,0.00015845709],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98959714,0.0062953695,0.0011424416,0.00031127047,0.002151061,0.00050273817],"domain_scores_gemma":[0.9910523,0.0030692609,0.0009646255,0.00035986156,0.0039944006,0.00055952586],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07160706,0.00020760247,0.00030939744,0.000548322,0.00059788756,0.0006138445,0.0005778901,0.00033810295,0.0005454243],"category_scores_gemma":[0.02051094,0.00017866587,0.00016146031,0.0010698441,0.0006466025,0.0013138542,0.000014089985,0.0005383619,0.000032990112],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003452245,0.00013062602,0.19336209,0.000011380024,0.000033905384,0.000009574605,0.007606053,0.0028706596,0.00026850007,0.0023184337,0.0036515899,0.78970265],"study_design_scores_gemma":[0.0020675438,0.00073724875,0.42229894,0.000096636235,0.00017026463,0.0005001313,0.005073654,0.19253737,0.0008948524,0.28533056,0.08994008,0.00035269],"about_ca_topic_score_codex":0.0020664807,"about_ca_topic_score_gemma":0.006417267,"teacher_disagreement_score":0.78935,"about_ca_system_score_codex":0.001469095,"about_ca_system_score_gemma":0.013423405,"threshold_uncertainty_score":0.99216956},"labels":[],"label_agreement":null},{"id":"W4366453124","doi":"10.3138/cjpe.020.006","title":"Participatory Evaluation in the Context of CBPD: Theory and Practice in International Development","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Citizen journalism; Context (archaeology); International development; Political science; Democracy; Participatory development; Participatory evaluation; Sociology; International community; Engineering ethics; Public administration; Politics; Engineering; Law; Geography","score_opus":0.4738059708487722,"score_gpt":0.5804406649322703,"score_spread":0.10663469408349813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366453124","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9869854,0.001142106,0.00018424376,0.0070228977,0.00030840738,0.0009801418,0.000001545368,0.00000138072,0.0033738657],"genre_scores_gemma":[0.9972674,0.00001768108,0.0019152804,0.00060136506,0.00007030676,0.000102017446,0.000005239723,0.0000035891576,0.000017089516],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99244994,0.0032864653,0.0012139233,0.00013372742,0.0027400162,0.00017590918],"domain_scores_gemma":[0.99509424,0.001739636,0.0006999156,0.00015447591,0.002200057,0.00011167066],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10343567,0.0000786463,0.0001529337,0.00069685915,0.00006440941,0.00014706788,0.00035389725,0.000050053484,0.0007807884],"category_scores_gemma":[0.01709892,0.000054236567,0.000034158213,0.00047697476,0.000089739806,0.00088856934,0.000010772401,0.00017525477,0.00001398244],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057743244,0.00007716769,0.023432655,0.0000013972773,0.000013125892,0.0000014461608,0.030204706,0.0017417766,0.000016309668,0.0011203068,0.00018496269,0.9431484],"study_design_scores_gemma":[0.003315239,0.0002986642,0.71374017,0.000116344476,0.00009823997,0.000076595694,0.08734853,0.073905334,0.00020381856,0.009462789,0.111264214,0.0001700897],"about_ca_topic_score_codex":0.00019620392,"about_ca_topic_score_gemma":0.04265371,"teacher_disagreement_score":0.9429783,"about_ca_system_score_codex":0.0004725236,"about_ca_system_score_gemma":0.004349501,"threshold_uncertainty_score":0.9911805},"labels":[],"label_agreement":null},{"id":"W4366453126","doi":"10.3138/cjpe.23.016","title":"Donna M. Mertens. (2009). <i>Transformative Research and Evaluation.</i> New York: Guilford Press. 402 pages.","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Transformative learning; Psychology; Pedagogy","score_opus":0.7747036186145636,"score_gpt":0.5580962906247038,"score_spread":0.21660732798985982,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366453126","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85835034,0.028672252,0.0038200545,0.03035682,0.0029446722,0.009998109,0.00005863097,0.00005710603,0.065742046],"genre_scores_gemma":[0.994066,0.00043574325,0.003667755,0.00034517876,0.00039709883,0.00013525924,0.000024982468,0.000019806495,0.0009081639],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98831093,0.001645452,0.001508974,0.0003907493,0.007500171,0.0006436997],"domain_scores_gemma":[0.98632485,0.00056876603,0.00068646134,0.0004910624,0.010745513,0.0011833578],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.04281211,0.00021617333,0.00039723172,0.0012047263,0.0008712383,0.0005851151,0.0007308683,0.00015686353,0.0024290187],"category_scores_gemma":[0.0044866283,0.00016754455,0.00013132258,0.0014661581,0.00043788215,0.001479276,0.000027011612,0.000586969,0.00010353308],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004833996,0.00006311267,0.005081261,0.0000062302593,0.000054000535,0.000011136714,0.0071244817,0.0013003722,0.00003226106,0.0002857672,0.18938059,0.79661244],"study_design_scores_gemma":[0.00582243,0.0025612796,0.114764325,0.00017029185,0.00026027326,0.00070152147,0.0038519618,0.13117242,0.0005846654,0.038607404,0.70095205,0.0005513892],"about_ca_topic_score_codex":0.0022101284,"about_ca_topic_score_gemma":0.01711246,"teacher_disagreement_score":0.79606104,"about_ca_system_score_codex":0.00056970713,"about_ca_system_score_gemma":0.0140418345,"threshold_uncertainty_score":0.9984829},"labels":[],"label_agreement":null},{"id":"W4366453138","doi":"10.3138/cjpe.28.007","title":"The Five Cs for Innovating in Evaluation Capacity Building: Lessons from the Field","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Ontario Centre of Excellence for Child and Youth Mental Health","funders":"","keywords":"Excellence; Coaching; Curiosity; Capacity building; Courage; Key (lock); Field (mathematics); Public relations; Business; Psychology; Knowledge management; Political science; Economic growth; Management; Economics; Computer science; Social psychology","score_opus":0.5626414314017943,"score_gpt":0.558423062289945,"score_spread":0.004218369111849363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366453138","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93155926,0.0004477229,0.0028542958,0.060239814,0.0011037006,0.0031771169,0.000009804258,0.0000043938066,0.00060389616],"genre_scores_gemma":[0.99317634,0.0000074240766,0.0049661393,0.0009494089,0.00028649007,0.0005547203,0.000010134911,0.000007170192,0.000042145974],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99542874,0.0009285325,0.0010475519,0.00019057113,0.0021044852,0.0003000992],"domain_scores_gemma":[0.9880474,0.004697798,0.00088200055,0.00035187212,0.0058641895,0.00015672922],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.035017442,0.00010951881,0.00016917224,0.00024685045,0.0006178138,0.0009340288,0.0006971493,0.00008364285,0.00082716095],"category_scores_gemma":[0.02851769,0.00006022901,0.00009965921,0.0008752045,0.000086748296,0.000667791,0.000015856347,0.0003009583,0.000023363558],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007953139,0.000012005782,0.014538422,8.275077e-7,0.000016612941,1.3685998e-7,0.0015410719,0.0022327583,0.0000541423,0.0012942336,0.014541472,0.96576035],"study_design_scores_gemma":[0.001136034,0.0002739337,0.24074544,0.00006331279,0.00006570035,0.0000036959775,0.0040986845,0.56871736,0.00017208907,0.15101436,0.03358428,0.00012508688],"about_ca_topic_score_codex":0.0067052683,"about_ca_topic_score_gemma":0.09823795,"teacher_disagreement_score":0.9656353,"about_ca_system_score_codex":0.00044582557,"about_ca_system_score_gemma":0.0035365757,"threshold_uncertainty_score":0.99990916},"labels":[],"label_agreement":null},{"id":"W4366453266","doi":"10.3138/cjpe.0027.004","title":"Preparing, Governing, and Managing the Paris Declaration Evaluation","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Credibility; Declaration; Stakeholder; Process management; Corporate governance; Joint (building); Stakeholder engagement; Business; Quality (philosophy); Public relations; Environmental resource management; Political science; Economics; Engineering","score_opus":0.30437993122529117,"score_gpt":0.5013173760618445,"score_spread":0.1969374448365533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366453266","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9627181,0.0022209876,0.002794249,0.008813122,0.0009879594,0.003520888,0.0000024599417,0.00001398902,0.01892824],"genre_scores_gemma":[0.9976253,0.00003589051,0.0014372418,0.00027422505,0.00016692218,0.00022327721,0.000010070746,0.000008441475,0.00021861865],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9947201,0.0009598923,0.0008510794,0.00021565658,0.0030086047,0.00024465454],"domain_scores_gemma":[0.99448884,0.00029147943,0.00089301285,0.00032104107,0.0037002412,0.000305381],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.025586603,0.00012032038,0.0001682313,0.0003624253,0.00045245598,0.0012604416,0.0003630781,0.00006941166,0.0032998493],"category_scores_gemma":[0.0031200568,0.000077134886,0.000076550365,0.0005100387,0.000104495746,0.0013780709,0.00002036324,0.00021182759,0.0001655178],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037691902,0.0000111519175,0.03467151,0.0000022338659,0.00002168622,2.8699276e-7,0.001428561,0.0035158559,0.00002453644,0.00029313544,0.013881922,0.94614536],"study_design_scores_gemma":[0.00063322537,0.00022123444,0.29035982,0.000031128886,0.00013683275,0.00003516933,0.002028074,0.6224361,0.000032583506,0.020883063,0.06308763,0.00011509719],"about_ca_topic_score_codex":0.0017052249,"about_ca_topic_score_gemma":0.017037885,"teacher_disagreement_score":0.94603026,"about_ca_system_score_codex":0.00039319962,"about_ca_system_score_gemma":0.0025190695,"threshold_uncertainty_score":0.99977636},"labels":[],"label_agreement":null},{"id":"W4366453408","doi":"10.3138/cjpe.020.002","title":"Ensuring Quality for Evaluation: Lessons from Auditors","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Audit; Documentation; Quality assurance; Quality (philosophy); Variety (cybernetics); Quality audit; Business; Point (geometry); Accounting; Process management; Computer science; Marketing","score_opus":0.6231916254204312,"score_gpt":0.6243646498296325,"score_spread":0.0011730244092013065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366453408","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9556951,0.0013433308,0.0065457746,0.025293648,0.0040852237,0.0031450898,0.000086410764,0.000020656478,0.0037848016],"genre_scores_gemma":[0.9851113,0.0000067155224,0.012242304,0.00027139523,0.0019320875,0.00021837653,0.00005230441,0.000012488307,0.00015303973],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9930303,0.0010257146,0.0014847036,0.00030077575,0.003828621,0.00032987838],"domain_scores_gemma":[0.9898871,0.000920682,0.0011974145,0.00039987045,0.007075246,0.00051969144],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.043579314,0.00014812953,0.00031098988,0.0005469818,0.00036802955,0.000511034,0.0005448051,0.00011116214,0.0053337137],"category_scores_gemma":[0.009494307,0.00012204368,0.00023240656,0.0005267738,0.000074818534,0.00094577024,0.000011576918,0.00018953854,0.000118819364],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002184201,0.000036794005,0.0069794143,0.0000019570894,0.000036871483,3.428305e-7,0.0009794647,0.012489028,0.000050916362,0.00041907508,0.008313416,0.9706709],"study_design_scores_gemma":[0.0038944543,0.00034932978,0.25035056,0.000060651415,0.00028926702,0.000009107907,0.0018728751,0.31541735,0.00044674738,0.033565976,0.39344126,0.00030240495],"about_ca_topic_score_codex":0.000676141,"about_ca_topic_score_gemma":0.052502412,"teacher_disagreement_score":0.97036844,"about_ca_system_score_codex":0.0009757869,"about_ca_system_score_gemma":0.007917928,"threshold_uncertainty_score":0.99884915},"labels":[],"label_agreement":null},{"id":"W4366465575","doi":"10.33137/ic.v6i.40980","title":"The Siena Summer Program: Objectives vs Results","year":2023,"lang":"en","type":"article","venue":"Italian Canadiana","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"University of Toronto; Università degli Studi di Siena","keywords":"Environmental science","score_opus":0.206978249313224,"score_gpt":0.4934986013237867,"score_spread":0.2865203520105627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366465575","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3884131,0.00035250155,0.000020987678,0.1315395,0.004000014,0.001626024,0.00038770228,0.00046218958,0.473198],"genre_scores_gemma":[0.93801403,0.00003041261,0.000059379407,0.00081473397,0.00014413404,0.0000769491,0.000023745728,0.000011245176,0.06082538],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99726033,0.00015937003,0.00045935143,0.0003662595,0.001273899,0.00048081728],"domain_scores_gemma":[0.99775654,0.0008703204,0.00013084625,0.0006837195,0.00027144965,0.00028714936],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003792164,0.00011250885,0.00012944998,0.00025473046,0.0005931458,0.0005860446,0.00068745454,0.00004899628,0.00032364315],"category_scores_gemma":[0.0019250812,0.00006815046,0.000085280786,0.0019109249,0.00014687625,0.00026387695,0.00005134686,0.00011537371,0.004134286],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029553967,0.000011209868,0.0051297704,0.0000012137626,0.000018113653,0.000017742936,0.001171373,0.00012228476,0.000007074395,0.003512719,0.6924504,0.2975285],"study_design_scores_gemma":[0.0002093054,0.000073990224,0.13586363,0.0000051751204,0.0000034063326,0.0000016718332,0.0021663962,0.0036065457,0.000032192664,0.0031387915,0.8547972,0.000101727426],"about_ca_topic_score_codex":0.0040751467,"about_ca_topic_score_gemma":0.17865068,"teacher_disagreement_score":0.5496009,"about_ca_system_score_codex":0.00013228822,"about_ca_system_score_gemma":0.0006473474,"threshold_uncertainty_score":0.9966411},"labels":[],"label_agreement":null},{"id":"W4366528077","doi":"10.1080/01924036.2023.2202868","title":"And you know, we’re on each other’s team: Lessons from an in-depth analysis of researcher–practitioner partnerships in criminal justice research","year":2023,"lang":"en","type":"article","venue":"International Journal of Comparative and Applied Criminal Justice","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University","funders":"","keywords":"Criminal justice; Economic Justice; Public relations; Field (mathematics); Process (computing); Sociology; Field research; Political science; Criminology; Law; Computer science; Social science","score_opus":0.7128288832103599,"score_gpt":0.6339662920640527,"score_spread":0.07886259114630711,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366528077","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98652697,0.00017260028,0.00057201163,0.0036845205,0.0001609016,0.00013010252,0.000054195483,0.0000048440693,0.008693878],"genre_scores_gemma":[0.99833316,0.0004924824,0.00052430126,0.00020918727,0.0002002269,0.000013332288,0.000024670602,0.000007665598,0.00019499585],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9941754,0.0009120944,0.0010313801,0.00039600235,0.003211459,0.0002737163],"domain_scores_gemma":[0.99239635,0.005237762,0.00050035026,0.00021699461,0.0014708133,0.00017770221],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008956745,0.00016023743,0.0005195901,0.0028544024,0.00014798965,0.0002592027,0.0006756969,0.0000819379,0.00033335277],"category_scores_gemma":[0.00076828606,0.00012492725,0.000076076634,0.0017557875,0.00028612764,0.00055689237,0.00014221373,0.0007786997,0.000040001603],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.02328498,0.0048148152,0.046991825,0.00040750043,0.0025524085,0.00042849066,0.34547508,0.11236515,0.028510716,0.31140065,0.014291502,0.10947689],"study_design_scores_gemma":[0.0025659306,0.0007769374,0.3515305,0.0003279198,0.0017272469,0.000014839716,0.55252755,0.06956306,0.0026574521,0.013907259,0.0040942067,0.0003071177],"about_ca_topic_score_codex":0.00015854095,"about_ca_topic_score_gemma":0.0014242064,"teacher_disagreement_score":0.3045387,"about_ca_system_score_codex":0.00012291122,"about_ca_system_score_gemma":0.0002690895,"threshold_uncertainty_score":0.5094385},"labels":[],"label_agreement":null},{"id":"W4366675053","doi":"10.3138/cjpe.0017.005","title":"Evaluation Capacity Building in the Voluntary/Nonprofit Sector","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Government of Ontario","funders":"","keywords":"Nonprofit sector; Work (physics); Capacity building; Business; Process (computing); Resource (disambiguation); Public relations; Knowledge management; Political science; Economic growth; Economics; Computer science","score_opus":0.582860873132594,"score_gpt":0.5211126018594392,"score_spread":0.06174827127315485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366675053","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9875314,0.00049924076,0.000986337,0.001731324,0.0011188982,0.001812441,0.0000037099605,0.0000045164466,0.0063121044],"genre_scores_gemma":[0.99569595,0.0000043139344,0.0036238977,0.00033899618,0.00015252309,0.0001408284,0.000004822446,0.00000820053,0.000030449035],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98853713,0.0040572253,0.001135702,0.00024702182,0.00566037,0.00036253882],"domain_scores_gemma":[0.9939224,0.0004631955,0.0006939337,0.0003876329,0.00427187,0.0002609563],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.105819605,0.00014066575,0.0002226507,0.00082134403,0.00027045913,0.0005022038,0.00061242824,0.000090051,0.0042285025],"category_scores_gemma":[0.011439119,0.00009298242,0.00012956753,0.0014956807,0.000087695575,0.0008248312,0.0000053140348,0.00036115825,0.0000596488],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011437353,0.000088354966,0.16528088,0.000004636265,0.00003484364,0.0000070215324,0.005522183,0.009857107,0.00010822889,0.0038868308,0.0032225165,0.81197596],"study_design_scores_gemma":[0.0029910868,0.0007308521,0.5688617,0.00009314353,0.00032283418,0.00020429656,0.0066983765,0.2254775,0.0003234816,0.113138266,0.0807993,0.00035917544],"about_ca_topic_score_codex":0.001103383,"about_ca_topic_score_gemma":0.05064383,"teacher_disagreement_score":0.8116168,"about_ca_system_score_codex":0.0009895322,"about_ca_system_score_gemma":0.0072561917,"threshold_uncertainty_score":0.9983717},"labels":[],"label_agreement":null},{"id":"W4366675147","doi":"10.3138/cjpe.0016.009","title":"Program Evaluation in the Government of the Northwest Territories, 1967–2000","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Government of Northwest Territories","funders":"","keywords":"Cabinet (room); Documentation; Government (linguistics); Business; Public administration; Political science; Public relations; Geography; Archaeology; Computer science","score_opus":0.29140734594736467,"score_gpt":0.46572274541019243,"score_spread":0.17431539946282776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366675147","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.974967,0.0010621111,0.000036906065,0.009629678,0.0017719705,0.0057133217,0.00003234162,0.0000066902544,0.006780004],"genre_scores_gemma":[0.99844897,0.000016411448,0.00062031014,0.00020671413,0.00021697175,0.00038619922,0.000008489916,0.000007834803,0.00008812411],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98809665,0.0016944478,0.0013049414,0.00020540363,0.008400128,0.0002984269],"domain_scores_gemma":[0.9957556,0.00030407318,0.001096418,0.00055609486,0.0021117448,0.00017607759],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.025967246,0.00014431165,0.00022782598,0.00024143452,0.00023742829,0.00033901914,0.0010423209,0.00008370956,0.0023083403],"category_scores_gemma":[0.0030159804,0.00007897049,0.00017108688,0.0014755435,0.00016230498,0.00051344343,0.000017907927,0.00030455829,0.000014478865],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006913751,0.000147009,0.15572533,0.0000031736133,0.00001201996,0.0000012977248,0.0037689975,0.002193182,0.0000057485654,0.000118800104,0.0012217009,0.8367958],"study_design_scores_gemma":[0.001275206,0.00060252415,0.70814395,0.00008516943,0.00014083284,0.00003445077,0.0035029955,0.14757909,0.00005940901,0.0024168945,0.13602704,0.00013243228],"about_ca_topic_score_codex":0.001585361,"about_ca_topic_score_gemma":0.1698806,"teacher_disagreement_score":0.8366634,"about_ca_system_score_codex":0.0010432311,"about_ca_system_score_gemma":0.0031088777,"threshold_uncertainty_score":0.9986037},"labels":[],"label_agreement":null},{"id":"W4366675148","doi":"10.3138/cjpe.0016.005","title":"Evaluation Policy and Practice in Ontario","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Laurentian University","funders":"","keywords":"Optimism; Government (linguistics); Public service; Public policy; Public administration; Service (business); Political science; Business; Public relations; Program evaluation; Psychology; Marketing; Social psychology","score_opus":0.5598804861443701,"score_gpt":0.5713121749383623,"score_spread":0.011431688793992145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366675148","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.866139,0.0028368838,0.00020002469,0.021185178,0.0009431038,0.0023981836,0.0000023715531,0.000007862753,0.10628742],"genre_scores_gemma":[0.9962285,0.00003092564,0.002710732,0.0004228483,0.00013586406,0.00005320732,0.0000029469356,0.0000060641332,0.00040887084],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99333286,0.0016159018,0.0008989659,0.00019820592,0.0037022752,0.00025179322],"domain_scores_gemma":[0.9933898,0.00073191174,0.00064682175,0.00021690346,0.004641399,0.00037317726],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04925423,0.000101494166,0.000184635,0.0012831511,0.00013087588,0.0004347314,0.00023807648,0.00007621585,0.006143807],"category_scores_gemma":[0.034330625,0.00008398706,0.00005252044,0.00090726983,0.00007035401,0.0014338404,0.000009764545,0.00026440664,0.00008033397],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008368435,0.000045310015,0.018666396,7.304803e-7,0.000012959136,0.000004580003,0.005237186,0.0016932487,0.0000070637484,0.00034865053,0.0011880453,0.97278744],"study_design_scores_gemma":[0.0027819881,0.0007163089,0.45129615,0.00006040657,0.00020778143,0.00029486668,0.0029384657,0.2410479,0.000010777023,0.023540344,0.27688834,0.00021667806],"about_ca_topic_score_codex":0.05250958,"about_ca_topic_score_gemma":0.8428295,"teacher_disagreement_score":0.9725708,"about_ca_system_score_codex":0.0019338197,"about_ca_system_score_gemma":0.009651016,"threshold_uncertainty_score":0.99596334},"labels":[],"label_agreement":null},{"id":"W4366675196","doi":"10.3138/cjpe.0016.008","title":"Evaluation in Newfoundland: Then Was Then and Now Is Now","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Accountability; Plan (archaeology); Audit; Business; Program evaluation; Strategic planning; Public administration; Political science; Public relations; Accounting; Process management; Environmental resource management; Geography; Marketing; Economics; Archaeology","score_opus":0.39082580630976066,"score_gpt":0.49751921985585973,"score_spread":0.10669341354609907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366675196","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9674581,0.0026635749,0.00020320968,0.012690771,0.00079661934,0.0017647385,0.00000788684,0.000008520543,0.0144065535],"genre_scores_gemma":[0.997668,0.000110602836,0.0010411469,0.00044468744,0.00018062026,0.00007253363,0.0000062598583,0.00001108633,0.00046502834],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99357027,0.001026075,0.0009987672,0.00027642574,0.003807208,0.000321271],"domain_scores_gemma":[0.99535173,0.00026904087,0.00060862006,0.00031666493,0.0030426802,0.0004112534],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.029139921,0.00015252663,0.00027247355,0.0009813786,0.00018738477,0.00056574005,0.00038438808,0.000107214735,0.010154459],"category_scores_gemma":[0.0022368806,0.00011586969,0.00008971823,0.0008203166,0.00009393789,0.0009492162,0.000014727623,0.00024833466,0.00025023022],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007896987,0.000041096595,0.10203213,0.0000023833884,0.000021218713,0.0000031023471,0.0046679783,0.0009360438,0.000013933472,0.00007601506,0.0056857504,0.88651246],"study_design_scores_gemma":[0.0022261867,0.00045186267,0.30296546,0.00006762569,0.00014480474,0.000054361044,0.0012850494,0.61196613,0.000015056553,0.021788988,0.058839448,0.00019501481],"about_ca_topic_score_codex":0.0009619505,"about_ca_topic_score_gemma":0.121901825,"teacher_disagreement_score":0.88631743,"about_ca_system_score_codex":0.00081850594,"about_ca_system_score_gemma":0.0020499618,"threshold_uncertainty_score":0.9997048},"labels":[],"label_agreement":null},{"id":"W4366675198","doi":"10.3138/cjpe.0020.010","title":"Program Evaluation in the Government of Canada: Plus ça change …","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Laurentian University","funders":"","keywords":"Treasury; Government (linguistics); Public administration; State (computer science); Function (biology); State government; Political science; Business; Accounting; Local government; Computer science; Law","score_opus":0.4207187134281067,"score_gpt":0.5004735994535432,"score_spread":0.07975488602543651,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366675198","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96526164,0.0013881245,0.00016141654,0.009419677,0.0012216889,0.007873292,0.000023692122,0.000006531378,0.014643953],"genre_scores_gemma":[0.99782443,0.0000061301707,0.0008658917,0.0002355331,0.00026085353,0.0007054285,0.00001638308,0.000007785037,0.0000775486],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98748535,0.0011934239,0.001358171,0.00020555346,0.009395984,0.000361502],"domain_scores_gemma":[0.9954495,0.00028136472,0.0011036822,0.00035132223,0.0026297814,0.00018434525],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.032794233,0.00014105448,0.0002708852,0.0003184435,0.00015706898,0.0002116436,0.0006350332,0.000071240866,0.0010627916],"category_scores_gemma":[0.0017902871,0.0000941436,0.00010155954,0.0011348684,0.00007872443,0.00049315393,0.000011443785,0.00021381413,0.000004586788],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018903935,0.00009594686,0.030382296,0.000005928741,0.000010496578,0.00000567317,0.0011984837,0.0062994044,0.000009360567,0.0004696889,0.005651333,0.9558525],"study_design_scores_gemma":[0.0017113424,0.0005321056,0.73396325,0.000074849806,0.000113006216,0.000024084406,0.0037239674,0.1895694,0.000081656384,0.0050247046,0.06502542,0.00015619502],"about_ca_topic_score_codex":0.17170388,"about_ca_topic_score_gemma":0.95555145,"teacher_disagreement_score":0.9556963,"about_ca_system_score_codex":0.00235609,"about_ca_system_score_gemma":0.015591209,"threshold_uncertainty_score":0.9998504},"labels":[],"label_agreement":null},{"id":"W4366675251","doi":"10.3138/cjpe.019.005","title":"An Empirical Study of Building the Evaluation Capacity of K–12 Site-Managed Project Personnel","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Argument (complex analysis); Psychology; Medical education; Program evaluation; Professional development; Evaluation methods; Capacity building; Applied psychology; Pedagogy; Political science; Engineering; Medicine","score_opus":0.5928942452671162,"score_gpt":0.566262734771,"score_spread":0.02663151049611623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366675251","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9944438,0.00009907216,0.0012111448,0.0006277495,0.00038557878,0.0029040407,0.000007249643,0.0000055465807,0.00031582586],"genre_scores_gemma":[0.9969576,0.00000232172,0.0027468028,0.000060917668,0.00012281143,0.000087918175,0.0000066468738,0.000010163681,0.0000048149377],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9907619,0.0022716732,0.0014578227,0.00027240903,0.0049729184,0.0002633174],"domain_scores_gemma":[0.9929871,0.00029284475,0.0015444566,0.000541518,0.004391194,0.00024289322],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.037384216,0.00015375638,0.00036089946,0.0009283377,0.00033496783,0.00021041048,0.00070394174,0.00008309857,0.0003394002],"category_scores_gemma":[0.0041059125,0.00009972147,0.00015595979,0.0013183652,0.00016670524,0.0008497999,0.000015408137,0.0002865021,0.00000414697],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000107049505,0.0010994736,0.30569777,0.000018014194,0.00014733127,0.000003895128,0.10800434,0.14520067,0.0017426342,0.0002048066,0.00024998165,0.43752405],"study_design_scores_gemma":[0.005159802,0.005559172,0.67198354,0.00010071629,0.0006424922,0.000036261645,0.07724205,0.23164016,0.00080289756,0.006179592,0.00041333836,0.00023996043],"about_ca_topic_score_codex":0.0044833035,"about_ca_topic_score_gemma":0.065653175,"teacher_disagreement_score":0.43728408,"about_ca_system_score_codex":0.0004810285,"about_ca_system_score_gemma":0.0062503275,"threshold_uncertainty_score":0.99938333},"labels":[],"label_agreement":null},{"id":"W4366675260","doi":"10.3138/cjpe.016.005","title":"The Politics and Practice of Empowerment Evaluation and Social Interventions: Lessons from the Atlantic Community Action Program for Children Regional Evaluation","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Nova Scotia Health Authority; Health Canada; Saint Mary's University","funders":"Health Canada","keywords":"Empowerment; Popularity; Politics; Context (archaeology); Sociology; Participatory action research; Action (physics); Citizen journalism; Psychological intervention; Public relations; Political science; Psychology; Social psychology; Law","score_opus":0.596221525877389,"score_gpt":0.6159796392535666,"score_spread":0.01975811337617761,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366675260","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9706271,0.001928654,0.00080149836,0.02131672,0.00038295757,0.0047841626,0.000029371513,0.000006949749,0.00012255163],"genre_scores_gemma":[0.99733293,0.00016752041,0.001425062,0.00014810653,0.00022390252,0.0004826315,0.0001924307,0.000010071079,0.00001734624],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9905504,0.0050215693,0.0011364849,0.00019688474,0.0028362712,0.00025840147],"domain_scores_gemma":[0.98722243,0.0032152894,0.0016004278,0.00031166524,0.007494313,0.00015587086],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05776846,0.00014679575,0.000226723,0.00023289371,0.0016813725,0.000640118,0.0003934441,0.000098262084,0.00015354661],"category_scores_gemma":[0.010431172,0.000090658425,0.0001971945,0.00041567668,0.00035126103,0.0007475113,0.000030745545,0.00032433262,0.000002054069],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000099797144,0.00015458156,0.028171808,0.00000642394,0.00016050713,1.1103976e-7,0.003356091,0.00033209712,0.000012631869,0.0007026338,0.0021952125,0.9648081],"study_design_scores_gemma":[0.0025055297,0.0011216697,0.84136564,0.00011611452,0.001270877,0.000093591894,0.013533179,0.089159064,0.0000071159357,0.033785105,0.016901733,0.0001404074],"about_ca_topic_score_codex":0.0053422265,"about_ca_topic_score_gemma":0.049401447,"teacher_disagreement_score":0.9646677,"about_ca_system_score_codex":0.00053645816,"about_ca_system_score_gemma":0.002924424,"threshold_uncertainty_score":0.9996183},"labels":[],"label_agreement":null},{"id":"W4366675286","doi":"10.3138/cjpe.0020.003","title":"Program Evaluation in Canada Seen through the Articles Published in CJPE","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"St. Lawrence College; Université Laval","funders":"","keywords":"Honour; Audit; Political science; Library science; Sociology; Public administration; Law; Management; Computer science; Economics","score_opus":0.3053697535010307,"score_gpt":0.4944470437878705,"score_spread":0.18907729028683984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366675286","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9760589,0.00074259826,0.000087107204,0.012577037,0.0007951326,0.0037925625,0.0000055234796,0.0000074716622,0.0059336456],"genre_scores_gemma":[0.99759537,0.0000048470697,0.0013226824,0.00029081813,0.00016826416,0.0005200034,0.00002577429,0.000010599564,0.000061639694],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.991391,0.001554294,0.0017317845,0.00029493298,0.0045227488,0.00050522835],"domain_scores_gemma":[0.99529666,0.00039475615,0.00081234117,0.00040782397,0.0028819938,0.00020643674],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.027122023,0.00016378806,0.00029105807,0.0006267376,0.00017416629,0.0007509827,0.0006864196,0.00007677641,0.0023275716],"category_scores_gemma":[0.0035320648,0.00010987124,0.00008558932,0.002428126,0.0000905477,0.0014352925,0.000016700687,0.00037216654,0.000019516758],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012605017,0.0000668171,0.22276624,0.0000022488935,0.0000073314245,0.000007855936,0.0007311204,0.03761829,0.000006682436,0.00028503305,0.0055539105,0.73294187],"study_design_scores_gemma":[0.0014036762,0.00015729229,0.6818048,0.00004291845,0.00003980393,0.000016903745,0.0028912162,0.25060043,0.000045668563,0.02862828,0.03422983,0.00013919237],"about_ca_topic_score_codex":0.8542695,"about_ca_topic_score_gemma":0.99891144,"teacher_disagreement_score":0.7328027,"about_ca_system_score_codex":0.0032143628,"about_ca_system_score_gemma":0.032147393,"threshold_uncertainty_score":0.99858445},"labels":[],"label_agreement":null},{"id":"W4366675294","doi":"10.3138/cjpe.0020.007","title":"Evaluation in Canada’s Social Services: Progress, Rifts, and Challenges","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Conceptualization; Empowerment; Business; Investment (military); Service (business); Public relations; Knowledge management; Tertiary sector of the economy; Marketing; Economic growth; Economics; Political science; Computer science","score_opus":0.3307560674375689,"score_gpt":0.4735947203942487,"score_spread":0.1428386529566798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366675294","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96505666,0.016029723,0.000013820543,0.012170779,0.00066200836,0.0015296459,0.000010236571,0.000005883834,0.0045212703],"genre_scores_gemma":[0.9989713,0.00007301563,0.0004759105,0.0000976578,0.00024570886,0.000088889436,0.000021188225,0.000008863849,0.000017482342],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9932548,0.00096793403,0.0010020022,0.00024290843,0.0042150295,0.00031733242],"domain_scores_gemma":[0.99527663,0.00011728756,0.00069776515,0.00016250976,0.0035161413,0.00022964357],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022686614,0.00013687517,0.0002586883,0.0005799301,0.0001997511,0.00028632232,0.00031342116,0.00007892254,0.0005331728],"category_scores_gemma":[0.0003618398,0.000114231785,0.000049823222,0.0005189286,0.00007490754,0.00062978955,0.000011860652,0.00018022135,0.00000787005],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007671422,0.000025001898,0.08728406,0.000013902796,0.000011182377,0.000005351703,0.0008295034,0.00085634796,0.0000023788664,0.0004670437,0.00055892963,0.90993863],"study_design_scores_gemma":[0.0012774951,0.00011945634,0.8521433,0.000062134925,0.000087388755,0.000021584816,0.0035865076,0.09116993,0.000010268304,0.0141871115,0.037188817,0.0001460011],"about_ca_topic_score_codex":0.574364,"about_ca_topic_score_gemma":0.9985322,"teacher_disagreement_score":0.9097926,"about_ca_system_score_codex":0.0017950571,"about_ca_system_score_gemma":0.027459234,"threshold_uncertainty_score":0.97805417},"labels":[],"label_agreement":null},{"id":"W4366678314","doi":"10.3138/cjpe.017.001","title":"Les coûts de la non-évaluation des politiques de l’éducation au Québec","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université TÉLUQ; Université Laval","funders":"","keywords":"Ideology; Sociology; Interpretation (philosophy); Valuation (finance); Positive economics; Welfare economics; Relevance (law); Epistemology; Political science; Economics; Philosophy; Law","score_opus":0.6347540541420319,"score_gpt":0.5938711188532354,"score_spread":0.040882935288796496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366678314","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9789403,0.0004790098,0.0034220142,0.0023653763,0.00029315075,0.0004734095,0.000002905034,0.000012102304,0.014011742],"genre_scores_gemma":[0.9920227,0.00006735255,0.006954966,0.00016200825,0.00028886544,0.00006992748,0.0000059183953,0.000012492046,0.0004157791],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9955552,0.0016151993,0.000762905,0.00016822205,0.0015291215,0.0003693419],"domain_scores_gemma":[0.99525785,0.00056508597,0.0005764858,0.00022453158,0.0028398002,0.00053622737],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.020063901,0.0001260785,0.00018613736,0.0006662761,0.0005316754,0.00037729362,0.0003615159,0.00012504078,0.002339484],"category_scores_gemma":[0.006728522,0.00010755255,0.00012216094,0.00054634415,0.0002464478,0.0006975997,0.000007386429,0.0002198393,0.00007469084],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000004869396,0.000054434357,0.16855009,0.0000044188814,0.00001584634,0.0000033435297,0.025131248,0.0015929266,0.00007652918,0.00019660697,0.004081676,0.800288],"study_design_scores_gemma":[0.00068478467,0.00035991654,0.7981979,0.00006515071,0.000079103105,0.00020968722,0.0042497437,0.1627588,0.00027846007,0.0120991375,0.02085995,0.00015733397],"about_ca_topic_score_codex":0.1319085,"about_ca_topic_score_gemma":0.42641595,"teacher_disagreement_score":0.80013067,"about_ca_system_score_codex":0.0050131883,"about_ca_system_score_gemma":0.020311449,"threshold_uncertainty_score":0.9988064},"labels":[],"label_agreement":null},{"id":"W4366678681","doi":"10.3138/cjpe.0017.003","title":"The Pitfalls and the Potential of Early Evaluation Efforts: Lessons Learned from the Health Services Sector","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Variety (cybernetics); Accountability; Protocol (science); Program evaluation; Outcome (game theory); Service delivery framework; Service (business); Psychology; Public relations; Process management; Computer science; Business; Medical education; Medicine; Political science; Marketing; Alternative medicine; Public administration","score_opus":0.2971180000051674,"score_gpt":0.5015325592971431,"score_spread":0.20441455929197572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366678681","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9543964,0.006664301,0.00048952637,0.03454263,0.0010688186,0.0022229857,0.00001883728,0.0000043551613,0.00059214584],"genre_scores_gemma":[0.9986508,0.00022084166,0.00036530616,0.0004881961,0.00014155122,0.000068576875,0.000008843999,0.000008223141,0.00004768752],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9911102,0.0040151346,0.0011030303,0.00020331432,0.0032880714,0.00028022693],"domain_scores_gemma":[0.9938389,0.0012801313,0.0014908133,0.00044924102,0.0027050464,0.00023583547],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.055949647,0.00012519685,0.0002547297,0.00014276369,0.00095548853,0.0007609216,0.0006187178,0.00005995704,0.000571428],"category_scores_gemma":[0.0022250763,0.000055815985,0.00013586089,0.00053938385,0.0003269739,0.00040300068,0.000015921498,0.00025327233,0.000011906956],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011177121,0.000022828895,0.008701558,0.0000044771164,0.00008901554,4.187998e-7,0.006629696,0.002317073,0.000021129243,0.0049816766,0.00076896546,0.9763514],"study_design_scores_gemma":[0.0073310346,0.0010411124,0.5272668,0.00018880768,0.0005253495,0.000036798374,0.020455293,0.1766882,0.00007067976,0.20158556,0.064570114,0.00024024936],"about_ca_topic_score_codex":0.005009561,"about_ca_topic_score_gemma":0.06785122,"teacher_disagreement_score":0.9761111,"about_ca_system_score_codex":0.00020205214,"about_ca_system_score_gemma":0.005712977,"threshold_uncertainty_score":0.9999237},"labels":[],"label_agreement":null},{"id":"W4366679319","doi":"10.3138/cjpe.35.2.v","title":"Editor’s Remarks","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Philosophy; Psychology; Business","score_opus":0.3130698758640696,"score_gpt":0.5203254987844013,"score_spread":0.20725562292033167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366679319","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.52900785,0.0040491326,0.027930891,0.27963135,0.053766813,0.0069849757,0.00004936131,0.000109825014,0.09846981],"genre_scores_gemma":[0.99058664,0.0000053420094,0.0038575812,0.0013054257,0.0041178796,0.000018446484,0.00000620796,0.0000075254093,0.00009497755],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9958979,0.00040524476,0.00080519787,0.00016036778,0.0025289329,0.00020235057],"domain_scores_gemma":[0.9951727,0.000161213,0.00056355965,0.00017884086,0.0030918855,0.0008318189],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010229976,0.00008598123,0.00018712904,0.0002938923,0.00013863586,0.00038374503,0.0004830046,0.0000647104,0.0061310297],"category_scores_gemma":[0.0065565505,0.000064959335,0.00011773652,0.0007403048,0.000056413235,0.00059451355,0.000009513816,0.00020880539,0.00028931972],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013141119,0.000012106104,0.0115501555,0.0000022819681,0.000014669857,0.000005402182,0.0012205056,0.0013830048,0.000036111567,0.00020052133,0.20221043,0.78335166],"study_design_scores_gemma":[0.00076907175,0.000649044,0.028208481,0.000020196903,0.00005483759,0.000017999322,0.0011803188,0.087478034,0.00007881379,0.004332372,0.877088,0.00012279728],"about_ca_topic_score_codex":0.00010812263,"about_ca_topic_score_gemma":0.0030603046,"teacher_disagreement_score":0.7832289,"about_ca_system_score_codex":0.00018679582,"about_ca_system_score_gemma":0.0055253017,"threshold_uncertainty_score":0.9947775},"labels":[],"label_agreement":null},{"id":"W4366706691","doi":"10.3138/cjpe.34.3.521","title":"Peer Reviewers for Volume 34 / Examinateurs des manuscrits du volume 34","year":2020,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Volume (thermodynamics); Psychology; Art; Thermodynamics; Physics","score_opus":0.44556158096013765,"score_gpt":0.4911233468799333,"score_spread":0.04556176591979566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366706691","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18019208,0.08272624,0.03768063,0.66145,0.018055426,0.010945417,0.00033439175,0.000057257985,0.008558517],"genre_scores_gemma":[0.90872353,0.001576338,0.039519552,0.0052546966,0.003945916,0.00047736106,0.00016348666,0.00010473278,0.040234376],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99183095,0.0012886066,0.0018798687,0.0004831813,0.0037296505,0.00078771985],"domain_scores_gemma":[0.98130196,0.00029333917,0.0012551649,0.00033864455,0.014918064,0.0018928177],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.027295433,0.00033695914,0.000630691,0.0005141935,0.0006108164,0.0011059793,0.0009028508,0.00023264028,0.011731302],"category_scores_gemma":[0.018961819,0.0003135777,0.00046130392,0.0013150497,0.00045287315,0.0018428903,0.0000290066,0.00044780393,0.0007539425],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003221082,0.000050492872,0.016492423,0.000119994686,0.00005978346,0.000016378273,0.0031754964,0.0011492248,0.00000907297,0.00030976924,0.20148015,0.777105],"study_design_scores_gemma":[0.0012451335,0.0017908213,0.020337861,0.0003097536,0.00043663045,0.00006744353,0.0033529643,0.20513165,0.000020469419,0.0027451394,0.7642815,0.0002806293],"about_ca_topic_score_codex":0.0011711783,"about_ca_topic_score_gemma":0.011237496,"teacher_disagreement_score":0.77682436,"about_ca_system_score_codex":0.0014509691,"about_ca_system_score_gemma":0.009754323,"threshold_uncertainty_score":0.99993163},"labels":[],"label_agreement":null},{"id":"W4366721381","doi":"10.3138/cjpe.15.006","title":"Logic Models in Primary Care Reform: Navigating the Evaluation","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Primary care; Logic model; Nova scotia; Strengths and weaknesses; Quality (philosophy); Political science; Public administration; Process management; Business; Economic growth; Medicine; Psychology; Sociology; Economics; Family medicine","score_opus":0.4326891670577493,"score_gpt":0.5423916433560159,"score_spread":0.10970247629826657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366721381","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9403664,0.0025593964,0.00017703093,0.0038480964,0.00047204233,0.0020921177,0.0000058011406,0.000008605857,0.050470505],"genre_scores_gemma":[0.99734557,0.000034240653,0.001665738,0.0005179776,0.00015261887,0.00014759727,0.000039813305,0.00000964805,0.00008680016],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9930535,0.0012735514,0.0012239162,0.00023358518,0.0038878676,0.000327595],"domain_scores_gemma":[0.99514365,0.00017081501,0.0005827518,0.0003877822,0.0034669477,0.00024806894],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.029461728,0.00013795053,0.00023216766,0.00033624299,0.00031941093,0.0004184403,0.0006356841,0.00009531771,0.0038038446],"category_scores_gemma":[0.0007618512,0.00008566247,0.00012416978,0.0011132478,0.000096017626,0.001172638,0.000010297338,0.00047605802,0.00008853933],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013046743,0.000014849825,0.0026712392,0.00000345215,0.0000063220555,0.000002122456,0.003910898,0.092586264,0.000005176884,0.00017594366,0.00014111765,0.90046954],"study_design_scores_gemma":[0.0019609411,0.00044830565,0.14740767,0.00023702742,0.000112348374,0.00006022556,0.010895811,0.7681948,0.00002430668,0.06321129,0.0072179665,0.00022932191],"about_ca_topic_score_codex":0.001753441,"about_ca_topic_score_gemma":0.032365177,"teacher_disagreement_score":0.90024024,"about_ca_system_score_codex":0.002557547,"about_ca_system_score_gemma":0.0078569865,"threshold_uncertainty_score":0.9993734},"labels":[],"label_agreement":null},{"id":"W4366721395","doi":"10.3138/cjpe.0017.007","title":"Introducing Program Teams to Logic Models: Facilitating the Learning Process","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Health Canada","funders":"University of Ottawa","keywords":"Logic model; Process (computing); Key (lock); Computer science; Articulation (sociology); Point (geometry); Facilitation; Knowledge management; Process management; Management science; Psychology; Business; Engineering; Sociology; Political science; Mathematics","score_opus":0.367515472877912,"score_gpt":0.5381391714975737,"score_spread":0.17062369861966176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366721395","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92899436,0.0008535786,0.0388575,0.0073682875,0.0013478481,0.005143493,0.0000032450764,0.00005396156,0.017377745],"genre_scores_gemma":[0.98772985,0.0000026484843,0.011353971,0.00027332263,0.00014074724,0.00026848473,0.0000037198695,0.000011451967,0.00021578811],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99434304,0.0013388993,0.001022898,0.0002991863,0.0025637108,0.00043225088],"domain_scores_gemma":[0.9940469,0.00042956337,0.00064498663,0.0003052311,0.004079579,0.0004937344],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.031031672,0.00015350571,0.00023770153,0.00052804104,0.0006339829,0.0008261352,0.00057002343,0.00006613876,0.00085496897],"category_scores_gemma":[0.01641264,0.0000957489,0.00011684025,0.0014856121,0.00008308391,0.0007759884,0.00001104028,0.0004470427,0.00008554665],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004734057,0.000021845628,0.003547528,0.0000031089155,0.000010497071,0.0000011146326,0.0042879926,0.3951189,0.000008428144,0.00063106796,0.000321046,0.59604377],"study_design_scores_gemma":[0.00074956164,0.0015507749,0.004239885,0.00008811879,0.000083319916,0.00007682385,0.035074487,0.8327271,0.00008107216,0.054422323,0.070626065,0.0002805128],"about_ca_topic_score_codex":0.00019218375,"about_ca_topic_score_gemma":0.0056027086,"teacher_disagreement_score":0.5957632,"about_ca_system_score_codex":0.0004017035,"about_ca_system_score_gemma":0.0047791866,"threshold_uncertainty_score":0.9977568},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4366722842","doi":"10.3138/cjpe.0017.006","title":"Preparing Nonprofits for New Accountability Demands","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Accountability; Transparency (behavior); Mandate; Government (linguistics); Public relations; Business; Corporate governance; Context (archaeology); Public administration; Political science; Finance","score_opus":0.4401471567317869,"score_gpt":0.558760116059299,"score_spread":0.11861295932751209,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366722842","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9315636,0.00096016534,0.038087994,0.0019664085,0.0030169308,0.004117907,0.000009933043,0.00001900292,0.02025805],"genre_scores_gemma":[0.9822742,0.0000029495147,0.016925402,0.00013843924,0.00019051907,0.00007601397,0.000004863359,0.000008342716,0.00037926654],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99665785,0.0003458917,0.000923781,0.00021152846,0.0015764824,0.00028446998],"domain_scores_gemma":[0.9951376,0.00034232717,0.0006080746,0.00029260165,0.0030609583,0.0005584913],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02388776,0.0001056512,0.00021628017,0.0003812995,0.0002270124,0.00042526878,0.00034878548,0.00007680935,0.0016534266],"category_scores_gemma":[0.008669934,0.000082211634,0.00015334423,0.0005436637,0.000043356107,0.00073921256,0.0000050965796,0.00012323745,0.000036131933],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020445761,0.000028347564,0.07016135,0.0000053152194,0.000022426568,3.6780835e-7,0.0008858706,0.002786078,0.000029631141,0.0013872351,0.010941492,0.91373146],"study_design_scores_gemma":[0.0033974114,0.001070883,0.114584655,0.00006392237,0.00019808151,0.000065282344,0.0018114732,0.06906839,0.0009193073,0.09639748,0.71209246,0.00033065956],"about_ca_topic_score_codex":0.00031310573,"about_ca_topic_score_gemma":0.028625732,"teacher_disagreement_score":0.91340077,"about_ca_system_score_codex":0.00040335057,"about_ca_system_score_gemma":0.010238446,"threshold_uncertainty_score":0.99968046},"labels":[],"label_agreement":null},{"id":"W4366722964","doi":"10.3138/cjpe.016.006","title":"An Evaluation Framework for the Maison Decision House Substance Abuse Treatment Program","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Substance abuse; Presentation (obstetrics); Abstinence; Intervention (counseling); Program evaluation; Psychology; Substance abuse treatment; Computer science; Applied psychology; Medicine; Psychiatry; Political science","score_opus":0.4319493016960513,"score_gpt":0.5692073647062006,"score_spread":0.1372580630101493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366722964","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91015905,0.0020921712,0.07469605,0.0024199523,0.002006245,0.00837365,0.0000136677545,0.00005315444,0.00018607442],"genre_scores_gemma":[0.9419998,0.00030128955,0.055136524,0.00020726405,0.0006228775,0.0016150406,0.00002464238,0.000037616224,0.00005497787],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99274457,0.00089729426,0.0013527744,0.0004282746,0.00405071,0.0005263641],"domain_scores_gemma":[0.98913157,0.0017025182,0.0011285461,0.0008923074,0.006501521,0.00064353744],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.026400464,0.00025893375,0.0003515045,0.0006270228,0.0007516343,0.0011720987,0.0009063035,0.00018094009,0.0015928278],"category_scores_gemma":[0.0030319751,0.00015822078,0.0002847543,0.0013325843,0.00013490944,0.0011892719,0.0000035967973,0.00023559431,0.000071261195],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014836609,0.0002306742,0.014273001,0.0000014920937,0.00004562346,0.00000308881,0.0032688752,0.015836533,0.0000100698635,0.0004219253,0.000785087,0.96497524],"study_design_scores_gemma":[0.0031576364,0.004603288,0.0912153,0.000106065425,0.0005275623,0.00006854632,0.0031642702,0.64494383,0.00009564419,0.055567347,0.1962488,0.0003016839],"about_ca_topic_score_codex":0.00031127868,"about_ca_topic_score_gemma":0.053620744,"teacher_disagreement_score":0.9646736,"about_ca_system_score_codex":0.0013477666,"about_ca_system_score_gemma":0.0042086444,"threshold_uncertainty_score":0.99986476},"labels":[],"label_agreement":null},{"id":"W4366723444","doi":"10.3138/cjpe.019.006","title":"The Lay of the Land: Evaluation Practice in Canada Today","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Health Canada; University of Waterloo; Treasury Board of Canada Secretariat; Government of Canada; Ministry of Education, Recreation and Sports; Ministry of Children, Community and Social Services","funders":"","keywords":"Blueprint; Public relations; Rigour; General partnership; Variety (cybernetics); Psychology; Program evaluation; Competence (human resources); Political science; Medical education; Sociology; Computer science; Social psychology; Medicine; Public administration; Engineering","score_opus":0.22766863648326166,"score_gpt":0.5077868401683105,"score_spread":0.2801182036850489,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366723444","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95733815,0.0016703379,0.00009157909,0.032253426,0.0020799336,0.0018857163,0.0000067873207,0.0000018754652,0.004672209],"genre_scores_gemma":[0.99909425,0.000023026329,0.00039269705,0.0003272065,0.000073788164,0.000049621205,0.0000022876814,0.0000050225394,0.000032122618],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9928027,0.001370681,0.0010518067,0.00013220384,0.0044046463,0.00023800817],"domain_scores_gemma":[0.9930322,0.0008939496,0.001159818,0.00036957013,0.004367837,0.00017663123],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.033709284,0.0000879633,0.00015759148,0.00020011913,0.00026398967,0.00018196549,0.00065725937,0.000041655305,0.00033289572],"category_scores_gemma":[0.016311144,0.0000466107,0.00007688431,0.0010106079,0.000078972196,0.00051076256,0.000014467427,0.00024859203,0.000007957528],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022168302,0.000027540313,0.063515656,0.0000017630013,0.000021608426,0.0000023780276,0.0012477881,0.09099854,0.000011868655,0.000497538,0.0012184287,0.8424347],"study_design_scores_gemma":[0.0030340431,0.00030396387,0.80854696,0.00013432473,0.0001868281,0.00007425074,0.0077985274,0.042039,0.00031907263,0.02694518,0.11044127,0.00017657042],"about_ca_topic_score_codex":0.6249642,"about_ca_topic_score_gemma":0.9963583,"teacher_disagreement_score":0.84225816,"about_ca_system_score_codex":0.0022516372,"about_ca_system_score_gemma":0.06220436,"threshold_uncertainty_score":0.99499965},"labels":[],"label_agreement":null},{"id":"W4366723551","doi":"10.3138/cjpe.0020.009","title":"Evaluating School Improvement in Canada: A Case Example","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Shared Health","funders":"","keywords":"Work (physics); Action (physics); Management science; Psychology; Engineering ethics; Process management; Political science; Business; Engineering","score_opus":0.4300939707557752,"score_gpt":0.5277537046643593,"score_spread":0.09765973390858412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366723551","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9946879,0.00034579798,0.00022993448,0.0010403991,0.00071462395,0.0011518404,0.0000103147395,0.0000037991208,0.0018153707],"genre_scores_gemma":[0.9959395,0.0000014994697,0.0033864882,0.00020537396,0.00020808101,0.00010035193,0.000011803673,0.0000099126555,0.00013699726],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99404883,0.00057829916,0.0016126243,0.00025714305,0.0030818146,0.00042125845],"domain_scores_gemma":[0.9954124,0.00029723046,0.0008581113,0.0003178005,0.0026195624,0.00049489894],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.021045182,0.00014255225,0.00026972752,0.00075035245,0.00019953039,0.00033444012,0.0003589426,0.000051239498,0.0035707105],"category_scores_gemma":[0.0026578044,0.00011734617,0.000080075224,0.0010044095,0.000035462388,0.00055435585,0.000014201557,0.00026072154,0.000030608022],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000010938073,0.00003249814,0.12294089,0.0000036728554,0.000010027029,0.00027460366,0.00019260416,0.023975717,0.00010348437,0.0001382924,0.003516437,0.84880084],"study_design_scores_gemma":[0.0037914468,0.000992781,0.52443314,0.000091242175,0.00010411675,0.0011431391,0.0053563,0.42957702,0.000272111,0.012845618,0.020984164,0.00040890227],"about_ca_topic_score_codex":0.9705993,"about_ca_topic_score_gemma":0.99938196,"teacher_disagreement_score":0.84839195,"about_ca_system_score_codex":0.0042477488,"about_ca_system_score_gemma":0.053144295,"threshold_uncertainty_score":0.9995748},"labels":[],"label_agreement":null},{"id":"W4366723971","doi":"10.3138/cjpe.69574","title":"Strategies for Mentoring and Advising Evaluation Graduate Students of Colour","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Ethnic group; Graduate students; Competence (human resources); Psychology; Salient; Cultural competence; Pedagogy; Medical education; Facilitation; Identity (music); Sociology; Social psychology; Medicine; Political science","score_opus":0.6206350525934264,"score_gpt":0.6121351996873615,"score_spread":0.00849985290606492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366723971","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9929984,0.00095531,0.0021982645,0.00090850436,0.0008156063,0.0012077217,0.000007859189,0.000003309257,0.000905001],"genre_scores_gemma":[0.9950054,0.00002193406,0.0046511507,0.000046248104,0.00010531647,0.00007355754,0.000014253723,0.0000073827505,0.00007472328],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9947621,0.0005855638,0.0009478322,0.00019559606,0.0032987734,0.00021012829],"domain_scores_gemma":[0.989743,0.0002967427,0.00082175684,0.00018329869,0.008700674,0.00025451498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025287848,0.00009969567,0.0002504698,0.00041003223,0.00018861442,0.0006252756,0.0002471113,0.000054660773,0.0003619598],"category_scores_gemma":[0.0031065305,0.00008476281,0.00009492456,0.0005087145,0.00006309651,0.0007885097,0.000016351874,0.000103097635,0.0000025605923],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025744614,0.000059809197,0.027032034,0.000020400335,0.00007315041,0.0000023204987,0.0033648366,0.004578826,0.0006608844,0.0009656796,0.0006807494,0.96253556],"study_design_scores_gemma":[0.006883852,0.0017311303,0.48341492,0.00038270885,0.0008960406,0.000088716275,0.05110603,0.32761562,0.0028392768,0.10868774,0.01595386,0.00040010057],"about_ca_topic_score_codex":0.00011545256,"about_ca_topic_score_gemma":0.0055526,"teacher_disagreement_score":0.96213543,"about_ca_system_score_codex":0.00029486543,"about_ca_system_score_gemma":0.008093042,"threshold_uncertainty_score":0.99753016},"labels":[],"label_agreement":null},{"id":"W4366724034","doi":"10.3138/cjpe.019.001","title":"Toward a Best Practice for Evaluating the Impact of Government Programs on Job Creation","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Industry Canada","keywords":"Government (linguistics); Interpretation (philosophy); Strengths and weaknesses; Computer science; Management science; Engineering; Psychology","score_opus":0.5293612574148838,"score_gpt":0.6057482510986992,"score_spread":0.07638699368381541,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366724034","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97755563,0.00029994783,0.0059277005,0.0068345247,0.0005835471,0.004501705,0.000028109569,0.000006702105,0.0042621135],"genre_scores_gemma":[0.98928976,0.000010437707,0.010035341,0.00010448677,0.00018340311,0.00026845394,0.00001085165,0.000012929036,0.000084350584],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9934768,0.0006118919,0.0011853502,0.0002173905,0.0042052846,0.00030327198],"domain_scores_gemma":[0.9918616,0.0008921915,0.0017912575,0.00035347466,0.004802335,0.00029913583],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.026141243,0.00015903065,0.00026753478,0.00023863793,0.00028097208,0.00042799482,0.0005063194,0.000077861754,0.0002888215],"category_scores_gemma":[0.014999791,0.00009291763,0.00032959238,0.00070214015,0.00011277907,0.00074654724,0.000011011172,0.00020651364,0.000024568819],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022683232,0.00030321142,0.004665802,0.000006572122,0.0000987406,0.0000013207481,0.0029165526,0.074580505,0.00011231406,0.0010976166,0.00038571446,0.9156048],"study_design_scores_gemma":[0.021033894,0.1482309,0.16913868,0.0014045116,0.0022922885,0.00043625807,0.045681998,0.46767595,0.0018991004,0.10805155,0.032987516,0.0011673479],"about_ca_topic_score_codex":0.0017871564,"about_ca_topic_score_gemma":0.0038154824,"teacher_disagreement_score":0.9144375,"about_ca_system_score_codex":0.0017667419,"about_ca_system_score_gemma":0.007049449,"threshold_uncertainty_score":0.9985797},"labels":[],"label_agreement":null},{"id":"W4366725054","doi":"10.3138/cjpe.36.1.intro-eng","title":"Editor’s Remarks","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Philosophy; Psychology","score_opus":0.24907328656822922,"score_gpt":0.5260421824238015,"score_spread":0.2769688958555723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366725054","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66646135,0.00848469,0.013335736,0.060082927,0.09410904,0.0032767758,0.000038588798,0.000057031946,0.15415385],"genre_scores_gemma":[0.9874534,0.00001558392,0.007574041,0.0004703086,0.003367456,0.00002437757,0.000015936552,0.000008693564,0.0010701943],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9955894,0.00059480726,0.00080670515,0.00016702883,0.0026236614,0.00021839343],"domain_scores_gemma":[0.99150455,0.00022448297,0.0004972822,0.0003039837,0.0069848844,0.0004848157],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.014229705,0.0000816102,0.00018418452,0.0003943422,0.00016976148,0.0005016518,0.00033342568,0.00007408231,0.009902852],"category_scores_gemma":[0.0070112874,0.000064475185,0.00013294282,0.0008305793,0.000053689728,0.00055873836,0.0000106177695,0.00019507862,0.00017803586],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004771146,0.00002726466,0.013244866,0.0000018085882,0.000018455205,0.000020942118,0.00042631634,0.00077422464,0.000060187565,0.0003956445,0.1209155,0.86411],"study_design_scores_gemma":[0.0007432926,0.00022337108,0.060123153,0.000040304654,0.00006494038,0.00012366119,0.0014823956,0.019062001,0.00034195877,0.0147848455,0.9028835,0.000126558],"about_ca_topic_score_codex":0.00011833131,"about_ca_topic_score_gemma":0.016689826,"teacher_disagreement_score":0.86398345,"about_ca_system_score_codex":0.00030759434,"about_ca_system_score_gemma":0.012715749,"threshold_uncertainty_score":0.99288124},"labels":[],"label_agreement":null},{"id":"W4366725272","doi":"10.3138/cjpe.19.006","title":"Integrating Evaluative Inquiry into the Organizational Culture: A Review and Synthesis of the Knowledge Base","year":2004,"lang":"en","type":"review","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":112,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Knowledge management; Organizational culture; Organizational learning; Knowledge base; Conceptual framework; Empirical research; Sociology; Work (physics); Management science; Epistemology; Political science; Computer science; Public relations; Social science; Engineering","score_opus":0.3839810064574307,"score_gpt":0.5592321866859272,"score_spread":0.1752511802284965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366725272","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002965983,0.9939319,0.000115029936,0.0013822453,0.00066675333,0.0032004537,0.000015249584,0.0000035734142,0.00065512647],"genre_scores_gemma":[0.0019391691,0.99548846,0.0016003347,0.00020841787,0.0002584776,0.00034213148,0.00002112166,0.000028471119,0.00011341261],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9907445,0.0039532837,0.0022614903,0.0003208791,0.0024737138,0.0002461489],"domain_scores_gemma":[0.98723143,0.0014413737,0.0034090765,0.0005855007,0.007030153,0.00030246054],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.031963017,0.00032503402,0.0011955436,0.00047206323,0.0004879673,0.00029139727,0.0012788922,0.00018445292,0.0011147165],"category_scores_gemma":[0.033977337,0.00014422815,0.00046373307,0.0027182798,0.00044949408,0.00035246677,0.000074266114,0.00062508316,0.00003371994],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[8.683301e-7,0.000029654342,0.00004999515,0.0018073716,0.0001026794,4.922361e-7,0.004615124,0.000018903807,1.0445794e-7,0.00057961233,0.0015902461,0.991205],"study_design_scores_gemma":[0.00041371604,0.00025500494,0.00035918053,0.0577091,0.006331761,0.0001734913,0.0026715177,0.00083183736,0.0000042755896,0.007302665,0.9236063,0.0003411495],"about_ca_topic_score_codex":0.0001483265,"about_ca_topic_score_gemma":0.006192862,"teacher_disagreement_score":0.9908638,"about_ca_system_score_codex":0.0010366212,"about_ca_system_score_gemma":0.03164942,"threshold_uncertainty_score":0.9997984},"labels":[],"label_agreement":null},{"id":"W4366726230","doi":"10.3138/cjpe.35.3.473","title":"Peer Reviewers for Volume 35 and Manuscripts Submitted in 2020 / Examinateurs et examinatrices des manuscrits du volume 35 et des manuscrits soumis en 2020","year":2021,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Volume (thermodynamics); Art; Humanities; Psychology; Physics","score_opus":0.2671932895686844,"score_gpt":0.46999302576202445,"score_spread":0.20279973619334007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366726230","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8085819,0.09597771,0.0020517528,0.08493051,0.003497959,0.003208686,0.0002215164,0.000020381904,0.0015096075],"genre_scores_gemma":[0.9169813,0.017256794,0.028113235,0.0019635728,0.0007666412,0.0004334652,0.00033102214,0.00009688812,0.034057118],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9886049,0.004339749,0.0021605373,0.0008075732,0.00306683,0.0010204073],"domain_scores_gemma":[0.98696065,0.0008627511,0.0010774274,0.00044458208,0.009459217,0.0011953998],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.040215615,0.0005111717,0.0008819715,0.00091880537,0.0005372673,0.001706701,0.0006949181,0.0003692338,0.0029200325],"category_scores_gemma":[0.016493341,0.00050917285,0.00032387843,0.0021140105,0.00058455596,0.0029834106,0.00008009687,0.00073726935,0.00008275478],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045875633,0.00017977206,0.1402274,0.0003768777,0.00008528513,0.00023682242,0.007638164,0.00055317493,0.000052048938,0.00020777322,0.04828731,0.8021095],"study_design_scores_gemma":[0.0025739255,0.001112519,0.5871414,0.0014033096,0.00051630044,0.0006138471,0.009029606,0.04407541,0.00007397331,0.007007673,0.3458993,0.00055269356],"about_ca_topic_score_codex":0.0028490338,"about_ca_topic_score_gemma":0.13016106,"teacher_disagreement_score":0.8015568,"about_ca_system_score_codex":0.0013442124,"about_ca_system_score_gemma":0.007346056,"threshold_uncertainty_score":0.999736},"labels":[],"label_agreement":null},{"id":"W4366726740","doi":"10.3138/cjpe.19.003","title":"Stakeholder Involvement in a Government-Funded Outcome Evaluation: Lessons from the Front Line","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Health Canada","funders":"","keywords":"Workload; Stakeholder; Government (linguistics); Strengths and weaknesses; Front line; Process (computing); Outcome (game theory); Data collection; Process management; Public relations; Program evaluation; Psychology; Business; Medical education; Knowledge management; Political science; Medicine; Computer science; Sociology; Public administration; Social psychology","score_opus":0.6625327886142328,"score_gpt":0.5396214187531866,"score_spread":0.12291136986104623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366726740","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94737786,0.0017687388,0.0019842577,0.04230648,0.0016711856,0.0030367018,0.000058567806,0.0000091145275,0.0017870659],"genre_scores_gemma":[0.99570847,0.00001657276,0.002552383,0.001095412,0.0002826467,0.00020006206,0.000032219865,0.000012061375,0.000100192454],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99005085,0.0009635779,0.0016566437,0.00031444844,0.006651932,0.000362531],"domain_scores_gemma":[0.99561816,0.00040110652,0.0009792808,0.0005427422,0.0020857372,0.00037298587],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.028095014,0.00018245897,0.00031340861,0.0002672546,0.00025825313,0.0005641945,0.00079197553,0.00009498122,0.0048917327],"category_scores_gemma":[0.00403271,0.00011894825,0.00015091345,0.0006796667,0.00010126154,0.000686403,0.000027861328,0.00036640608,0.00012394278],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034813613,0.0001633526,0.14387776,0.0000021669528,0.00006019249,0.000009338455,0.0054415683,0.04911865,0.00003590097,0.00073571794,0.0015560898,0.79896444],"study_design_scores_gemma":[0.0073620654,0.00061669794,0.8170996,0.0001566142,0.0002814468,0.000012740972,0.013593847,0.059903234,0.00015080956,0.069750935,0.030755898,0.0003161299],"about_ca_topic_score_codex":0.0054132645,"about_ca_topic_score_gemma":0.40579924,"teacher_disagreement_score":0.7986483,"about_ca_system_score_codex":0.0029772497,"about_ca_system_score_gemma":0.0060575656,"threshold_uncertainty_score":0.99957716},"labels":[],"label_agreement":null},{"id":"W4366728118","doi":"10.3138/cjpe.0016.003","title":"Evaluation in the Government of Alberta: Adapting to the “New Way”","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"Government of Alberta","keywords":"Scrutiny; Government (linguistics); Meaning (existential); Emphasis (telecommunications); Focus (optics); Empowerment; Process management; Public relations; Management science; Political science; Sociology; Business; Computer science; Epistemology; Economics; Law","score_opus":0.4323374369274828,"score_gpt":0.49519588504531975,"score_spread":0.06285844811783697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366728118","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8805529,0.0016504561,0.001487694,0.076815225,0.0013474543,0.0047011822,0.0000055646883,0.000003551823,0.033436],"genre_scores_gemma":[0.9979646,0.000009703971,0.00092866074,0.000559415,0.00019434514,0.00007694732,0.0000012292345,0.0000055233327,0.00025957302],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9883861,0.0016191414,0.001111898,0.00016949902,0.008464206,0.000249135],"domain_scores_gemma":[0.9961305,0.00071636273,0.00071515515,0.00039105513,0.0018244585,0.00022242422],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.052082513,0.00010147983,0.00017572877,0.00026080082,0.00016538614,0.00024360318,0.0007817299,0.000046754685,0.0045592976],"category_scores_gemma":[0.00996808,0.000054778215,0.00010253684,0.0011640284,0.000040669976,0.00037199695,0.000013616116,0.00019415191,0.000068033776],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000060643165,0.00003290709,0.0046204273,0.0000010050932,0.000011645282,6.389798e-7,0.010055653,0.017673649,0.000018170196,0.00026290264,0.0147359725,0.952581],"study_design_scores_gemma":[0.0016155296,0.0008340789,0.15805478,0.000118816264,0.00023703891,0.000028502138,0.015791455,0.65330917,0.00012081587,0.006214163,0.16349764,0.00017800074],"about_ca_topic_score_codex":0.0016069339,"about_ca_topic_score_gemma":0.13631433,"teacher_disagreement_score":0.95240295,"about_ca_system_score_codex":0.0005150855,"about_ca_system_score_gemma":0.0017836145,"threshold_uncertainty_score":0.99837136},"labels":[],"label_agreement":null},{"id":"W4366728120","doi":"10.3138/cjpe.0016.002","title":"Program Evaluation in British Columbia in a Time of Transition: 1995-2000","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Victoria","funders":"University of Victoria","keywords":"Accountability; Transparency (behavior); Scarcity; Public administration; Government (linguistics); Politics; Performance measurement; Business; Performance management; Strategic planning; Public sector; Accounting; Political science; Public relations; Economics; Marketing; Law","score_opus":0.24730137240434352,"score_gpt":0.4603232882871255,"score_spread":0.21302191588278196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366728120","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99207914,0.0009774574,0.000041900774,0.0010210923,0.000294112,0.0035732507,0.000014542658,0.000009017337,0.0019894775],"genre_scores_gemma":[0.9972563,0.000027262255,0.0018506367,0.000104182305,0.00008994946,0.00039058257,0.00002755224,0.000012096191,0.00024145051],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9923738,0.0012597841,0.001815036,0.0002874738,0.0038980027,0.00036586102],"domain_scores_gemma":[0.9957491,0.0001781769,0.0007584779,0.00027204645,0.0027193774,0.00032280217],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02418496,0.000113705966,0.000402815,0.00089732895,0.00010218994,0.00075642864,0.00047494977,0.00014333008,0.019921102],"category_scores_gemma":[0.0017836328,0.00014758563,0.00014661333,0.0021677855,0.00012414208,0.00091583916,0.000007786718,0.00028732818,0.000079596546],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008181476,0.00027902325,0.067855254,0.0000070092674,0.000010930825,0.000014095503,0.0024737096,0.004441462,0.000013965536,0.0000024769865,0.0021233526,0.92277056],"study_design_scores_gemma":[0.0032404053,0.00090778014,0.44843704,0.00027622285,0.00007329299,0.000087246495,0.0009862784,0.53443867,0.000011706231,0.0029084787,0.008442485,0.00019038648],"about_ca_topic_score_codex":0.014651485,"about_ca_topic_score_gemma":0.68194497,"teacher_disagreement_score":0.9225802,"about_ca_system_score_codex":0.0010308491,"about_ca_system_score_gemma":0.0036737537,"threshold_uncertainty_score":0.99191004},"labels":[],"label_agreement":null},{"id":"W4366728330","doi":"10.3138/cjpe.0016.007","title":"Evaluation Policy and Practice in the Provincial Government of Prince Edward Island","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Health PEI","funders":"","keywords":"Accountability; Theme (computing); Government (linguistics); Public administration; Public policy; Public sector; Political science; History; Law; Philosophy; Computer science","score_opus":0.2650363576252401,"score_gpt":0.5108291781477593,"score_spread":0.24579282052251922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366728330","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9076708,0.0024296464,0.00050577807,0.029081648,0.0005648217,0.0040353104,0.000019237252,0.000004044435,0.05568871],"genre_scores_gemma":[0.9981601,0.00006326862,0.001126165,0.00032405186,0.0001971358,0.00006303083,0.000001364445,0.0000045284637,0.00006032673],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9892968,0.0023034113,0.0009246358,0.00016601218,0.007106601,0.00020251864],"domain_scores_gemma":[0.99498385,0.0010171317,0.0009655141,0.00024067263,0.002638244,0.00015459649],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.054558273,0.000093146184,0.00017218497,0.000354377,0.000117203585,0.00023767688,0.0003515729,0.000056824723,0.0007348929],"category_scores_gemma":[0.03331284,0.000060880884,0.00005361649,0.0007901493,0.00009838752,0.0007885569,0.000012539858,0.00017453628,0.000008706394],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001932101,0.000078280245,0.009087247,0.0000033833735,0.000012299253,0.0000022990355,0.006349814,0.0010544248,0.000019036199,0.000508804,0.00092195877,0.98194313],"study_design_scores_gemma":[0.004424782,0.0019329375,0.42986253,0.00014793266,0.00047830964,0.00031863127,0.014960333,0.36144146,0.00008792961,0.016630698,0.16941243,0.0003020327],"about_ca_topic_score_codex":0.000590729,"about_ca_topic_score_gemma":0.030144027,"teacher_disagreement_score":0.9816411,"about_ca_system_score_codex":0.00062187476,"about_ca_system_score_gemma":0.0034408015,"threshold_uncertainty_score":0.9875533},"labels":[],"label_agreement":null},{"id":"W4366728344","doi":"10.3138/cjpe.0016.004","title":"Program Evaluation in the Manitoba Government: Past, Present, and Future","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Program evaluation; Civil service; State (computer science); Service (business); State government; Political science; Psychology; Public administration; Business; Local government; Public service; Computer science; Marketing","score_opus":0.31480988225866346,"score_gpt":0.47898588581411383,"score_spread":0.16417600355545037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366728344","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90323603,0.0053712605,0.0000985476,0.056671645,0.0018041217,0.01010939,0.000015866235,0.000018885296,0.022674238],"genre_scores_gemma":[0.99628687,0.00007434203,0.001152638,0.00031899547,0.0015319221,0.0005417237,0.000008244774,0.000009603872,0.000075677104],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99156725,0.0014859551,0.00091836636,0.0002524545,0.005450157,0.00032583214],"domain_scores_gemma":[0.99700725,0.00025227413,0.00063141657,0.0003526386,0.0014789011,0.00027749245],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02370249,0.00015125932,0.00020411142,0.000341455,0.0002465086,0.000798177,0.00054129766,0.00009502889,0.0022632652],"category_scores_gemma":[0.0006346563,0.00009694785,0.00009023756,0.00095313805,0.000098999306,0.0008106101,0.000014369574,0.00030456393,0.000044727203],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007165213,0.0000939384,0.027136886,0.000003152342,0.000012654132,0.0000049180685,0.0021316998,0.00034715695,0.0000022471445,0.00012666504,0.011467606,0.9586659],"study_design_scores_gemma":[0.0013503642,0.0005967364,0.28845322,0.00002776976,0.00010457322,0.00007870148,0.007946527,0.22062849,0.0000053143867,0.003295327,0.47738072,0.0001322698],"about_ca_topic_score_codex":0.0002337399,"about_ca_topic_score_gemma":0.018892271,"teacher_disagreement_score":0.95853364,"about_ca_system_score_codex":0.0005269195,"about_ca_system_score_gemma":0.00069472217,"threshold_uncertainty_score":0.9990104},"labels":[],"label_agreement":null},{"id":"W4367016705","doi":"10.7202/1098703ar","title":"Argumenter sur l’argumentation : regards croisés sur les apports de la transdisciplinarité en recherche","year":2023,"lang":"fr","type":"article","venue":"Enjeux et société Approches transdisciplinaires","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.30216713572282894,"score_gpt":0.527272048142313,"score_spread":0.22510491241948405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367016705","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8648408,0.005107666,0.021259882,0.07228791,0.0018645194,0.0016599934,0.00024934098,0.0006754896,0.032054413],"genre_scores_gemma":[0.91724956,0.0063414895,0.005536784,0.0006180255,0.00050721504,0.0005957546,0.0003073153,0.00017424187,0.068669595],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98496157,0.0064528184,0.0020717643,0.0017482813,0.0031517625,0.0016137777],"domain_scores_gemma":[0.98708314,0.01017713,0.00055903645,0.0009677646,0.0006607715,0.000552183],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.033182483,0.00096829556,0.0010595204,0.00070641324,0.0010682056,0.001150089,0.0014560343,0.001514634,0.004727154],"category_scores_gemma":[0.0018124328,0.0009017618,0.0009494886,0.002571677,0.0011377247,0.0021003617,0.00032801813,0.0020049212,0.0008237935],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047579614,0.0015269232,0.009637213,0.0012256978,0.0004928237,0.00013076057,0.35801855,0.006877863,0.003776682,0.0104627665,0.020305034,0.58706987],"study_design_scores_gemma":[0.0070966734,0.0007523399,0.49119633,0.0016318111,0.0007141712,0.00012593177,0.11115271,0.03802759,0.006765542,0.23025164,0.1098171,0.0024681434],"about_ca_topic_score_codex":0.00042595816,"about_ca_topic_score_gemma":0.0012893294,"teacher_disagreement_score":0.58460176,"about_ca_system_score_codex":0.0008985663,"about_ca_system_score_gemma":0.0027458451,"threshold_uncertainty_score":0.99995416},"labels":[],"label_agreement":null},{"id":"W4367029949","doi":"10.3138/cjpe.25.002","title":"Contribution Analysis Applied: Reflections on Scope and Methodology","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Scope (computer science); Perspective (graphical); Relation (database); Elaboration; Management science; Epistemology; Computer science; Engineering ethics; Sociology; Engineering; Data mining; Philosophy","score_opus":0.6370922382666173,"score_gpt":0.6304102886950795,"score_spread":0.006681949571537782,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367029949","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9580563,0.00019568655,0.020845715,0.004537449,0.0017487154,0.0011334677,0.000011903018,0.000014345343,0.0134564685],"genre_scores_gemma":[0.98703414,0.0000070957367,0.012404017,0.000271026,0.00016343452,0.00004366703,0.000013878665,0.0000043900422,0.000058321242],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99710107,0.0006299663,0.000673239,0.00020414489,0.0011882762,0.0002032806],"domain_scores_gemma":[0.99555993,0.0005912374,0.0005623714,0.00025404032,0.0026317195,0.00040068745],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.024034401,0.000093125585,0.00027058035,0.0015434788,0.000301154,0.00030599043,0.00022229998,0.000111384106,0.002028733],"category_scores_gemma":[0.0056073354,0.00007051111,0.00011225827,0.0016011331,0.00011608314,0.0002522332,0.0000073142323,0.00035136475,0.000045330475],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037109457,0.00003831101,0.016793266,0.0000010755865,0.00017128275,0.0000018647173,0.0006567735,0.0040079444,0.0012915178,0.019304512,0.0008308703,0.9568655],"study_design_scores_gemma":[0.0025456937,0.0018408059,0.69974864,0.000018206083,0.0019406669,0.00012983434,0.0018095269,0.053491604,0.0014998598,0.08617953,0.15039498,0.00040067956],"about_ca_topic_score_codex":0.0003017261,"about_ca_topic_score_gemma":0.08202588,"teacher_disagreement_score":0.95646477,"about_ca_system_score_codex":0.0001356015,"about_ca_system_score_gemma":0.0018222139,"threshold_uncertainty_score":0.99888355},"labels":[],"label_agreement":null},{"id":"W4367029998","doi":"10.3138/cjpe.0015.007","title":"Critical Perspectives on Educational Evaluation","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Lifeworld; Mainstream; Rationality; Epistemology; Sociology; Critical theory; Critical thinking; Citizen journalism; Postmodernism; Formal education; Engineering ethics; Pedagogy; Social science; Political science; Law; Philosophy","score_opus":0.46646186255614186,"score_gpt":0.6165222477440031,"score_spread":0.15006038518786124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367029998","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85182977,0.0022659786,0.0014676226,0.06768306,0.0037198786,0.0023476048,0.000011765715,0.000017427634,0.07065688],"genre_scores_gemma":[0.99661046,0.000018654968,0.0019452458,0.000309013,0.00067118485,0.0001139306,0.000013791821,0.000009939595,0.0003077765],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9927348,0.0010491951,0.00088420894,0.0002872429,0.004746827,0.00029771557],"domain_scores_gemma":[0.9867097,0.0008821857,0.00045498126,0.00033146987,0.011072213,0.00054946565],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.023381507,0.00013675219,0.00020407532,0.001033584,0.00033311764,0.00057164714,0.00043720845,0.00008565185,0.024166163],"category_scores_gemma":[0.024185082,0.00010826304,0.00015116735,0.00094875187,0.00016084385,0.0009372358,0.0000072913076,0.00025417111,0.00042197775],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044096454,0.00020580651,0.025767665,0.0000018362974,0.000027793598,0.0000040415207,0.0031927896,0.004017093,0.000021501502,0.017437013,0.010081267,0.9391991],"study_design_scores_gemma":[0.0022027164,0.0017555689,0.521587,0.00011063976,0.00026274825,0.00023609336,0.01340381,0.17477646,0.000049123868,0.19185936,0.09337318,0.00038323848],"about_ca_topic_score_codex":0.00015105725,"about_ca_topic_score_gemma":0.004668118,"teacher_disagreement_score":0.93881583,"about_ca_system_score_codex":0.0010347714,"about_ca_system_score_gemma":0.010539088,"threshold_uncertainty_score":0.9950702},"labels":[],"label_agreement":null},{"id":"W4367030000","doi":"10.3138/cjpe.0015.004","title":"Evaluability Assessment of Staff Training in Special Care Units for Persons with Dementia: Strategic Issues","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Dementia; Curriculum; Psychology; Training (meteorology); Work (physics); Medical education; Professional development; Nursing; Pedagogy; Disease; Medicine","score_opus":0.526951152664895,"score_gpt":0.5564320320386825,"score_spread":0.029480879373787516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030000","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9897304,0.0004838454,0.00081412104,0.0008429778,0.00044218573,0.0017767418,0.000029205841,0.0000039771603,0.0058765025],"genre_scores_gemma":[0.99184173,0.000010497629,0.007588336,0.000019419713,0.0003265489,0.00013755515,0.00002687806,0.000009649399,0.000039358296],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99554926,0.00059208815,0.0010450253,0.00023997201,0.002246481,0.00032716236],"domain_scores_gemma":[0.9930261,0.00023333922,0.0007717693,0.00024055937,0.005438428,0.00028983408],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0131706465,0.00014231993,0.00035692178,0.0007168734,0.00016321626,0.00022056478,0.0003597945,0.00007484532,0.0019621144],"category_scores_gemma":[0.0008688709,0.00010808196,0.00009298367,0.0012147436,0.00011872841,0.0005174375,0.000007010434,0.00019299335,0.0000018490404],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000105526626,0.00009448042,0.17390156,0.000029241208,0.00009101972,0.000009705448,0.024450777,0.027557334,0.000026923448,0.0015971682,0.0004196704,0.7717166],"study_design_scores_gemma":[0.0071284757,0.0078018503,0.39635324,0.00034512047,0.0005405388,0.00006066194,0.38521534,0.1451288,0.0000795874,0.018619059,0.03823796,0.0004893646],"about_ca_topic_score_codex":0.00052957836,"about_ca_topic_score_gemma":0.14542615,"teacher_disagreement_score":0.77122724,"about_ca_system_score_codex":0.0005953021,"about_ca_system_score_gemma":0.016714511,"threshold_uncertainty_score":0.99895024},"labels":[],"label_agreement":null},{"id":"W4367030021","doi":"10.3138/cjpe.018.014","title":"Marisol Estrella (Ed.). (2000). Learning from Change: Issues and Experiences in Participatory Monitoring and Evaluation.","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Citizen journalism; Psychology; Computer science; World Wide Web","score_opus":0.5219994103232556,"score_gpt":0.5476537462520411,"score_spread":0.02565433592878552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030021","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9825459,0.015150971,0.000032315045,0.00055447855,0.00061479275,0.00071255065,8.185283e-7,0.000004752424,0.0003833988],"genre_scores_gemma":[0.99759704,0.00018107671,0.0017003177,0.00003154222,0.0001710482,0.00026370934,0.0000027782726,0.000007851808,0.000044664972],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9954886,0.0014176811,0.0007449953,0.00026347887,0.0018095797,0.00027570024],"domain_scores_gemma":[0.9975698,0.00031661667,0.00044471893,0.0001526308,0.0011294056,0.00038681456],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01629402,0.00012863736,0.00023449856,0.00049458107,0.00022574363,0.0004658691,0.00015593054,0.000084140214,0.0017568348],"category_scores_gemma":[0.0041414206,0.00010857382,0.000034220597,0.00044223407,0.000116259565,0.00081794785,0.000010893359,0.00022856319,0.000015255099],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000056383515,0.0000148000045,0.46431637,0.0000017797754,0.000008440802,0.0000030965443,0.022113265,0.00064857036,0.000015380547,0.00002933403,0.000075550735,0.5127678],"study_design_scores_gemma":[0.0018214736,0.0005534789,0.7558076,0.00017120298,0.00011958349,0.000024007193,0.08276766,0.13374667,0.00042587798,0.004339773,0.019924875,0.00029781347],"about_ca_topic_score_codex":0.0025855652,"about_ca_topic_score_gemma":0.0074135344,"teacher_disagreement_score":0.51246995,"about_ca_system_score_codex":0.00026991902,"about_ca_system_score_gemma":0.0021904672,"threshold_uncertainty_score":0.9991557},"labels":[],"label_agreement":null},{"id":"W4367030027","doi":"10.3138/cjpe.018.005","title":"Impacts of the Canadian Evaluation Society’s Evaluation Competitions for Students","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Health Canada; Canadian Institutes of Health Research","funders":"","keywords":"Political science; Psychology; Business; Sociology","score_opus":0.4394839068331859,"score_gpt":0.5880745552752973,"score_spread":0.1485906484421114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030027","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97300494,0.0010565834,0.00089028466,0.004937757,0.0034775923,0.009998714,0.00008976061,0.000007727151,0.006536652],"genre_scores_gemma":[0.9963912,0.0000075457688,0.0026235923,0.00032752074,0.00012636938,0.0003866519,0.000045713834,0.000015866495,0.00007554281],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9884951,0.0020053973,0.0014384837,0.0002791755,0.007323669,0.00045815206],"domain_scores_gemma":[0.9801863,0.00039753382,0.0014337592,0.000535519,0.016774338,0.0006725527],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06834959,0.00018410731,0.00031174612,0.0006605746,0.0008881856,0.0005318697,0.0008398511,0.00015731085,0.0030862922],"category_scores_gemma":[0.013246658,0.00013300238,0.00042359895,0.0013448938,0.0001779381,0.0006629828,0.0000117580585,0.00024217635,0.000023164666],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033345474,0.00029606512,0.3593599,0.000035135625,0.0003624107,6.833237e-7,0.0075711207,0.039880056,0.0003109856,0.0074491594,0.02871062,0.5559905],"study_design_scores_gemma":[0.00654893,0.0008319111,0.5947446,0.00022688975,0.0014068332,0.000045999648,0.0049188347,0.25371173,0.00081964355,0.060323972,0.07600419,0.00041641446],"about_ca_topic_score_codex":0.016937673,"about_ca_topic_score_gemma":0.8244774,"teacher_disagreement_score":0.8075397,"about_ca_system_score_codex":0.0028010579,"about_ca_system_score_gemma":0.043780938,"threshold_uncertainty_score":0.997825},"labels":[],"label_agreement":null},{"id":"W4367030054","doi":"10.3138/cjpe.0019.012","title":"Évaluation des coûts des services de soutien en santé mentale communautaire","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Activity-based costing; Valuation (finance); Business; Mental health; Agency (philosophy); Contingent valuation; Health services; Environmental health; Psychology; Medicine; Marketing; Sociology; Willingness to pay; Economics; Finance; Psychiatry; Population","score_opus":0.2645309011810223,"score_gpt":0.509113088193697,"score_spread":0.24458218701267476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030054","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9927083,0.0010649674,0.001251211,0.0011354916,0.00024686332,0.0007062349,0.000008091157,0.000015343589,0.002863453],"genre_scores_gemma":[0.9733421,0.000041867286,0.025803063,0.0003100289,0.00025964328,0.000050851002,0.00002170096,0.000012981931,0.00015777044],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9949067,0.0013728429,0.0009645026,0.0001851085,0.0021714238,0.00039941102],"domain_scores_gemma":[0.9958152,0.00033274124,0.00061427633,0.00030266307,0.0024288893,0.0005062354],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.024141517,0.00015429345,0.00023536981,0.0006063601,0.00059457624,0.0005895632,0.00066094677,0.000101422316,0.002756646],"category_scores_gemma":[0.001230772,0.00012588323,0.0001344871,0.0006553497,0.0002176228,0.00139932,0.000023174494,0.00021606257,0.00015814819],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014074233,0.000049298265,0.112792976,0.000008290427,0.000024658008,0.0000017458112,0.016544223,0.006895759,0.0001372875,0.00006272184,0.00041184208,0.86305714],"study_design_scores_gemma":[0.0012879454,0.0005248715,0.7011478,0.00014132768,0.00013877843,0.00010865498,0.011490802,0.23908381,0.00062725804,0.023540169,0.021700814,0.00020778111],"about_ca_topic_score_codex":0.0014822128,"about_ca_topic_score_gemma":0.11442116,"teacher_disagreement_score":0.86284935,"about_ca_system_score_codex":0.0013848366,"about_ca_system_score_gemma":0.003877342,"threshold_uncertainty_score":0.998155},"labels":[],"label_agreement":null},{"id":"W4367030058","doi":"10.3138/cjpe.018.015","title":"Irving Rootman, Michael Goodstadt, Brian Hyndman, David V. McQueen, Louise Potvin, Jane Springett, &amp; Erio Ziglio (Éds.) (2001). Evaluation in Health Promotion: Principles and Perspectives.","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Promotion (chess); Sociology; Theology; Political science; Philosophy; Law; Politics","score_opus":0.42290356227939263,"score_gpt":0.49069272073410203,"score_spread":0.0677891584547094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030058","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9660669,0.009397428,0.002274774,0.011681104,0.0012175709,0.004810572,0.00001500235,0.00002904573,0.004507588],"genre_scores_gemma":[0.9882125,0.00023538395,0.010389758,0.00020768068,0.0002284357,0.00016341713,0.000029470464,0.000032583797,0.00050077005],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9896738,0.002900552,0.002193163,0.0006863273,0.0037572882,0.00078886567],"domain_scores_gemma":[0.9920356,0.0002486186,0.0017305085,0.0006011106,0.004350318,0.0010338099],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.053784993,0.00033360653,0.00058034755,0.001738251,0.0004950681,0.00077758497,0.0004980057,0.00017043679,0.002955517],"category_scores_gemma":[0.009347311,0.00030321203,0.00014662463,0.0016030978,0.00018820382,0.0013489173,0.00003190488,0.0005498256,0.000059837585],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006675189,0.0005394291,0.23465307,0.00007816326,0.00009720448,0.0000218957,0.017350566,0.013806744,0.00015395657,0.003983143,0.0030844102,0.72616464],"study_design_scores_gemma":[0.0053275265,0.0017150438,0.68888736,0.00061567855,0.00018137002,0.00037944946,0.009523974,0.08900853,0.00008597775,0.0130650755,0.19043878,0.00077122636],"about_ca_topic_score_codex":0.0020784303,"about_ca_topic_score_gemma":0.1922245,"teacher_disagreement_score":0.7253934,"about_ca_system_score_codex":0.002422445,"about_ca_system_score_gemma":0.012682974,"threshold_uncertainty_score":0.999942},"labels":[],"label_agreement":null},{"id":"W4367030059","doi":"10.3138/cjpe.25.007","title":"S. Donaldson, C.A. Christie, and M.M. Mark. (2009) <i>What Counts as Credible Evidence in Applied Research and Evaluation Practice?</i> Thousand Oaks, CA: Sage. 265 pages.","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"SAGE; Psychology; Physics","score_opus":0.3534349116066584,"score_gpt":0.5479246449963839,"score_spread":0.19448973338972553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030059","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92413664,0.024746476,0.00013889707,0.01741785,0.002668926,0.0042425985,0.000011423266,0.000013536112,0.02662367],"genre_scores_gemma":[0.99487805,0.0019152904,0.0021605385,0.0002833547,0.00022834846,0.00012970834,0.0000099103945,0.000012206227,0.00038261237],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99361765,0.0008903885,0.00077347783,0.00034192236,0.004023171,0.00035340613],"domain_scores_gemma":[0.9934585,0.0013723738,0.0004905142,0.00030316476,0.0039139134,0.00046149915],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06571472,0.00013203752,0.00022315425,0.0008755207,0.00028645803,0.0013557936,0.00030240943,0.00014672925,0.0025463311],"category_scores_gemma":[0.011137591,0.00010947944,0.000029375513,0.00096495985,0.00025753348,0.001761228,0.000030114601,0.0006690407,0.000113420516],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006660221,0.0000447795,0.0072110123,0.0000102335825,0.000012831175,0.000009309807,0.00081082835,0.000111784364,0.00022900364,0.00032957262,0.014652112,0.97651196],"study_design_scores_gemma":[0.003748184,0.0011987307,0.19557875,0.00064512214,0.00023594654,0.00040560318,0.008365675,0.0880501,0.00027726116,0.0468626,0.6541066,0.00052538526],"about_ca_topic_score_codex":0.00063177274,"about_ca_topic_score_gemma":0.023456562,"teacher_disagreement_score":0.97598654,"about_ca_system_score_codex":0.00027789883,"about_ca_system_score_gemma":0.0058688545,"threshold_uncertainty_score":0.99976695},"labels":[],"label_agreement":null},{"id":"W4367030095","doi":"10.3138/cjpe.0015.002","title":"System-Wide Program Assessment with Performance Indicators: Alberta’s Performance Funding Mechanism","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Mechanism (biology); Performance indicator; Business; Performance measurement; Organizational performance; Process management; Political science; Accounting; Marketing","score_opus":0.20148791032238003,"score_gpt":0.46823971684013654,"score_spread":0.26675180651775654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030095","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9739059,0.00011284697,0.0018422399,0.0010941057,0.00096431124,0.0025052852,0.000002728073,0.000045113036,0.019527454],"genre_scores_gemma":[0.9886471,0.00003861788,0.009887894,0.00014517599,0.00025630338,0.0004289257,0.000020632147,0.000031025847,0.00054432853],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9924458,0.0005519852,0.0015224736,0.00043232137,0.004298111,0.000749299],"domain_scores_gemma":[0.99394685,0.00031172528,0.0015977621,0.0005677595,0.0026206013,0.0009552939],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016169483,0.00031377157,0.0004861174,0.0017217543,0.00069709716,0.00092249905,0.000915573,0.00014983602,0.0013926482],"category_scores_gemma":[0.00063822523,0.00022219405,0.00014871775,0.0022635444,0.0001460135,0.0018546673,0.000027283852,0.00048987946,0.00013891803],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042084437,0.000086069005,0.32533944,0.000029722982,0.00005947854,0.000014442751,0.0005966697,0.0025617909,0.000007273199,0.00081401155,0.00037704792,0.67007196],"study_design_scores_gemma":[0.0028680535,0.005275967,0.48031965,0.00068666117,0.00031232665,0.00070948154,0.003966513,0.40407422,0.0001927515,0.00040222326,0.10057018,0.00062197127],"about_ca_topic_score_codex":0.00055615476,"about_ca_topic_score_gemma":0.011009869,"teacher_disagreement_score":0.66945,"about_ca_system_score_codex":0.0015673742,"about_ca_system_score_gemma":0.008131118,"threshold_uncertainty_score":0.99952024},"labels":[],"label_agreement":null},{"id":"W4367030101","doi":"10.3138/cjpe.25.008","title":"D. Russ-Eft &amp; H. Preskill. (2009). <i>Evaluation in Organizations: A Systematic Approach to Enhancing Learning, Performance and Change (2nd ed.)</i> . New York, NY: Basic Books. 552 pages.","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Computer science","score_opus":0.22454373486820348,"score_gpt":0.418268263955533,"score_spread":0.19372452908732954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030101","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9729846,0.0031541113,0.0058468035,0.0020745306,0.0018192058,0.009756218,0.0000069260886,0.000042651267,0.0043149507],"genre_scores_gemma":[0.9890352,0.00006657011,0.008764241,0.0003389753,0.00041210302,0.00048157116,0.000040345712,0.000033185162,0.0008278236],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99298054,0.0011149711,0.0016841526,0.00047477483,0.0032374873,0.0005080933],"domain_scores_gemma":[0.9937376,0.00033220943,0.0011129217,0.0005011147,0.0034493876,0.0008668166],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.030770833,0.00027307484,0.0005225988,0.0015257801,0.00037287513,0.0008781349,0.00056361296,0.00018347263,0.0011978867],"category_scores_gemma":[0.011872485,0.00022709683,0.00007607271,0.0019601702,0.00007597923,0.0013102414,0.000036372523,0.00065406266,0.000143622],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000518101,0.00024572245,0.12406837,0.00077770784,0.00008885416,0.0000032451342,0.040118877,0.018757856,0.00086408376,0.00031488534,0.01690185,0.79780674],"study_design_scores_gemma":[0.0055423686,0.0013673847,0.34909844,0.0034444556,0.0007850082,0.00035483847,0.0066752825,0.56046104,0.00045280173,0.0021426985,0.06837698,0.001298656],"about_ca_topic_score_codex":0.0011123689,"about_ca_topic_score_gemma":0.06441633,"teacher_disagreement_score":0.7965081,"about_ca_system_score_codex":0.0004750046,"about_ca_system_score_gemma":0.005689514,"threshold_uncertainty_score":0.9999473},"labels":[],"label_agreement":null},{"id":"W4367030138","doi":"10.3138/cjpe.0015.008","title":"Stakeholder Involvement in Educational Evaluation: Québec’s Commission d’évaluation de l’enseignement collégial","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Stakeholder; Commission; Valuation (finance); Program evaluation; Evaluation methods; Theory of change; Medical education; Psychology; Political science; Pedagogy; Public relations; Management; Business; Medicine; Public administration; Accounting; Engineering; Economics","score_opus":0.47640868414258253,"score_gpt":0.50445403529336,"score_spread":0.028045351150777442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030138","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9656986,0.0012161442,0.0011658671,0.016437791,0.0013013855,0.0028378223,0.000006047113,0.000009314757,0.011327034],"genre_scores_gemma":[0.9936074,0.00003390313,0.0045550372,0.00041297392,0.000383003,0.00039366487,0.00005518223,0.000015449305,0.0005433649],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99003845,0.0018574853,0.0017714745,0.00034338547,0.005521838,0.00046737137],"domain_scores_gemma":[0.9919843,0.00045526924,0.0009967377,0.0004084946,0.005559349,0.0005958141],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.045396205,0.00020649614,0.0003133133,0.0013986906,0.00035993205,0.00045450273,0.0005599838,0.00013187692,0.01630167],"category_scores_gemma":[0.0051082894,0.00017827899,0.00013697798,0.001438703,0.00009954572,0.0008339412,0.000020329324,0.00030533288,0.00009033327],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00006111725,0.0002929086,0.21253522,0.000005210889,0.000030385061,0.0000052787655,0.005661942,0.020596309,0.00013339212,0.00031162807,0.014168916,0.7461977],"study_design_scores_gemma":[0.0032534455,0.00059777295,0.7004727,0.00011562596,0.00013858323,0.000066043955,0.0045378474,0.18835282,0.00005947945,0.01879258,0.08335905,0.00025405275],"about_ca_topic_score_codex":0.011728717,"about_ca_topic_score_gemma":0.40398407,"teacher_disagreement_score":0.74594367,"about_ca_system_score_codex":0.0077709667,"about_ca_system_score_gemma":0.04941398,"threshold_uncertainty_score":0.996038},"labels":[],"label_agreement":null},{"id":"W4367030203","doi":"10.3138/cjpe.0015.001","title":"Editor’s Introduction: Educational Evaluation at the Turn of the Millennium","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Turn (biochemistry); Chemistry","score_opus":0.22207381985994942,"score_gpt":0.5014377426141619,"score_spread":0.2793639227542124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030203","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80308044,0.002849556,0.0001211837,0.15534379,0.030789196,0.0026015916,0.000013691947,0.000005565984,0.0051949946],"genre_scores_gemma":[0.9886802,0.000037951173,0.00027899325,0.00027546586,0.008931895,0.0001165413,0.000018986515,0.0000092345645,0.0016507764],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99233204,0.0013128724,0.0010923754,0.00021524602,0.004813798,0.00023367],"domain_scores_gemma":[0.98984045,0.00041105042,0.0013131762,0.0005985985,0.007620358,0.00021639481],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.025202177,0.00012450089,0.0001860825,0.00034720582,0.00055169704,0.00020638395,0.00077465054,0.00008087033,0.015097943],"category_scores_gemma":[0.0063573904,0.00006676863,0.00020182846,0.0012403405,0.00026340937,0.0005140139,0.000029974819,0.00024565024,0.00009390362],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032622862,0.0000667955,0.04853712,0.000003112593,0.000045121906,2.412536e-7,0.0012659783,0.013502581,0.00012790658,0.0003510588,0.46075314,0.4753143],"study_design_scores_gemma":[0.0007582235,0.00019096523,0.27521315,0.000027671977,0.00019067488,0.00011183157,0.0013299285,0.019587774,0.00025295693,0.009255975,0.6929712,0.00010965006],"about_ca_topic_score_codex":0.00028872056,"about_ca_topic_score_gemma":0.02053901,"teacher_disagreement_score":0.47520465,"about_ca_system_score_codex":0.0009379199,"about_ca_system_score_gemma":0.008779669,"threshold_uncertainty_score":0.9973336},"labels":[],"label_agreement":null},{"id":"W4367030207","doi":"10.3138/cjpe.018.004","title":"Contribution de la cartographie de concepts à la modélisation des interventions en situation de crise en protection de la jeunesse","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Brainstorming; Context (archaeology); Elaboration; Structuring; Psychology; Agency (philosophy); Humanities; Sociology; Political science; Computer science; Geography; Philosophy; Social science","score_opus":0.1982564198429033,"score_gpt":0.5171773982803248,"score_spread":0.3189209784374215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030207","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76733565,0.00037449074,0.22977602,0.00051431183,0.00017707529,0.0008998602,0.0000070429805,0.000021034279,0.00089450454],"genre_scores_gemma":[0.990026,0.000068111505,0.0093346,0.000064590065,0.00013163999,0.00029131028,0.000020366351,0.000015368134,0.000048019425],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98688996,0.010551731,0.00085234875,0.00021190444,0.0010788123,0.0004152573],"domain_scores_gemma":[0.99525607,0.0011848458,0.00069069216,0.00019790766,0.0021910826,0.00047942248],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05428484,0.0001575222,0.00021620315,0.0008716555,0.0004302007,0.00070670445,0.00025941597,0.00028312168,0.00046864856],"category_scores_gemma":[0.01887705,0.00014834263,0.00024508068,0.00091437326,0.00027895614,0.0009140501,0.000007854512,0.00043133853,0.000012984061],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000109305955,0.00040998147,0.18775444,0.000065364315,0.00015158091,0.00002966605,0.037105322,0.10583841,0.00544337,0.016708009,0.001110178,0.6452744],"study_design_scores_gemma":[0.0033755824,0.00075704174,0.5204257,0.00039059366,0.00045925708,0.00071285357,0.0101356115,0.24456824,0.0034721952,0.19594876,0.019384693,0.00036948672],"about_ca_topic_score_codex":0.00120961,"about_ca_topic_score_gemma":0.009832301,"teacher_disagreement_score":0.6449049,"about_ca_system_score_codex":0.0021094924,"about_ca_system_score_gemma":0.0061113434,"threshold_uncertainty_score":0.9995231},"labels":[],"label_agreement":null},{"id":"W4367030218","doi":"10.3138/cjpe.0014.009","title":"Empowerment Goes Large Scale: The Canada Prenatal Nutrition Experience","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Empowerment; Referral; Scale (ratio); Psychology; Program evaluation; Nursing; Stakeholder; Medical education; Public relations; Medicine; Political science; Economic growth; Economics","score_opus":0.15092984205043414,"score_gpt":0.4754820314681291,"score_spread":0.324552189417695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030218","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98716414,0.0006851057,0.00011690439,0.0058760573,0.00092845666,0.0011555289,0.000027955728,0.0000058656565,0.0040399623],"genre_scores_gemma":[0.9979649,0.000028366127,0.0004655759,0.00055129925,0.00021523192,0.00014253787,0.000015989315,0.0000063795515,0.00060969015],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99521714,0.0004820122,0.000806788,0.00018989647,0.0029668582,0.00033728115],"domain_scores_gemma":[0.99722636,0.00015502494,0.00037639256,0.000329063,0.001507671,0.00040546266],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0072758747,0.00011625785,0.00016544624,0.00018129952,0.0004690179,0.00042562478,0.00063316827,0.000048047215,0.016290199],"category_scores_gemma":[0.00058996247,0.000072783965,0.000086783926,0.0006347762,0.00009189653,0.00061031344,0.000008635859,0.00019295505,0.000056424495],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024303317,0.00008012014,0.012158743,0.000004048663,0.000016451913,0.000009761815,0.0043922393,0.0012361715,0.000008847936,0.00009126502,0.026823329,0.9551547],"study_design_scores_gemma":[0.0013176026,0.0003277271,0.09845378,0.000086180684,0.000049567523,0.000102811835,0.00954131,0.03841596,0.0002579262,0.0018420806,0.84941584,0.0001892411],"about_ca_topic_score_codex":0.0675094,"about_ca_topic_score_gemma":0.91790706,"teacher_disagreement_score":0.9549655,"about_ca_system_score_codex":0.00064115046,"about_ca_system_score_gemma":0.008551554,"threshold_uncertainty_score":0.99706906},"labels":[],"label_agreement":null},{"id":"W4367030226","doi":"10.3138/cjpe.25.003","title":"Pre-Measurement Triangulation: Considerations for Program Evaluation in Human Service Enterprises","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Children's Hospital of Eastern Ontario; University of Ottawa","funders":"","keywords":"Triangulation; Service (business); Interpretation (philosophy); Computer science; Foundation (evidence); Order (exchange); Management science; Simple (philosophy); Process management; Business; Engineering; Epistemology; Mathematics; Marketing; Political science","score_opus":0.5377527213062439,"score_gpt":0.5605725975894016,"score_spread":0.022819876283157736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030226","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9719647,0.0002622204,0.0019123788,0.007452924,0.0023448702,0.01419029,0.000019880084,0.000029847119,0.0018228566],"genre_scores_gemma":[0.98389286,0.0000014100295,0.013111996,0.00026903712,0.00037850733,0.0022470844,0.000047370406,0.000016211103,0.000035527402],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99259895,0.00081814796,0.0017676989,0.00034609917,0.004096091,0.00037298616],"domain_scores_gemma":[0.9831877,0.0004484163,0.0010689083,0.00043754044,0.01443656,0.0004209198],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.043001197,0.00019135769,0.000330217,0.0011372808,0.00044914059,0.0008370587,0.00039350518,0.00015758988,0.0034173387],"category_scores_gemma":[0.011389837,0.0001653066,0.00016911849,0.00096417643,0.000077601864,0.0009964562,0.00001199227,0.00034895382,0.00002043779],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050500566,0.00031258832,0.032901764,0.00001622,0.00004687245,0.0000019032796,0.0027712975,0.010220602,0.0014072143,0.0009948506,0.0028052202,0.94847095],"study_design_scores_gemma":[0.0073032477,0.0013528491,0.43991926,0.00013481211,0.00033899606,0.00005110561,0.0013039104,0.4202382,0.0006521096,0.07873759,0.04956065,0.0004072419],"about_ca_topic_score_codex":0.0005879531,"about_ca_topic_score_gemma":0.27724606,"teacher_disagreement_score":0.94806373,"about_ca_system_score_codex":0.00068952213,"about_ca_system_score_gemma":0.009653811,"threshold_uncertainty_score":0.9974937},"labels":[],"label_agreement":null},{"id":"W4367030229","doi":"10.3138/cjpe.0019.010","title":"The Experience of Developing a Package of Instruments to Measure the Critical Characteristics of Community Support Programs for People with a Severe Mental Illness","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Canadian Mental Health Association; University of Alberta; University of Toronto; Western University; Centre for Addiction and Mental Health","funders":"","keywords":"Mental illness; Measure (data warehouse); Process (computing); Process management; Program evaluation; Psychology; Computer science; Management science; Mental health; Business; Psychotherapist; Political science; Engineering","score_opus":0.26904403914193825,"score_gpt":0.48578448857306383,"score_spread":0.21674044943112558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030229","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9926472,0.000029054027,0.0019540477,0.0034964639,0.0002041569,0.0015350675,0.000028169272,0.000001803717,0.000104065366],"genre_scores_gemma":[0.99482137,0.000003882863,0.004847396,0.00009724136,0.00003380157,0.00016465831,0.000010701334,0.0000065632867,0.000014365288],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99631697,0.0005412834,0.0010067107,0.00008487491,0.0018284745,0.00022167728],"domain_scores_gemma":[0.9940515,0.00047621844,0.0007936457,0.00031844294,0.004173037,0.00018713165],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011539261,0.00009919221,0.00026996544,0.00014941959,0.00044574193,0.00012740139,0.0006658384,0.000040649757,0.00009193211],"category_scores_gemma":[0.002878663,0.000053600594,0.000081445876,0.0005704242,0.00026960636,0.00032929674,0.000026067157,0.00015463115,0.0000013122424],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011078184,0.0000803385,0.04212083,0.0000192478,0.000031013962,1.3000299e-7,0.035074588,0.00003629178,0.000088650835,0.0003382109,0.00017569547,0.92192423],"study_design_scores_gemma":[0.0034319938,0.005531651,0.7756859,0.0006975712,0.00028448945,0.00015524274,0.16001058,0.010717932,0.0069325315,0.0023160402,0.033788193,0.00044784814],"about_ca_topic_score_codex":0.0003065832,"about_ca_topic_score_gemma":0.027409537,"teacher_disagreement_score":0.92147636,"about_ca_system_score_codex":0.00019546201,"about_ca_system_score_gemma":0.003345058,"threshold_uncertainty_score":0.9903377},"labels":[],"label_agreement":null},{"id":"W4367030230","doi":"10.3138/cjpe.25.006","title":"J. A. Morell. (2010). <i>Evaluation in the Face of Uncertainty: Anticipating Surprise and Responding to the Inevitable</i> . New York, NY: Guilford. 303 pages.","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Surprise; Face (sociological concept); Psychology; Social psychology; Philosophy; Linguistics","score_opus":0.38195705889810144,"score_gpt":0.489306172726481,"score_spread":0.10734911382837958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030230","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97392803,0.0006637206,0.0007040323,0.020397143,0.0009995942,0.0021811966,0.0000066451494,0.000003930155,0.0011157184],"genre_scores_gemma":[0.99683666,0.000018132265,0.002149673,0.00053970126,0.00020968504,0.00007463672,0.000008168595,0.000010208171,0.00015316202],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9935129,0.0013944972,0.0012602515,0.0002551799,0.0032211856,0.0003559724],"domain_scores_gemma":[0.99508137,0.0010697863,0.0009144983,0.0005421978,0.0020542343,0.00033789303],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06610746,0.00015427057,0.00027918187,0.0011054416,0.00028150858,0.0005174442,0.0008343755,0.000095962794,0.0005069352],"category_scores_gemma":[0.012837441,0.000089143854,0.00008357279,0.002419371,0.000109398046,0.00049497356,0.000030323272,0.0004913728,0.000017515702],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037721493,0.000029042063,0.035523176,0.000004880024,0.000015345144,0.000001914008,0.012941006,0.02295475,0.00051923376,0.00038866437,0.012334967,0.9152493],"study_design_scores_gemma":[0.0029658242,0.0009919835,0.3857213,0.00024486118,0.00031771752,0.0000879686,0.026523266,0.44269356,0.00036570395,0.012022369,0.12766694,0.00039853007],"about_ca_topic_score_codex":0.0021274297,"about_ca_topic_score_gemma":0.094243295,"teacher_disagreement_score":0.9148508,"about_ca_system_score_codex":0.00017219892,"about_ca_system_score_gemma":0.0048424075,"threshold_uncertainty_score":0.99547786},"labels":[],"label_agreement":null},{"id":"W4367030235","doi":"10.3138/cjpe.0014.004","title":"Facilitating Development of Organizational Productive Capacity: A Role for Empowerment Evaluation","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Empowerment; Organization development; Group cohesiveness; Organizational effectiveness; Organizational learning; Knowledge management; Organizational commitment; Psychology; Business; Public relations; Process management; Social psychology; Political science; Economics; Economic growth; Computer science","score_opus":0.3047962368639325,"score_gpt":0.4947043086901009,"score_spread":0.18990807182616842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030235","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99087316,0.0002297426,0.0031385068,0.00068915717,0.00038372193,0.0028273228,0.00002414336,0.0000062332215,0.001828019],"genre_scores_gemma":[0.9483567,0.0000016987802,0.050961994,0.00004849101,0.00012589157,0.00024863615,0.000060598955,0.000010661794,0.00018535047],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.994101,0.00051541824,0.0014706306,0.0002661362,0.0033922687,0.000254538],"domain_scores_gemma":[0.98799336,0.0003028274,0.00087203097,0.00022413654,0.0103426,0.00026506998],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.024490627,0.0001370495,0.0002669061,0.0005532634,0.00031624635,0.00015798633,0.00033261138,0.00006951991,0.007293561],"category_scores_gemma":[0.0059314664,0.00011442015,0.000102620514,0.0008208286,0.0000844523,0.0005823103,0.0000066601388,0.00011096023,0.000043792264],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031934043,0.00007329392,0.004001392,0.000008112037,0.00004973735,1.2436803e-7,0.0144508,0.008671862,0.00033484137,0.00014994649,0.000361784,0.9718662],"study_design_scores_gemma":[0.0075542745,0.002367067,0.17106812,0.00031008828,0.00059211155,0.000061121405,0.029871454,0.53698254,0.011335951,0.08645786,0.15255184,0.00084756163],"about_ca_topic_score_codex":0.000073199175,"about_ca_topic_score_gemma":0.0032352887,"teacher_disagreement_score":0.9710186,"about_ca_system_score_codex":0.0007719047,"about_ca_system_score_gemma":0.011963779,"threshold_uncertainty_score":0.99363744},"labels":[],"label_agreement":null},{"id":"W4367030240","doi":"10.3138/cjpe.0019.007","title":"Conducting Evaluation Research with Hard-to-Follow Populations: Adopting a Participant-Centred Approach to Maximize Participant Retention","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Canadian Mental Health Association; University of Ottawa","funders":"","keywords":"Interview; Attrition; Participant observation; Psychology; Applied psychology; Investment (military); Medical education; Social psychology; Medicine; Sociology","score_opus":0.9454488731941052,"score_gpt":0.6050153259743052,"score_spread":0.3404335472198,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030240","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9782573,0.00043788354,0.0058883256,0.007988398,0.0006114818,0.0050282557,0.000007934869,0.000025360223,0.0017550439],"genre_scores_gemma":[0.90153587,0.000002159079,0.09688655,0.00024129801,0.00040967474,0.0006774125,0.000034161472,0.000024816474,0.00018802812],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98607504,0.0029130802,0.0019069131,0.00059225864,0.0075691487,0.00094355136],"domain_scores_gemma":[0.98516935,0.00032835678,0.00086782203,0.00060197245,0.011695554,0.0013369402],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0662783,0.00022522188,0.00044261653,0.0018765283,0.0008201376,0.0011031947,0.00061029044,0.00011308354,0.0011148328],"category_scores_gemma":[0.01599719,0.00017499134,0.00014264799,0.0031038763,0.00009772569,0.0013256603,0.000036449106,0.00044880333,0.00025888465],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014496903,0.00017167599,0.012551121,0.000008168469,0.00007135855,0.0000025138363,0.0125244465,0.25771716,0.00034294106,0.00049586577,0.0027249441,0.71324486],"study_design_scores_gemma":[0.0037577676,0.0016555787,0.091112696,0.00036623867,0.00073000765,0.00007911887,0.032848954,0.8421797,0.0003288779,0.0024466796,0.023968862,0.0005255009],"about_ca_topic_score_codex":0.0006463698,"about_ca_topic_score_gemma":0.016878406,"teacher_disagreement_score":0.7127193,"about_ca_system_score_codex":0.0012537441,"about_ca_system_score_gemma":0.0062174303,"threshold_uncertainty_score":0.9999338},"labels":[{"model":"gpt","categories":[],"domain":"methods","study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":["metaresearch"],"domain":"methods","study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"opus","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W4367030244","doi":"10.3138/cjpe.0015.012","title":"Reflections on Program Evaluation, 35 Years on","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Program evaluation; Psychology; Statistics; Mathematics","score_opus":0.6401574684201251,"score_gpt":0.6365197505771939,"score_spread":0.0036377178429312096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030244","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8817617,0.00034774287,0.00043824752,0.007690133,0.0038181022,0.006744652,0.000012378905,0.00006935975,0.09911762],"genre_scores_gemma":[0.9950123,0.00002361881,0.002540412,0.00071252225,0.00050967024,0.00054245,0.00002774747,0.000019884103,0.0006114027],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99179596,0.0011053646,0.0011370853,0.00035781492,0.005181741,0.000422061],"domain_scores_gemma":[0.9930512,0.00031493354,0.00081308285,0.000534385,0.0046421196,0.0006442788],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02127247,0.00018949174,0.000272568,0.0015034043,0.00040124237,0.0006674807,0.000557304,0.0001316164,0.0064469483],"category_scores_gemma":[0.004653381,0.00015456528,0.00020517726,0.001872531,0.00010685728,0.0005861836,0.00000935938,0.00040260676,0.00063473603],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004446663,0.0001891805,0.0033375816,0.0000010241033,0.000030475743,0.000008942214,0.0007013088,0.0111094015,0.000015982987,0.00080898055,0.009322418,0.97443026],"study_design_scores_gemma":[0.00231496,0.004467501,0.21496075,0.00012147304,0.00019845174,0.00010733374,0.0014881769,0.07536236,0.00005833198,0.018474888,0.68212825,0.00031749197],"about_ca_topic_score_codex":0.00024508918,"about_ca_topic_score_gemma":0.01590385,"teacher_disagreement_score":0.97411275,"about_ca_system_score_codex":0.0010950001,"about_ca_system_score_gemma":0.0062127803,"threshold_uncertainty_score":0.99942106},"labels":[],"label_agreement":null},{"id":"W4367030275","doi":"10.3138/cjpe.025.007","title":"Nick L. Smith &amp; Paul R. Brandon (Éds.). (2008). <i>Fundamental Issues in Evaluation</i> . New-York: Guilford, 266 pages.","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Philosophy","score_opus":0.35888501749321366,"score_gpt":0.5087863772677234,"score_spread":0.1499013597745097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030275","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.963967,0.0046022334,0.0005009831,0.014605898,0.0049885367,0.003424588,0.000024820674,0.000028753733,0.007857138],"genre_scores_gemma":[0.9873266,0.00009050622,0.009245792,0.0005207487,0.0008563195,0.00013261869,0.00007652198,0.000030032033,0.0017208431],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99057615,0.0010462325,0.0019586345,0.000476353,0.005294312,0.0006482903],"domain_scores_gemma":[0.99329424,0.00037589204,0.0011937608,0.0007275805,0.0034126514,0.0009958881],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03643211,0.0002959954,0.0005030139,0.0013447333,0.0003168058,0.0009989737,0.0009913413,0.00022615524,0.017351555],"category_scores_gemma":[0.0062986305,0.0002420595,0.00023112171,0.0015440802,0.00017386787,0.0013333085,0.000031972493,0.00077517855,0.0005646269],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000492524,0.00009465228,0.07073606,0.0000047325548,0.000030442618,0.000005506374,0.0015847434,0.0018280655,0.0002713165,0.00010314123,0.12395574,0.80133635],"study_design_scores_gemma":[0.0059676804,0.000519817,0.16864802,0.00011401982,0.00017668979,0.00012900868,0.0013944908,0.030425167,0.00031029424,0.016317664,0.7755411,0.0004560358],"about_ca_topic_score_codex":0.002705815,"about_ca_topic_score_gemma":0.26385763,"teacher_disagreement_score":0.8008803,"about_ca_system_score_codex":0.00068936,"about_ca_system_score_gemma":0.0145571055,"threshold_uncertainty_score":0.9921959},"labels":[],"label_agreement":null},{"id":"W4367030286","doi":"10.3138/cjpe.25.005","title":"Managing Evaluataion: Responding to Common Problems with a 10-Step Process","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"Centers for Disease Control and Prevention","keywords":"Conceptualization; Process (computing); Stakeholder; Unit (ring theory); Public sector; Relation (database); Business; Process management; Program evaluation; Knowledge management; Management science; Public relations; Sociology; Psychology; Computer science; Political science; Economics; Public administration","score_opus":0.2596048059938968,"score_gpt":0.5263633695337143,"score_spread":0.26675856353981753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030286","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9730007,0.00010122962,0.0021958787,0.009118632,0.0009620164,0.0025225244,0.000005678142,0.000022672068,0.012070672],"genre_scores_gemma":[0.9905291,0.0000013882202,0.007890099,0.00029793865,0.00024456414,0.00018764385,0.000009661892,0.000020295964,0.00081926625],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99387604,0.00047419753,0.0010264233,0.00033522584,0.0038531974,0.00043490672],"domain_scores_gemma":[0.99251676,0.00022950023,0.000794004,0.00049265247,0.0050725886,0.0008945168],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.026325282,0.00018619122,0.00031376278,0.0024356206,0.0004008647,0.00089533563,0.0008251159,0.00009134764,0.005681521],"category_scores_gemma":[0.0024423017,0.00013181378,0.00008713549,0.0029440962,0.00009610779,0.0010252096,0.000019432871,0.00045090186,0.00020636305],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011400229,0.00004785305,0.026762808,0.000013990936,0.000031232892,0.0000145768145,0.0026821622,0.011171338,0.0002836044,0.00054412783,0.0028816322,0.9554527],"study_design_scores_gemma":[0.0051003485,0.0058612823,0.0959582,0.0007478524,0.0004427897,0.0007180178,0.008277957,0.34018025,0.0011154689,0.032659244,0.50786227,0.0010763302],"about_ca_topic_score_codex":0.00019246005,"about_ca_topic_score_gemma":0.05245799,"teacher_disagreement_score":0.95437634,"about_ca_system_score_codex":0.00027174468,"about_ca_system_score_gemma":0.0056328,"threshold_uncertainty_score":0.99923456},"labels":[],"label_agreement":null},{"id":"W4367030299","doi":"10.3138/cjpe.25.004","title":"Jugement crédible en évaluation de programme : définition et conditions requises","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Viewpoints; Argumentation theory; Valuation (finance); Coherence (philosophical gambling strategy); Management science; Psychology; Quality (philosophy); Sociology; Epistemology; Business; Economics; Philosophy; Mathematics; Accounting","score_opus":0.4673144395102768,"score_gpt":0.5733540275195889,"score_spread":0.10603958800931207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030299","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9723673,0.00009800457,0.0039496794,0.00984735,0.0018859629,0.0018995127,0.00002231337,0.000031907988,0.009897961],"genre_scores_gemma":[0.9762732,0.000014002199,0.022259442,0.00051147485,0.0003435128,0.00028458625,0.00009431187,0.000015305319,0.0002042117],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9943432,0.0012082848,0.0011312899,0.00025184223,0.0026227126,0.00044262075],"domain_scores_gemma":[0.9935392,0.000547316,0.00085437216,0.00037090958,0.0040573296,0.00063086604],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03927157,0.0001592969,0.0002324731,0.0009845353,0.00034923467,0.0007978073,0.0004824794,0.0001461933,0.006255761],"category_scores_gemma":[0.008533667,0.0001338831,0.00016737898,0.0008430694,0.00012942852,0.0011641069,0.000015954985,0.00048770482,0.00016979803],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021499187,0.00018605267,0.034525752,0.000008167075,0.000050521223,0.000008277112,0.0030876133,0.0033439852,0.002685733,0.012845394,0.00795582,0.93528116],"study_design_scores_gemma":[0.0029814045,0.0015438625,0.44769883,0.000108014036,0.00036734145,0.00023189669,0.0038760283,0.10201637,0.0017033287,0.19874142,0.24025163,0.00047988092],"about_ca_topic_score_codex":0.00043804853,"about_ca_topic_score_gemma":0.033567347,"teacher_disagreement_score":0.9348013,"about_ca_system_score_codex":0.00043195608,"about_ca_system_score_gemma":0.011362536,"threshold_uncertainty_score":0.99981785},"labels":[],"label_agreement":null},{"id":"W4367153888","doi":"10.7202/1095488ar","title":"Mitchell, B. (2021). A Research Agenda for Graduate Education. University of Toronto Press","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Educational Administration and Policy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Vancouver Island University","funders":"","keywords":"Administration (probate law); Political science; Sociology; Graduate education; Library science; Educational administration; Educational research; Media studies; Public administration; Higher education; Pedagogy","score_opus":0.4382408143675989,"score_gpt":0.5624374802312312,"score_spread":0.12419666586363232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367153888","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7009439,0.0022871406,0.00021332879,0.22727366,0.0024622986,0.00081991387,0.0004100819,0.0000055218593,0.06558417],"genre_scores_gemma":[0.9717345,0.000323689,0.00057715364,0.00018332005,0.0005725558,0.0000033136441,0.00003221172,0.0000044949816,0.02656872],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99854624,0.00015487747,0.00040353276,0.00012830162,0.0005918712,0.00017519464],"domain_scores_gemma":[0.99584466,0.0010229585,0.00027548897,0.0001520173,0.0022832106,0.00042166174],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0028662288,0.000059842776,0.00012428586,0.0003419171,0.0003015836,0.00011770079,0.00029029086,0.00004308693,0.0017372279],"category_scores_gemma":[0.0025283918,0.00005615284,0.00006613171,0.00036286662,0.00013735755,0.00038364984,0.000010055997,0.00008635887,0.000035212106],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057016943,0.00008034555,0.0048711617,0.000024504223,0.000028919247,0.0000010480343,0.005761546,0.00004338433,0.000108630185,0.15819706,0.78919625,0.04163014],"study_design_scores_gemma":[0.00025289113,0.00020889976,0.14151993,0.000027140932,0.000009716524,0.000019187068,0.0068888213,0.00021670217,0.000087936656,0.026440019,0.8242561,0.000072610695],"about_ca_topic_score_codex":0.020671338,"about_ca_topic_score_gemma":0.08664495,"teacher_disagreement_score":0.27079064,"about_ca_system_score_codex":0.00018981847,"about_ca_system_score_gemma":0.032021385,"threshold_uncertainty_score":0.9991753},"labels":[],"label_agreement":null},{"id":"W4367154861","doi":"10.36487/acg_repo/2355_64","title":"Critical timelines and pathways: addressing environmental, social, governance and permitting","year":2023,"lang":"en","type":"article","venue":"Paste/˜Pœaste","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Banff Centre; Geomechanica (Canada); University of Alberta","funders":"","keywords":"Timeline; Corporate governance; Computer science; Process management; Business; Geography","score_opus":0.29895359989882603,"score_gpt":0.4759279073333971,"score_spread":0.1769743074345711,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367154861","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9914365,0.00066675013,0.00016247956,0.004020748,0.0002448367,0.00011948131,0.00004787936,0.00005794002,0.0032434128],"genre_scores_gemma":[0.9973509,0.00024796335,0.00042800748,0.0004493562,0.00023053076,0.000014715177,0.0000065440377,0.000011998711,0.0012600302],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9975643,0.00016261979,0.0004511835,0.0004421822,0.0010795953,0.00030012312],"domain_scores_gemma":[0.99851036,0.0009825198,0.00014324332,0.00019516578,0.000055523476,0.00011316738],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020047263,0.00014672962,0.00022701657,0.00008568669,0.00054528355,0.00042465716,0.00017769667,0.000064801294,0.00068963814],"category_scores_gemma":[0.00079402735,0.00011791738,0.000044023524,0.0002883359,0.00023598778,0.0005485189,0.00026242246,0.00013217397,0.0005022228],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003025215,0.0000589331,0.080286585,0.000055244946,0.000019166937,0.000024054776,0.007117194,0.0000615592,0.011040629,0.0025270917,0.010452567,0.8883267],"study_design_scores_gemma":[0.0011829642,0.00018271331,0.7286583,0.00019547198,0.00005053088,0.000055550903,0.023874763,0.15856399,0.0012338748,0.0076942607,0.0775629,0.00074464706],"about_ca_topic_score_codex":0.000003971415,"about_ca_topic_score_gemma":0.0000053914396,"teacher_disagreement_score":0.88758206,"about_ca_system_score_codex":0.000024850362,"about_ca_system_score_gemma":0.000041033934,"threshold_uncertainty_score":0.7551054},"labels":[],"label_agreement":null},{"id":"W4367158827","doi":"10.7202/1081339ar","title":"Implementing Participatory Action Research in the Canadian North: A Case Study of the Gwich’in Language and Cultural Project","year":2021,"lang":"en","type":"article","venue":"Culture","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Participatory action research; Context (archaeology); Action research; Citizen journalism; Sociology; Action (physics); Participatory GIS; Government (linguistics); Political science; Public relations; Pedagogy; Geography; Anthropology; Law; Archaeology; Linguistics","score_opus":0.7348607624197315,"score_gpt":0.6586024525051274,"score_spread":0.07625830991460414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367158827","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99688333,0.00009839436,1.0100089e-7,0.0009242531,0.00005032012,0.0003955074,0.000005008691,0.0000012117304,0.0016418606],"genre_scores_gemma":[0.9994122,0.0000044511257,0.000008397221,0.000101891696,0.000027815431,0.000030641073,0.0000021350093,0.0000015650647,0.00041092373],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99747664,0.0010836773,0.0002468627,0.00016960551,0.0008094167,0.00021378662],"domain_scores_gemma":[0.9992566,0.0001501804,0.000055269353,0.00025726928,0.00025226182,0.000028384371],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00499388,0.000047283356,0.0000786091,0.00009495356,0.00029611966,0.00016497039,0.00018799213,0.000027767343,0.00007693448],"category_scores_gemma":[0.00039965194,0.000021035565,0.000018694915,0.0013225785,0.000039766914,0.00015377105,0.00007410005,0.0002670605,0.000004715748],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000026421103,0.00006687672,0.6250822,0.0000047724066,0.0000038205517,0.000206013,0.3684676,0.00002843489,0.00012945262,0.00004101879,0.001582213,0.0043849805],"study_design_scores_gemma":[0.00023198595,0.000026167205,0.3026983,0.0000073658975,0.000003187712,0.00005792774,0.6921603,0.00031941858,0.000062515675,0.000024284485,0.004382221,0.00002629502],"about_ca_topic_score_codex":0.097673535,"about_ca_topic_score_gemma":0.9901129,"teacher_disagreement_score":0.89243937,"about_ca_system_score_codex":0.00006845337,"about_ca_system_score_gemma":0.00038651534,"threshold_uncertainty_score":0.90833515},"labels":[],"label_agreement":null},{"id":"W4367285108","doi":"10.51744/cip2","title":"Designing evaluations to provide evidence to inform action in new settings","year":2018,"lang":"en","type":"report","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact","funders":"","keywords":"Psychological intervention; Context (archaeology); Action (physics); Public relations; Promotion (chess); Psychology; Political science; Geography","score_opus":0.7086949615913435,"score_gpt":0.6482410702142726,"score_spread":0.06045389137707091,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367285108","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025834965,0.00030855165,0.30909544,0.06549532,0.007846535,0.009536045,0.000021025533,0.00034873732,0.58151335],"genre_scores_gemma":[0.073398836,0.000350621,0.14399558,0.011898483,0.0026201056,0.00072135194,0.000053630614,0.00008575644,0.7668756],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98787236,0.00023007911,0.0018899634,0.00091553084,0.008634313,0.0004577244],"domain_scores_gemma":[0.9923433,0.001675051,0.0006875433,0.0010378131,0.0038096965,0.00044658867],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.029000616,0.00031512562,0.00051951164,0.0018029085,0.00024951546,0.0007702681,0.0009789879,0.0002517171,0.010332274],"category_scores_gemma":[0.03988921,0.0002396563,0.00012885536,0.0032928267,0.000024909068,0.0015090008,0.0003249747,0.00034705442,0.009035832],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002399622,0.000012574691,0.0030594817,0.000016919423,0.000007302132,7.457867e-7,0.0014872283,0.0010154276,0.00021289797,0.000024119508,0.5998243,0.394315],"study_design_scores_gemma":[0.00017007296,0.00034852218,0.023856774,0.00088025513,0.00002836443,0.000010742835,0.0012201632,0.0020064947,0.001258671,0.0009906417,0.96881646,0.00041286537],"about_ca_topic_score_codex":0.0012439484,"about_ca_topic_score_gemma":0.010059333,"teacher_disagreement_score":0.39390212,"about_ca_system_score_codex":0.0014200071,"about_ca_system_score_gemma":0.017004622,"threshold_uncertainty_score":0.9998482},"labels":[],"label_agreement":null},{"id":"W4375933288","doi":"10.1007/978-3-030-90434-0_15-1","title":"Evaluation and Policy Evaluation","year":2023,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Computer science","score_opus":0.5487738952681284,"score_gpt":0.5911378189388959,"score_spread":0.04236392367076758,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4375933288","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002442332,0.00020608453,0.00018369513,0.00376287,0.00059442985,0.0010347574,0.000017280967,0.00007587979,0.99388075],"genre_scores_gemma":[0.021237895,0.0003142019,0.00014177796,0.0005869546,0.00049546425,0.00007708255,0.00009727657,0.000037392823,0.977012],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9864954,0.00027590094,0.00086202973,0.00069916813,0.011477902,0.00018962557],"domain_scores_gemma":[0.99426496,0.0007350998,0.0004601142,0.0007036586,0.0037166453,0.0001195476],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.036943413,0.0002521061,0.0003273852,0.0011118236,0.00017318122,0.00034132352,0.0003190593,0.00026465583,0.038306296],"category_scores_gemma":[0.0041808304,0.00018679048,0.00010867538,0.00023492315,0.000082449136,0.0003350175,0.00015894062,0.00019922316,0.010853327],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000398613,0.000003821326,0.00003540239,0.0000026471691,0.000029932686,2.7611094e-7,0.00013636884,0.00020712928,0.000004680965,0.23117754,0.017443618,0.7509546],"study_design_scores_gemma":[0.00046871995,0.000057458237,0.0026882233,0.000032370062,0.00016757986,0.000002926375,0.00008535069,0.12793252,0.0000055049995,0.7215569,0.14678168,0.00022074052],"about_ca_topic_score_codex":0.000022712225,"about_ca_topic_score_gemma":0.00025549222,"teacher_disagreement_score":0.75073385,"about_ca_system_score_codex":0.00033848773,"about_ca_system_score_gemma":0.0022334352,"threshold_uncertainty_score":0.9916694},"labels":[],"label_agreement":null},{"id":"W4376474565","doi":"10.51744/cip10","title":"Economics and Epidemiology: Two Sides of the Same Coin or Different Currencies for Evaluating Impact?","year":2018,"lang":"en","type":"report","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Impact","funders":"","keywords":"Excellence; Conversation; Engineering ethics; Public relations; Sociology; Political science; Engineering; Law","score_opus":0.7077382628357403,"score_gpt":0.6426830493890888,"score_spread":0.06505521344665144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376474565","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9743145,0.0009308702,0.0015423698,0.0018614875,0.0032559605,0.0016547701,0.00039227176,0.00002129958,0.016026478],"genre_scores_gemma":[0.9253054,0.006928547,0.0087061785,0.0010884877,0.0013421079,0.00031192342,0.000101082835,0.000060903705,0.056155346],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9953482,0.00060768693,0.0020353436,0.00060001534,0.0010766034,0.00033214394],"domain_scores_gemma":[0.98202634,0.012809492,0.002338641,0.0008947055,0.0018253343,0.00010550266],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.026840657,0.0003144534,0.0011608744,0.00020175226,0.00023247475,0.000097942495,0.0007033448,0.00019442251,0.0024939217],"category_scores_gemma":[0.031693365,0.00012702329,0.0004003655,0.00016639601,0.00039714828,0.00016489722,0.00035678328,0.00019147953,0.00001735807],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002436968,0.00011786903,0.49983898,0.00020613182,0.00035743156,1.2991217e-7,0.0010061162,0.0013015616,0.00005644697,0.002740019,0.14880577,0.34532586],"study_design_scores_gemma":[0.00209851,0.0020519998,0.4973751,0.00047816153,0.00041549906,0.00006496869,0.0022395232,0.2365631,0.0004758121,0.1073658,0.14998168,0.0008898446],"about_ca_topic_score_codex":0.00026940595,"about_ca_topic_score_gemma":0.0030496747,"teacher_disagreement_score":0.34443602,"about_ca_system_score_codex":0.0002449363,"about_ca_system_score_gemma":0.0034172898,"threshold_uncertainty_score":0.9984179},"labels":[],"label_agreement":null},{"id":"W4376629346","doi":"10.4337/9780857930699.00004","title":"Contributors","year":2012,"lang":"en","type":"book-chapter","venue":"Edward Elgar Publishing eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Office of International Science and Engineering; Rotman School of Management, University of Toronto; International Development Research Centre; University of Toronto; Aga Khan Foundation","keywords":"Philosophy","score_opus":0.17287623316850648,"score_gpt":0.40344862555236577,"score_spread":0.2305723923838593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376629346","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007733102,0.0005991642,0.00048387997,0.0018167034,0.004103781,0.00041458392,0.00009809756,0.00019575759,0.9922107],"genre_scores_gemma":[0.021163296,0.000026569065,0.00040043378,0.0019397655,0.002331162,0.000023856124,0.00010881391,0.00008466449,0.9739214],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9922347,0.00014601079,0.001368085,0.0008048183,0.0047837673,0.00066260656],"domain_scores_gemma":[0.9944534,0.0011579475,0.0010835616,0.0014660798,0.0013697711,0.00046928276],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.011050709,0.0005126102,0.0007844846,0.00073624554,0.0003422846,0.004739991,0.0019320201,0.00076839613,0.015449135],"category_scores_gemma":[0.0024861207,0.00039750175,0.00043511725,0.000070201044,0.00016663462,0.0020810121,0.0005040129,0.0012496253,0.0056900135],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015817332,0.000010071895,0.00027227457,0.000007861158,0.00007054535,0.0000059675476,0.00048318584,0.000004184022,0.0000071994195,0.34994066,0.36325282,0.2859294],"study_design_scores_gemma":[0.00032761466,0.000037523718,0.00029627097,0.000063346764,0.000047020632,0.0000098582395,0.000050126186,0.000059962964,0.000035440273,0.08741405,0.9112157,0.0004430329],"about_ca_topic_score_codex":0.000024599876,"about_ca_topic_score_gemma":0.00008753476,"teacher_disagreement_score":0.5479629,"about_ca_system_score_codex":0.00028223847,"about_ca_system_score_gemma":0.0007890537,"threshold_uncertainty_score":0.9998477},"labels":[],"label_agreement":null},{"id":"W4377091894","doi":"10.1016/j.evalprogplan.2023.102318","title":"Mapping the evaluation capacity building landscape: A bibliometric analysis of scholarly communities and themes","year":2023,"lang":"en","type":"article","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":32,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of Ottawa","funders":"","keywords":"Scholarship; Bibliometrics; Cover (algebra); Regional science; Sociology; Political science; Library science; Engineering; Computer science","score_opus":0.6130985989473278,"score_gpt":0.5573777674261452,"score_spread":0.05572083152118257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377091894","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99377286,0.0022156578,0.00071728113,0.0007919553,0.000106404965,0.0007221942,0.000010342956,0.0000635881,0.0015997093],"genre_scores_gemma":[0.9984071,0.00017577854,0.0009892688,0.00010538648,0.00002865961,0.00016834453,0.00007667302,0.0000057312595,0.0000430525],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9940853,0.0014061048,0.00061520375,0.00024963717,0.003444371,0.00019939414],"domain_scores_gemma":[0.9951001,0.0024272606,0.00041269403,0.00037066478,0.001627259,0.00006202467],"candidate_categories":["metaresearch","bibliometrics","scholarly_communication"],"consensus_categories":["bibliometrics"],"category_scores_codex":[0.0432756,0.00012593498,0.00028201117,0.028436076,0.0006083488,0.0012342171,0.000292429,0.00006783288,0.0004574986],"category_scores_gemma":[0.003247499,0.00008109975,0.00007880374,0.09017033,0.00012433229,0.0010291773,0.00013363501,0.00020047255,0.000008908002],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007683697,0.000016312595,0.40849152,0.000007631666,0.00016354113,8.501734e-8,0.0113718975,0.0063419337,0.00009524641,0.00021656736,0.0002202698,0.5730673],"study_design_scores_gemma":[0.00025120986,0.000037974703,0.50082296,0.000022425338,0.00020320115,8.64299e-7,0.014307971,0.481927,0.000016285703,0.0015349842,0.0008187661,0.000056333407],"about_ca_topic_score_codex":0.000067239016,"about_ca_topic_score_gemma":0.000047337355,"teacher_disagreement_score":0.573011,"about_ca_system_score_codex":0.000026776748,"about_ca_system_score_gemma":0.00012015332,"threshold_uncertainty_score":0.9998026},"labels":[],"label_agreement":null},{"id":"W4377141999","doi":"10.56645/jmde.v19i43.825","title":"The Program Evaluation Standards in Evaluation Scholarship and Practice","year":2023,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Scholarship; Medical education; Systematic review; Resource (disambiguation); Professional association; Political science; Psychology; Medicine; Sociology; Public relations; MEDLINE; Computer science","score_opus":0.42328942187289514,"score_gpt":0.6372998949468092,"score_spread":0.21401047307391402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377141999","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9734507,0.001763823,0.00021842735,0.017093917,0.0013527339,0.0034755256,0.000006582515,0.000026115973,0.0026121337],"genre_scores_gemma":[0.9969889,0.000597044,0.0016140958,0.000048145408,0.00023283453,0.0003938515,0.00002138741,0.00001541432,0.00008831292],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.955358,0.012586404,0.0029896987,0.00060849084,0.027946489,0.00051088707],"domain_scores_gemma":[0.975273,0.0064484654,0.001822502,0.00049986265,0.015821937,0.00013420885],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3790371,0.00018921962,0.00030380738,0.0009145065,0.0006558075,0.0006930978,0.00051360053,0.00012469664,0.00030262882],"category_scores_gemma":[0.09272421,0.000118499265,0.00012005241,0.002301801,0.0001309019,0.0030387952,0.00016730532,0.00047014348,0.00007268391],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004974358,0.00015674325,0.013649196,0.0000053589683,0.00003124994,0.0000031381408,0.0030796453,0.036530416,0.00035113463,0.00012647927,0.0012637111,0.9443055],"study_design_scores_gemma":[0.00246046,0.0004113656,0.40059668,0.000063229796,0.00016049205,0.000041488158,0.0071131275,0.5621546,0.00004350179,0.02296677,0.003887026,0.000101243],"about_ca_topic_score_codex":0.0000043579166,"about_ca_topic_score_gemma":0.00018286808,"teacher_disagreement_score":0.9442043,"about_ca_system_score_codex":0.0010710917,"about_ca_system_score_gemma":0.0034313856,"threshold_uncertainty_score":0.9149182},"labels":[],"label_agreement":null},{"id":"W4377223985","doi":"10.1093/oxfordhb/9780190916329.013.44","title":"The Whys and Hows of Impact Measurement Standards","year":2023,"lang":"en","type":"book-chapter","venue":"Oxford University Press eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Argument (complex analysis); Certainty; Context (archaeology); Simplicity; Political science; Epistemology; Geography","score_opus":0.22886602492558672,"score_gpt":0.39463110349742786,"score_spread":0.16576507857184114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377223985","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003444784,0.000106831,0.00023464201,0.000092356844,0.00021300468,0.00032207975,0.00030737364,0.000029212653,0.99835],"genre_scores_gemma":[0.0116236685,0.0008787188,0.000031114017,0.00001595144,0.00003413048,6.2331156e-7,0.0000037316045,0.000017001159,0.98739505],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99564785,0.00008991467,0.00033794768,0.00032470084,0.0034175639,0.0001820375],"domain_scores_gemma":[0.9971209,0.00039867536,0.0004561936,0.0006154602,0.0013008621,0.000107875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041826605,0.00020109394,0.00032650898,0.0001880075,0.00033980247,0.0001392979,0.0006553909,0.00014017899,0.00011982511],"category_scores_gemma":[0.00015702279,0.00013028437,0.00019444931,0.000022228833,0.0002577179,0.000107827385,0.0003650571,0.0002195091,0.0000022582085],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004036195,0.0000102912945,0.00014955048,0.000036407186,0.0003939285,0.000016681824,0.00090591254,0.00010083734,0.000034234592,0.76797754,0.03260237,0.19736864],"study_design_scores_gemma":[0.00036009855,0.0001231451,0.00041244845,0.000067049994,0.0000648384,0.0000011039826,0.00020800681,0.0002770626,0.000037687045,0.0054399096,0.992865,0.0001436489],"about_ca_topic_score_codex":0.00003582482,"about_ca_topic_score_gemma":0.00021837403,"teacher_disagreement_score":0.96026266,"about_ca_system_score_codex":0.00024479767,"about_ca_system_score_gemma":0.000618399,"threshold_uncertainty_score":0.5312843},"labels":[],"label_agreement":null},{"id":"W4377966389","doi":"10.1080/1068316x.2023.2213388","title":"Addressing racial bias in parole decisions: A pre-registered study of the Five-Level Risk and Needs System of risk communication","year":2023,"lang":"en","type":"article","venue":"Psychology Crime and Law","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Carleton University; Dalhousie University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Status quo; Risk assessment; Psychology; Indigenous; Actuarial science; Risk communication; Applied psychology; Social psychology; Medicine; Risk analysis (engineering); Business; Computer science; Political science; Computer security","score_opus":0.5439614682932082,"score_gpt":0.5470746047737634,"score_spread":0.003113136480555112,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377966389","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99522483,0.00037762208,0.000089369605,0.00017291796,0.00014639468,0.00034155525,0.00002962722,0.000010836724,0.0036068526],"genre_scores_gemma":[0.99941134,0.00023189643,0.00012184462,0.000079646095,0.000010524125,0.000022478462,0.0000019965435,0.000004377747,0.000115914685],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9969981,0.0014718282,0.000718229,0.00022145332,0.00047684196,0.00011355156],"domain_scores_gemma":[0.99644715,0.0019920089,0.00058213936,0.0007981278,0.00014853965,0.000032049687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005781398,0.00008355184,0.0002766086,0.00026572184,0.00024059271,0.00004216458,0.00040809033,0.000073000745,0.000023285385],"category_scores_gemma":[0.0009888811,0.0000518702,0.000036648755,0.0008141426,0.00024636008,0.0001378164,0.00019353612,0.00016945993,0.000009035786],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027564587,0.0003205831,0.8854002,0.000012584459,0.00003482036,7.3721094e-7,0.047421217,0.00020392817,0.00010441545,0.0032324253,0.000935983,0.06205747],"study_design_scores_gemma":[0.0015444155,0.0001343192,0.9719154,0.00008185778,0.00003191042,0.0000025712504,0.019753246,0.0025855498,0.00002940561,0.0032258907,0.0006419673,0.0000534147],"about_ca_topic_score_codex":0.0008294443,"about_ca_topic_score_gemma":0.0017852245,"teacher_disagreement_score":0.08651526,"about_ca_system_score_codex":0.000008239,"about_ca_system_score_gemma":0.000026610905,"threshold_uncertainty_score":0.21152054},"labels":[],"label_agreement":null},{"id":"W4378087002","doi":"10.22215/cjcr.v9i1.4042","title":"From the Editor","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Children s Rights / Revue canadienne des droits des enfants","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.042950511522207475,"score_gpt":0.3238324249714331,"score_spread":0.28088191344922564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378087002","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9877551,0.00076207885,0.000081160084,0.0014554808,0.0063691586,0.00020988336,0.00045313904,0.0000067032593,0.0029072922],"genre_scores_gemma":[0.99218327,0.000013463602,0.00027806414,0.0006923082,0.00443259,0.0000091506245,0.000029365263,0.000021897766,0.0023399196],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.996428,0.0005427563,0.0010501582,0.00036155552,0.0008631898,0.0007543294],"domain_scores_gemma":[0.99565023,0.000693255,0.000721979,0.0007018756,0.00077846006,0.0014541829],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004018685,0.00022840453,0.0004264276,0.00055999006,0.0022520071,0.00041476873,0.0023564934,0.00006460073,0.008369379],"category_scores_gemma":[0.0008989181,0.00015011273,0.00024949166,0.0010756673,0.00046899304,0.00061949005,0.000073512565,0.00063034735,0.00007108117],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014127149,0.00010416423,0.43043157,0.000008514374,0.00065261865,0.00085416867,0.07476589,0.0072690067,0.00007802206,0.015788645,0.3197405,0.15016562],"study_design_scores_gemma":[0.0007886062,0.00029255246,0.24820602,0.000064387794,0.00007452178,0.0010661073,0.0015046111,0.0004161803,0.00005883943,0.1129442,0.6342473,0.00033664927],"about_ca_topic_score_codex":0.10538774,"about_ca_topic_score_gemma":0.78000826,"teacher_disagreement_score":0.6746205,"about_ca_system_score_codex":0.001164555,"about_ca_system_score_gemma":0.0019472606,"threshold_uncertainty_score":0.9990469},"labels":[],"label_agreement":null},{"id":"W4378223319","doi":"10.1002/ev.20539","title":"Meeting the challenges of educating internal evaluators","year":2023,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; Queen's University","funders":"","keywords":"Front line; Public relations; Geopolitics; Coronavirus disease 2019 (COVID-19); Pandemic; Program evaluation; Political science; Business; Medicine; Public administration","score_opus":0.3888663697506948,"score_gpt":0.5659171151344419,"score_spread":0.1770507453837471,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378223319","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81679654,0.002155344,0.0053557097,0.032410588,0.0065827146,0.002995843,0.000019475445,0.00027154636,0.13341226],"genre_scores_gemma":[0.9955015,0.00014315336,0.00076143583,0.00005847383,0.00041959816,0.0002911571,0.0000131421575,0.000012777656,0.0027987494],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960158,0.00050998747,0.0006999962,0.00031110246,0.0022760285,0.00018709348],"domain_scores_gemma":[0.9951709,0.0025355215,0.0004472402,0.00043268382,0.0013577846,0.000055878445],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.024371296,0.000100550555,0.0001610651,0.0004154885,0.00047797454,0.00009592403,0.00037412968,0.000047153564,0.0007444051],"category_scores_gemma":[0.010487166,0.000066315064,0.00015030542,0.0012658661,0.0000421683,0.00028712075,0.000056722296,0.00008789517,0.00021985687],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016667489,0.000040345905,0.0019444905,0.000007415414,0.000033568267,1.683456e-8,0.004373027,0.010803508,0.0004864877,0.006708819,0.022143131,0.9534425],"study_design_scores_gemma":[0.0013548174,0.00019682081,0.10862375,0.00008520552,0.00015900457,0.000004377574,0.018435454,0.7021917,0.0034182116,0.09723347,0.06809587,0.00020128334],"about_ca_topic_score_codex":0.00009024751,"about_ca_topic_score_gemma":0.00043902232,"teacher_disagreement_score":0.9532412,"about_ca_system_score_codex":0.000102066435,"about_ca_system_score_gemma":0.0005498398,"threshold_uncertainty_score":0.9978479},"labels":[],"label_agreement":null},{"id":"W4378223534","doi":"10.1002/ev.20536","title":"Learning by linking the Canadian Evaluation Society's student case competition within a graduate evaluation course","year":2023,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Experiential learning; Dialogic; Pedagogy; Psychology; Nature versus nurture; Situated; Competition (biology); Professional development; Assessment for learning; Sociology; Formative assessment; Computer science","score_opus":0.34293943692583495,"score_gpt":0.5475533572533501,"score_spread":0.20461392032751513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378223534","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95149624,0.0005276616,0.0061716596,0.019021247,0.0053449147,0.009802668,0.00008894522,0.0003878107,0.0071588443],"genre_scores_gemma":[0.9921185,0.00004963144,0.00041968687,0.00039644452,0.000512786,0.002359136,0.0015035017,0.000040056966,0.0026002913],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98632854,0.0025590588,0.0011682152,0.0008428421,0.008563664,0.0005376657],"domain_scores_gemma":[0.99048924,0.00152772,0.00075859914,0.0006627764,0.0062870984,0.00027458568],"candidate_categories":["metaresearch","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.08201619,0.0002943852,0.0002813505,0.00055217004,0.0041687996,0.0011071658,0.00041369032,0.00019529849,0.001570499],"category_scores_gemma":[0.0046274257,0.00023439845,0.00029382302,0.0029893944,0.00010113196,0.0008964866,0.00005741287,0.00045271206,0.0005705869],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024592073,0.000098087155,0.0033222707,0.000008447749,0.00015582205,0.0000014189,0.016023908,0.35544565,0.00028585494,0.0008382401,0.08079413,0.5430016],"study_design_scores_gemma":[0.0023268582,0.00016665782,0.014739879,0.00003401322,0.00070203963,0.000043097258,0.013097922,0.93604726,0.00014607846,0.011793256,0.020627752,0.00027520285],"about_ca_topic_score_codex":0.012895173,"about_ca_topic_score_gemma":0.25234655,"teacher_disagreement_score":0.58060163,"about_ca_system_score_codex":0.0020827928,"about_ca_system_score_gemma":0.004821155,"threshold_uncertainty_score":0.9999298},"labels":[],"label_agreement":null},{"id":"W4378223570","doi":"10.1002/ev.20540","title":"What we can learn from the international program for development evaluation training (IPDET)","year":2023,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Program evaluation; Training (meteorology); Monitoring and evaluation; Diversity (politics); Medical education; Corporate governance; Political science; Psychology; Business; Medicine; Geography; Public administration; Finance","score_opus":0.5304740430548962,"score_gpt":0.569693978952799,"score_spread":0.03921993589790285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378223570","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60155666,0.0015055815,0.051582206,0.26209196,0.043193158,0.02989428,0.0002483742,0.0013844905,0.008543247],"genre_scores_gemma":[0.8953398,0.00060191785,0.032613263,0.0017155617,0.0039056386,0.026778976,0.0059145438,0.00010506078,0.033025254],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9940389,0.0003564642,0.0008220404,0.0006102448,0.0038630227,0.00030932165],"domain_scores_gemma":[0.99392647,0.0026959223,0.00039128863,0.00042918773,0.002459302,0.00009782404],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.020275827,0.00018073295,0.0001945055,0.00038146926,0.00095626886,0.0011836049,0.0005673315,0.00009727187,0.0017426191],"category_scores_gemma":[0.0061981454,0.0001325587,0.00017733841,0.00117908,0.000038535414,0.000978679,0.000061704166,0.00011496855,0.0002619385],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037922997,0.00003987788,0.00033755956,0.0000015549485,0.000062554784,2.0138792e-8,0.008020009,0.0072679254,0.00012977568,0.00021686904,0.05327784,0.9306081],"study_design_scores_gemma":[0.0014806249,0.00006568262,0.013364019,0.00003419938,0.0000887798,5.442189e-7,0.0072771306,0.4473603,0.0003893526,0.022468109,0.5073485,0.00012280054],"about_ca_topic_score_codex":0.00006608532,"about_ca_topic_score_gemma":0.0036262511,"teacher_disagreement_score":0.9304853,"about_ca_system_score_codex":0.0005514317,"about_ca_system_score_gemma":0.0024848708,"threshold_uncertainty_score":0.99985325},"labels":[],"label_agreement":null},{"id":"W4378223607","doi":"10.1002/ev.20543","title":"Guest Editors’ notes","year":2023,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Timeline; Adventure; Ethos; Dream; Psychology; Sociology; Operations research; Library science; Computer science; Law; History; Political science; Artificial intelligence; Engineering","score_opus":0.3729067314618274,"score_gpt":0.5685543924994344,"score_spread":0.195647661037607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378223607","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39055502,0.000508165,0.10093265,0.09566969,0.26543757,0.009821494,0.00022382937,0.0031329677,0.13371861],"genre_scores_gemma":[0.9092156,0.00008943823,0.0035820547,0.0004772673,0.0332639,0.0011923923,0.00050736556,0.000048512164,0.051623456],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964512,0.00019500857,0.0004903719,0.00037627292,0.002273031,0.00021410575],"domain_scores_gemma":[0.99618614,0.0019022638,0.00017878752,0.00041474932,0.0012154243,0.00010264577],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0095142545,0.000105270956,0.00014256449,0.00058234687,0.00046021756,0.00022915732,0.00023636596,0.000074619886,0.0022602496],"category_scores_gemma":[0.0091219675,0.00008691567,0.00012689825,0.0020370882,0.000025389765,0.00053289393,0.0000340383,0.00006901746,0.0037450655],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013402688,0.000025848683,0.0024919445,0.0000017472369,0.000011801628,5.273941e-8,0.0004013477,0.0034714262,0.0004200109,0.00056781503,0.6949603,0.2976343],"study_design_scores_gemma":[0.0008332748,0.000077747696,0.037245747,0.0000068107324,0.000040975192,9.617311e-7,0.0002740351,0.16106911,0.001229236,0.026005384,0.7730998,0.000116912925],"about_ca_topic_score_codex":0.000058404905,"about_ca_topic_score_gemma":0.00025851128,"teacher_disagreement_score":0.5186606,"about_ca_system_score_codex":0.00012568003,"about_ca_system_score_gemma":0.0005420085,"threshold_uncertainty_score":0.9992246},"labels":[],"label_agreement":null},{"id":"W4378373311","doi":"10.1177/1035719x231179984","title":"Advancing an ethical imperative for collaborative approaches to evaluation with low incidence and underserved communities: Insights from a DeafBlind Support Services pilot program evaluation","year":2023,"lang":"en","type":"article","venue":"Evaluation Journal of Australasia","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Transformative learning; Vocational education; Recreation; Service (business); Participatory evaluation; Psychology; Public relations; Medical education; Sociology; Political science; Medicine; Pedagogy; Business","score_opus":0.4662869316973545,"score_gpt":0.508740093857817,"score_spread":0.04245316216046252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378373311","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9858291,0.00006709424,0.004033766,0.0040510925,0.00029994166,0.0054620043,0.000037594134,0.00003700111,0.00018237831],"genre_scores_gemma":[0.9834609,0.000023253551,0.014534305,0.00038571656,0.00020095473,0.0010090844,0.00033791084,0.000025424228,0.000022425333],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9862161,0.0037934538,0.0015304354,0.0005060865,0.0075936057,0.00036030618],"domain_scores_gemma":[0.9842301,0.0020311181,0.0012991222,0.00049358694,0.011572286,0.0003737862],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03836672,0.00031644193,0.0005463703,0.00087214226,0.0005649667,0.0008134449,0.00057905045,0.00019490166,0.00065258186],"category_scores_gemma":[0.00203345,0.00022997885,0.00007790538,0.002000052,0.00015466067,0.0026576768,0.00007832156,0.0005164151,0.000034974946],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0030140039,0.00078452844,0.022234382,0.00007936016,0.00042758437,0.00000470391,0.15214032,0.501812,0.0025272951,0.0007726454,0.001210678,0.31499252],"study_design_scores_gemma":[0.0045193722,0.005859018,0.099463515,0.0002059728,0.00038617157,0.000012817579,0.11402939,0.76057744,0.0008247614,0.013595279,0.00024993805,0.00027629832],"about_ca_topic_score_codex":0.000042952568,"about_ca_topic_score_gemma":0.0038496882,"teacher_disagreement_score":0.31471622,"about_ca_system_score_codex":0.00046360848,"about_ca_system_score_gemma":0.0034088006,"threshold_uncertainty_score":0.9902038},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"qualitative","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"qualitative","genre":"methods","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W4378436138","doi":"10.1515/9780228002369-002","title":"Changing Subjects of Action Research","year":2020,"lang":"en","type":"book-chapter","venue":"McGill-Queen's University Press eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Action (physics); Psychology; Physics","score_opus":0.2691703333815943,"score_gpt":0.41555498460564916,"score_spread":0.14638465122405486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378436138","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000072319475,0.0000013842023,0.00017564684,0.00041110342,0.000307097,0.00048188958,0.00016452714,0.00006690155,0.99831915],"genre_scores_gemma":[0.04788549,0.00009484352,0.00014994052,0.000089837275,0.00011847388,0.0000013422224,0.000021626995,0.000031207444,0.9516072],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99479425,0.00034992018,0.0004919493,0.0007431348,0.00324358,0.0003771846],"domain_scores_gemma":[0.9963969,0.0007195974,0.000545908,0.00079439045,0.0013291666,0.00021404853],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0025724096,0.00028091655,0.0005310643,0.0013575908,0.000589299,0.00007807498,0.0010373783,0.00035056646,0.00054259],"category_scores_gemma":[0.00019319363,0.00027375077,0.00025857813,0.00013236963,0.00024703977,0.00028269883,0.00085074385,0.00079398684,0.00016888964],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019665479,0.000015286734,0.000009708953,0.000068449095,0.00008799287,0.000052143565,0.000547314,0.00005872075,0.000090639245,0.97919023,0.0055907024,0.014092139],"study_design_scores_gemma":[0.00044145976,0.00015510737,0.000026188725,0.00013239039,0.000051551666,0.0000011297063,0.000847261,0.0002584638,0.0028057185,0.0041343723,0.9908839,0.00026247167],"about_ca_topic_score_codex":0.00015085143,"about_ca_topic_score_gemma":0.0000017190507,"teacher_disagreement_score":0.9852932,"about_ca_system_score_codex":0.00030001183,"about_ca_system_score_gemma":0.000239297,"threshold_uncertainty_score":0.99997145},"labels":[],"label_agreement":null},{"id":"W4378605776","doi":"10.1353/cye.2005.0003","title":"Building a Child Impact Assessment Tool for the City of Edmonton","year":2005,"lang":"en","type":"article","venue":"Children Youth and Environments","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Agency (philosophy); Government (linguistics); Poverty; Child poverty; Local government; Political science; Economic growth; Business; Public administration; Sociology; Social science; Law; Economics","score_opus":0.07331142695539981,"score_gpt":0.4250770038905492,"score_spread":0.35176557693514937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378605776","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9836794,0.00028106672,0.014357667,0.0005700712,0.00006559582,0.000422221,0.00015502634,0.000005459118,0.00046345562],"genre_scores_gemma":[0.9967112,0.0001272136,0.0025634023,0.00026659862,0.00015214145,0.000018702563,0.000027889646,0.000007097776,0.00012576322],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99825585,0.000053181575,0.00041643108,0.0002902785,0.000791988,0.00019229641],"domain_scores_gemma":[0.9989909,0.00029124395,0.00022513856,0.0004038881,0.00001489973,0.00007393543],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014756162,0.00013309998,0.00019108558,0.00005569353,0.00025163306,0.00008662222,0.000326891,0.000045920562,0.00046470755],"category_scores_gemma":[0.00009483462,0.00007394736,0.00012026671,0.000089634086,0.000082482984,0.00026135863,0.00010296987,0.00009546589,0.00001409513],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003759249,0.000098706325,0.836705,7.8127886e-7,0.00007552128,2.9037398e-8,0.0010717461,0.0014849032,0.0003281498,0.0001507472,0.00015494086,0.15989184],"study_design_scores_gemma":[0.0007887025,0.000079264755,0.99198085,0.000008215649,0.000046336012,9.884545e-7,0.00016220313,0.0041508325,0.00050528144,0.00040314381,0.0017775965,0.000096582306],"about_ca_topic_score_codex":0.00006145741,"about_ca_topic_score_gemma":0.0000065554455,"teacher_disagreement_score":0.15979525,"about_ca_system_score_codex":0.000054661185,"about_ca_system_score_gemma":0.000027971957,"threshold_uncertainty_score":0.5088222},"labels":[],"label_agreement":null},{"id":"W4378650648","doi":"10.7202/1099979ar","title":"Assessment in Saskatchewan: Examining Provincial Approaches to Contemporary Assessment Principles through School Division Administrative Policies","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Educational Administration and Policy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Regina","funders":"","keywords":"Summative assessment; Equity (law); Content analysis; Inclusion (mineral); Christian ministry; Triangulation; Grading (engineering); Focus group; Sociology; Public relations; Public administration; Political science; Pedagogy; Formative assessment; Social science; Geography; Engineering; Law","score_opus":0.5120527115732113,"score_gpt":0.5104462948097198,"score_spread":0.0016064167634914917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378650648","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8651637,0.000051254756,0.00031662715,0.09498292,0.00043005846,0.00044466194,0.00008744277,0.0000070031992,0.038516317],"genre_scores_gemma":[0.9913432,0.0000095537025,0.0028789777,0.0014229531,0.00062178954,0.00004851956,0.00005716711,0.000012597765,0.0036052333],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9965301,0.00034683757,0.0013248705,0.00033611502,0.0011063872,0.00035564514],"domain_scores_gemma":[0.99681157,0.0009604944,0.0006152116,0.0002446476,0.0004396457,0.0009284334],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00345426,0.00021037812,0.0003518012,0.0015019415,0.00034594713,0.0006275875,0.00041935896,0.0000957215,0.0006062121],"category_scores_gemma":[0.0021745088,0.00017695494,0.000073879804,0.0016078207,0.0001393253,0.0009059814,0.00004285941,0.0003417766,0.000058043202],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040018815,0.00016076569,0.74344856,0.00002343221,0.000038530583,0.00002043732,0.013874317,0.001096871,0.00011486868,0.22451426,0.010099991,0.0065679667],"study_design_scores_gemma":[0.00041512045,0.00056408346,0.94207597,0.000071547176,0.000005369817,0.00003357418,0.025578827,0.00045600982,0.000049443483,0.012002404,0.01856295,0.00018473165],"about_ca_topic_score_codex":0.0031658073,"about_ca_topic_score_gemma":0.06328165,"teacher_disagreement_score":0.21251185,"about_ca_system_score_codex":0.00055751385,"about_ca_system_score_gemma":0.0689251,"threshold_uncertainty_score":0.95381105},"labels":[],"label_agreement":null},{"id":"W4378650751","doi":"10.7202/1099984ar","title":"Point de vue des directions et des directions adjointes d’établissement du réseau scolaire public québécois sur la dynamique de prise de décision en contexte de crise au moment de la première vague de la COVID-19","year":2023,"lang":"fr","type":"article","venue":"Canadian Journal of Educational Administration and Policy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université du Québec à Rimouski","funders":"","keywords":"Political science; Humanities; Sociology","score_opus":0.0637466246932163,"score_gpt":0.4438909809033173,"score_spread":0.380144356210101,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378650751","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7843008,0.0012082682,0.008381037,0.1971693,0.00041815132,0.0002995179,0.00023755296,0.000024114188,0.007961266],"genre_scores_gemma":[0.98133373,0.0039652265,0.0039148796,0.0030193492,0.00072311744,0.00011964533,0.000044217908,0.000030394418,0.0068494594],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9939661,0.003498356,0.00090407644,0.00030982998,0.00051054475,0.0008111015],"domain_scores_gemma":[0.9882246,0.007022592,0.00047415716,0.00022915358,0.00087387156,0.0031755737],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.013083824,0.00028610206,0.00029843478,0.0013279369,0.0014851637,0.0013124967,0.00039166058,0.00028687215,0.0013821448],"category_scores_gemma":[0.02085821,0.00029159017,0.0001974826,0.0012561118,0.00076800113,0.001024276,0.000035708246,0.000573839,0.000019989127],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00012801103,0.0007953095,0.6209908,0.00020458689,0.00020388603,0.00009784326,0.122409604,0.006105846,0.000620257,0.14456974,0.0728013,0.031072779],"study_design_scores_gemma":[0.0006556194,0.0002813133,0.6422528,0.00035309207,0.00008644886,0.003200742,0.020116758,0.005574424,0.00016146892,0.046476793,0.28056112,0.00027939328],"about_ca_topic_score_codex":0.19474167,"about_ca_topic_score_gemma":0.5959756,"teacher_disagreement_score":0.40123388,"about_ca_system_score_codex":0.009259826,"about_ca_system_score_gemma":0.18776935,"threshold_uncertainty_score":0.9999536},"labels":[],"label_agreement":null},{"id":"W4378803945","doi":"10.1080/17425964.2023.2218991","title":"Self-Study as Expanding Our Ways of Knowing","year":2023,"lang":"en","type":"article","venue":"Studying Teacher Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University","funders":"","keywords":"Pedagogy; Psychology; Sociology; Mathematics education","score_opus":0.3773032908265572,"score_gpt":0.5465295920617902,"score_spread":0.16922630123523297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378803945","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9753065,0.000023240184,0.00014661453,0.0051086163,0.0010386388,0.0005143482,3.924539e-7,0.00015088278,0.017710729],"genre_scores_gemma":[0.99510354,0.000004484745,0.0005857809,0.0003373421,0.00026248544,0.00010127569,0.00000491792,0.000012172908,0.00358801],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9971649,0.00030321625,0.0005682368,0.00034975953,0.0014128276,0.00020106864],"domain_scores_gemma":[0.998649,0.00023277705,0.00024980775,0.0004914104,0.00032431976,0.00005271348],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0065239975,0.00011077719,0.00019169021,0.00051061145,0.00026084943,0.0001296031,0.00040386687,0.000042193158,0.00022460635],"category_scores_gemma":[0.0010449165,0.00008974968,0.00006375336,0.0015472709,0.000008999732,0.0003646315,0.00011225229,0.00016247082,0.0010722388],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007041801,0.001067713,0.8340849,0.000010525186,0.000035394773,8.343738e-7,0.07308226,0.00008316627,0.00037048254,0.0004807135,0.024433708,0.06634324],"study_design_scores_gemma":[0.00049086113,0.0002432511,0.51373273,0.000027041628,0.00004452735,0.0000018221098,0.4632403,0.0025703951,0.00031563712,0.0053132195,0.013817974,0.00020225052],"about_ca_topic_score_codex":0.00007296521,"about_ca_topic_score_gemma":0.000012282394,"teacher_disagreement_score":0.39015803,"about_ca_system_score_codex":0.000098272045,"about_ca_system_score_gemma":0.00049161713,"threshold_uncertainty_score":0.99970555},"labels":[],"label_agreement":null},{"id":"W4378982888","doi":"10.1016/j.evalprogplan.2023.102322","title":"Culturally responsive evaluation: A scoping review of the evaluation literature","year":2023,"lang":"en","type":"review","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; NOSM University; Lakehead University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Participatory evaluation; Situated; Culturally appropriate; Citizen journalism; Culturally sensitive; Evaluation methods; Psychology; Community-based participatory research; Program evaluation; Participatory action research; Applied psychology; Medical education; Medicine; Sociology; Social psychology; Engineering; Political science; Computer science; Gerontology; Social science","score_opus":0.599779829732056,"score_gpt":0.675526932126798,"score_spread":0.07574710239474203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378982888","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000035813482,0.9771755,0.000012058561,0.0006761169,0.0010366801,0.018148996,0.000040680374,0.000073588606,0.0028005652],"genre_scores_gemma":[0.0000372756,0.99318045,0.0004402724,0.0003198845,0.0002418924,0.0044810544,0.00075384515,0.0000385778,0.0005067245],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9722792,0.010836596,0.0030534936,0.0010879315,0.01235892,0.0003838416],"domain_scores_gemma":[0.98458517,0.0028343657,0.0031266431,0.0012028232,0.008123103,0.00012789266],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09043532,0.0005356642,0.0016663622,0.00061040727,0.0005095017,0.0006479509,0.0009099178,0.0003639943,0.0016899679],"category_scores_gemma":[0.030795468,0.00029999166,0.00062640366,0.0045046164,0.00014006543,0.0005861364,0.00028969173,0.0006287816,0.0001459594],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000070321425,0.000023645418,0.000019676685,0.025783073,0.000079069476,5.2487536e-7,0.0008478627,0.00012002722,1.5019121e-7,0.000051888477,0.003011065,0.970056],"study_design_scores_gemma":[0.00056630594,0.00011060227,0.00030541624,0.7250091,0.002619983,0.000032961976,0.0002825902,0.021526283,6.5844443e-7,0.0010944502,0.24807063,0.0003810554],"about_ca_topic_score_codex":0.0000024797237,"about_ca_topic_score_gemma":0.000014282142,"teacher_disagreement_score":0.96967494,"about_ca_system_score_codex":0.00030870424,"about_ca_system_score_gemma":0.00574218,"threshold_uncertainty_score":0.9999452},"labels":[],"label_agreement":null},{"id":"W4379742513","doi":"10.1111/capa.12522","title":"Morality analysis: Reducing moral backlash to public policy","year":2023,"lang":"en","type":"article","venue":"Canadian Public Administration","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Vale (Canada)","funders":"","keywords":"Morality; Backlash; Public policy; Incentive; Government (linguistics); Policy analysis; Political science; Public administration; Public economics; Law and economics; Economics; Sociology; Law; Computer science; Microeconomics","score_opus":0.30648099244065635,"score_gpt":0.4929595553286005,"score_spread":0.18647856288794412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379742513","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48899645,0.000006143793,0.00078616006,0.4869174,0.00037634413,0.00032957713,0.00013847183,0.00013145906,0.022317983],"genre_scores_gemma":[0.98842674,0.000002989053,0.00030579141,0.0029370894,0.00030290737,0.00006570064,0.00042913537,0.000011796591,0.0075178267],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960048,0.0002829593,0.0007886037,0.00063723273,0.001556677,0.0007297082],"domain_scores_gemma":[0.99621,0.00017729016,0.00019797453,0.000902349,0.000833472,0.0016789315],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0053186277,0.00017172346,0.00028421666,0.004464089,0.0005259747,0.001901535,0.0007571523,0.00011706069,0.0036117174],"category_scores_gemma":[0.0042140526,0.00015983758,0.00016109901,0.015865598,0.00006265278,0.0012644453,0.00006109243,0.00014346596,0.0032581396],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012076003,0.0000566042,0.19661197,0.000006680923,0.0002010544,0.000026891512,0.00060388003,0.00072581944,0.00007669087,0.51808023,0.18367639,0.09992171],"study_design_scores_gemma":[0.00019237772,0.00011301047,0.39923182,0.0000035413127,0.000036570487,0.0000049694886,0.0011295241,0.0332601,0.000052512947,0.0037791864,0.56187856,0.00031784645],"about_ca_topic_score_codex":0.0058207302,"about_ca_topic_score_gemma":0.4987417,"teacher_disagreement_score":0.51430106,"about_ca_system_score_codex":0.0006147666,"about_ca_system_score_gemma":0.011094233,"threshold_uncertainty_score":0.9991346},"labels":[],"label_agreement":null},{"id":"W4380563111","doi":"10.2307/jj.4032504.21","title":"Evaluating and monitoring the implementation of the first Child Advocacy Centre in the Quebec City region:","year":2023,"lang":"en","type":"book-chapter","venue":"Presses de l'Université du Québec eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Environmental planning; Geography; Public administration","score_opus":0.10490034685581397,"score_gpt":0.36558837561515045,"score_spread":0.2606880287593365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380563111","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6483582,0.0010557945,0.00011343766,0.037881337,0.000826573,0.0028236497,0.000039802882,0.00008587739,0.3088153],"genre_scores_gemma":[0.94665647,0.00017673436,0.00001825257,0.0002760866,0.00016790439,0.000012184147,0.0000032566006,0.00002001135,0.052669115],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9974386,0.00023015679,0.00047647068,0.00033571385,0.0013256033,0.00019344955],"domain_scores_gemma":[0.9968656,0.0015484575,0.0006161095,0.000683563,0.00025059117,0.00003573254],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021200678,0.00020677826,0.00022809797,0.00013476181,0.0006445314,0.0001658097,0.001160844,0.000096923235,0.0008167271],"category_scores_gemma":[0.00018379408,0.00011086269,0.00014454739,0.00009011333,0.00020088747,0.00013951695,0.00048161487,0.00037606974,0.00003408242],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011326121,0.000026620586,0.42115068,0.000107365006,0.00017688391,0.000023952894,0.17113453,0.0008029444,0.00002383916,0.008548865,0.013695098,0.38419595],"study_design_scores_gemma":[0.0015595014,0.00010597795,0.6013155,0.00076020247,0.00035066128,0.00003999526,0.06385571,0.0011842832,0.0003323487,0.008125833,0.3219008,0.00046917715],"about_ca_topic_score_codex":0.032024406,"about_ca_topic_score_gemma":0.3844352,"teacher_disagreement_score":0.38372678,"about_ca_system_score_codex":0.00020642114,"about_ca_system_score_gemma":0.00078889,"threshold_uncertainty_score":0.97442144},"labels":[],"label_agreement":null},{"id":"W4380787339","doi":"10.1080/15575330.2023.2225089","title":"School districts as constrained leaders in the WoW Bus rural early childhood outreach collaborative","year":2023,"lang":"en","type":"article","venue":"Community Development","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; Michael Smith Health Research BC","keywords":"Outreach; Early childhood; Accountability; Early childhood education; Public relations; Sustainability; Economic growth; Theory of change; Political science; Sociology; Psychology; Economics","score_opus":0.1933972558883424,"score_gpt":0.4516084989149438,"score_spread":0.2582112430266014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380787339","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97259474,0.000029337392,0.00005160197,0.006502194,0.00018801104,0.0005377709,0.000011078015,0.00006779423,0.020017458],"genre_scores_gemma":[0.9968662,0.000024599574,0.00036764028,0.0012702248,0.000019415984,0.00011923952,0.000079499114,0.000008044332,0.0012450999],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9953714,0.0017257363,0.0006740644,0.0001823198,0.001687978,0.00035849508],"domain_scores_gemma":[0.9966782,0.001903583,0.00017679458,0.0007648313,0.00035521414,0.000121417106],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0083732,0.00018751559,0.0002480617,0.00038567252,0.00094619545,0.00040926738,0.0014814832,0.00007225975,0.000522831],"category_scores_gemma":[0.0023250717,0.00012207827,0.000047295056,0.0033537943,0.00020942127,0.00033505776,0.0002777981,0.00071228493,0.003078466],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006818489,0.00078806514,0.28310162,0.000011431756,0.000095173185,0.000026293694,0.5208632,0.00047742378,0.000081181446,0.0017467797,0.035154838,0.1575858],"study_design_scores_gemma":[0.00066983595,0.000062914805,0.7663681,0.000026746471,0.0000030312058,0.0000032594326,0.22158168,0.00007162791,0.000081741506,0.0014764809,0.0095124785,0.00014211998],"about_ca_topic_score_codex":0.00014803284,"about_ca_topic_score_gemma":0.00085669424,"teacher_disagreement_score":0.48326644,"about_ca_system_score_codex":0.00018160156,"about_ca_system_score_gemma":0.0015617672,"threshold_uncertainty_score":0.9976978},"labels":[],"label_agreement":null},{"id":"W4380995842","doi":"10.18438/eblip30376","title":"Evidence Summary Theme: Professional Issues","year":2023,"lang":"en","type":"article","venue":"Evidence Based Library and Information Practice","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Theme (computing); Data science; Computer science; Engineering ethics; Library science; World Wide Web; Engineering","score_opus":0.17749419638726038,"score_gpt":0.47826969008815196,"score_spread":0.30077549370089157,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380995842","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025592966,0.0039177057,0.0020977661,0.9399269,0.0017207884,0.00095846393,0.0000294096,0.00065555115,0.025100453],"genre_scores_gemma":[0.5297538,0.047300696,0.013889797,0.3552619,0.00073044066,0.00036250413,0.0002649662,0.000038949973,0.052396934],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956263,0.000812795,0.0008988854,0.00027946918,0.0021301683,0.00025243015],"domain_scores_gemma":[0.98481905,0.013598015,0.00059210823,0.0005269087,0.00030259351,0.0001612981],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["scholarly_communication","insufficient_payload"],"category_scores_codex":[0.0074867173,0.0001616091,0.00018180232,0.00054064865,0.00043670874,0.001261829,0.00060361053,0.00009159559,0.004212943],"category_scores_gemma":[0.017590892,0.000114867726,0.00005921616,0.0020950993,0.00009503807,0.3736125,0.00030814973,0.00027076417,0.0037341767],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009209203,0.000059267302,0.018615944,0.00013248518,0.000021371432,0.000009731924,0.0015924493,0.0015781816,0.00017580636,0.18983427,0.56208503,0.22497456],"study_design_scores_gemma":[0.00021602995,0.0001226366,0.055362742,0.00071260054,0.0000125844335,0.000007571648,0.0027586203,0.042341176,0.00074208155,0.00162959,0.8959125,0.00018181713],"about_ca_topic_score_codex":0.0000035514688,"about_ca_topic_score_gemma":6.486184e-8,"teacher_disagreement_score":0.584665,"about_ca_system_score_codex":0.000012044992,"about_ca_system_score_gemma":0.000662481,"threshold_uncertainty_score":0.99977493},"labels":[],"label_agreement":null},{"id":"W4381052654","doi":"10.29011/2577-2228.100329","title":"Health Programs Uncovered: Simplifying Evaluative Research Decisions with Logic Analysis","year":2023,"lang":"en","type":"article","venue":"Journal of Community Medicine & Public Health","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Vitalité Health Network","funders":"","keywords":"Psychology; Computer science; Management science; Data science; Engineering","score_opus":0.872133077825113,"score_gpt":0.6968941438434303,"score_spread":0.17523893398168267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381052654","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41646862,0.0006409328,0.019685464,0.55799234,0.00036764576,0.0007380432,0.000012656941,0.00005968243,0.004034591],"genre_scores_gemma":[0.989235,0.0013535048,0.0018530581,0.0068045375,0.00022999576,0.000016473618,0.00007425535,0.000017063872,0.00041609927],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.95919204,0.023015518,0.0033177487,0.00028196845,0.012978772,0.0012139314],"domain_scores_gemma":[0.97100633,0.015812522,0.00240416,0.0014827002,0.007894365,0.0013999343],"candidate_categories":["metaresearch","bibliometrics","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2851669,0.0002243579,0.0014513822,0.0055332677,0.0024935417,0.00033996627,0.0021626852,0.0000827994,0.00096797984],"category_scores_gemma":[0.026339753,0.00012289686,0.0002196234,0.02258508,0.0005482297,0.0008761127,0.0002829617,0.002854942,0.00013344757],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012616599,0.0006261135,0.06231705,0.00003500007,0.0004958481,0.000009961713,0.044229258,0.002301459,0.0000030425576,0.0020441778,0.10864561,0.7791663],"study_design_scores_gemma":[0.0034460137,0.015524191,0.48843977,0.0005656161,0.00009712848,0.000105834144,0.24863842,0.008653773,7.4586774e-7,0.03282241,0.20146568,0.00024040185],"about_ca_topic_score_codex":0.0017223253,"about_ca_topic_score_gemma":0.004981017,"teacher_disagreement_score":0.7789259,"about_ca_system_score_codex":0.0010132537,"about_ca_system_score_gemma":0.010935492,"threshold_uncertainty_score":0.9999453},"labels":[],"label_agreement":null},{"id":"W4381623780","doi":"10.1007/978-3-030-90434-0_15-2","title":"Evaluation and Policy Evaluation","year":2023,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Political science; Computer science","score_opus":0.5487738952681284,"score_gpt":0.5911378189388959,"score_spread":0.04236392367076758,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381623780","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002442332,0.00020608453,0.00018369513,0.00376287,0.00059442985,0.0010347574,0.000017280967,0.00007587979,0.99388075],"genre_scores_gemma":[0.021237895,0.0003142019,0.00014177796,0.0005869546,0.00049546425,0.00007708255,0.00009727657,0.000037392823,0.977012],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9864954,0.00027590094,0.00086202973,0.00069916813,0.011477902,0.00018962557],"domain_scores_gemma":[0.99426496,0.0007350998,0.0004601142,0.0007036586,0.0037166453,0.0001195476],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.036943413,0.0002521061,0.0003273852,0.0011118236,0.00017318122,0.00034132352,0.0003190593,0.00026465583,0.038306296],"category_scores_gemma":[0.0041808304,0.00018679048,0.00010867538,0.00023492315,0.000082449136,0.0003350175,0.00015894062,0.00019922316,0.010853327],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000398613,0.000003821326,0.00003540239,0.0000026471691,0.000029932686,2.7611094e-7,0.00013636884,0.00020712928,0.000004680965,0.23117754,0.017443618,0.7509546],"study_design_scores_gemma":[0.00046871995,0.000057458237,0.0026882233,0.000032370062,0.00016757986,0.000002926375,0.00008535069,0.12793252,0.0000055049995,0.7215569,0.14678168,0.00022074052],"about_ca_topic_score_codex":0.000022712225,"about_ca_topic_score_gemma":0.00025549222,"teacher_disagreement_score":0.75073385,"about_ca_system_score_codex":0.00033848773,"about_ca_system_score_gemma":0.0022334352,"threshold_uncertainty_score":0.9916694},"labels":[],"label_agreement":null},{"id":"W4382244540","doi":"10.1515/9781553393412-007","title":"Lineation And Lobbying: Policy Networks And Higher Education Policy In Ontario","year":2013,"lang":"en","type":"book-chapter","venue":"McGill-Queen's University Press eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.07519857778771163,"score_gpt":0.3372273224418575,"score_spread":0.26202874465414583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382244540","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005221861,0.000006975567,0.000055005694,0.0012191669,0.00022973397,0.0005341924,0.000021995143,0.000034916422,0.99737585],"genre_scores_gemma":[0.040952604,0.00020581778,0.00017885235,0.0005887151,0.0002146133,0.0000034004906,0.000034232387,0.000022133805,0.9577996],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99785376,0.000108298314,0.0004353117,0.0006323065,0.00070447463,0.00026584018],"domain_scores_gemma":[0.99836314,0.00020106124,0.0004159946,0.00047569818,0.00033209068,0.00021201893],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00048017842,0.00032726824,0.00040158766,0.0010666263,0.00028712116,0.00019824774,0.00034022136,0.00040801722,0.00047072707],"category_scores_gemma":[0.000037622878,0.0003163864,0.00007464675,0.000058978054,0.00015193167,0.00043833043,0.00037334373,0.0004957475,0.00002621628],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000393152,0.000017687427,0.0007241325,0.000012148957,0.00002574533,0.0000036344702,0.00023787488,0.00014980753,0.0000010172074,0.9593751,0.0023790016,0.037034564],"study_design_scores_gemma":[0.00052744435,0.000053669333,0.016946308,0.00009898558,0.000034784563,0.000002006363,0.000056668203,0.00036329287,0.0000034731804,0.008097592,0.9734983,0.00031751083],"about_ca_topic_score_codex":0.09028166,"about_ca_topic_score_gemma":0.0008681155,"teacher_disagreement_score":0.9711193,"about_ca_system_score_codex":0.00080305105,"about_ca_system_score_gemma":0.0007098431,"threshold_uncertainty_score":0.99992883},"labels":[],"label_agreement":null},{"id":"W4382562365","doi":"10.1080/23268263.2023.2223818","title":"Cross-Disciplinary Research and Scholarship","year":2023,"lang":"en","type":"article","venue":"Voice and Speech Review","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Winnipeg","funders":"","keywords":"Scholarship; Cross disciplinary; Discipline; Sociology; Political science; Social science; Computer science; Data science","score_opus":0.6704574161198528,"score_gpt":0.6576873409442576,"score_spread":0.012770075175595141,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382562365","genre_codex":"empirical","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8552084,0.10584127,0.0000060932266,0.019273615,0.00017396368,0.0005412768,0.000007912687,0.000058890746,0.018888554],"genre_scores_gemma":[0.27966973,0.66121775,0.0005448544,0.0027662623,0.00023446788,0.00008544239,0.000016423623,0.000019876894,0.055445183],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970747,0.00027393608,0.00042618823,0.00039445463,0.0015734135,0.00025731398],"domain_scores_gemma":[0.99778557,0.0010798271,0.00006929665,0.00043303147,0.0004929106,0.00013934515],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.023432242,0.000085419124,0.00023475241,0.00023868473,0.00043384027,0.000423999,0.0003122781,0.000047309954,0.0009766669],"category_scores_gemma":[0.0023148244,0.000055397042,0.000036208858,0.0018530221,0.0001628441,0.0005221138,0.000345215,0.0002586939,0.0040742443],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011685152,0.000034673147,0.26789126,0.0010360713,0.000009291327,0.000029414417,0.0002323087,0.000001131443,0.00014608825,0.0018542162,0.04214578,0.6866081],"study_design_scores_gemma":[0.00016946513,0.00013145494,0.47785497,0.0015584059,0.000007956592,0.000027014983,0.00015337515,0.0004041293,0.00004964749,0.022035306,0.49747935,0.00012894266],"about_ca_topic_score_codex":0.000003899185,"about_ca_topic_score_gemma":0.000018542323,"teacher_disagreement_score":0.68647915,"about_ca_system_score_codex":0.000012783241,"about_ca_system_score_gemma":0.00008735057,"threshold_uncertainty_score":0.9999366},"labels":[],"label_agreement":null},{"id":"W4382865019","doi":"10.1515/9780773568976-007","title":"Preparing to Invade Canada","year":2001,"lang":"en","type":"book-chapter","venue":"McGill-Queen's University Press eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.07992751441717855,"score_gpt":0.3212322335653554,"score_spread":0.24130471914817686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382865019","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004972654,8.219383e-7,0.00014262658,0.00050816947,0.00049524865,0.00055604824,0.0002739658,0.000080283186,0.9978931],"genre_scores_gemma":[0.006971415,0.00003504721,0.00021751727,0.000990331,0.000096389565,0.0000020424598,0.000021391172,0.000036516765,0.99162936],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99540645,0.000110943234,0.0005636016,0.0009344198,0.0025473016,0.00043731253],"domain_scores_gemma":[0.9969745,0.00035296992,0.00045117576,0.0011734746,0.0005870598,0.00046077612],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007573562,0.00043327478,0.0005724587,0.0004650022,0.0005570112,0.00013248847,0.0014445035,0.00028081398,0.0009212348],"category_scores_gemma":[0.00011051331,0.00042846755,0.00018640545,0.000055410397,0.000074183336,0.00022553917,0.00090435235,0.0004664206,0.00014439289],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001266583,0.000013182443,0.00006191543,0.00002076182,0.00012902716,0.00019900713,0.00017595476,0.0010028192,0.000005021382,0.80190915,0.17792149,0.018434998],"study_design_scores_gemma":[0.00035359655,0.000057206773,0.000073867974,0.0000885726,0.0000638552,0.0000032916057,0.00011500167,0.00010868949,0.00010937153,0.0010789863,0.9974491,0.00049843284],"about_ca_topic_score_codex":0.18040198,"about_ca_topic_score_gemma":0.018225435,"teacher_disagreement_score":0.8195276,"about_ca_system_score_codex":0.0009967472,"about_ca_system_score_gemma":0.0008266214,"threshold_uncertainty_score":0.9999921},"labels":[],"label_agreement":null},{"id":"W4383270982","doi":"10.23889/ijpds.v8i1.1843.review.r2.dec","title":"Editorial Decision: Student Achievement Trajectories in Ontario: Creating and validating a province-wide, multi-cohort and longitudinal database","year":2022,"lang":"en","type":"editorial","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Database; Cohort; Longitudinal data; Computer science; Data science; Statistics; Data mining; Mathematics","score_opus":0.10263769816753528,"score_gpt":0.4374365353281561,"score_spread":0.3347988371606208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383270982","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09601513,0.00014698337,0.0006123756,0.00006231139,0.90053594,0.0012531575,0.00014371512,0.000040769766,0.0011896179],"genre_scores_gemma":[0.0057063075,0.00022913971,0.012179037,0.000057724177,0.9733117,0.00049215567,0.00057326915,0.000057149216,0.007393475],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9853193,0.0005429315,0.0020932022,0.0018833836,0.009607708,0.0005534748],"domain_scores_gemma":[0.98637944,0.0108976085,0.0008521953,0.0009357324,0.00067289657,0.0002621169],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01673042,0.000599313,0.0010362541,0.00061473163,0.00077930314,0.0015313096,0.00095143897,0.00038486958,0.0031926369],"category_scores_gemma":[0.0086907735,0.00046662922,0.000108502245,0.0005143522,0.00013412497,0.0010852539,0.0019187185,0.0018415138,0.000015167573],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013723828,0.0002055251,0.4857974,0.000016792152,0.000039350136,0.000013857541,0.001131355,0.00006706774,0.000003323243,0.000036210302,0.5110006,0.0015513344],"study_design_scores_gemma":[0.0028638253,0.00040422732,0.18490109,0.00014647882,0.00008044801,0.0000020488985,0.003662885,0.0004909944,0.000004983108,0.00011945077,0.8067482,0.0005753479],"about_ca_topic_score_codex":0.04538019,"about_ca_topic_score_gemma":0.5279346,"teacher_disagreement_score":0.4825544,"about_ca_system_score_codex":0.0010737316,"about_ca_system_score_gemma":0.0033133905,"threshold_uncertainty_score":0.99977857},"labels":[],"label_agreement":null},{"id":"W4383271016","doi":"10.23889/ijpds.v8i1.1843.review.r1.dec","title":"Editorial Decision: Student Achievement Trajectories in Ontario: Creating and validating a province-wide, multi-cohort and longitudinal database","year":2022,"lang":"en","type":"editorial","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Cohort; Database; Longitudinal data; Computer science; Data science; Statistics; Data mining; Mathematics","score_opus":0.10263769816753528,"score_gpt":0.4374365353281561,"score_spread":0.3347988371606208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383271016","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09601513,0.00014698337,0.0006123756,0.00006231139,0.90053594,0.0012531575,0.00014371512,0.000040769766,0.0011896179],"genre_scores_gemma":[0.0057063075,0.00022913971,0.012179037,0.000057724177,0.9733117,0.00049215567,0.00057326915,0.000057149216,0.007393475],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9853193,0.0005429315,0.0020932022,0.0018833836,0.009607708,0.0005534748],"domain_scores_gemma":[0.98637944,0.0108976085,0.0008521953,0.0009357324,0.00067289657,0.0002621169],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01673042,0.000599313,0.0010362541,0.00061473163,0.00077930314,0.0015313096,0.00095143897,0.00038486958,0.0031926369],"category_scores_gemma":[0.0086907735,0.00046662922,0.000108502245,0.0005143522,0.00013412497,0.0010852539,0.0019187185,0.0018415138,0.000015167573],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013723828,0.0002055251,0.4857974,0.000016792152,0.000039350136,0.000013857541,0.001131355,0.00006706774,0.000003323243,0.000036210302,0.5110006,0.0015513344],"study_design_scores_gemma":[0.0028638253,0.00040422732,0.18490109,0.00014647882,0.00008044801,0.0000020488985,0.003662885,0.0004909944,0.000004983108,0.00011945077,0.8067482,0.0005753479],"about_ca_topic_score_codex":0.04538019,"about_ca_topic_score_gemma":0.5279346,"teacher_disagreement_score":0.4825544,"about_ca_system_score_codex":0.0010737316,"about_ca_system_score_gemma":0.0033133905,"threshold_uncertainty_score":0.99977857},"labels":[],"label_agreement":null},{"id":"W4383454879","doi":"10.1515/9780773552616-011","title":"Decolonizing Evaluation in Winnipeg","year":2018,"lang":"en","type":"book-chapter","venue":"McGill-Queen's University Press eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"History; Geography","score_opus":0.1270561290298885,"score_gpt":0.3655607560715928,"score_spread":0.23850462704170428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383454879","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003756701,0.000002603563,0.0000925084,0.00024870495,0.00053719466,0.000860573,0.00010292622,0.000069945614,0.9977099],"genre_scores_gemma":[0.0169517,0.000049776845,0.00038503553,0.00024545155,0.0001280689,0.0000043466343,0.000041524225,0.00003695038,0.9821572],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99454033,0.0003725842,0.0007153464,0.00096629595,0.0030205785,0.00038489004],"domain_scores_gemma":[0.99625933,0.00049947505,0.00069754646,0.0010225379,0.001346733,0.00017436821],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0039878353,0.00040944174,0.0005655169,0.0009946058,0.00043324826,0.0001403925,0.0010795315,0.00049269764,0.0033851564],"category_scores_gemma":[0.00025713604,0.0004059361,0.00022897561,0.000072520204,0.00021296796,0.00043620777,0.0005449109,0.00050626154,0.0004727669],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032099336,0.00006636815,0.00028775682,0.000041615014,0.00016588,0.00012369036,0.0012313048,0.00063848624,0.000016009635,0.901144,0.029543204,0.06642068],"study_design_scores_gemma":[0.0010879972,0.00010866292,0.00041513142,0.0001435915,0.00011134393,0.0000016452847,0.00019261758,0.0020034565,0.00009562284,0.010331768,0.9850567,0.00045147171],"about_ca_topic_score_codex":0.00024287497,"about_ca_topic_score_gemma":0.000024132443,"teacher_disagreement_score":0.9555135,"about_ca_system_score_codex":0.0008749502,"about_ca_system_score_gemma":0.00039224172,"threshold_uncertainty_score":0.99983925},"labels":[],"label_agreement":null},{"id":"W4383557002","doi":"10.3389/frhs.2023.1162762","title":"Connecting the science and practice of implementation – applying the lens of context to inform study design in implementation research","year":2023,"lang":"en","type":"article","venue":"Frontiers in Health Services","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of Ottawa; Dalhousie University","funders":"Canadian Institutes of Health Research","keywords":"Context (archaeology); Computer science; Implementation research; Engineering ethics; Discipline; Analogy; Position paper; Knowledge management; Management science; Sociology; Psychology; Engineering; World Wide Web","score_opus":0.48424212633900504,"score_gpt":0.6364270795980652,"score_spread":0.15218495325906017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383557002","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9839322,0.00016072126,0.0006938144,0.010526886,0.0002643894,0.0042527197,0.0000056261124,0.0000067789883,0.00015688322],"genre_scores_gemma":[0.9970435,0.00007944699,0.0018594695,0.00069699826,0.000010269705,0.00030097927,0.0000017720738,0.000003500032,0.000004053068],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9938999,0.0015731448,0.0011349323,0.000277351,0.0027589751,0.00035573286],"domain_scores_gemma":[0.9942538,0.003948791,0.00052074663,0.00029634347,0.0009375925,0.00004272865],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.10548114,0.00006287606,0.00017891874,0.0009190128,0.00059085025,0.00013285098,0.0005928067,0.0000145124295,0.000025324473],"category_scores_gemma":[0.0011171278,0.000037854606,0.000009799084,0.00587188,0.000094744064,0.00096698187,0.00022456155,0.00013875085,0.000004496588],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014257917,0.000046509373,0.2496794,0.00009212375,0.0000087199605,3.4055148e-7,0.2960942,0.0034203157,0.000114955976,0.000612119,0.00058990263,0.4491988],"study_design_scores_gemma":[0.000447507,0.00029132122,0.19774316,0.00003283672,0.0000019427587,4.1251167e-7,0.78183115,0.016742764,0.00012281245,0.0005136583,0.0022423556,0.00003006271],"about_ca_topic_score_codex":0.0067083063,"about_ca_topic_score_gemma":0.011167464,"teacher_disagreement_score":0.48573697,"about_ca_system_score_codex":0.00016996592,"about_ca_system_score_gemma":0.00066839304,"threshold_uncertainty_score":0.9999061},"labels":[],"label_agreement":null},{"id":"W4383760480","doi":"10.56687/9781447353621","title":"Implementing Evidence-Based Research","year":2021,"lang":"en","type":"book","venue":"Policy Press eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Data science","score_opus":0.8465082539945432,"score_gpt":0.6583054366334357,"score_spread":0.18820281736110755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383760480","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000053604384,0.0013529537,0.00025732873,0.0014678412,0.00031502589,0.0006478027,0.00006074839,0.000057960817,0.9957867],"genre_scores_gemma":[0.0021369904,0.00010394502,0.00044798196,0.0013896944,0.0019183321,0.00019369736,0.00003902751,0.000050054554,0.9937203],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98737526,0.0014066139,0.0013578443,0.0010821276,0.0076277186,0.0011504388],"domain_scores_gemma":[0.988415,0.0060464824,0.0005849524,0.002004286,0.0026680916,0.00028116064],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02247493,0.00034853612,0.0005993699,0.0012996111,0.000675594,0.0014422825,0.0019489012,0.00031955578,0.0031065415],"category_scores_gemma":[0.006052711,0.0002832781,0.00032549072,0.00020511303,0.00027774315,0.0002589665,0.0012397656,0.001056131,0.00045737135],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034453053,0.000026940801,0.00011654485,0.0001068545,0.00006230254,0.000024954747,0.000977569,0.000079308506,0.00011035536,0.1735412,0.65190786,0.17301165],"study_design_scores_gemma":[0.00026563884,0.000064895554,0.000078036115,0.0005864335,0.00002022141,0.0000027284025,0.000065507265,0.001245366,0.0011470194,0.028638232,0.9676068,0.0002791564],"about_ca_topic_score_codex":0.0007549887,"about_ca_topic_score_gemma":0.0003405135,"teacher_disagreement_score":0.31569892,"about_ca_system_score_codex":0.00057288207,"about_ca_system_score_gemma":0.0120766675,"threshold_uncertainty_score":0.9999619},"labels":[],"label_agreement":null},{"id":"W4383768404","doi":"10.56687/9781447345527-021","title":"Using evidence in Canada","year":2019,"lang":"en","type":"book-chapter","venue":"Policy Press eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"History","score_opus":0.6860390556166668,"score_gpt":0.5379510163831983,"score_spread":0.14808803923346847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383768404","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00065917097,0.00040540806,0.000050301147,0.00020422901,0.00047388618,0.00039742404,0.00003943888,0.000009887777,0.99776024],"genre_scores_gemma":[0.059224438,0.00006161309,0.00014143564,0.0012581322,0.00028098488,0.000007768289,0.0000019301376,0.000029531202,0.93899417],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99592626,0.00008727271,0.0008433893,0.00051147374,0.0023136195,0.00031797556],"domain_scores_gemma":[0.9973561,0.000844126,0.000489055,0.000938977,0.00025051285,0.00012122158],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012972419,0.0002650693,0.00046390446,0.0004089676,0.00005672648,0.00015208578,0.0008891796,0.00014070985,0.00070041197],"category_scores_gemma":[0.00042461188,0.00021697932,0.00008831071,0.000026279035,0.000050184528,0.00016019249,0.00026934478,0.00035567052,0.00014516652],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006838645,0.000007843939,0.0030573632,0.00010388273,0.00005958797,0.00004429445,0.0010533526,0.0059946403,0.00008053434,0.86059636,0.019337643,0.109596096],"study_design_scores_gemma":[0.0002624936,0.000022625938,0.0009933722,0.00058579,0.000019591416,0.000009082801,0.000027370837,0.01199669,0.00011924708,0.024819734,0.9606771,0.00046690236],"about_ca_topic_score_codex":0.91042936,"about_ca_topic_score_gemma":0.89789015,"teacher_disagreement_score":0.94133943,"about_ca_system_score_codex":0.0011452774,"about_ca_system_score_gemma":0.0146006625,"threshold_uncertainty_score":0.99098563},"labels":[],"label_agreement":null},{"id":"W4383769725","doi":"10.56687/9781447334927-005","title":"The policy analysis profession in Canada","year":2018,"lang":"en","type":"book-chapter","venue":"Policy Press eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.22757285867885083,"score_gpt":0.4917554903432765,"score_spread":0.2641826316644257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383769725","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00052970427,0.00014441431,0.000023003988,0.002590733,0.0003233492,0.0004282408,0.00007996735,0.000016238457,0.99586433],"genre_scores_gemma":[0.06355401,0.000100741956,0.000023729992,0.0013415836,0.00085370895,0.00005348323,0.00001188688,0.000026999563,0.9340339],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9948465,0.0002204482,0.0011470811,0.00056592637,0.002733935,0.0004860805],"domain_scores_gemma":[0.9961774,0.0009575158,0.0007509164,0.0014737311,0.00045465791,0.00018583173],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023407235,0.00033324465,0.0005630886,0.0010651465,0.00035311587,0.0002794314,0.0014525187,0.00018866562,0.0006933103],"category_scores_gemma":[0.00062044075,0.00019506832,0.00022296041,0.00018566696,0.00018192979,0.000080403355,0.00041681674,0.0004263986,0.00012773844],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000089411726,0.000011579131,0.0014973049,0.000018230225,0.00052477606,0.00001152204,0.0026117377,0.00028867554,0.0000048588886,0.71030265,0.110258274,0.17438096],"study_design_scores_gemma":[0.00018428422,0.000019151847,0.0022453163,0.000038751452,0.00007667152,0.0000010757861,0.00009904456,0.0019192805,0.000037866306,0.05680643,0.9383265,0.00024565158],"about_ca_topic_score_codex":0.89449155,"about_ca_topic_score_gemma":0.98294663,"teacher_disagreement_score":0.8280682,"about_ca_system_score_codex":0.0010922506,"about_ca_system_score_gemma":0.011072902,"threshold_uncertainty_score":0.9945334},"labels":[],"label_agreement":null},{"id":"W4383808933","doi":"10.56687/9781847423405","title":"Rethinking professional governance","year":2008,"lang":"en","type":"book","venue":"Policy Press eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Corporate governance; Process management; Business; Finance","score_opus":0.3603713834878263,"score_gpt":0.5057472606669112,"score_spread":0.1453758771790849,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383808933","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006334547,0.0004593167,0.000062745785,0.0007179972,0.0012079842,0.0004715484,0.00011584893,0.000088965455,0.9968122],"genre_scores_gemma":[0.0013874779,0.00021936696,0.0003853576,0.0024562979,0.0020645235,0.00008421136,0.000027026068,0.000051334002,0.9933244],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9926757,0.00027599442,0.0010955711,0.0007670472,0.004725118,0.0004605759],"domain_scores_gemma":[0.9959602,0.0009069104,0.0011500631,0.0012483924,0.0005402199,0.00019426152],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0019435539,0.00040234686,0.0005886316,0.00025928763,0.00039371473,0.00023078888,0.0016131887,0.00046676103,0.0005071623],"category_scores_gemma":[0.0009622207,0.00029912483,0.00027205356,0.00005726847,0.00025051113,0.0002072902,0.00053828006,0.0008835856,0.00067509786],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022858316,0.000015061791,0.000026379663,0.000020608377,0.000026870066,0.000011111335,0.0025553403,0.000025136078,0.000005208076,0.40258026,0.56254137,0.032169804],"study_design_scores_gemma":[0.0002685745,0.000027557371,0.00039700422,0.00017169047,0.000011128723,0.000019468926,0.000004642965,0.00040282327,0.000080929814,0.14900391,0.84931487,0.00029743428],"about_ca_topic_score_codex":0.00017131324,"about_ca_topic_score_gemma":0.000061147264,"teacher_disagreement_score":0.28677347,"about_ca_system_score_codex":0.0003992183,"about_ca_system_score_gemma":0.004851121,"threshold_uncertainty_score":0.99994606},"labels":[],"label_agreement":null},{"id":"W4383891699","doi":"10.1108/978-1-80382-513-720231005","title":"A Theory of Action Approach to Examining Interventions","year":2023,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Psychological intervention; Action (physics); Psychology; Computer science; Epistemology; Philosophy; Physics; Psychiatry","score_opus":0.7778459242131487,"score_gpt":0.5583122054950207,"score_spread":0.219533718718128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383891699","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000104245715,0.000015898533,0.05904227,0.00010736076,0.00046743924,0.00025445348,0.000015488631,0.000051268595,0.9399416],"genre_scores_gemma":[0.021967558,0.000022197968,0.0020617477,0.00014346767,0.00007076219,0.000024304152,0.000021923597,0.000020095682,0.97566795],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99723375,0.00007656845,0.0008195735,0.00036545517,0.0014004873,0.00010415558],"domain_scores_gemma":[0.9979583,0.00068845454,0.00037466382,0.00052676175,0.00036214307,0.00008969582],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.005740415,0.00013819149,0.0003072841,0.0007386093,0.000062245206,0.00007476352,0.00042354077,0.00012505466,0.011454994],"category_scores_gemma":[0.00064690993,0.000099195124,0.00023914839,0.00017302188,0.000041711366,0.00013987522,0.0001752721,0.00015804361,0.0029260134],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013754013,0.000023002198,0.000027738708,0.000028692159,0.00003985868,2.252727e-7,0.00039652898,0.00022523347,0.00001829617,0.8281266,0.012615288,0.15848479],"study_design_scores_gemma":[0.00044687206,0.0004335765,0.004779669,0.0006983665,0.00013766033,0.0000060255984,0.006385816,0.0028347909,0.000123348,0.7495826,0.2339516,0.0006196914],"about_ca_topic_score_codex":0.0000031441145,"about_ca_topic_score_gemma":0.00003248655,"teacher_disagreement_score":0.2213363,"about_ca_system_score_codex":0.000039586925,"about_ca_system_score_gemma":0.0001293386,"threshold_uncertainty_score":0.9978503},"labels":[],"label_agreement":null},{"id":"W4384152283","doi":"10.1515/9780773555839-024","title":"An Ontario Report on Education and Two International Commissions","year":2019,"lang":"en","type":"book-chapter","venue":"McGill-Queen's University Press eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Library science; Computer science","score_opus":0.08382197580848194,"score_gpt":0.37547182363793347,"score_spread":0.2916498478294515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384152283","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00042376644,4.4633845e-7,0.00006237446,0.00049233297,0.001128614,0.00038110281,0.0001131487,0.00004865816,0.99734956],"genre_scores_gemma":[0.014929456,0.000017672752,0.00037069712,0.00037718014,0.00009427371,0.0000011858326,0.00015529263,0.000020433627,0.9840338],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99705666,0.000098501754,0.00043957328,0.0007632271,0.0014774152,0.00016464053],"domain_scores_gemma":[0.9972612,0.00021605498,0.0005969806,0.0010388996,0.000654716,0.00023214819],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007829165,0.0002895168,0.00033845325,0.00049513497,0.00038347443,0.000166251,0.0007743137,0.00022315691,0.0013723152],"category_scores_gemma":[0.00004931662,0.00026734042,0.00012804828,0.000015798816,0.00009886342,0.0003699437,0.0003049714,0.000481403,0.00010113123],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000102231934,0.00007822025,0.00067651144,0.0000058121054,0.000071406466,0.00005490914,0.00032813664,0.000105269755,0.000004794476,0.9678219,0.012127006,0.018623777],"study_design_scores_gemma":[0.0004706954,0.00011244992,0.0013207687,0.000100242156,0.000055597528,0.00001533149,0.00014385238,0.00013809415,0.000025816214,0.003056701,0.9942614,0.00029903758],"about_ca_topic_score_codex":0.0050704647,"about_ca_topic_score_gemma":0.0001916698,"teacher_disagreement_score":0.9821344,"about_ca_system_score_codex":0.00054946495,"about_ca_system_score_gemma":0.000815889,"threshold_uncertainty_score":0.9999779},"labels":[],"label_agreement":null},{"id":"W4384200366","doi":"10.1111/1467-8500.12595","title":"Assessing the ‘forgotten fundamental’ in policy advisory systems research: Policy shops and the role(s) of core policy professionals","year":2023,"lang":"en","type":"article","venue":"Australian Journal of Public Administration","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Simon Fraser University; Toronto Metropolitan University","funders":"","keywords":"Government (linguistics); Work (physics); Public policy; Distribution (mathematics); Advice (programming); Public relations; Core (optical fiber); Political science; Business; Public administration; Engineering; Law; Computer science","score_opus":0.5736256102983246,"score_gpt":0.6152550634437988,"score_spread":0.04162945314547417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384200366","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79767597,0.000103195795,0.00003797588,0.1990788,0.00019924444,0.00045745214,0.000014498479,0.000008436779,0.002424405],"genre_scores_gemma":[0.9956642,0.000087604,0.000046308818,0.00024058146,0.000775404,0.000025129593,0.000008924414,0.000011005294,0.0031408574],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99199915,0.0023485057,0.001740433,0.00022694349,0.0032087609,0.00047618596],"domain_scores_gemma":[0.9942357,0.002467804,0.0013097464,0.0004194565,0.0013554883,0.00021180019],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.036743026,0.00015232501,0.0003714562,0.0021011338,0.0004438132,0.0011829385,0.00091545354,0.00011517248,0.000097377546],"category_scores_gemma":[0.009024615,0.000077693585,0.000119377335,0.0046478254,0.0006642725,0.0017447016,0.00014520611,0.00060163223,0.00002603928],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027629398,0.00033326496,0.19141039,0.00006935342,0.0001193955,0.000024136672,0.011446252,0.00053907325,0.002123933,0.702642,0.012735218,0.07828065],"study_design_scores_gemma":[0.0027879644,0.0006071297,0.6255187,0.00034627176,0.000021780492,0.00030443617,0.22988775,0.0059504276,0.00042421848,0.10179638,0.032122158,0.00023280972],"about_ca_topic_score_codex":0.00024670898,"about_ca_topic_score_gemma":0.00010922967,"teacher_disagreement_score":0.60084563,"about_ca_system_score_codex":0.00025138166,"about_ca_system_score_gemma":0.006488221,"threshold_uncertainty_score":0.9998539},"labels":[],"label_agreement":null},{"id":"W4384704009","doi":"10.3138/cjpe.75471","title":"Doing the Inner Work for Sustainable Practices","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mindset; Work (physics); Sociology; Grounded theory; Reflective practice; Engineering ethics; Psychology; Epistemology; Public relations; Pedagogy; Qualitative research; Social science; Political science; Engineering","score_opus":0.46181610888955293,"score_gpt":0.5772504504403074,"score_spread":0.1154343415507545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384704009","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8820776,0.0013972542,0.0061212797,0.08007551,0.0032525163,0.0072574727,0.000007315421,0.000059836628,0.019751236],"genre_scores_gemma":[0.99313676,0.000010167578,0.003010128,0.000319728,0.00036824716,0.00023848843,0.000009206922,0.000009874887,0.0028973925],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967588,0.00045903013,0.0006358381,0.00014147692,0.0016537933,0.00035104807],"domain_scores_gemma":[0.9922365,0.0012785735,0.0012491441,0.00024939547,0.004762447,0.00022394504],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.040824447,0.00007791218,0.00013528187,0.0005964659,0.000557767,0.0009785369,0.00051343074,0.000049740353,0.00068641076],"category_scores_gemma":[0.016198318,0.000046130943,0.00010934413,0.002105596,0.00006403236,0.00096344255,0.000014882268,0.00015744929,0.00011262929],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025129328,0.000012424478,0.012464137,0.0000063355915,0.000026973898,0.000006639375,0.0018201679,0.007813207,0.0000052599044,0.0020375447,0.081564344,0.89421785],"study_design_scores_gemma":[0.0005029915,0.00023015057,0.03701074,0.00002204948,0.00006609606,0.000010802344,0.011643618,0.024256555,0.000019027453,0.017247166,0.90891147,0.000079348036],"about_ca_topic_score_codex":0.0002655462,"about_ca_topic_score_gemma":0.0048017683,"teacher_disagreement_score":0.8941385,"about_ca_system_score_codex":0.00023714484,"about_ca_system_score_gemma":0.0050067906,"threshold_uncertainty_score":0.9920887},"labels":[],"label_agreement":null},{"id":"W4384704011","doi":"10.3138/cjpe.74373","title":"Building Capacity With Evaluation Standards and Guidelines in Prince Edward Island: Responding to Academics’ “Call to Action”","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Prince Edward Island","funders":"","keywords":"Government (linguistics); Process (computing); Action (physics); Capacity building; Public relations; Political science; Resource (disambiguation); Public administration; Business; Sociology; Computer science; Law","score_opus":0.422866600441089,"score_gpt":0.5731474583533296,"score_spread":0.1502808579122406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384704011","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9798857,0.00009059007,0.0065100095,0.010899602,0.0004885542,0.0017140907,0.000020973466,0.000015102366,0.00037535783],"genre_scores_gemma":[0.9795263,0.0000199499,0.019342907,0.0005025688,0.00021680552,0.00016575595,0.000005412727,0.000014888356,0.00020544491],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99281067,0.00072921644,0.001113736,0.00035510797,0.0046064677,0.000384783],"domain_scores_gemma":[0.99169815,0.00030277975,0.00044231306,0.00023753742,0.00667792,0.0006413167],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.060223598,0.00015124545,0.000276524,0.003738445,0.00022383126,0.00043599968,0.00034455335,0.0001005771,0.00026601102],"category_scores_gemma":[0.01575067,0.00011730407,0.000045479414,0.0041513615,0.000044218927,0.00076202635,0.000029469978,0.00029494896,0.000029477142],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010580921,0.0000073696933,0.05892661,0.000005771832,0.000014442387,0.00000431138,0.0024960667,0.06929574,0.00039665357,0.00020948282,0.0055378554,0.8629999],"study_design_scores_gemma":[0.0025431064,0.0013879014,0.4558022,0.000691182,0.0001217109,0.0000780818,0.0030783932,0.26988432,0.0005465352,0.008216789,0.25719285,0.0004569135],"about_ca_topic_score_codex":0.00047251978,"about_ca_topic_score_gemma":0.084180675,"teacher_disagreement_score":0.862543,"about_ca_system_score_codex":0.0013947533,"about_ca_system_score_gemma":0.0056316215,"threshold_uncertainty_score":0.99902546},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":true,"confidence":"medium"}],"label_agreement":"split"},{"id":"W4384704021","doi":"10.3138/cjpe.76349","title":"Sustainability-Ready Evaluation: A Call to Action","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Sustainability; Nexus (standard); Call to action; Work (physics); Action (physics); Sustainability science; Environmental resource management; Business; Sustainability organizations; Environmental planning; Political science; Computer science; Engineering; Ecology; Marketing; Geography; Economics","score_opus":0.5953134200335379,"score_gpt":0.6226408964927189,"score_spread":0.027327476459180988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384704021","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9510036,0.00017006502,0.0015477606,0.0339226,0.003051926,0.0048125796,0.000014530288,0.000056953646,0.0054199486],"genre_scores_gemma":[0.99717647,0.000004695412,0.00084401754,0.0003343243,0.00036226446,0.00033836195,0.000039066163,0.000013655992,0.0008871267],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99177986,0.001234329,0.001161482,0.00032362202,0.005053306,0.00044737445],"domain_scores_gemma":[0.9828637,0.00037951415,0.0005603371,0.000467924,0.014895845,0.00083264755],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.05154241,0.00014903475,0.00026682267,0.0018635408,0.0003412631,0.0005726919,0.0005424152,0.000101987025,0.0030658408],"category_scores_gemma":[0.017539142,0.00012189112,0.00014056133,0.0032486992,0.00006601941,0.0008381197,0.000022257871,0.00022728686,0.0008679425],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019991377,0.00002565791,0.00940404,0.000005031366,0.00001870472,0.000005427436,0.0015322226,0.025566872,0.000026858921,0.00028393604,0.03765589,0.9254554],"study_design_scores_gemma":[0.001404551,0.0010062333,0.28402156,0.000040159262,0.00017353924,0.00004300146,0.006899802,0.2645583,0.00009120157,0.034435775,0.4070535,0.0002723858],"about_ca_topic_score_codex":0.000763083,"about_ca_topic_score_gemma":0.031059371,"teacher_disagreement_score":0.925183,"about_ca_system_score_codex":0.001943955,"about_ca_system_score_gemma":0.015139469,"threshold_uncertainty_score":0.99991},"labels":[],"label_agreement":null},{"id":"W4384704143","doi":"10.3138/cjpe.71619","title":"How to Conduct a Metaevaluation?: A Metaevaluation Practice","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Strengths and weaknesses; Computer science; Evaluation methods; Quality (philosophy); Process (computing); Management science; Process management; Psychology; Reliability engineering; Social psychology; Business; Engineering","score_opus":0.718641825237931,"score_gpt":0.625746580813898,"score_spread":0.09289524442403296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384704143","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55420166,0.0018467533,0.023782926,0.37212098,0.009968706,0.013501498,0.000069829606,0.00022625091,0.024281377],"genre_scores_gemma":[0.9763773,0.000019533005,0.019804832,0.0013517824,0.00048871886,0.0004087924,0.000038970426,0.000029101804,0.0014809899],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98263407,0.002760812,0.00147262,0.000462598,0.012114012,0.0005559006],"domain_scores_gemma":[0.9665969,0.0014233445,0.0013564886,0.0006158876,0.029018853,0.0009884953],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.12004442,0.00023217803,0.00045515018,0.0028329527,0.00041894207,0.0018837444,0.000823913,0.000122231,0.0021467884],"category_scores_gemma":[0.12740064,0.0001829034,0.00025711165,0.0051423684,0.00008354901,0.0028918497,0.00003431151,0.00029869957,0.0012579171],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043251348,0.00004935063,0.0007975313,0.0000051211123,0.00013051475,0.00001445862,0.0031129322,0.014965108,0.00046736686,0.0014476829,0.07079294,0.90817374],"study_design_scores_gemma":[0.0015721638,0.0010666269,0.022401962,0.00004507059,0.00060437975,0.00009929321,0.008631141,0.1383503,0.00038205326,0.017059067,0.80945426,0.00033368447],"about_ca_topic_score_codex":0.00030924272,"about_ca_topic_score_gemma":0.008229631,"teacher_disagreement_score":0.9078401,"about_ca_system_score_codex":0.0012490222,"about_ca_system_score_gemma":0.014153463,"threshold_uncertainty_score":0.9995197},"labels":[],"label_agreement":null},{"id":"W4384704152","doi":"10.3138/cjpe.76738","title":"<i>Evaluating and Valuing in Social Research</i> , by Thomas A. Schwandt and Emily F. Gates","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sociology; Psychology; Positive economics; Economics","score_opus":0.6880176902655514,"score_gpt":0.6452034549058989,"score_spread":0.04281423535965245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384704152","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99083525,0.0012206824,0.000024114473,0.0053924355,0.00021360292,0.0006986524,0.0000064799087,0.000009866944,0.0015989349],"genre_scores_gemma":[0.9984538,0.00006906959,0.0009407045,0.00009080755,0.00015196801,0.00005685071,0.000010854784,0.00001058918,0.00021535633],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9941303,0.0014985636,0.0008158329,0.0002659169,0.002860298,0.00042910167],"domain_scores_gemma":[0.9962712,0.000866381,0.00032214055,0.0001259876,0.0020696272,0.00034469576],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0672141,0.00010416792,0.00022950665,0.0013083828,0.0005945756,0.00078511453,0.00024968587,0.00008889561,0.00018796284],"category_scores_gemma":[0.0070093935,0.0000865421,0.00004156066,0.0019187593,0.00022004121,0.00070683984,0.00003739398,0.00037445972,0.000025349236],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017281935,0.000014229761,0.06854527,0.000009132345,0.000011187213,0.000008082562,0.0041796947,0.00026333862,0.00073262135,0.00046944548,0.015356894,0.9103928],"study_design_scores_gemma":[0.004040427,0.0013412047,0.49473506,0.00026171975,0.00007258492,0.00007078692,0.01913971,0.3130351,0.0003616769,0.10595063,0.0605789,0.0004122088],"about_ca_topic_score_codex":0.00045422564,"about_ca_topic_score_gemma":0.0065515405,"teacher_disagreement_score":0.9099806,"about_ca_system_score_codex":0.00023826433,"about_ca_system_score_gemma":0.002448206,"threshold_uncertainty_score":0.96049935},"labels":[],"label_agreement":null},{"id":"W4384704212","doi":"10.3138/cjpe.77058-fr","title":"Nos racines et nos liens : une célébration de bons remèdes en évaluation autochtone","year":2023,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Forestry; Geography","score_opus":0.385499950579361,"score_gpt":0.5506690169872253,"score_spread":0.16516906640786427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384704212","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7521996,0.0033995658,0.015069046,0.20550275,0.009386982,0.0049556927,0.000096191616,0.000119789314,0.009270419],"genre_scores_gemma":[0.97978765,0.00055277534,0.011967051,0.0008314942,0.0011220576,0.00023354945,0.00020129398,0.000046862435,0.0052572545],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98942494,0.003604267,0.0019702003,0.00045134846,0.0037145314,0.00083468645],"domain_scores_gemma":[0.990989,0.0012274563,0.0014127438,0.0004829973,0.0049380464,0.00094971684],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.05055136,0.00032966494,0.00049111457,0.0018944258,0.000593647,0.0010739495,0.00056919234,0.00036088022,0.0034902352],"category_scores_gemma":[0.010864343,0.00031138473,0.00030160398,0.0037372431,0.00024447075,0.0020937496,0.00003406862,0.000625414,0.00094621093],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003617453,0.00011037563,0.0101724,0.000034565102,0.00009116818,0.000032906704,0.015236776,0.06994353,0.0004475536,0.0034873164,0.022775996,0.87763125],"study_design_scores_gemma":[0.0015553465,0.0010249723,0.25443795,0.00039000754,0.00042003774,0.00013974584,0.004761764,0.6014761,0.00022372125,0.0227195,0.112514764,0.00033613737],"about_ca_topic_score_codex":0.004701063,"about_ca_topic_score_gemma":0.10931039,"teacher_disagreement_score":0.8772951,"about_ca_system_score_codex":0.0014781294,"about_ca_system_score_gemma":0.029573822,"threshold_uncertainty_score":0.99996305},"labels":[],"label_agreement":null},{"id":"W4384704276","doi":"10.3138/cjpe.77058-en","title":"Roots and Relations: Celebrating Good Medicine in Indigenous Evaluation","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Indigenous; Traditional medicine; Sociology; Political science; Engineering ethics; Environmental ethics; Medicine; Engineering; Philosophy; Biology; Ecology","score_opus":0.32934335382480695,"score_gpt":0.5403537153913232,"score_spread":0.2110103615665162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384704276","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9858684,0.0010982257,0.00016983863,0.006685187,0.0007033188,0.0016580146,0.0000029402163,0.000015153463,0.0037989344],"genre_scores_gemma":[0.9986137,0.00003219508,0.0007581337,0.00010654693,0.0001726894,0.00011274165,0.000032100153,0.000009629282,0.00016227209],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9941622,0.0009974445,0.0012431791,0.00023257753,0.0030641444,0.00030045884],"domain_scores_gemma":[0.9956428,0.0005512476,0.00072445825,0.00021703441,0.0025373697,0.00032712152],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.046871148,0.00011712482,0.00024846228,0.002035258,0.00027411798,0.00022019203,0.00025743997,0.00009581783,0.0016097925],"category_scores_gemma":[0.0084395325,0.0000923402,0.00004589754,0.002461729,0.00009253137,0.000781714,0.00001324091,0.0002457252,0.00010251801],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000051916527,0.000012593064,0.17173205,0.0000032393382,0.000010070433,0.0000053030994,0.0052356864,0.008269131,0.00004477407,0.00022625795,0.0013764512,0.81307924],"study_design_scores_gemma":[0.0013955714,0.00037706082,0.7174889,0.00010370658,0.00006178742,0.000027149472,0.0035262352,0.2460786,0.000010819034,0.02524394,0.0055812737,0.00010498577],"about_ca_topic_score_codex":0.0010426218,"about_ca_topic_score_gemma":0.06395073,"teacher_disagreement_score":0.8129743,"about_ca_system_score_codex":0.0005371223,"about_ca_system_score_gemma":0.0047000647,"threshold_uncertainty_score":0.9999128},"labels":[],"label_agreement":null},{"id":"W4384704291","doi":"10.3138/cjpe.38.1.ed-en","title":"Editor’s Remarks","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Philosophy; Psychology","score_opus":0.3016607384097375,"score_gpt":0.5419447489581198,"score_spread":0.24028401054838233,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384704291","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83711743,0.00097156427,0.002445411,0.03685035,0.06468003,0.0036134229,0.000029206036,0.00013233752,0.05416026],"genre_scores_gemma":[0.9940449,0.000013220605,0.0014438768,0.00020563856,0.0031648087,0.000045330296,0.00001773646,0.000009942429,0.0010545491],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9955053,0.000415694,0.0007865304,0.00015167915,0.002868767,0.0002720561],"domain_scores_gemma":[0.9953159,0.00028554566,0.0004931246,0.0002655536,0.0031687526,0.0004710908],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.024627816,0.000083011575,0.00016917981,0.0010701319,0.00019822734,0.0003929544,0.0004595897,0.00007228107,0.0038903803],"category_scores_gemma":[0.005499139,0.00006263263,0.00011801692,0.0016472327,0.00006102372,0.0005616982,0.000011080702,0.00017529621,0.00091196224],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004549832,0.000008382617,0.0116367815,0.000001386721,0.000010852067,0.0000064418723,0.00047632185,0.0016546788,0.000018128467,0.00019120304,0.28842306,0.69756824],"study_design_scores_gemma":[0.0006104685,0.0003107812,0.13341339,0.00003110775,0.000040280895,0.000023838049,0.0013397733,0.07667341,0.000042513147,0.016967505,0.7704299,0.00011702141],"about_ca_topic_score_codex":0.0001839598,"about_ca_topic_score_gemma":0.008594621,"teacher_disagreement_score":0.6974512,"about_ca_system_score_codex":0.00025826498,"about_ca_system_score_gemma":0.0053484077,"threshold_uncertainty_score":0.99986595},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W4384704311","doi":"10.3138/cjpe.76031","title":"<i>Ethics for Evaluation. Beyond “Doing No Harm” to “Tackling Bad” and “Doing Good”</i> , par Rob van den Berg, Penny Hawkins et Nicoletta Stame (dir.)","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Harm; Psychology; Social psychology","score_opus":0.2641401555920312,"score_gpt":0.5229258898039616,"score_spread":0.2587857342119304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384704311","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86715776,0.003075873,0.03819168,0.05694571,0.0063500074,0.014003333,0.00021312399,0.00014993103,0.013912596],"genre_scores_gemma":[0.95786345,0.00006492747,0.03723099,0.0029563264,0.00058423734,0.00049046596,0.00011357413,0.000054543958,0.0006415057],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99134046,0.0014032944,0.0015547534,0.0005524119,0.0044077635,0.00074134395],"domain_scores_gemma":[0.9877919,0.0018444167,0.000951898,0.00046465656,0.00796303,0.0009841194],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07420288,0.0002763988,0.00045331442,0.0014012874,0.0009937779,0.0013808694,0.000640267,0.00020099815,0.0010879221],"category_scores_gemma":[0.011284974,0.00024917178,0.00019850724,0.0016101372,0.00010014703,0.0012606077,0.00006908104,0.00058206444,0.00022214354],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006127976,0.000047873553,0.013453381,0.000039450744,0.00011733918,0.000007984241,0.00725974,0.06465901,0.00053101237,0.0010202473,0.023341576,0.8894611],"study_design_scores_gemma":[0.0035101355,0.0011942405,0.035142157,0.0003487155,0.000488298,0.000045519824,0.0033877064,0.45081273,0.00023982392,0.011923268,0.4923358,0.0005716034],"about_ca_topic_score_codex":0.00035057572,"about_ca_topic_score_gemma":0.028264726,"teacher_disagreement_score":0.8888895,"about_ca_system_score_codex":0.0006603084,"about_ca_system_score_gemma":0.009781825,"threshold_uncertainty_score":0.99999607},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W4384704622","doi":"10.7202/1099898ar","title":"Prioritizing Improvement Among Disadvantaged Students in Principle and in Practice","year":2023,"lang":"en","type":"article","venue":"Philosophical Inquiry in Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Disadvantaged; Normative; Point (geometry); Psychology; Social psychology; Sociology; Inequality; Mathematics education; Pedagogy; Political science; Economic growth; Economics; Law","score_opus":0.20610878453042067,"score_gpt":0.570699198818896,"score_spread":0.3645904142884753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384704622","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98167384,0.00004869132,0.00001287163,0.016075622,0.0008011641,0.0005477922,0.0000010121768,0.000019407868,0.0008196232],"genre_scores_gemma":[0.9983765,0.00017591399,0.00020124081,0.0007479427,0.00019806743,0.00019871548,0.000013401787,0.000008400757,0.000079838064],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99687713,0.0003456141,0.00081703666,0.00046668053,0.0012444285,0.00024912422],"domain_scores_gemma":[0.99829674,0.0010125157,0.00018113406,0.00030598536,0.00012301972,0.00008060949],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006585379,0.0001157769,0.00019409068,0.00077251287,0.000058635254,0.00017207892,0.0003138014,0.000080353115,0.00002505168],"category_scores_gemma":[0.0034348764,0.00010359169,0.000020745378,0.0017073317,0.00009322904,0.0011071012,0.00020152886,0.00032673075,0.0000828101],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004713867,0.0006190876,0.96860987,0.000012074546,0.0000026497373,0.000006481539,0.006391155,0.00019989174,0.00041916026,0.004123835,0.000040705294,0.019527953],"study_design_scores_gemma":[0.00059357745,0.000052361727,0.9259971,0.00006749642,0.0000030488409,0.000001356578,0.008605803,0.0034963624,0.000029623634,0.06049755,0.0005397742,0.00011597318],"about_ca_topic_score_codex":0.00008060435,"about_ca_topic_score_gemma":0.00040300694,"teacher_disagreement_score":0.05637371,"about_ca_system_score_codex":0.00026751828,"about_ca_system_score_gemma":0.00022881433,"threshold_uncertainty_score":0.42243463},"labels":[],"label_agreement":null},{"id":"W4384929312","doi":"10.56645/jmde.v19i44.773","title":"Decolonizing Evaluation of Indigenous Land-Based Programs: A Settler Perspective on What We Can Learn from the LANDBACK Movement","year":2023,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Aurora College","funders":"","keywords":"Indigenous; Sovereignty; Perspective (graphical); Land rights; Sociology; Environmental ethics; Political science; Ecology; Law; Ethnology; Computer science; Politics; Artificial intelligence","score_opus":0.30421046055774864,"score_gpt":0.5120849863126739,"score_spread":0.2078745257549252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384929312","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9741374,0.00068457273,0.00017318633,0.022527225,0.00092132133,0.0013516451,0.000019331643,0.000015315267,0.00016995592],"genre_scores_gemma":[0.99866277,0.00021457902,0.00043694896,0.00018295721,0.00027187561,0.000081913924,0.000064573695,0.000016266004,0.000068090776],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98762524,0.0022369607,0.0012191335,0.00033915872,0.008324793,0.00025471262],"domain_scores_gemma":[0.99046504,0.0019662431,0.0016719111,0.00048529575,0.005317609,0.0000939223],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03766251,0.00019087367,0.00035573725,0.00050433935,0.00037849,0.00029712325,0.0005608976,0.00009801366,0.0005376642],"category_scores_gemma":[0.002367873,0.000113001,0.00023121579,0.0011821409,0.000080852355,0.00071258866,0.00009091457,0.00031280066,0.0001210315],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005670809,0.00058389525,0.11475793,0.00000895101,0.0001737145,0.000004548927,0.05583861,0.4551748,0.0008007975,0.00004571433,0.0011857799,0.37085816],"study_design_scores_gemma":[0.003324469,0.00096681796,0.42402604,0.00031982228,0.0002533458,0.000001985306,0.053919833,0.4963037,0.0007609843,0.019830396,0.00015518077,0.00013741448],"about_ca_topic_score_codex":0.00009190908,"about_ca_topic_score_gemma":0.00113473,"teacher_disagreement_score":0.37072074,"about_ca_system_score_codex":0.0009722608,"about_ca_system_score_gemma":0.0020851202,"threshold_uncertainty_score":0.99092895},"labels":[],"label_agreement":null},{"id":"W4384932226","doi":"10.56645/jmde.v19i44.809","title":"Steps Toward Evaluation as Decluttering: Learnings from Hawaiian Epistemology","year":2023,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Indigenous; CLARITY; Negotiation; Epistemology; Identity (music); Field (mathematics); Meaning (existential); Sociology; Social science; Aesthetics; Philosophy; Ecology","score_opus":0.35745616972763433,"score_gpt":0.5449069672074174,"score_spread":0.18745079747978305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384932226","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9813511,0.00023716617,0.002211588,0.010452098,0.0025117001,0.0006487091,0.000008714718,0.00004124151,0.002537724],"genre_scores_gemma":[0.9966856,0.00007483596,0.0016021471,0.00013232665,0.000580223,0.000044510958,0.00008238774,0.000024250168,0.00077367615],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.985773,0.0026960995,0.002140015,0.0005199294,0.008506575,0.0003643326],"domain_scores_gemma":[0.990879,0.0019265942,0.0021539184,0.0005576487,0.0042621014,0.00022073604],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.050227974,0.00024308018,0.0005283382,0.0011605405,0.0003717786,0.00025668743,0.0008014199,0.0001839803,0.0058781244],"category_scores_gemma":[0.00818814,0.0001863408,0.0002938974,0.0013968397,0.0000959228,0.0013345188,0.0002509413,0.000417603,0.0025515703],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00068102207,0.0002687024,0.10150862,0.000016630289,0.00018617905,0.00004756739,0.022499379,0.18224514,0.013622812,0.00020718496,0.011314478,0.66740227],"study_design_scores_gemma":[0.0022708313,0.0005174312,0.4593824,0.00006568663,0.00016855124,0.000051416395,0.009611815,0.48951688,0.0005067382,0.03566944,0.0020520135,0.00018678377],"about_ca_topic_score_codex":0.000039914972,"about_ca_topic_score_gemma":0.00006203009,"teacher_disagreement_score":0.6672155,"about_ca_system_score_codex":0.0005057035,"about_ca_system_score_gemma":0.001506878,"threshold_uncertainty_score":0.99822503},"labels":[],"label_agreement":null},{"id":"W4385212885","doi":"10.5465/amproc.2023.12768symposium","title":"In the Eye of the Beholder: Advancing Feedback Research with a Focus on Perceptions","year":2023,"lang":"en","type":"article","venue":"Academy of Management Proceedings","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kellogg's (Canada)","funders":"","keywords":"Perception; Silence; Power (physics); Field (mathematics); Psychology; Sociology; Public relations; Political science","score_opus":0.2786477107184681,"score_gpt":0.51768922824745,"score_spread":0.2390415175289819,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385212885","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.876516,0.000009225043,0.000008862308,0.062116105,0.00003165429,0.0007045526,0.0000017481096,0.000013318591,0.060598575],"genre_scores_gemma":[0.9927294,0.00012551076,0.00017392867,0.00076906604,0.000032952412,0.000099188685,2.7559787e-7,0.0000072401435,0.0060624327],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99542624,0.0000972415,0.00047082812,0.00030457362,0.0034032462,0.00029784467],"domain_scores_gemma":[0.9989762,0.00042417907,0.00020911015,0.00018446051,0.00017865137,0.000027436166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012941045,0.00009224747,0.00014982246,0.00061966357,0.00022443177,0.000074821,0.0013578235,0.000047868783,0.00020361561],"category_scores_gemma":[0.00027310272,0.000044193832,0.000056584635,0.003999627,0.00019950203,0.00043925448,0.0003025249,0.00039054768,0.0001468889],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024456964,0.00039683454,0.19153465,0.0002725612,0.00007954043,0.0000023265561,0.025616542,0.001855645,0.0018051562,0.39107308,0.31309903,0.074020065],"study_design_scores_gemma":[0.0005888639,0.00018640334,0.8823398,0.00020917348,0.000016599768,8.7795183e-7,0.04208986,0.0012485563,0.0009946348,0.036772545,0.03545976,0.00009296632],"about_ca_topic_score_codex":0.000009589405,"about_ca_topic_score_gemma":0.000008582163,"teacher_disagreement_score":0.6908051,"about_ca_system_score_codex":0.00004269957,"about_ca_system_score_gemma":0.000024233452,"threshold_uncertainty_score":0.4485134},"labels":[],"label_agreement":null},{"id":"W4385216962","doi":"10.5465/amproc.2023.14930symposium","title":"Essence, Silence, Vitality: The Moral and Ethical Dimensions of Professional and Occupational Work","year":2023,"lang":"en","type":"article","venue":"Academy of Management Proceedings","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Quest University Canada","funders":"","keywords":"Vitality; Silence; Work (physics); Psychology; Engineering ethics; Social psychology; Sociology; Aesthetics; Philosophy; Engineering; Theology","score_opus":0.19544596508608353,"score_gpt":0.47829478805278414,"score_spread":0.2828488229667006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385216962","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96959907,0.000049720842,0.000032665055,0.02664681,0.00008359686,0.00036569758,0.000005834047,0.000024712368,0.0031919032],"genre_scores_gemma":[0.99572796,0.0002311484,0.0005796594,0.0010904782,0.000028538876,0.000040467123,0.000002091563,0.000004722632,0.0022949136],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99707186,0.00004361091,0.00056836556,0.00032418317,0.0018200506,0.00017193524],"domain_scores_gemma":[0.99876434,0.00061258633,0.00031354505,0.000078252764,0.00016928178,0.00006196836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005257849,0.0001047942,0.0001940405,0.0002846348,0.0002441937,0.00005709219,0.00036122891,0.00012099858,0.000106044354],"category_scores_gemma":[0.0003627975,0.000057190588,0.000038081525,0.0013840642,0.00038896708,0.0002798429,0.00054082123,0.00029885906,0.000021085501],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011201776,0.000048874423,0.39303195,0.00012787232,0.000054578435,4.2982205e-7,0.001693699,0.000039031376,0.000407296,0.50370646,0.07305951,0.027718272],"study_design_scores_gemma":[0.00026447244,0.000030153817,0.91611165,0.00009690131,0.0000251164,0.0000010589696,0.003751634,0.0021180543,0.00013414539,0.070090726,0.007296889,0.00007917649],"about_ca_topic_score_codex":0.0000015814007,"about_ca_topic_score_gemma":1.7783066e-7,"teacher_disagreement_score":0.5230797,"about_ca_system_score_codex":0.0000073442734,"about_ca_system_score_gemma":0.000025007632,"threshold_uncertainty_score":0.23321643},"labels":[],"label_agreement":null},{"id":"W4385254759","doi":"10.57054/jhea.v15i1.1488","title":"1 - Why Measurement Matters: The Learning Outcomes Approach – A Case Study from Canada","year":2022,"lang":"en","type":"article","venue":"Journal of Higher Education in Africa","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Accountability; Quality assurance; Quality (philosophy); Higher education; Experiential learning; Active learning (machine learning); Learning sciences; Open learning; Computer science; Psychology; Medical education; Cooperative learning; Mathematics education; Teaching method; Political science; Artificial intelligence; Business; Medicine","score_opus":0.24434535425817028,"score_gpt":0.45271669053085295,"score_spread":0.20837133627268267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385254759","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9527128,0.00051243283,0.00010243535,0.041089606,0.0029402997,0.00028013161,0.0000029728574,0.0000035525873,0.002355804],"genre_scores_gemma":[0.99326885,0.0000011666774,0.00019282966,0.0037933758,0.00010750477,0.000047605343,6.887549e-7,0.0000055843734,0.002582373],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99435335,0.001134979,0.0007973968,0.0001509854,0.0034368236,0.00012644778],"domain_scores_gemma":[0.99801475,0.00051096984,0.0006919391,0.0002599718,0.00045745235,0.000064941465],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0060142153,0.000086422806,0.0001980578,0.00022896132,0.00034616952,0.0001517041,0.0005262087,0.000010468865,0.0039583743],"category_scores_gemma":[0.0001921469,0.000050618517,0.000058080434,0.0005932768,0.000013263061,0.00019457487,0.00008193865,0.00041290227,0.000004830968],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000230812,0.0009954743,0.5730787,0.0000011972546,0.000055729823,0.000056119912,0.0135507565,0.014858557,0.000009326144,0.000027727705,0.39421397,0.0031293582],"study_design_scores_gemma":[0.00042883138,0.00010416373,0.28967994,0.0000033134872,0.000024030813,0.000108630935,0.16632727,0.00023372966,9.2239145e-7,0.00034093097,0.542675,0.000073196694],"about_ca_topic_score_codex":0.10591205,"about_ca_topic_score_gemma":0.035197694,"teacher_disagreement_score":0.28339875,"about_ca_system_score_codex":0.0007502671,"about_ca_system_score_gemma":0.0027734502,"threshold_uncertainty_score":0.9969521},"labels":[],"label_agreement":null},{"id":"W4385311561","doi":"10.1515/9780773572232-015","title":"Statistics, Social Relevance, Policy, and Analysis: Why They Are Bound Together","year":2004,"lang":"en","type":"book-chapter","venue":"McGill-Queen's University Press eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Relevance (law); Social statistics; Statistics; Sociology; Political science; Social science; Mathematics; Law","score_opus":0.06691377855937385,"score_gpt":0.3424819937572234,"score_spread":0.2755682151978495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385311561","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000047022528,0.0000038502635,0.0014654177,0.0007576288,0.00015852501,0.00038032667,0.0027509579,0.00008065248,0.9943556],"genre_scores_gemma":[0.012767448,0.00019522572,0.0006863822,0.00079740863,0.00018505567,0.0000016606517,0.000083771054,0.000042694206,0.98524034],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960608,0.00019732204,0.0005576901,0.0008998193,0.0019005134,0.00038387178],"domain_scores_gemma":[0.9968582,0.00047913636,0.0009207539,0.00070541597,0.0008128839,0.00022360198],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008460111,0.0004658235,0.0008385955,0.0010837708,0.00094185607,0.00026374363,0.0007642143,0.00043271546,0.0005772944],"category_scores_gemma":[0.0001421047,0.000435513,0.00032182186,0.0000914397,0.00037324516,0.0002631252,0.000490202,0.0004935243,0.00005596184],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008835511,0.000016825581,0.00009489389,0.000022165614,0.0005903269,0.000052020667,0.00046521853,0.00018394295,9.2498664e-7,0.9884249,0.0057522184,0.0043082377],"study_design_scores_gemma":[0.00071033364,0.000056331017,0.0007304926,0.000046590638,0.0007372405,9.510902e-7,0.00024636765,0.00012964252,0.000009242351,0.065106176,0.9317438,0.00048281532],"about_ca_topic_score_codex":0.001596622,"about_ca_topic_score_gemma":0.000080537735,"teacher_disagreement_score":0.9259916,"about_ca_system_score_codex":0.00052642694,"about_ca_system_score_gemma":0.00030017842,"threshold_uncertainty_score":0.9998097},"labels":[],"label_agreement":null},{"id":"W4385491133","doi":"10.7202/1102405ar","title":"A Short Report from the Core of Practice-Based Research","year":2023,"lang":"en","type":"article","venue":"Performance Matters","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Concordia University","funders":"","keywords":"Core (optical fiber); Reflection (computer programming); Computer science; Telecommunications; Programming language","score_opus":0.6453321051226547,"score_gpt":0.5998648716660211,"score_spread":0.045467233456633616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385491133","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9490577,0.000025669066,0.00017969165,0.04304508,0.00047540708,0.00029371108,0.00001606127,0.000048520586,0.0068581463],"genre_scores_gemma":[0.99453306,0.00004482707,0.00038665885,0.002974751,0.00011175896,0.00006505707,0.00004196532,0.000011352441,0.0018305838],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9943824,0.00027296718,0.0007524654,0.0003705181,0.0038818112,0.00033987302],"domain_scores_gemma":[0.9929869,0.0046567586,0.00023261967,0.0011521457,0.0009033606,0.000068168316],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.019093249,0.000105769424,0.00019506307,0.00030298176,0.00033381837,0.00014988332,0.00091137737,0.000048555725,0.0012532027],"category_scores_gemma":[0.0022023716,0.00006195666,0.00007930086,0.0021542443,0.0002584975,0.00049905834,0.00017410042,0.00029964992,0.001574193],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000116183546,0.000053787215,0.46362448,0.000010234021,0.000025870948,0.000029245964,0.0018899067,0.0041828174,0.00074391643,0.000060642356,0.4795421,0.049720816],"study_design_scores_gemma":[0.0002637395,0.000080180005,0.66223294,0.000055484055,0.000013453103,0.000011938253,0.003747979,0.07270225,0.0014940883,0.0004793408,0.25879526,0.00012335533],"about_ca_topic_score_codex":0.00013028583,"about_ca_topic_score_gemma":0.000030924708,"teacher_disagreement_score":0.22074685,"about_ca_system_score_codex":0.00005537264,"about_ca_system_score_gemma":0.00032064968,"threshold_uncertainty_score":0.9996598},"labels":[],"label_agreement":null},{"id":"W4385505415","doi":"10.59350/t5g2a-74804","title":"A bridge to access research: Reflections on the Community Scholars Program developmental evaluation","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Mitacs; Simon Fraser University","keywords":"Mindset; Bridge (graph theory); Research program; Sociology; Public relations; Alice (programming language); Political science; Library science; Management; Computer science; Medicine","score_opus":0.9439888335462863,"score_gpt":0.7442593168158681,"score_spread":0.19972951673041817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385505415","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79032266,0.00001605831,0.0006197547,0.017903872,0.0007766635,0.0034055873,0.000013673976,0.00008971472,0.18685201],"genre_scores_gemma":[0.98583835,0.000024732122,0.005111175,0.0032082538,0.00010410982,0.0029564467,0.00011999644,0.000017767352,0.002619181],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9776195,0.010870783,0.0009436721,0.0007730779,0.009352877,0.00044008018],"domain_scores_gemma":[0.9884953,0.0034989696,0.00023500223,0.0020138125,0.0055508288,0.00020606739],"candidate_categories":["metaresearch","sts","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.08656628,0.00024795145,0.000301157,0.0008592612,0.0025229433,0.006678333,0.003465297,0.00020980828,0.010047055],"category_scores_gemma":[0.017432652,0.00015242219,0.00015766564,0.0029911764,0.00014279856,0.00059096643,0.0047170906,0.0035269146,0.0013783064],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010551141,0.0018604184,0.008425246,0.000027773935,0.00016660822,0.000002817186,0.020592872,0.007876118,0.0003801205,0.0033300144,0.140629,0.8166035],"study_design_scores_gemma":[0.0005983918,0.000516169,0.77948636,0.0004343907,0.00004643782,0.000009510596,0.05173805,0.017111726,0.0026588705,0.03502324,0.11165305,0.00072380103],"about_ca_topic_score_codex":0.0010857686,"about_ca_topic_score_gemma":0.011180815,"teacher_disagreement_score":0.8158797,"about_ca_system_score_codex":0.0011805195,"about_ca_system_score_gemma":0.0048124464,"threshold_uncertainty_score":0.99939924},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"qualitative","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W4385722533","doi":"10.59962/9780774815710-008","title":"Public Policy in Ontario Higher Education: From Frost to Harris","year":2009,"lang":"en","type":"book-chapter","venue":"University of British Columbia Press eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Frost (temperature); Political science; Public administration; Geography; Meteorology","score_opus":0.14411155894228692,"score_gpt":0.322091110654464,"score_spread":0.17797955171217708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385722533","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008413694,0.00011409215,0.000012525,0.000496565,0.00041504973,0.0004878333,0.00041905005,0.000028098078,0.9896131],"genre_scores_gemma":[0.024121426,0.000033444587,0.00062699616,0.0007781902,0.00013591311,0.0000011944251,0.00008204641,0.000015162865,0.9742056],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.997054,0.000074270705,0.0005187146,0.0006872925,0.0014173309,0.00024842887],"domain_scores_gemma":[0.9977933,0.00013786486,0.00041813593,0.0007155516,0.0006661403,0.00026898293],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000500678,0.000157147,0.0005363771,0.00034961436,0.00015516825,0.00062959327,0.0011477,0.00031608858,0.022175733],"category_scores_gemma":[0.000047435075,0.00031656458,0.00017788527,0.000052011655,0.00014020079,0.00029109805,0.00031266693,0.00039676458,0.00016044751],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003425118,0.00010688478,0.0063966904,0.000007354354,0.000057579655,0.000051701052,0.0010109268,0.000011102876,0.000003884662,0.00836948,0.41283858,0.57111156],"study_design_scores_gemma":[0.0004358192,0.00005539312,0.16616087,0.00020557572,0.000020969743,0.0000026703428,0.000060024966,0.0000047144326,4.2422064e-7,0.021153804,0.81164694,0.0002527698],"about_ca_topic_score_codex":0.93154216,"about_ca_topic_score_gemma":0.9901616,"teacher_disagreement_score":0.5708588,"about_ca_system_score_codex":0.00068871456,"about_ca_system_score_gemma":0.0031511735,"threshold_uncertainty_score":0.99992865},"labels":[],"label_agreement":null},{"id":"W4385723228","doi":"10.1177/15586898231194525","title":"Media Review: Mixed Methods Research","year":2023,"lang":"en","type":"article","venue":"Journal of Mixed Methods Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Multimethodology; Sociology; Management science; Computer science; Social science; Engineering","score_opus":0.8688938090039084,"score_gpt":0.8028793892747539,"score_spread":0.06601441972915456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385723228","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0558758,0.107615784,0.5060129,0.1871796,0.023207502,0.004112021,0.00005288526,0.00019789138,0.1157456],"genre_scores_gemma":[0.0052626003,0.06303492,0.9140414,0.00043514167,0.0015362393,0.000094981115,0.000006964176,0.00006889387,0.015518871],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8194063,0.1448482,0.004703892,0.00106423,0.027767684,0.0022097004],"domain_scores_gemma":[0.837941,0.13814817,0.0010173055,0.001951494,0.019867174,0.0010748784],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.70490646,0.00023432804,0.0011882342,0.00540719,0.0007739518,0.0005132078,0.0035553186,0.0002407757,0.005043053],"category_scores_gemma":[0.28343758,0.00015144018,0.0005339086,0.015520358,0.0006211003,0.00080927485,0.0011744563,0.0035617976,0.0023940732],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006695046,0.000056031648,0.00016582722,0.00006994448,0.00003715336,0.00003868162,0.0005418013,0.000030622778,0.008428006,0.00060511,0.34974793,0.64021194],"study_design_scores_gemma":[0.0007421779,0.00053727214,0.016322074,0.0007069494,0.000025797543,0.00008633754,0.006707527,0.0026374757,0.021992745,0.08352752,0.86650586,0.0002082855],"about_ca_topic_score_codex":0.000019187013,"about_ca_topic_score_gemma":0.00002432675,"teacher_disagreement_score":0.6400037,"about_ca_system_score_codex":0.0003668575,"about_ca_system_score_gemma":0.0025394047,"threshold_uncertainty_score":0.99873704},"labels":[],"label_agreement":null},{"id":"W4385785105","doi":"10.1007/978-3-031-30889-5_10","title":"Using Monitoring and Evaluation and Evidence-Based Data to Build a More Resilient and Sustainable Caribbean Post-COVID-19","year":2023,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Sustainable development; Coronavirus disease 2019 (COVID-19); Political science; Business; Environmental planning; Economic growth; Geography; Economics","score_opus":0.5908247312230585,"score_gpt":0.5594704924496586,"score_spread":0.03135423877339982,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385785105","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7174262,0.026937451,0.015485063,0.12568614,0.0038215555,0.021955112,0.0008668125,0.0008140562,0.08700763],"genre_scores_gemma":[0.49158716,0.0017401539,0.014368823,0.0049198726,0.0007777864,0.0001269376,0.00023188654,0.00017042899,0.48607695],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99434763,0.00017735973,0.00070619106,0.001309135,0.0031060572,0.0003536198],"domain_scores_gemma":[0.99481696,0.0017954393,0.00031176678,0.0012920985,0.0013157474,0.00046801654],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.015435886,0.00031969242,0.00041234476,0.00087820675,0.00054361834,0.00088683394,0.0005349151,0.00019322499,0.00038717245],"category_scores_gemma":[0.006084489,0.00025308854,0.00003502047,0.00025436035,0.00013664858,0.0010096258,0.0012683944,0.00021751142,0.000034380595],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025883603,0.00017865778,0.18870308,0.00437484,0.0007228712,0.0004736661,0.022653867,0.076349236,0.0039003044,0.14338885,0.06523269,0.4914336],"study_design_scores_gemma":[0.0036292274,0.001112976,0.05160801,0.0030209483,0.0010539471,0.000066279004,0.0318587,0.6964614,0.00023103866,0.04774882,0.1605662,0.0026424828],"about_ca_topic_score_codex":0.0010994698,"about_ca_topic_score_gemma":0.0003437333,"teacher_disagreement_score":0.6201121,"about_ca_system_score_codex":0.0003549303,"about_ca_system_score_gemma":0.0019815546,"threshold_uncertainty_score":0.99999213},"labels":[],"label_agreement":null},{"id":"W4385839249","doi":"10.4102/aej.v11i1.654","title":"Etat des systèmes de suivi et d’évaluation en Afrique francophone : une approximation au moyen d’un diagnostic rapide","year":2023,"lang":"fr","type":"article","venue":"African Evaluation Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Global Affairs Canada; École Nationale d'Administration Publique","funders":"","keywords":"French; Institutionalisation; Context (archaeology); Valuation (finance); Political science; Humanities; Welfare economics; Business; Geography; Accounting; Economics; Philosophy","score_opus":0.11246508197300573,"score_gpt":0.4336464619317929,"score_spread":0.32118137995878715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385839249","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79562277,0.0029600817,0.10667753,0.07856525,0.0050379145,0.0017035777,0.000052189273,0.00015106179,0.009229615],"genre_scores_gemma":[0.983843,0.003490058,0.006938978,0.0005847692,0.0013687924,0.0003306009,0.000133423,0.00006814153,0.0032422368],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97433233,0.013881436,0.0023751063,0.00078720273,0.0071357116,0.001488182],"domain_scores_gemma":[0.9825593,0.011102783,0.0015909423,0.00067951664,0.0033293783,0.0007380784],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.12883073,0.00052286196,0.0006852307,0.0014583461,0.0015052466,0.001097483,0.0008604747,0.0003987149,0.00947466],"category_scores_gemma":[0.038313977,0.00047791572,0.0003926551,0.0058145463,0.0004062292,0.0026270458,0.00016161041,0.0010551215,0.003196668],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007813014,0.00019644503,0.011489528,0.00007443845,0.00017442269,0.000033509245,0.113247216,0.15913342,0.0011108399,0.001469265,0.008925847,0.70406693],"study_design_scores_gemma":[0.0020155425,0.0003295915,0.3817849,0.0003831698,0.0002600368,0.00027031003,0.02381332,0.430263,0.00042857326,0.15614597,0.0038925246,0.00041306586],"about_ca_topic_score_codex":0.00046404757,"about_ca_topic_score_gemma":0.0009570286,"teacher_disagreement_score":0.7036539,"about_ca_system_score_codex":0.003127677,"about_ca_system_score_gemma":0.011930975,"threshold_uncertainty_score":0.9999395},"labels":[],"label_agreement":null},{"id":"W4385854848","doi":"10.59962/9780774818735-007","title":"Monitoring Programs in French Canada","year":2011,"lang":"en","type":"book-chapter","venue":"University of British Columbia Press eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.15680341001311343,"score_gpt":0.29360622016036897,"score_spread":0.13680281014725554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385854848","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016807469,0.0001763283,0.00001752286,0.0000062457193,0.00043246077,0.00039957496,0.00011607181,0.000020351008,0.98202395],"genre_scores_gemma":[0.12847774,0.00010781001,0.00022555768,0.0000096030835,0.000036378082,7.3401117e-7,0.0000074792774,0.000012590014,0.8711221],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973647,0.000051738563,0.00042818085,0.00046267654,0.0014715315,0.00022119112],"domain_scores_gemma":[0.99838734,0.000100623096,0.00042968444,0.00045380855,0.00050568744,0.00012283932],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00062294566,0.00011597592,0.0004243463,0.00008370927,0.00011177992,0.00017084317,0.00088383135,0.0002044715,0.0015903194],"category_scores_gemma":[0.000027186798,0.00023622173,0.00010863033,0.000021688313,0.00016558895,0.00012721385,0.00026454264,0.00030501615,0.000009762744],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012609626,0.000037654787,0.024426768,0.0000448748,0.00006484285,0.00039881395,0.00080631016,0.000009602603,0.0000014156384,0.00060537935,0.04431546,0.9292763],"study_design_scores_gemma":[0.00068366865,0.00008003214,0.04873075,0.00081774,0.00004154179,0.000013889339,0.0003451879,0.000053499763,0.0000032066766,0.00554876,0.94327414,0.00040760566],"about_ca_topic_score_codex":0.9893915,"about_ca_topic_score_gemma":0.998618,"teacher_disagreement_score":0.92886865,"about_ca_system_score_codex":0.00021734071,"about_ca_system_score_gemma":0.0010632863,"threshold_uncertainty_score":0.99932235},"labels":[],"label_agreement":null},{"id":"W4385957643","doi":"10.1051/shsconf/202317501030","title":"Les attitudes des enseignants des ISPITS du Maroc envers l’évaluation formative : cas des enseignants intervenants au sein de l’option santé et environnement","year":2023,"lang":"fr","type":"article","venue":"SHS Web of Conferences","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Valuation (finance); Formative assessment; Humanities; Sociology; Art; Business; Pedagogy","score_opus":0.40154016465249387,"score_gpt":0.47000564203413886,"score_spread":0.06846547738164499,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385957643","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9652987,0.0015153576,0.0075366586,0.0005615418,0.00085076113,0.0006296622,0.00023482856,0.00008322205,0.023289258],"genre_scores_gemma":[0.9842658,0.010392012,0.001942909,0.000106543,0.00011731396,0.00009675147,0.00008659401,0.000028052866,0.002964033],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9926267,0.0017947224,0.0016373439,0.0007157622,0.0021990186,0.0010264],"domain_scores_gemma":[0.9957422,0.0015185227,0.0009841246,0.0004653941,0.0009993551,0.000290385],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010669767,0.000545688,0.0007323256,0.000785306,0.0011033992,0.00042649917,0.0008415203,0.00029251043,0.0046648295],"category_scores_gemma":[0.0015236366,0.0004494667,0.00027716154,0.0011221068,0.0021597838,0.0020646239,0.00034258005,0.00030556103,0.00074246514],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012946753,0.00031111442,0.3126509,0.00038812283,0.00016933471,0.000013008306,0.054707136,0.0016904875,0.0017306616,0.011206624,0.00036609214,0.61663705],"study_design_scores_gemma":[0.0013119291,0.0010527291,0.83592075,0.0022355807,0.0001385957,0.000021469805,0.05065102,0.064396985,0.007547862,0.028472787,0.0077146753,0.0005356391],"about_ca_topic_score_codex":0.0067775752,"about_ca_topic_score_gemma":0.019570773,"teacher_disagreement_score":0.61610144,"about_ca_system_score_codex":0.00069796375,"about_ca_system_score_gemma":0.010568386,"threshold_uncertainty_score":0.9998364},"labels":[],"label_agreement":null},{"id":"W4385957920","doi":"10.1051/e3sconf/202341201043","title":"The role of formative evaluation in the teaching/learning process at ISPITS in Morocco: Exploratory study of teachers involved in the health environment option","year":2023,"lang":"en","type":"article","venue":"E3S Web of Conferences","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Formative assessment; Operationalization; Curriculum; Exploratory research; Workload; Process (computing); Medical education; Psychology; Mathematics education; Pedagogy; Medicine; Sociology; Computer science; Social science","score_opus":0.20555985651256214,"score_gpt":0.471744517388907,"score_spread":0.26618466087634485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385957920","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99587184,0.00019160318,0.000012197798,0.0010359912,0.00004304475,0.0010791151,0.0000017795244,0.0000042455636,0.0017602036],"genre_scores_gemma":[0.99952775,0.00014769894,0.0000063812463,0.00003777357,0.0000078452995,0.00024373858,0.0000070569736,0.0000029279684,0.000018845085],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9917138,0.0040395968,0.0011044457,0.00021361093,0.0027423876,0.0001861498],"domain_scores_gemma":[0.99719846,0.0015283547,0.00082908466,0.00029252318,0.00013461093,0.000016936667],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03668898,0.00010435195,0.00025473768,0.00030836323,0.00017685958,0.00004769238,0.0007286582,0.000035514855,0.000058134967],"category_scores_gemma":[0.0008232235,0.00005048966,0.000033662,0.0007107732,0.000114355,0.00036129713,0.00007469564,0.00029539844,0.000010276008],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004902467,0.00027444828,0.5341316,0.0000089669165,0.0000073094498,1.1801513e-7,0.3980885,0.020823866,0.00008183457,0.00082431675,0.000040201045,0.045669816],"study_design_scores_gemma":[0.0005041636,0.0004003142,0.39076474,0.000037729587,0.0000036194053,6.716522e-8,0.5317237,0.07345415,0.00008047605,0.002672224,0.00032177547,0.00003701844],"about_ca_topic_score_codex":0.00024812188,"about_ca_topic_score_gemma":0.0071838354,"teacher_disagreement_score":0.14336681,"about_ca_system_score_codex":0.00008760877,"about_ca_system_score_gemma":0.0007763423,"threshold_uncertainty_score":0.99193144},"labels":[],"label_agreement":null},{"id":"W4386024436","doi":"10.1016/j.evalprogplan.2023.102364","title":"The extent to which the recommendations issued after the periodic evaluation of university programs are targeted, specific, measurable and unequivocal: An exploratory analysis","year":2023,"lang":"en","type":"article","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Relevance (law); Best practice; Quality (philosophy); Exploratory analysis; Process (computing); Exploratory research; Root (linguistics); Point (geometry); Action (physics); Public relations; Process management; Psychology; Medical education; Management science; Computer science; Business; Political science; Medicine; Data science; Engineering; Sociology; Mathematics","score_opus":0.3555251994563828,"score_gpt":0.5018668231322345,"score_spread":0.14634162367585174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386024436","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9774582,0.0020016748,0.0005985542,0.016678825,0.00026272822,0.0024240827,0.000014499892,0.000075633645,0.00048583376],"genre_scores_gemma":[0.99858946,0.0002162512,0.00034327275,0.00012529723,0.000047205864,0.00037047415,0.000088869754,0.000007962579,0.00021123543],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9922785,0.0034407745,0.0005135984,0.00044504082,0.0030645707,0.00025748552],"domain_scores_gemma":[0.99567485,0.00086826936,0.0003554269,0.0006077704,0.0023763462,0.000117334566],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.048254203,0.00014779874,0.00020205804,0.00032131225,0.0013955545,0.0007154885,0.0003890843,0.0000554484,0.00036123896],"category_scores_gemma":[0.0010341855,0.00007743553,0.00007176426,0.00396541,0.00015617468,0.00046856038,0.00012214606,0.00016486911,0.000036251487],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018357568,0.00007264409,0.058089424,0.0000040393197,0.00014987789,4.5418037e-7,0.020870447,0.015720483,0.000029585426,0.00014425405,0.0030313754,0.90170383],"study_design_scores_gemma":[0.00046055941,0.00016608705,0.39277992,0.000030283498,0.00039219408,0.0000011048613,0.074430175,0.4509239,0.000013478205,0.0007130186,0.07996183,0.00012746453],"about_ca_topic_score_codex":0.000021519334,"about_ca_topic_score_gemma":0.0008145987,"teacher_disagreement_score":0.9015764,"about_ca_system_score_codex":0.000077220764,"about_ca_system_score_gemma":0.00024329264,"threshold_uncertainty_score":0.9999045},"labels":[],"label_agreement":null},{"id":"W4386055062","doi":"10.1522/rhe.v7i2.1536","title":"Les stages au baccalauréat d’éducation préscolaire et d’enseignement primaire","year":2023,"lang":"fr","type":"article","venue":"Revue hybride de l éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Political science; Humanities; Philosophy","score_opus":0.32212481831058654,"score_gpt":0.5081048671931511,"score_spread":0.18598004888256453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386055062","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85997,0.0010118579,0.0029306333,0.10526509,0.008708619,0.0010348796,0.0000711593,0.00020963943,0.020798156],"genre_scores_gemma":[0.89692,0.0011947082,0.0014283558,0.0012126275,0.0008616697,0.0002728079,0.00040993566,0.000050975264,0.09764892],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99459946,0.0011614786,0.0011900631,0.00085650856,0.0014229913,0.0007695233],"domain_scores_gemma":[0.99621284,0.0010261656,0.0006683465,0.0009854351,0.0008054215,0.00030180492],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.009318023,0.00036058808,0.00040127375,0.00063897594,0.0007019535,0.0005891932,0.0006090195,0.00020682806,0.0038806256],"category_scores_gemma":[0.00206942,0.00037725558,0.00021320031,0.0018425729,0.00013887261,0.0012455327,0.00015895748,0.00040221293,0.0064635077],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00004082507,0.00064384786,0.06701179,0.0006402904,0.00008129574,0.00001952521,0.09881654,0.005680551,0.0009728001,0.027471155,0.30341753,0.49520385],"study_design_scores_gemma":[0.0005468144,0.00018667853,0.5989925,0.0006626475,0.0001057229,0.00006557833,0.02947414,0.02729635,0.0009963562,0.006260942,0.33487314,0.00053909],"about_ca_topic_score_codex":0.0016612585,"about_ca_topic_score_gemma":0.0038258852,"teacher_disagreement_score":0.53198075,"about_ca_system_score_codex":0.0048769168,"about_ca_system_score_gemma":0.006428041,"threshold_uncertainty_score":0.9998679},"labels":[],"label_agreement":null},{"id":"W4386055109","doi":"10.1522/rhe.v7i2.1305","title":"Les politiques institutionnelles d’évaluation des apprentissages : moteur ou frein à la qualité de l’évaluation au collégial?","year":2023,"lang":"fr","type":"article","venue":"Revue hybride de l éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Université du Québec à Montréal","funders":"","keywords":"Political science; Humanities; Art","score_opus":0.4643532329098856,"score_gpt":0.5207582518378947,"score_spread":0.05640501892800909,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386055109","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93360907,0.0011327305,0.036053855,0.011633271,0.002625669,0.00076203485,0.00008189551,0.00023685042,0.01386462],"genre_scores_gemma":[0.9436877,0.003448536,0.005477579,0.00020663183,0.0011479792,0.00026349467,0.00044314816,0.000046977,0.045277994],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99145925,0.004004234,0.0013871352,0.0007833626,0.0015167097,0.00084928516],"domain_scores_gemma":[0.99463737,0.0024682288,0.0006751451,0.0007235441,0.0011958302,0.00029987414],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.02238605,0.00038309096,0.00043354768,0.00087756175,0.0010471005,0.0007432251,0.0005697504,0.00033758732,0.0012036148],"category_scores_gemma":[0.008785314,0.00041934266,0.0002468183,0.0020371124,0.00042113225,0.0014646207,0.00012330967,0.00037068778,0.0016123645],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003913335,0.00029811758,0.053383857,0.00041996894,0.00006763144,0.000011976862,0.07924922,0.032351863,0.0015841168,0.043077327,0.00985117,0.77966565],"study_design_scores_gemma":[0.0007606524,0.00013557392,0.59812236,0.0008736913,0.00020231395,0.00013335928,0.023646245,0.20075695,0.0030401312,0.10692298,0.06483906,0.0005666823],"about_ca_topic_score_codex":0.0069972193,"about_ca_topic_score_gemma":0.0033060235,"teacher_disagreement_score":0.7790989,"about_ca_system_score_codex":0.0035253405,"about_ca_system_score_gemma":0.0056768963,"threshold_uncertainty_score":0.99996},"labels":[],"label_agreement":null},{"id":"W4386095343","doi":"10.1002/jls.21860","title":"Editor’s Notes","year":2023,"lang":"en","type":"article","venue":"Journal of Leadership Studies","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Luck; Theme (computing); Associate editor; Aside; Editor in chief; Editorial board; Operations research; Library science; Psychology; Management; Public relations; Media studies; Sociology; Political science; Computer science; World Wide Web; Engineering; Epistemology; Philosophy","score_opus":0.7645243052744733,"score_gpt":0.5909344290331774,"score_spread":0.17358987624129596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386095343","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5188866,0.007904247,0.0006959995,0.42081738,0.047703255,0.00019814618,0.0000044719145,0.000092890776,0.003696995],"genre_scores_gemma":[0.98939806,0.0005642568,0.0003011199,0.0009961198,0.005558622,0.0000018972061,2.1343325e-7,0.0000057531065,0.0031739813],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968061,0.00015636008,0.0007078667,0.000106683445,0.0020351014,0.00018793027],"domain_scores_gemma":[0.99504864,0.0030581595,0.0004903124,0.00015635794,0.0011837505,0.000062755316],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007495453,0.000081396436,0.00029526226,0.00044134897,0.00013385717,0.00008558281,0.00036661708,0.000032556625,0.00018995965],"category_scores_gemma":[0.008297707,0.000047641257,0.00014302597,0.00086059206,0.000104899096,0.00041203023,0.00005761,0.00017145199,0.0009056358],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002634786,0.000020477271,0.03498166,0.000012378595,0.000108022046,0.000015656922,0.008695369,0.00052195514,0.0001543169,0.00015974978,0.92543155,0.029872512],"study_design_scores_gemma":[0.0011622029,0.00060329586,0.20407395,0.00015240708,0.000068134665,0.000039861854,0.3748239,0.000568739,0.0011506359,0.018662967,0.39842716,0.00026673806],"about_ca_topic_score_codex":5.664897e-7,"about_ca_topic_score_gemma":0.000015370464,"teacher_disagreement_score":0.52700436,"about_ca_system_score_codex":0.000041970394,"about_ca_system_score_gemma":0.00011973957,"threshold_uncertainty_score":0.99987227},"labels":[],"label_agreement":null},{"id":"W4386161259","doi":"10.32920/23900202.v1","title":"Assessing the ‘forgotten fundamental’ in policy advisory systems research: Policy shops and the role(s) of core policy professionals","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Simon Fraser University; Toronto Metropolitan University","funders":"","keywords":"Government (linguistics); Work (physics); Public policy; Distribution (mathematics); Public relations; Core (optical fiber); Political science; Advice (programming); Business; Engineering; Computer science; Law","score_opus":0.6512064772978872,"score_gpt":0.650407059807897,"score_spread":0.0007994174899901285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386161259","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.638761,0.0020326776,0.00015519187,0.22446506,0.0012940293,0.0060428367,0.00018270354,0.00012608034,0.12694044],"genre_scores_gemma":[0.98000896,0.00053573726,0.00008373504,0.0012070369,0.0010461222,0.00043867066,0.000027131478,0.0000412178,0.016611386],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9858383,0.0043407525,0.002133518,0.0009357754,0.005932963,0.0008186974],"domain_scores_gemma":[0.9857161,0.00982052,0.0010515164,0.0019270274,0.0012948985,0.00018994269],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.048558068,0.00038757687,0.00090223143,0.0033193529,0.0006792598,0.0016830142,0.002595108,0.00036852033,0.00025603542],"category_scores_gemma":[0.0116485385,0.0001772286,0.00022544885,0.0042912075,0.0013127488,0.0005160865,0.0045250608,0.0016758639,0.00018103693],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022250896,0.0003007135,0.11255803,0.0003280848,0.00017837834,0.0000053330978,0.024777684,0.0064609717,0.00029135885,0.77303565,0.013088259,0.068753004],"study_design_scores_gemma":[0.0018041064,0.00007292451,0.26506624,0.0011844333,0.000022480428,0.0000154937,0.17963247,0.09005717,0.00007191675,0.45051008,0.011122177,0.00044051424],"about_ca_topic_score_codex":0.031204892,"about_ca_topic_score_gemma":0.0013200237,"teacher_disagreement_score":0.34124798,"about_ca_system_score_codex":0.0006413863,"about_ca_system_score_gemma":0.009168218,"threshold_uncertainty_score":0.99935335},"labels":[],"label_agreement":null},{"id":"W4386169044","doi":"10.32920/23900202","title":"Assessing the ‘forgotten fundamental’ in policy advisory systems research: Policy shops and the role(s) of core policy professionals","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Simon Fraser University; Toronto Metropolitan University","funders":"","keywords":"Government (linguistics); Distribution (mathematics); Public policy; Work (physics); Advice (programming); Core (optical fiber); Political science; Public relations; Business; Engineering; Law; Computer science","score_opus":0.6512064772978872,"score_gpt":0.650407059807897,"score_spread":0.0007994174899901285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386169044","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.638761,0.0020326776,0.00015519187,0.22446506,0.0012940293,0.0060428367,0.00018270354,0.00012608034,0.12694044],"genre_scores_gemma":[0.98000896,0.00053573726,0.00008373504,0.0012070369,0.0010461222,0.00043867066,0.000027131478,0.0000412178,0.016611386],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9858383,0.0043407525,0.002133518,0.0009357754,0.005932963,0.0008186974],"domain_scores_gemma":[0.9857161,0.00982052,0.0010515164,0.0019270274,0.0012948985,0.00018994269],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.048558068,0.00038757687,0.00090223143,0.0033193529,0.0006792598,0.0016830142,0.002595108,0.00036852033,0.00025603542],"category_scores_gemma":[0.0116485385,0.0001772286,0.00022544885,0.0042912075,0.0013127488,0.0005160865,0.0045250608,0.0016758639,0.00018103693],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022250896,0.0003007135,0.11255803,0.0003280848,0.00017837834,0.0000053330978,0.024777684,0.0064609717,0.00029135885,0.77303565,0.013088259,0.068753004],"study_design_scores_gemma":[0.0018041064,0.00007292451,0.26506624,0.0011844333,0.000022480428,0.0000154937,0.17963247,0.09005717,0.00007191675,0.45051008,0.011122177,0.00044051424],"about_ca_topic_score_codex":0.031204892,"about_ca_topic_score_gemma":0.0013200237,"teacher_disagreement_score":0.34124798,"about_ca_system_score_codex":0.0006413863,"about_ca_system_score_gemma":0.009168218,"threshold_uncertainty_score":0.99935335},"labels":[],"label_agreement":null},{"id":"W4386193217","doi":"10.1007/s42330-023-00288-9","title":"Integrating Theory and Practice","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Science Mathematics and Technology Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Institute for Christian Studies; University of Toronto","funders":"","keywords":"Psychology; Computer science","score_opus":0.10177235681336834,"score_gpt":0.4819653292278249,"score_spread":0.3801929724144566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386193217","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9635469,0.00033128046,0.0017031898,0.025266087,0.0005579015,0.00008405067,8.382392e-7,0.000010030224,0.0084997555],"genre_scores_gemma":[0.9835458,0.000054502114,0.015802478,0.00019786374,0.000024666095,0.0000023535652,1.4316957e-7,0.0000024944432,0.0003696888],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989635,0.000039557635,0.00033918503,0.000111828216,0.00040298744,0.00014297667],"domain_scores_gemma":[0.99735963,0.0008678139,0.00033543925,0.00015134417,0.0011004952,0.00018525017],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.015471059,0.000047665682,0.0001004083,0.001930225,0.00038750007,0.00026546474,0.00033909772,0.000040491675,0.000050765346],"category_scores_gemma":[0.025289562,0.00003278407,0.000010052597,0.0023517085,0.000966865,0.00061301375,0.000028312894,0.00012529135,0.000020608843],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010990753,0.000011393519,0.003021664,0.0000044388053,0.0000031402847,0.000002023021,0.005288481,0.0000024785827,0.0008926615,0.76446396,0.0010853711,0.22522327],"study_design_scores_gemma":[0.00006942806,0.00007455296,0.0033539452,0.00005970815,0.000011390619,0.0005033371,0.15724045,0.0017678112,0.00028471317,0.8257229,0.010847497,0.0000642721],"about_ca_topic_score_codex":0.00003215118,"about_ca_topic_score_gemma":0.00025101582,"teacher_disagreement_score":0.225159,"about_ca_system_score_codex":0.000049185957,"about_ca_system_score_gemma":0.0037712653,"threshold_uncertainty_score":0.9829208},"labels":[],"label_agreement":null},{"id":"W4386217831","doi":"10.3102/2008477","title":"A Critical Policy Analysis of the Equity and Inclusive Education Strategy: A Case Study of Ontario, Canada","year":2023,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Equity (law); Public economics; Political science; Public administration; Computer science; Regional science; Economics; Sociology","score_opus":0.2155714807899912,"score_gpt":0.5800169623144888,"score_spread":0.3644454815244976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386217831","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9879715,0.0000031030381,0.000010799283,0.0023465108,0.000069309004,0.00015124772,0.000009630674,0.0000026278603,0.009435281],"genre_scores_gemma":[0.9979354,5.015694e-7,0.000017485152,0.00024544014,0.00000904908,0.000007947528,0.0000012253539,0.0000011224902,0.0017818324],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99800885,0.00015414257,0.00040551226,0.00014726444,0.0011989828,0.000085245985],"domain_scores_gemma":[0.9984033,0.00056858314,0.00011555185,0.00031549597,0.0005436108,0.000053467422],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017240476,0.00004761383,0.00017227695,0.0003217288,0.00012548905,0.00004435183,0.00020687812,0.000015486035,0.00088520616],"category_scores_gemma":[0.00091388146,0.000026785705,0.000035777713,0.002859913,0.000047716723,0.00010646035,0.00037694743,0.000049422575,0.0000011104191],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001243254,0.00048662882,0.9088741,0.000008961607,0.00023617425,0.000016191329,0.027073277,0.0035723564,0.000053338026,0.010639799,0.0057962784,0.043230496],"study_design_scores_gemma":[0.00013707276,0.000088754336,0.8822445,0.0000022463757,0.00015847114,0.000008161301,0.105255865,0.008905885,0.000029751727,0.002875792,0.000251768,0.000041699794],"about_ca_topic_score_codex":0.9947175,"about_ca_topic_score_gemma":0.9997355,"teacher_disagreement_score":0.078182586,"about_ca_system_score_codex":0.00021612218,"about_ca_system_score_gemma":0.011089114,"threshold_uncertainty_score":0.9945171},"labels":[],"label_agreement":null},{"id":"W4386218974","doi":"10.3102/2005747","title":"Individualized Classroom Assessment Scoring System (inCLASS) Factorial Validity: What It Entails for Research Conducted in Quebec on Child Engagement","year":2023,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Factorial; Computer science; Factorial analysis; Psychology; Mathematics education; Mathematics; Statistics","score_opus":0.715560859422791,"score_gpt":0.6130036206391462,"score_spread":0.10255723878364487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386218974","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91971993,0.000025998857,0.0037101796,0.01736355,0.010244112,0.005208828,0.00008208229,0.00041031057,0.04323502],"genre_scores_gemma":[0.9887881,0.000105846826,0.00070216594,0.00034322546,0.000581609,0.0008515907,0.00014679777,0.000031990494,0.008448618],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9868166,0.0028449139,0.0015524384,0.0010904856,0.0067377384,0.0009578555],"domain_scores_gemma":[0.99032354,0.0073048547,0.00031542446,0.0009621304,0.00086305244,0.00023098632],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.046768602,0.00030047956,0.0005966896,0.0019234206,0.0008408621,0.0026316817,0.00110329,0.00019383238,0.0016797261],"category_scores_gemma":[0.0019568664,0.00022404768,0.00018838218,0.002816247,0.00008586886,0.0017527601,0.00048864173,0.0007624617,0.0012434083],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013922459,0.0017128442,0.106931634,0.0005115458,0.00042400838,0.000073690135,0.023601145,0.0059268083,0.0059797973,0.29569545,0.36240304,0.19534777],"study_design_scores_gemma":[0.01256695,0.0013441851,0.09530821,0.0012349094,0.000042568336,0.000002749596,0.2123512,0.06523353,0.0054605566,0.006166542,0.59928226,0.0010063333],"about_ca_topic_score_codex":0.0012407089,"about_ca_topic_score_gemma":0.009125786,"teacher_disagreement_score":0.28952894,"about_ca_system_score_codex":0.0015172452,"about_ca_system_score_gemma":0.0010229276,"threshold_uncertainty_score":0.99953425},"labels":[],"label_agreement":null},{"id":"W4386237748","doi":"10.3102/2003530","title":"Educational Leadership Practices in Student Success Policy Making in the Government of Ontario","year":2023,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Educational leadership; Public relations; Computer science; Political science; Business; Sociology; Pedagogy","score_opus":0.5950445807908612,"score_gpt":0.6119812701875255,"score_spread":0.016936689396664262,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386237748","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8574412,0.0000097951615,0.000009459318,0.048112705,0.000113078546,0.0001723037,9.999451e-7,0.0000035417665,0.09413691],"genre_scores_gemma":[0.9879204,0.0000062081635,0.00011117955,0.0012763867,0.00004651739,0.00003502647,0.0000013417715,0.0000020375203,0.010600904],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9956234,0.0002489674,0.00049857615,0.00018706892,0.003281868,0.00016012735],"domain_scores_gemma":[0.99752605,0.0017677827,0.0003602038,0.00026286565,0.000066745815,0.000016331669],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008113305,0.000059341302,0.000105684085,0.00024125924,0.00004159039,0.00012826711,0.0006368128,0.000023306107,0.0024046786],"category_scores_gemma":[0.0012553016,0.0000347541,0.000029397874,0.0013983076,0.000028611039,0.0003879857,0.000078914134,0.00012248955,0.00012500728],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010689386,0.00013120366,0.9553052,0.0000030967224,0.0000024214012,7.484512e-7,0.022997145,0.0008395063,0.000013666357,0.015670067,0.0011400094,0.0038862221],"study_design_scores_gemma":[0.00019374995,0.000021219537,0.9462193,0.000016452996,0.0000014278212,7.357917e-7,0.043983452,0.00071711605,0.000019880277,0.003125164,0.0056601255,0.000041381],"about_ca_topic_score_codex":0.0076037436,"about_ca_topic_score_gemma":0.2653979,"teacher_disagreement_score":0.25779414,"about_ca_system_score_codex":0.00046498651,"about_ca_system_score_gemma":0.0012727402,"threshold_uncertainty_score":0.9990047},"labels":[],"label_agreement":null},{"id":"W4386244299","doi":"10.7202/1105562ar","title":"Élaboration et validation d’une échelle de mesure de la professionnalisation des étudiants et des étudiantes universitaires en sciences de la santé","year":2023,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université Laval; Université de Montréal; Université de Sherbrooke","funders":"","keywords":"Humanities; Political science; Art","score_opus":0.17198827260133503,"score_gpt":0.5493514144413283,"score_spread":0.37736314183999325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386244299","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89856887,0.000622252,0.05803052,0.03548628,0.0008440257,0.0007391769,0.00006005454,0.00019095316,0.0054578874],"genre_scores_gemma":[0.97570467,0.004260141,0.017231805,0.00044114253,0.0002321611,0.0001240149,0.000423139,0.00004023876,0.001542702],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9370427,0.058184557,0.0009795937,0.0008035729,0.0023077363,0.00068184646],"domain_scores_gemma":[0.9837301,0.013561281,0.00074384606,0.00042049118,0.0013471054,0.00019719967],"candidate_categories":["metaresearch","metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.18618488,0.00039083496,0.00035511047,0.0009716132,0.001457053,0.0009876286,0.0005586533,0.0005336772,0.0010792544],"category_scores_gemma":[0.018807655,0.0003785386,0.00014742756,0.004887366,0.0008035768,0.0049279667,0.00012927034,0.00054440304,0.00036518287],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000069396265,0.00050071074,0.41734084,0.00016847327,0.000085317166,0.0000059990234,0.39283082,0.075565,0.008898624,0.02432607,0.01888539,0.061323356],"study_design_scores_gemma":[0.00071200065,0.00013819714,0.7601869,0.00041956917,0.00013456026,0.0000218812,0.055572364,0.07947408,0.0029502707,0.098797634,0.0012572383,0.00033528998],"about_ca_topic_score_codex":0.0004916812,"about_ca_topic_score_gemma":0.0014742925,"teacher_disagreement_score":0.34284607,"about_ca_system_score_codex":0.0017096741,"about_ca_system_score_gemma":0.0108116465,"threshold_uncertainty_score":0.99986666},"labels":[],"label_agreement":null},{"id":"W4386692566","doi":"10.5195/aa.2023.472","title":"Realizing Possibilities: A Conversation with Akaninyene A. Otu","year":2023,"lang":"en","type":"article","venue":"Anthropology & Aging","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Conversation; Psychology; Communication; Cognitive science","score_opus":0.19305098553946556,"score_gpt":0.516815494953348,"score_spread":0.32376450941388246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386692566","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9589722,0.00004727284,0.0074375113,0.020133046,0.0006093193,0.00017673195,0.00000708316,0.0002289989,0.012387815],"genre_scores_gemma":[0.9957173,0.00005822925,0.00046688272,0.0008778859,0.000091622576,0.000014986091,0.000022745131,0.000010583927,0.0027397769],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9978929,0.00020639304,0.00039709322,0.00040678584,0.0007794688,0.0003173379],"domain_scores_gemma":[0.99834627,0.0007409965,0.00017886872,0.00042207615,0.00024898487,0.00006282284],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0027498517,0.000112463764,0.0002040553,0.00035028704,0.00037015055,0.00011044143,0.00027011638,0.00005681447,0.0036274535],"category_scores_gemma":[0.0003381151,0.000078728204,0.000043346903,0.0010598411,0.0004716694,0.0004319938,0.00008153713,0.0001191845,0.0010815609],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014453949,0.00010347986,0.7039617,0.00003542433,0.00014363945,0.00012048621,0.08302457,0.0028237745,0.0024450107,0.0562612,0.044245638,0.106690556],"study_design_scores_gemma":[0.0029961262,0.00093422463,0.37221384,0.00014056214,0.00007593103,0.000116056864,0.39581358,0.12014844,0.005399829,0.04251592,0.058790606,0.0008548675],"about_ca_topic_score_codex":0.0005993424,"about_ca_topic_score_gemma":0.0004096131,"teacher_disagreement_score":0.33174783,"about_ca_system_score_codex":0.000059545328,"about_ca_system_score_gemma":0.00019624493,"threshold_uncertainty_score":0.9996962},"labels":[],"label_agreement":null},{"id":"W4386813275","doi":"10.56645/jmde.v19i45.739","title":"We Can’t Hear You – You’re on Mute: Findings From a Review of Evaluation Capacity Building (ECB) Practice Online","year":2023,"lang":"en","type":"review","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of Ottawa","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Context (archaeology); Capacity building; Intervention (counseling); Descriptive statistics; Data collection; Medical education; Modalities; Computer science; The Internet; Coronavirus disease 2019 (COVID-19); Work (physics); Psychology; Sociology; Political science; Medicine; World Wide Web; Engineering; Social science; Statistics","score_opus":0.6006527710065875,"score_gpt":0.6003414472637132,"score_spread":0.0003113237428743476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386813275","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0041351994,0.9792918,0.00021963807,0.009008336,0.0029019935,0.003608176,0.000547696,0.000026679847,0.00026049936],"genre_scores_gemma":[0.00041065563,0.9918234,0.0056611355,0.00020913917,0.0009359212,0.00013268762,0.00053628744,0.00008088018,0.00020992832],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9672694,0.00806033,0.006882126,0.0010016978,0.01634272,0.00044368557],"domain_scores_gemma":[0.9692913,0.0085964175,0.011712356,0.0013367567,0.008774157,0.00028900878],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.091738194,0.0007417793,0.0033150262,0.001782122,0.0003618844,0.00019654538,0.0013035808,0.0004938079,0.0021089665],"category_scores_gemma":[0.04437036,0.000518566,0.0014240745,0.002823403,0.000121873505,0.001488222,0.00034754447,0.0014962554,0.0002843016],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012895667,0.000632965,0.00003608277,0.007912749,0.00046223376,0.000014539543,0.001991909,0.0023267874,0.000014746469,0.000035090412,0.008121221,0.97832274],"study_design_scores_gemma":[0.0034903404,0.0019171318,0.0015985084,0.3428222,0.014469063,0.00021537668,0.0041723144,0.058067266,0.000024026518,0.00473634,0.5672829,0.001204525],"about_ca_topic_score_codex":0.000048841244,"about_ca_topic_score_gemma":0.00007999692,"teacher_disagreement_score":0.9771182,"about_ca_system_score_codex":0.0019539306,"about_ca_system_score_gemma":0.0058782757,"threshold_uncertainty_score":0.99975747},"labels":[],"label_agreement":null},{"id":"W4386858087","doi":"10.4324/9781003028130-11","title":"Equity-centered and relational learning","year":2023,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Equity (law); Psychology; Computer science; Political science","score_opus":0.5650114556217549,"score_gpt":0.5279599635017875,"score_spread":0.03705149211996739,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386858087","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007511693,0.00004754978,0.001088089,0.0014162562,0.00036633256,0.00010858474,0.00000758163,0.00007517474,0.9968153],"genre_scores_gemma":[0.0068893386,0.00017300223,0.00037446877,0.000267364,0.000093032395,0.0000030247693,0.000043595825,0.00001831439,0.99213785],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99698853,0.00003624052,0.0005064132,0.00037854383,0.0019627141,0.00012758224],"domain_scores_gemma":[0.9983642,0.00082417903,0.00025068322,0.00022626253,0.00025194994,0.00008271236],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0030402963,0.0001405234,0.00021577258,0.00029494258,0.00016938438,0.00019955884,0.0002069163,0.00015271205,0.022626098],"category_scores_gemma":[0.0004524177,0.00010286151,0.0000767247,0.000057248035,0.000059477778,0.00018110631,0.00036329788,0.00032325467,0.008074838],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000071754985,0.0000026929938,0.0011710097,0.0000036832805,0.00001961624,0.0000026415844,0.000103963604,0.0001339205,0.0000031506936,0.8998025,0.019336812,0.07941284],"study_design_scores_gemma":[0.0001930464,0.000045131666,0.0034176703,0.000035345845,0.000010160154,0.0000034247564,0.00006582006,0.0055799643,9.5136534e-7,0.22635928,0.76413935,0.0001498227],"about_ca_topic_score_codex":0.0000022423117,"about_ca_topic_score_gemma":0.000036408983,"teacher_disagreement_score":0.7448026,"about_ca_system_score_codex":0.000036224676,"about_ca_system_score_gemma":0.00014220506,"threshold_uncertainty_score":0.9926975},"labels":[],"label_agreement":null},{"id":"W4386878517","doi":"10.1111/medu.15218","title":"To prove or improve? Examining how paradoxical tensions shape evaluation practices in accreditation contexts","year":2023,"lang":"en","type":"article","venue":"Medical Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; Centre for Global Health Research; The Wilson Centre; University of Toronto; Centre for Addiction and Mental Health","funders":"","keywords":"Accreditation; Credibility; Context (archaeology); Public relations; Situated; Sociology; Medical education; Psychology; Political science; Medicine; Computer science; Law","score_opus":0.41237310714234426,"score_gpt":0.5956808583089721,"score_spread":0.18330775116662784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386878517","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88393724,0.000032994063,0.0007980905,0.11013832,0.0025575482,0.0010712665,0.0000032129417,0.00006558305,0.001395734],"genre_scores_gemma":[0.9909968,0.000026971145,0.0007814954,0.004409165,0.00046078238,0.0006898927,0.00008598846,0.0000113209135,0.0025375946],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99311745,0.00068458315,0.00068927195,0.0005857036,0.0046199,0.0003030787],"domain_scores_gemma":[0.99477565,0.0029503615,0.00052332674,0.0004198293,0.0010430687,0.00028778453],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.016709514,0.00013493991,0.00022373245,0.0006718992,0.00015150187,0.00029577798,0.00042697883,0.00015482832,0.0036516236],"category_scores_gemma":[0.16573799,0.00009270698,0.000035240428,0.0023881397,0.000052133473,0.00096047437,0.000094772164,0.00026103333,0.0011374091],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007543612,0.00019528576,0.011470025,0.00000854155,0.0000052280516,0.0000023184102,0.0029708506,0.00013133325,0.0006836181,0.00026924518,0.075732216,0.9084559],"study_design_scores_gemma":[0.00086071517,0.00031962682,0.5468808,0.00012148457,0.000021221134,0.000006555157,0.01376495,0.40204018,0.00011193229,0.0029006375,0.032770965,0.0002009508],"about_ca_topic_score_codex":0.000041442032,"about_ca_topic_score_gemma":0.00047340489,"teacher_disagreement_score":0.908255,"about_ca_system_score_codex":0.00019425573,"about_ca_system_score_gemma":0.0057686926,"threshold_uncertainty_score":0.9998677},"labels":[],"label_agreement":null},{"id":"W4387228944","doi":"10.5281/zenodo.8297430","title":"Guidelines for the students' projects and research reporting formats","year":2023,"lang":"en","type":"report","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canarie","funders":"","keywords":"Computer science; Mathematics education; Data science; Medical education; Psychology; Medicine","score_opus":0.8032948658692478,"score_gpt":0.6143486667895423,"score_spread":0.18894619907970556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387228944","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037430447,0.0043565826,0.019298159,0.057974778,0.0085253855,0.025296932,0.002676005,0.004517745,0.839924],"genre_scores_gemma":[0.31075698,0.03158711,0.00492991,0.002870921,0.012792964,0.000026590365,0.012070932,0.016443942,0.6085207],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98613894,0.00096304924,0.0024719746,0.0010217301,0.008676303,0.0007279856],"domain_scores_gemma":[0.97075945,0.001426004,0.0018916555,0.0014826925,0.024219489,0.00022068931],"candidate_categories":["metaresearch","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.0963161,0.0002714079,0.00046998242,0.0010279075,0.0069332006,0.0057032066,0.0033410569,0.00020160351,0.0038988495],"category_scores_gemma":[0.14797813,0.00018161685,0.00016504615,0.0020571784,0.0003302359,0.00047101482,0.0044892635,0.0008290692,0.004410286],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029897796,0.000032968237,0.00005246328,0.00009645304,0.00005829195,0.0000063305542,0.0012481711,0.000040166495,0.00003293048,0.00028073636,0.7670864,0.2310352],"study_design_scores_gemma":[0.00035072432,0.00023420477,0.0025474592,0.00014256088,0.00003137307,0.00014138698,0.005084941,0.0025502918,0.000028096669,0.0008759914,0.98780406,0.0002089262],"about_ca_topic_score_codex":0.0000916473,"about_ca_topic_score_gemma":0.0000074473114,"teacher_disagreement_score":0.27332652,"about_ca_system_score_codex":0.0003804562,"about_ca_system_score_gemma":0.00016581228,"threshold_uncertainty_score":0.9970117},"labels":[],"label_agreement":null},{"id":"W4387386802","doi":"10.3138/9781487542535-016","title":"Conclusion: The Future of Leading for Systemic Educational Transformationin Canada","year":2022,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Transformation (genetics); Biology","score_opus":0.09883255913264864,"score_gpt":0.4146753138572781,"score_spread":0.31584275472462947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387386802","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001544165,0.001384598,0.0014837636,0.054226298,0.0025517745,0.0011664135,0.00027371617,0.0000094752295,0.93874955],"genre_scores_gemma":[0.06059966,0.00016080482,0.00016842716,0.0017895923,0.0005436516,0.00011410298,0.00020397925,0.000016059514,0.93640375],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99642354,0.000047885835,0.0008837832,0.00021739981,0.0023168114,0.000110572626],"domain_scores_gemma":[0.99705505,0.0013612177,0.0005349505,0.00037710936,0.0006274349,0.00004421592],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0023155902,0.00014618065,0.0003025754,0.00011913264,0.00046828532,0.000055876844,0.0006679802,0.00007246311,0.04812732],"category_scores_gemma":[0.00004991039,0.000085430685,0.00014729903,0.00008128143,0.000041076986,0.00015745913,0.000046389825,0.00018085052,0.000033684366],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009505492,0.0000028929035,0.000017092865,0.000025443136,0.000020236865,1.0907823e-7,0.0003487334,0.0004266337,0.000003391293,0.8023119,0.18707529,0.009758792],"study_design_scores_gemma":[0.00016773253,0.000028854462,0.000032669108,0.000028604398,0.000021488066,0.000021253567,0.0017231887,0.0011265199,0.000012241194,0.022302682,0.9744223,0.000112479946],"about_ca_topic_score_codex":0.0032154466,"about_ca_topic_score_gemma":0.12714833,"teacher_disagreement_score":0.787347,"about_ca_system_score_codex":0.00031663646,"about_ca_system_score_gemma":0.004833825,"threshold_uncertainty_score":0.9527428},"labels":[],"label_agreement":null},{"id":"W4387589954","doi":"10.1108/978-1-80382-481-920231008","title":"Bridging Policy-Practice Gaps and Building Policy Capacity","year":2023,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Francis Xavier University","funders":"","keywords":"Bridging (networking); Business; Computer science; Computer security","score_opus":0.2937692259031425,"score_gpt":0.5117628396365772,"score_spread":0.21799361373343473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387589954","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00033935258,0.000080380625,0.001867987,0.025604572,0.00038374844,0.0002134109,0.00003548915,0.0001385656,0.9713365],"genre_scores_gemma":[0.015008435,0.0009911826,0.002726725,0.005503881,0.0014713607,0.0000071480713,0.000007896149,0.00005220348,0.9742312],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9955574,0.0000951583,0.0008068608,0.00070544716,0.0024866397,0.0003484412],"domain_scores_gemma":[0.9958104,0.002048374,0.00055623805,0.00075384,0.000599533,0.00023159881],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.005412689,0.00031756764,0.00045257155,0.0014753214,0.00031712156,0.00065771124,0.00053744327,0.00024294473,0.0018932038],"category_scores_gemma":[0.006384165,0.00024724228,0.00013961986,0.00037681713,0.00015110704,0.0007357842,0.0004401525,0.00046261735,0.0025999523],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007656751,0.0000047927006,0.00005152124,0.000009925632,0.00003331613,0.0000059003596,0.00025765144,0.00004034044,0.000045419638,0.8885458,0.01416134,0.09683631],"study_design_scores_gemma":[0.0002148087,0.00004161372,0.0005199541,0.000081461396,0.000030460182,0.00005143275,0.00016454935,0.002770527,0.000056691784,0.23169023,0.7640269,0.0003513855],"about_ca_topic_score_codex":0.0011172135,"about_ca_topic_score_gemma":0.00023622414,"teacher_disagreement_score":0.74986553,"about_ca_system_score_codex":0.00020987472,"about_ca_system_score_gemma":0.0008776346,"threshold_uncertainty_score":0.999998},"labels":[],"label_agreement":null},{"id":"W4387635574","doi":"10.1787/ddb90d48-en","title":"Executive summary","year":2022,"lang":"en","type":"book-chapter","venue":"Connecting people with jobs","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Work (physics); Christian ministry; Public policy; Executive summary; Value (mathematics); Public relations; Political science; Public administration; Business; Public economics; Economics; Economic growth; Finance; Engineering","score_opus":0.12837353861634124,"score_gpt":0.3985571591630538,"score_spread":0.2701836205467125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387635574","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016947591,0.00037286137,0.00038064757,0.0011620206,0.0010567397,0.0004326523,0.00006615213,0.00011862482,0.9947156],"genre_scores_gemma":[0.03583348,0.00011570799,0.0005668863,0.0007916965,0.00028817664,0.000053697906,0.000109003726,0.00008806041,0.9621533],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9952031,0.00011630285,0.00074083783,0.00087120465,0.0027552398,0.00031335079],"domain_scores_gemma":[0.9952436,0.0022783105,0.00085535954,0.0009519445,0.0005307383,0.00014006668],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0030237425,0.0003741751,0.00062640477,0.00043692687,0.0006775522,0.0002700953,0.0008178411,0.00015423498,0.043184455],"category_scores_gemma":[0.0006783326,0.0002792023,0.00018695364,0.00025083736,0.000052270738,0.0003083032,0.0003886382,0.0007412927,0.0008303595],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00055830245,0.00015943845,0.015444023,0.00008908856,0.00050103426,0.0002051513,0.01603123,0.0036778825,0.00002559691,0.54346347,0.23415159,0.1856932],"study_design_scores_gemma":[0.00041372378,0.00035442147,0.0005909666,0.000084257066,0.000053676195,0.000056315585,0.001523509,0.0005521271,0.00001212443,0.010614157,0.9852856,0.00045913708],"about_ca_topic_score_codex":0.00006111874,"about_ca_topic_score_gemma":0.0016121259,"teacher_disagreement_score":0.751134,"about_ca_system_score_codex":0.00020335503,"about_ca_system_score_gemma":0.000600354,"threshold_uncertainty_score":0.999966},"labels":[],"label_agreement":null},{"id":"W4387663246","doi":"10.5539/ass.v19n6p1","title":"Best Practices in Advancing Family Well-Being in Asia: A Multimethod Qualitative Study","year":2023,"lang":"en","type":"article","venue":"Asian Social Science","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Best practice; Qualitative research; Sustainability; Psychological intervention; Interpretation (philosophy); Psychology; Public relations; Medical education; Sociology; Political science; Medicine; Nursing; Social science; Computer science","score_opus":0.31838581801990623,"score_gpt":0.6271086211705745,"score_spread":0.3087228031506683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387663246","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67154753,0.000006246301,0.00021174304,0.002439246,0.0002887627,0.00043193187,0.0000011204952,0.000032227315,0.32504117],"genre_scores_gemma":[0.996893,0.000006313546,0.0018649735,0.00016511988,0.0000623368,0.000057802594,7.3334974e-7,0.0000065103222,0.0009432454],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9932128,0.0015642546,0.00075865816,0.0007484177,0.003124369,0.00059149705],"domain_scores_gemma":[0.9967657,0.0020235688,0.00054691464,0.0002701597,0.0002920565,0.00010165302],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.046311814,0.00013378337,0.00028955122,0.0010608722,0.00056926184,0.00038841015,0.0009773814,0.00005354784,0.00011917557],"category_scores_gemma":[0.009499706,0.000112784175,0.000045865254,0.011006399,0.00031027416,0.002239841,0.00026234298,0.00030237273,0.00084704935],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021957178,0.0002804577,0.052480724,0.000002918334,0.0000031437226,0.000033146265,0.6368499,0.00007071847,0.0012682563,0.002741638,0.00018694061,0.30606022],"study_design_scores_gemma":[0.00039906366,0.00008205351,0.35793406,0.000013180918,0.0000021819599,3.6860126e-7,0.63051885,0.002443359,0.000039374012,0.0077050147,0.00075203856,0.000110447916],"about_ca_topic_score_codex":0.00069019746,"about_ca_topic_score_gemma":0.0028117169,"teacher_disagreement_score":0.32534543,"about_ca_system_score_codex":0.0002849944,"about_ca_system_score_gemma":0.0006946973,"threshold_uncertainty_score":0.9999309},"labels":[],"label_agreement":null},{"id":"W4387670261","doi":"10.21203/rs.3.rs-3369555/v1","title":"Program Evaluation Activities in Competence by Design: A Survey of Specialty/Subspecialty Program Directors","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Competence (human resources); Medical education; Specialty; Subspecialty; Descriptive statistics; Program evaluation; Program Design Language; Evaluation methods; Survey research; Curriculum; Descriptive research; Psychology; Medicine; Family medicine; Computer science; Political science; Applied psychology; Pedagogy; Engineering; Sociology","score_opus":0.6823018805970905,"score_gpt":0.6383738635957723,"score_spread":0.04392801700131821,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387670261","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9623517,0.0007941083,0.0007342675,0.0010572044,0.0017524131,0.026348198,0.0008131744,0.00036816442,0.005780806],"genre_scores_gemma":[0.98779005,0.0005924359,0.0028398773,0.000007742895,0.00021631492,0.006806025,0.00056145946,0.00005262785,0.0011334618],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9641019,0.015045726,0.0018969476,0.0015571363,0.016346758,0.0010515249],"domain_scores_gemma":[0.9813296,0.010900264,0.00070798997,0.001481914,0.005347394,0.00023279988],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10478939,0.00037556773,0.0009398303,0.0019829138,0.00025805956,0.00087724143,0.0018559034,0.00041713475,0.0015995791],"category_scores_gemma":[0.021668417,0.0003116257,0.00020165471,0.0050020707,0.00056569657,0.00040114118,0.0013017671,0.0016288235,0.00025189976],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028556332,0.0013560499,0.2516683,0.00023793033,0.00004655548,0.000006120738,0.0017434779,0.00522805,0.00006930552,0.000056397905,0.021522848,0.7177794],"study_design_scores_gemma":[0.0006052949,0.0007981988,0.8786822,0.0005454437,0.000009737506,4.237432e-7,0.0014740096,0.108418934,0.000621089,0.0051671555,0.0033374247,0.0003400839],"about_ca_topic_score_codex":0.0035613284,"about_ca_topic_score_gemma":0.021671483,"teacher_disagreement_score":0.7174393,"about_ca_system_score_codex":0.00088776986,"about_ca_system_score_gemma":0.004944245,"threshold_uncertainty_score":0.9999336},"labels":[],"label_agreement":null},{"id":"W4388146429","doi":"10.24124/c677/20211623","title":"Tuition Policy Instruments in Canada Public Policy Choices for What Problems","year":2022,"lang":"fr","type":"article","venue":"Canadian Political Science Review","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Typology; Political science; Public policy; Public administration; Humanities; Sociology","score_opus":0.19042478448664754,"score_gpt":0.47099314597185254,"score_spread":0.28056836148520503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388146429","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0083645275,0.057376757,0.000018544353,0.9102325,0.0027840661,0.0027313111,0.0007981956,0.000010669855,0.017683435],"genre_scores_gemma":[0.86111784,0.02288946,0.00010616803,0.111019686,0.000416375,0.0008022,0.00005195777,0.000019167435,0.0035771548],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9899623,0.0005782112,0.0012767811,0.00090704346,0.0031749243,0.004100786],"domain_scores_gemma":[0.993292,0.00043646366,0.00027465483,0.0006977505,0.00059314555,0.004706029],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011805917,0.00028893695,0.00057232805,0.0017743853,0.0014401,0.0010697535,0.0021434492,0.00005449354,0.006349177],"category_scores_gemma":[0.007204915,0.00027516863,0.00013678432,0.010239307,0.00073763577,0.0033265073,0.00030206708,0.0004092783,0.00012904509],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[7.396362e-7,0.000030330259,0.0036601822,0.0003801753,0.0000034877328,0.000003867437,0.00005533596,0.000040979765,0.0000016001621,0.54620945,0.003184388,0.44642946],"study_design_scores_gemma":[0.0003032425,0.00010486738,0.00996858,0.0012583785,0.000014067395,0.000046653255,0.001059147,0.0043736603,0.000004304921,0.03161928,0.95090425,0.00034356216],"about_ca_topic_score_codex":0.9974939,"about_ca_topic_score_gemma":0.9983265,"teacher_disagreement_score":0.9477199,"about_ca_system_score_codex":0.049450647,"about_ca_system_score_gemma":0.34295204,"threshold_uncertainty_score":0.9999701},"labels":[],"label_agreement":null},{"id":"W4388161876","doi":"10.1016/j.refiri.2023.100307","title":"Cocréation d’un modèle logique dans une démarche d’amélioration continue : le cas du Strengths-Based Nursing","year":2023,"lang":"fr","type":"article","venue":"Revue Francophone Internationale de Recherche Infirmière","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut Universitaire en Santé Mentale de Québec; McGill University; Université de Montréal; Université du Québec en Outaouais","funders":"McGill University Health Centre","keywords":"Humanities; Political science; Philosophy","score_opus":0.2493182205253496,"score_gpt":0.46946868473495895,"score_spread":0.22015046420960935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388161876","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5609423,0.0012726157,0.29385126,0.11458808,0.00597059,0.0010232141,0.00027474554,0.00031530345,0.021761857],"genre_scores_gemma":[0.9425816,0.00181339,0.02310982,0.0007140342,0.0017669831,0.0002554471,0.000594843,0.000089842564,0.029074028],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9921111,0.003019354,0.0015811387,0.0009088832,0.0016687071,0.0007108448],"domain_scores_gemma":[0.9893372,0.0071233097,0.00084094837,0.00076084654,0.0016503074,0.00028738167],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.013334557,0.00047372348,0.00060023414,0.0008703685,0.0004893706,0.00044987648,0.0010164359,0.0010331443,0.0018527099],"category_scores_gemma":[0.007379295,0.0005272282,0.00036508928,0.0048242263,0.0003270301,0.0010794753,0.000111232155,0.001474403,0.0024796138],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019301003,0.00075411866,0.03167783,0.00016441445,0.00013935589,0.000105101964,0.014801463,0.155586,0.0070567215,0.016511567,0.015495336,0.7575151],"study_design_scores_gemma":[0.0021261128,0.00018676289,0.08090541,0.0011627581,0.00004884803,0.00009355708,0.0072068446,0.7744808,0.01217414,0.04085101,0.08015302,0.0006106938],"about_ca_topic_score_codex":0.0027115492,"about_ca_topic_score_gemma":0.0038490372,"teacher_disagreement_score":0.75690436,"about_ca_system_score_codex":0.0031957927,"about_ca_system_score_gemma":0.003902364,"threshold_uncertainty_score":0.99971795},"labels":[],"label_agreement":null},{"id":"W4388306673","doi":"10.1002/ev.20564","title":"Artificial intelligence and the future of evaluation education: Possibilities and prototypes","year":2023,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Fraser Health","funders":"","keywords":"Chatbot; Evaluation methods; Engineering ethics; Literacy; Computer science; Program evaluation; Management science; Psychology; Pedagogy; Artificial intelligence; Political science; Engineering","score_opus":0.2331504610129478,"score_gpt":0.5285796286386468,"score_spread":0.29542916762569904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388306673","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92493236,0.005009631,0.008771664,0.037902303,0.0041904515,0.012171764,0.000029939401,0.00012421433,0.006867656],"genre_scores_gemma":[0.9944193,0.00028498506,0.0010264373,0.00009483676,0.0005414897,0.0015889743,0.000042919604,0.000008171827,0.0019928867],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99694914,0.000518244,0.0005869541,0.00030462322,0.0015329632,0.00010808988],"domain_scores_gemma":[0.99639004,0.0012500217,0.00026043758,0.00029895312,0.0017531373,0.000047394013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017285567,0.00009295601,0.00015872052,0.00032584355,0.0003833795,0.0001679127,0.00010992475,0.000056948036,0.00047319444],"category_scores_gemma":[0.0032217961,0.00006000196,0.00005839018,0.0010346783,0.00016321105,0.00037779508,0.000033141918,0.00006323629,0.000026523765],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009152033,0.000023590937,0.0005221862,0.000009302708,0.000010928699,3.4237106e-9,0.0027270888,0.0007941752,0.000039307386,0.036056466,0.0019884575,0.95773697],"study_design_scores_gemma":[0.00041533372,0.000088342415,0.020256178,0.000016972896,0.00010542194,0.000002574249,0.00967973,0.32230806,0.0005779981,0.6381781,0.008294486,0.00007680805],"about_ca_topic_score_codex":0.00006165556,"about_ca_topic_score_gemma":0.00039799913,"teacher_disagreement_score":0.95766014,"about_ca_system_score_codex":0.000054958946,"about_ca_system_score_gemma":0.0010919448,"threshold_uncertainty_score":0.5990867},"labels":[],"label_agreement":null},{"id":"W4388365390","doi":"10.1093/oso/9780198529446.003.0011","title":"How to take matters further","year":2005,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Ask price; Point (geometry); Scarcity; Computer science; Wasting; Public relations; Knowledge management; Business; Political science; Economics; Microeconomics; Medicine; Mathematics; Finance","score_opus":0.2250227788281736,"score_gpt":0.4473584159007144,"score_spread":0.2223356370725408,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388365390","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000021353902,0.000036933758,0.0026708608,0.13892323,0.00046219875,0.00025122878,0.000015000799,0.000040642404,0.8575786],"genre_scores_gemma":[0.0014603812,0.000022647257,0.0026833958,0.030474411,0.0004190605,0.000009598935,0.000007752287,0.000027306643,0.9648954],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99642575,0.000021913094,0.00045682356,0.0005144895,0.0023820486,0.0001990015],"domain_scores_gemma":[0.9982831,0.00020258485,0.00021105086,0.0007999742,0.00032371754,0.00017955503],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0014163175,0.0002436168,0.00031981396,0.00039402433,0.00006223772,0.0005887918,0.0006703762,0.00016180049,0.13368443],"category_scores_gemma":[0.00007170334,0.00016014607,0.0001649378,0.00006934889,0.00003686914,0.00024868862,0.00012006875,0.0001716339,0.03383703],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000067385654,0.0000054149536,0.000033075437,0.0000014658405,0.000016971695,0.0000019337797,0.00021874812,0.000048062506,0.000012001648,0.05251892,0.68287855,0.2642581],"study_design_scores_gemma":[0.0001054847,0.000041065206,0.00016808447,0.00001674839,0.000008850612,0.0000025852573,0.00014070582,0.00012461943,0.000015789032,0.0102145625,0.98892677,0.00023473558],"about_ca_topic_score_codex":0.0000027681208,"about_ca_topic_score_gemma":0.00021174987,"teacher_disagreement_score":0.30604818,"about_ca_system_score_codex":0.00007393038,"about_ca_system_score_gemma":0.0001222133,"threshold_uncertainty_score":0.96691525},"labels":[],"label_agreement":null},{"id":"W4388544016","doi":"10.1007/978-3-031-40829-8_4","title":"The Instruments of Professional Independence","year":2023,"lang":"en","type":"book-chapter","venue":"Society, environment and statistics","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Independence (probability theory); Politics; Government (linguistics); Quality (philosophy); Political science; Public relations; Public administration; Business; Law; Mathematics; Epistemology; Statistics","score_opus":0.12486669237306436,"score_gpt":0.40741879137813986,"score_spread":0.2825520990050755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388544016","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008969417,0.0038269479,0.05592725,0.01129952,0.01272768,0.005795604,0.011230269,0.00018755795,0.89003575],"genre_scores_gemma":[0.0054708035,0.010317335,0.0036759407,0.0001295304,0.00006397935,0.000014222021,0.000073919604,0.000024304753,0.98023],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.996074,0.000040794683,0.0006393793,0.00030983827,0.0027743175,0.00016167849],"domain_scores_gemma":[0.997952,0.0010092686,0.0005362618,0.00036233471,0.00007200032,0.000068172296],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0021245137,0.00017885127,0.00023998109,0.000031330044,0.00036425304,0.000077235294,0.00035876635,0.00018634765,0.0013377557],"category_scores_gemma":[0.00009352923,0.00011033903,0.000095378484,0.000029243398,0.00046345612,0.00006507145,0.00034322703,0.00032083842,0.00037586532],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021033826,0.000035405723,0.0048890985,0.000037954233,0.00016530149,0.0000022677975,0.0014783134,0.000049707684,0.000016947444,0.5340388,0.12922314,0.33004203],"study_design_scores_gemma":[0.0003598433,0.00012103167,0.015876157,0.00006155995,0.000055453667,0.0000012506194,0.0009511202,0.004713425,0.000008609376,0.58292145,0.39467603,0.0002540951],"about_ca_topic_score_codex":0.0000023311457,"about_ca_topic_score_gemma":0.000009914526,"teacher_disagreement_score":0.32978794,"about_ca_system_score_codex":0.000052147807,"about_ca_system_score_gemma":0.00014159853,"threshold_uncertainty_score":0.99957514},"labels":[],"label_agreement":null},{"id":"W4388720744","doi":"10.1370/afm.22.s1.5013","title":"How the champion can make the change implementation a success - a realist evaluation approach","year":2023,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Champion; Context (archaeology); Theory of change; Process management; Knowledge management; Computer science; Public relations; Psychology; Political science; Management; Engineering; Law","score_opus":0.6136670948276672,"score_gpt":0.5617713610355805,"score_spread":0.051895733792086784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388720744","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4683467,0.00010807734,0.0061470466,0.4599999,0.0014878629,0.005935569,0.00009281037,0.00026394514,0.057618134],"genre_scores_gemma":[0.9914869,0.00004608893,0.00007988624,0.0022803026,0.0002770356,0.0011184306,0.00022196052,0.000008511829,0.0044808667],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99480665,0.0007787377,0.00036103805,0.00034501855,0.0034507301,0.00025783258],"domain_scores_gemma":[0.9980027,0.0004888585,0.00024725028,0.0006884205,0.0005260222,0.000046733356],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017510727,0.00011841379,0.00011693063,0.00018466175,0.00065971015,0.00096090516,0.0006749919,0.00003832442,0.0008774738],"category_scores_gemma":[0.00035248874,0.00005050245,0.000073417505,0.0018664543,0.000071995455,0.00031694642,0.00012697314,0.00010495736,0.00012630025],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011364496,0.000024120101,0.0138275465,0.0000044867793,0.00001813594,2.882846e-7,0.011173291,0.00024213374,0.00006975966,0.017075099,0.025404565,0.93214923],"study_design_scores_gemma":[0.0007098936,0.00006550721,0.5276504,0.000004316395,0.000038271148,0.0000045027837,0.050527338,0.33498916,0.00018653576,0.009811184,0.07584581,0.00016705807],"about_ca_topic_score_codex":0.00083990005,"about_ca_topic_score_gemma":0.008751653,"teacher_disagreement_score":0.93198216,"about_ca_system_score_codex":0.00008495469,"about_ca_system_score_gemma":0.00016984534,"threshold_uncertainty_score":0.9607723},"labels":[],"label_agreement":null},{"id":"W4388901331","doi":"10.22215/cjcr.v10i2.4493","title":"From the Editor","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Children s Rights / Revue canadienne des droits des enfants","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"University of Ottawa","keywords":"Computer science","score_opus":0.054953406665476504,"score_gpt":0.34256078164049314,"score_spread":0.28760737497501665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388901331","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.989032,0.00034660043,0.00006680689,0.001646898,0.005761793,0.00018944575,0.00025660638,0.00001587772,0.0026840288],"genre_scores_gemma":[0.9898129,0.000043166136,0.00021253637,0.00037335628,0.0062632705,0.0000043206783,0.000034196124,0.000024146966,0.003232115],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99672884,0.00029732427,0.0010526842,0.0003597993,0.00067735784,0.0008840098],"domain_scores_gemma":[0.9950569,0.0009362709,0.00057133887,0.00070112164,0.0010467294,0.0016876417],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0037802684,0.00024222839,0.00044371202,0.00075717026,0.001072102,0.0005386525,0.0018939963,0.0001237811,0.0020664085],"category_scores_gemma":[0.0017115461,0.00014783345,0.0002442582,0.001739828,0.0005613193,0.00076053664,0.000038748123,0.00040938225,0.0005116932],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059080616,0.00003374163,0.39436075,0.000011069432,0.0004955108,0.00074689445,0.046446037,0.0019899535,0.000080877704,0.009189712,0.39396897,0.15261741],"study_design_scores_gemma":[0.0006168595,0.00013677414,0.55567664,0.00018557176,0.00006107658,0.0003527515,0.00074677466,0.0005921931,0.00010477302,0.12967981,0.311546,0.0003007506],"about_ca_topic_score_codex":0.07780917,"about_ca_topic_score_gemma":0.8401126,"teacher_disagreement_score":0.7623035,"about_ca_system_score_codex":0.00054604,"about_ca_system_score_gemma":0.0014563099,"threshold_uncertainty_score":0.9988458},"labels":[],"label_agreement":null},{"id":"W4389065788","doi":"10.7202/1106956ar","title":"Étude de cas d’une évaluation participative : compromis ou atteinte à la validité scientifique ?","year":2023,"lang":"fr","type":"article","venue":"Reflets Revue d’intervention sociale et communautaire","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Moncton","funders":"","keywords":"Political science; Humanities; Gynecology; Philosophy; Medicine","score_opus":0.32570879476596515,"score_gpt":0.5282931801980805,"score_spread":0.20258438543211532,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389065788","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85560554,0.000735549,0.013732386,0.109025925,0.004229006,0.001245268,0.00021284162,0.00037049205,0.014842985],"genre_scores_gemma":[0.91295415,0.00067590503,0.00086495676,0.0007837774,0.00034225057,0.00030826358,0.0003176138,0.00007003043,0.08368305],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98540944,0.008578014,0.0020499395,0.00090404286,0.0020808738,0.0009777094],"domain_scores_gemma":[0.9933088,0.0026416318,0.0012232343,0.0011681018,0.0013447206,0.00031352285],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.030754192,0.00048944063,0.0008156084,0.0005998604,0.0012305127,0.0010943386,0.0011951835,0.0004697856,0.004420081],"category_scores_gemma":[0.0027069075,0.00051749294,0.0010029913,0.0031877048,0.00071435096,0.0012934966,0.00071112067,0.0010026617,0.003951339],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013217083,0.0013960352,0.011490927,0.0007641872,0.00038758712,0.00012558393,0.079803556,0.005685318,0.0014359526,0.052759632,0.026735466,0.8192836],"study_design_scores_gemma":[0.005053203,0.00075580354,0.3941937,0.006426996,0.0005199225,0.00013384757,0.029658835,0.20402111,0.003059268,0.08753835,0.26706836,0.0015705855],"about_ca_topic_score_codex":0.0016931413,"about_ca_topic_score_gemma":0.009845767,"teacher_disagreement_score":0.817713,"about_ca_system_score_codex":0.00082392007,"about_ca_system_score_gemma":0.0008092499,"threshold_uncertainty_score":0.9999426},"labels":[],"label_agreement":null},{"id":"W4389065798","doi":"10.7202/1106958ar","title":"L’expérience d’une communauté de pratique en évaluation en contexte collective : quelques leçons apprises","year":2023,"lang":"fr","type":"article","venue":"Reflets Revue d’intervention sociale et communautaire","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Humanities; Valuation (finance); Political science; Sociology; Philosophy; Economics","score_opus":0.12209368894435585,"score_gpt":0.4809320441796786,"score_spread":0.35883835523532276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389065798","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.72011733,0.0031632949,0.030788708,0.17361379,0.0051163766,0.0032126107,0.00040614107,0.0008682793,0.0627135],"genre_scores_gemma":[0.86849236,0.003060257,0.0019924806,0.0015912337,0.0003859067,0.0005196922,0.00034052055,0.000082141036,0.12353543],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9773382,0.01671289,0.0022587203,0.00086627,0.0018668614,0.00095706625],"domain_scores_gemma":[0.9870908,0.008492257,0.0014135824,0.0013891599,0.0013431633,0.00027103114],"candidate_categories":["metaresearch","metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.02953818,0.00060722465,0.0010496058,0.0006509558,0.0018442131,0.0009717645,0.0018123552,0.00072100735,0.0029165808],"category_scores_gemma":[0.007247819,0.0006486135,0.00094803213,0.003448225,0.0007122315,0.0020444237,0.0009585443,0.0015448021,0.0017190059],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018046278,0.0011739031,0.0072982316,0.00043044094,0.00036627834,0.00005935103,0.3439725,0.0023924462,0.00050141686,0.06061638,0.02924586,0.55376273],"study_design_scores_gemma":[0.004900581,0.0017386668,0.23257247,0.00689044,0.00039829756,0.00017939947,0.15938343,0.092455685,0.0010345422,0.16867948,0.32996964,0.001797346],"about_ca_topic_score_codex":0.002476309,"about_ca_topic_score_gemma":0.011825496,"teacher_disagreement_score":0.55196536,"about_ca_system_score_codex":0.0021815265,"about_ca_system_score_gemma":0.0027369813,"threshold_uncertainty_score":0.99959654},"labels":[],"label_agreement":null},{"id":"W4389065800","doi":"10.7202/1106957ar","title":"Construire la démarche d’évaluation d’impact de la Couverture des témoins au Musée canadien pour les droits de la personne","year":2023,"lang":"fr","type":"article","venue":"Reflets Revue d’intervention sociale et communautaire","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Musée de la Civilisation","funders":"","keywords":"Humanities; Valuation (finance); Political science; Art; Business","score_opus":0.13553759359468565,"score_gpt":0.4943229688947232,"score_spread":0.35878537530003757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389065800","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92309827,0.0010832199,0.0027081335,0.019784998,0.0008107238,0.00053926365,0.00029897346,0.00021155582,0.051464893],"genre_scores_gemma":[0.9604539,0.0011057345,0.0012291002,0.00033628356,0.00042297365,0.00009239319,0.00020869693,0.0000763874,0.036074486],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9815141,0.0144961225,0.0011652862,0.0005900135,0.001254888,0.0009795956],"domain_scores_gemma":[0.99089706,0.006538262,0.0007676445,0.00073534454,0.0006496013,0.00041206833],"candidate_categories":["metaresearch","metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.028902268,0.00048789385,0.0006945189,0.00054231996,0.001529459,0.00091650744,0.0010252574,0.00087792607,0.0031993345],"category_scores_gemma":[0.004901464,0.0004906494,0.0009953098,0.001493897,0.0015647305,0.00093083456,0.00037356614,0.0013729932,0.00038599406],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010229136,0.00064125244,0.09693952,0.000544965,0.0003708794,0.00020139219,0.06686697,0.0026498013,0.00039789695,0.030543525,0.02030625,0.78043526],"study_design_scores_gemma":[0.003714487,0.0005202715,0.6449843,0.0042078886,0.00034601378,0.00079938764,0.07263235,0.06850684,0.0001278588,0.051212505,0.15196958,0.0009784948],"about_ca_topic_score_codex":0.016241597,"about_ca_topic_score_gemma":0.04206567,"teacher_disagreement_score":0.77945673,"about_ca_system_score_codex":0.0042697587,"about_ca_system_score_gemma":0.0051681935,"threshold_uncertainty_score":0.99994946},"labels":[],"label_agreement":null},{"id":"W4389068470","doi":"10.55016/ojs/ajer.v69i2.74894","title":"“Beg, Borrow, and Steal”: School Division Perspectives of Assessment Policy Creation in Saskatchewan","year":2023,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Regina","funders":"","keywords":"Autonomy; Valuation (finance); Christian ministry; Limiting; Political science; Sociology; Public administration; Humanities; Law; Economics; Finance; Art","score_opus":0.2267232433139548,"score_gpt":0.6131495110667196,"score_spread":0.3864262677527648,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389068470","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93699175,0.00018767145,0.000017702178,0.038778428,0.000112422575,0.00015869133,0.0000030690433,4.841314e-7,0.023749761],"genre_scores_gemma":[0.9776559,0.00033248917,0.0003228283,0.000042579984,0.0002006469,0.000011547931,0.000005359041,0.000006989339,0.021421678],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9948612,0.0007496702,0.0008830957,0.00023006978,0.0030185902,0.0002574129],"domain_scores_gemma":[0.97649205,0.020549422,0.0003738151,0.00025094146,0.002122878,0.00021087089],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011250231,0.00008580009,0.00023694354,0.0024831973,0.00016178274,0.00015790196,0.00045380546,0.000054663287,0.006706081],"category_scores_gemma":[0.028710723,0.00006356172,0.0000693851,0.0026588433,0.00017605677,0.0006898937,0.00012976055,0.00038979133,0.0001690262],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008255471,0.00039397174,0.9367163,0.0000188638,0.00002988075,5.5548486e-7,0.013801966,0.0006719025,0.0017481694,0.023745999,0.010619188,0.012170623],"study_design_scores_gemma":[0.0004590137,0.00024166952,0.9257829,0.00008157087,0.0000034928705,0.000006797945,0.055562638,0.0013505771,0.00010187722,0.014536043,0.0018159352,0.000057459103],"about_ca_topic_score_codex":0.0015241966,"about_ca_topic_score_gemma":0.0027269383,"teacher_disagreement_score":0.041760672,"about_ca_system_score_codex":0.0003592452,"about_ca_system_score_gemma":0.006042878,"threshold_uncertainty_score":0.99959195},"labels":[],"label_agreement":null},{"id":"W4389089559","doi":"10.5489/cuaj.8653","title":"Mental models in practice: The macro view and the cone of influence","year":2023,"lang":"en","type":"article","venue":"Canadian Urological Association Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Macro; Cone (formal languages); Mental model; Psychology; Epistemology; Computer science; Cognitive science; Philosophy; Algorithm; Programming language","score_opus":0.09911881286640709,"score_gpt":0.42082504797029613,"score_spread":0.32170623510388907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389089559","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7219386,0.0002864664,0.00003133903,0.27328786,0.00018906682,0.00020231449,0.000014149233,0.0000047080807,0.004045509],"genre_scores_gemma":[0.99164754,0.000665296,0.000028004992,0.0073258085,0.00004610156,0.000008217028,0.0000011807635,0.000001847404,0.0002759964],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99717385,0.0009909859,0.0005084201,0.000109057866,0.0010035374,0.00021412756],"domain_scores_gemma":[0.99583375,0.0030955467,0.00045159,0.00011054653,0.0003846028,0.00012393773],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016981082,0.000056783956,0.00015517937,0.00013950172,0.00031101014,0.00021263146,0.0003310056,0.00006408894,0.000268921],"category_scores_gemma":[0.0065099793,0.000025989266,0.00004667504,0.0007281281,0.00010955143,0.00038908006,0.000038208847,0.00033664663,0.00006451149],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023506726,0.000041102485,0.7562127,0.0000029587047,0.0001287648,0.000031160438,0.012878091,0.04095665,0.00004990383,0.07286817,0.03988956,0.07670589],"study_design_scores_gemma":[0.0012733411,0.000058131343,0.7611708,0.000006946965,0.000017601858,0.000042877313,0.0028095483,0.055837955,0.0000024604371,0.07131551,0.107393235,0.00007156781],"about_ca_topic_score_codex":0.000787395,"about_ca_topic_score_gemma":0.0020362965,"teacher_disagreement_score":0.26970896,"about_ca_system_score_codex":0.00017783964,"about_ca_system_score_gemma":0.00037936086,"threshold_uncertainty_score":0.7793523},"labels":[],"label_agreement":null},{"id":"W4389104512","doi":"10.1177/16094069231217915","title":"Policy Feedback &amp; Research Methods: How Qualitative Research Designs With Marginalized Groups Inform Theory","year":2023,"lang":"en","type":"article","venue":"International Journal of Qualitative Methods","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Qualitative research; Legitimacy; Management science; Sociology; Democratic legitimacy; Public relations; Engineering ethics; Political science; Social science; Economics; Politics; Engineering","score_opus":0.9604508809697415,"score_gpt":0.833181009885129,"score_spread":0.12726987108461252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389104512","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038673382,0.00020415902,0.89640224,0.04929805,0.0009374675,0.00050222746,0.00004787278,0.000037319383,0.01389729],"genre_scores_gemma":[0.071469,0.0002788059,0.90091,0.0005618014,0.0008629235,0.00009978235,0.000022905539,0.000051145395,0.025743598],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.75523204,0.22032328,0.0029706962,0.000857431,0.01935509,0.0012614338],"domain_scores_gemma":[0.789604,0.17752832,0.0016413665,0.00071219594,0.030069947,0.00044413484],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5848923,0.00030968292,0.0008114486,0.007297741,0.0005452072,0.0011418498,0.0030608554,0.00016043751,0.0013684493],"category_scores_gemma":[0.144307,0.00019662251,0.00035070046,0.0074441643,0.0015732902,0.0019734686,0.0005616227,0.0017921722,0.00058584864],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023856086,0.0001420795,0.000114483475,0.000015969345,0.00062198035,0.000031524844,0.45446146,0.00021072818,0.0039093303,0.3307982,0.0147282835,0.19258033],"study_design_scores_gemma":[0.0012561365,0.0006172962,0.0011479704,0.00011564856,0.00001209109,0.000045618603,0.35545158,0.00037326335,0.0016147557,0.5854665,0.05371917,0.0001799621],"about_ca_topic_score_codex":0.00007689196,"about_ca_topic_score_gemma":0.00004814535,"teacher_disagreement_score":0.4405853,"about_ca_system_score_codex":0.0008396731,"about_ca_system_score_gemma":0.0026180155,"threshold_uncertainty_score":0.99989504},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W4389191924","doi":"10.22215/etd/2023-15812","title":"The Susceptibility of Policy Analysis to Cultural Bias: Policy Analytic Methods and Cultural Theory","year":2023,"lang":"en","type":"dissertation","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Operationalization; Causality (physics); Cultural policy; Positive economics; Omitted-variable bias; Cultural bias; Cultural analysis; Policy analysis; Construct (python library); Culture theory; Sociology; Social psychology; Epistemology; Political science; Psychology; Social science; Econometrics; Economics; Computer science; Public administration","score_opus":0.2834723446149457,"score_gpt":0.6374524438081377,"score_spread":0.353980099193192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389191924","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94957405,0.0002281216,0.0009301218,0.005147572,0.00049937656,0.0007011761,0.00006143201,0.000078659505,0.042779483],"genre_scores_gemma":[0.7846763,0.0004252482,0.0025559142,0.00038682032,0.00024207753,0.00004881047,0.00022927672,0.000018742568,0.2114168],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99375206,0.001770857,0.001433342,0.00072498963,0.001952919,0.0003658246],"domain_scores_gemma":[0.9909631,0.005278582,0.0007162322,0.001053133,0.0017754291,0.00021352807],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01797387,0.00031904675,0.0008070348,0.0017835206,0.00042439476,0.0006096595,0.000959192,0.00018791037,0.00074407185],"category_scores_gemma":[0.021797186,0.00014931626,0.0005635194,0.0096527515,0.000165977,0.00029354743,0.00015074149,0.00023600944,0.00015250799],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046201423,0.000092742775,0.024074443,0.00007168455,0.0028611447,8.917241e-7,0.045774657,0.0016572359,0.0018251641,0.09841632,0.01343175,0.8113319],"study_design_scores_gemma":[0.0002644999,0.00014607233,0.7591734,0.000025446747,0.0008659359,9.109501e-7,0.17130636,0.007149946,0.0011009612,0.05408489,0.005435251,0.00044633396],"about_ca_topic_score_codex":0.0028274218,"about_ca_topic_score_gemma":0.028639542,"teacher_disagreement_score":0.8108856,"about_ca_system_score_codex":0.00017111485,"about_ca_system_score_gemma":0.0008118157,"threshold_uncertainty_score":0.98908526},"labels":[],"label_agreement":null},{"id":"W4389220236","doi":"10.1016/j.jmir.2023.09.010","title":"LOCAL ACTION, GLOBAL IMPACT: ESTABLISHMENT OF AN ADVANCED PRACTICE INTERNATIONAL COMMUNITY OF PRACTICE","year":2023,"lang":"en","type":"article","venue":"Journal of medical imaging and radiation sciences","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Action (physics); Community practice; Political science; Medicine; Nursing","score_opus":0.1246957064045917,"score_gpt":0.5758418180930143,"score_spread":0.45114611168842256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389220236","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90865386,0.0005523144,0.018283833,0.06757804,0.00203414,0.00008385654,0.000014135406,0.000012955484,0.002786854],"genre_scores_gemma":[0.99567604,0.0011946935,0.0024026874,0.00059604744,0.00011083241,7.4150535e-7,0.0000024763058,0.0000018105095,0.00001467427],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9922008,0.0009320319,0.0010054079,0.00012892549,0.0056009484,0.0001318728],"domain_scores_gemma":[0.9921477,0.0039850986,0.0017028827,0.00015372959,0.0017908891,0.00021972698],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.034512073,0.000074242365,0.0002208613,0.0003747353,0.00021907956,0.00018531783,0.0008002472,0.000041426385,0.00021901658],"category_scores_gemma":[0.029319815,0.000046985027,0.00006763834,0.0013712982,0.0005383947,0.004255985,0.00010115717,0.00028334346,0.0000047842805],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013328088,0.00029442692,0.018404702,0.0000065129257,0.000036539834,0.000008143144,0.0025546714,0.009492252,0.00014176243,0.00072353816,0.0051451097,0.96305907],"study_design_scores_gemma":[0.0024393932,0.0009956032,0.3008046,0.00016089967,0.00007267146,0.00078923925,0.24740349,0.37891662,0.0005552635,0.006067406,0.06161932,0.00017549301],"about_ca_topic_score_codex":0.00018818867,"about_ca_topic_score_gemma":0.000018238197,"teacher_disagreement_score":0.9628836,"about_ca_system_score_codex":0.00008603826,"about_ca_system_score_gemma":0.0010423663,"threshold_uncertainty_score":0.994173},"labels":[],"label_agreement":null},{"id":"W4389296080","doi":"10.2307/j.ctt7zw6d.28","title":"Collaboration on Global Issues – A Democratic Dividend for Canada and Mexico?","year":2012,"lang":"en","type":"book-chapter","venue":"McGill-Queen's University Press eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Democracy; Dividend; Political science; Development economics; Economics; Law","score_opus":0.06660089902743141,"score_gpt":0.342894812346817,"score_spread":0.2762939133193856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389296080","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017096003,0.000014686739,0.00022257993,0.0015031234,0.0005762733,0.0010342291,0.0019959337,0.000049063554,0.99443316],"genre_scores_gemma":[0.020244975,0.00010707627,0.00036019654,0.0005843902,0.000113746806,0.0000048607353,0.000059391015,0.000021893695,0.97850347],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99706787,0.00011602258,0.00040208604,0.00058151444,0.0015301798,0.0003023424],"domain_scores_gemma":[0.99756175,0.00049191667,0.00047191294,0.0005340974,0.0006920755,0.00024821633],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00068262214,0.00035061952,0.00046862417,0.00015768525,0.000585134,0.00015382023,0.00046996903,0.0002493324,0.00013930045],"category_scores_gemma":[0.00012725659,0.00032271552,0.000098129494,0.00003644149,0.000102613565,0.00032691128,0.00022218279,0.00017582584,0.000012783521],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016513432,0.000013217046,0.00013180904,0.000035945966,0.000098804616,0.000012893277,0.00009123168,0.00007647928,0.0000015949174,0.9316905,0.058088858,0.009593519],"study_design_scores_gemma":[0.0006241266,0.00012890439,0.00022315976,0.00007612801,0.00013546117,0.0000012803464,0.00013340576,0.00022062987,0.00008533423,0.007418222,0.99059814,0.0003552329],"about_ca_topic_score_codex":0.034925018,"about_ca_topic_score_gemma":0.011376607,"teacher_disagreement_score":0.93250924,"about_ca_system_score_codex":0.00067728263,"about_ca_system_score_gemma":0.00053115364,"threshold_uncertainty_score":0.9999225},"labels":[],"label_agreement":null},{"id":"W4389359743","doi":"10.55016/ojs/ajer.v58i1.55554","title":"Positioning Ontario’s Character Development Initiative In/Through Its Policy Web of Relationships","year":2012,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"York University","funders":"","keywords":"Political science; Education policy; Sociology; Public relations; Policy analysis; Public administration; Higher education; Law","score_opus":0.6438227018767598,"score_gpt":0.5975032833816799,"score_spread":0.04631941849507992,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389359743","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8640031,0.00017199463,0.000011180145,0.014789531,0.0002506935,0.00012047941,0.0000014436265,1.7683242e-7,0.12065138],"genre_scores_gemma":[0.98346156,0.00003267887,0.0012432138,0.00019095205,0.00035671136,0.000015528785,0.000008858797,0.0000061778815,0.014684312],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99506825,0.0008044751,0.0011829459,0.00013063279,0.0024782724,0.00033544248],"domain_scores_gemma":[0.97502786,0.021477027,0.00055464543,0.00017251371,0.002595704,0.00017226319],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010429613,0.000086625005,0.00020919964,0.001250173,0.0002544903,0.00007804288,0.00043905762,0.000065076056,0.020925796],"category_scores_gemma":[0.02379428,0.000067130626,0.00006493709,0.0013810715,0.0000824436,0.0019509151,0.000078741185,0.00064993463,0.0007764665],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006379877,0.00037999626,0.9163806,0.0000054919988,0.000027552345,1.1190264e-7,0.026947176,0.00005694473,0.00020140053,0.052911866,0.002572311,0.00045275988],"study_design_scores_gemma":[0.00031843086,0.000059993654,0.94828486,0.00009325242,0.0000038318367,0.00002245046,0.0017366495,0.0000334016,0.0006358662,0.0033642994,0.04537935,0.000067579305],"about_ca_topic_score_codex":0.0012304594,"about_ca_topic_score_gemma":0.014184847,"teacher_disagreement_score":0.119458444,"about_ca_system_score_codex":0.00084056385,"about_ca_system_score_gemma":0.012797323,"threshold_uncertainty_score":0.9980165},"labels":[],"label_agreement":null},{"id":"W4389384749","doi":"10.1097/ceh.0000000000000535","title":"Principles-Focused Evaluation: A Promising Practice in the Evaluation of Continuing Professional Development","year":2023,"lang":"en","type":"article","venue":"Journal of Continuing Education in the Health Professions","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Humber River Regional Hospital; Canadian Centre on Substance Use and Addiction","funders":"Health Canada","keywords":"Program evaluation; Process (computing); Computer science; Management science; Process management; Program Design Language; Engineering ethics; Engineering; Political science; Software engineering","score_opus":0.37434525904062016,"score_gpt":0.6091254155061485,"score_spread":0.23478015646552836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389384749","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9387577,0.000714258,0.00015978538,0.052916627,0.0030282014,0.0026141575,0.0000012600123,0.0000081058515,0.0017999004],"genre_scores_gemma":[0.9951903,0.000066982255,0.002378474,0.0010956648,0.0002324051,0.00029616698,0.000010844182,0.0000108208105,0.0007182939],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9696592,0.016244562,0.0041291984,0.00033106777,0.009183487,0.00045249934],"domain_scores_gemma":[0.98214823,0.0076047853,0.00447795,0.00055497064,0.005128796,0.000085240805],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.22465973,0.000159961,0.00041312244,0.0010711434,0.00037110545,0.00014269701,0.0010033436,0.00009361463,0.00017641322],"category_scores_gemma":[0.02822783,0.000085173946,0.00009428039,0.0027532878,0.000060191433,0.00090481475,0.000079928875,0.00080623064,0.000028142164],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009975109,0.00068929495,0.016842572,0.00004129904,0.00001157404,8.837974e-7,0.3299846,0.0016122044,0.000064040694,0.0009389297,0.0064486754,0.64326614],"study_design_scores_gemma":[0.001995929,0.00013120193,0.62564874,0.0026827655,0.00005038832,0.00003449613,0.32356557,0.011645767,0.00004193495,0.004005836,0.030072767,0.00012460131],"about_ca_topic_score_codex":0.00001810056,"about_ca_topic_score_gemma":0.00016019838,"teacher_disagreement_score":0.64314157,"about_ca_system_score_codex":0.00048546662,"about_ca_system_score_gemma":0.013916817,"threshold_uncertainty_score":0.99167335},"labels":[],"label_agreement":null},{"id":"W4389582723","doi":"10.7185/gold2023.19348","title":"Reestablishing Epistemic Justice through narrative tools and refractive dialogue","year":2023,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Narrative; Economic Justice; Epistemology; Computer science; Sociology; Psychology; Cognitive science; Philosophy; Political science; Linguistics","score_opus":0.37258572314042215,"score_gpt":0.5204003095503265,"score_spread":0.1478145864099043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389582723","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6587284,0.00006657591,0.0059840456,0.02354344,0.0010681975,0.00041794818,0.000043654563,0.00020900894,0.3099387],"genre_scores_gemma":[0.9776064,0.00014317801,0.001488474,0.0014133826,0.00012185183,0.000028152866,0.000026451162,0.0000074986683,0.019164614],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.9975531,0.00026760093,0.0004304301,0.00040222987,0.0011303233,0.0002163229],"domain_scores_gemma":[0.99542725,0.0036297329,0.00017381275,0.00033022717,0.00036914306,0.00006982873],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0041759154,0.00010729938,0.00019529046,0.00014276785,0.00037533033,0.0006540201,0.0002842279,0.00006155443,0.0011659514],"category_scores_gemma":[0.0052119307,0.00007250532,0.000036583766,0.0011721982,0.00008122247,0.0027527404,0.000156611,0.00015922921,0.0010752822],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019365553,0.000102680104,0.017659834,0.000050077888,0.00008724763,0.0000458059,0.1994758,0.001972418,0.0042860056,0.1843543,0.37740692,0.21436524],"study_design_scores_gemma":[0.0013518061,0.00030463093,0.16531643,0.00007320923,0.00006414385,0.000023392187,0.36111048,0.027528415,0.00145833,0.24925196,0.19290265,0.0006145286],"about_ca_topic_score_codex":0.00006368382,"about_ca_topic_score_gemma":0.00018831885,"teacher_disagreement_score":0.31887797,"about_ca_system_score_codex":0.000047393085,"about_ca_system_score_gemma":0.0001375319,"threshold_uncertainty_score":0.9997471},"labels":[],"label_agreement":null},{"id":"W4389600041","doi":"10.1177/13563890231207115","title":"Interorganizational evaluation capacity building in the public, health and community sectors","year":2023,"lang":"en","type":"article","venue":"Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Capacity building; Work (physics); Business; Public sector; Public relations; Joint (building); Knowledge management; Political science; Economic growth; Economics; Computer science; Engineering","score_opus":0.6482669341035596,"score_gpt":0.5566919701817297,"score_spread":0.09157496392182995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389600041","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9787655,0.000053296244,0.0013916023,0.017591268,0.0003688876,0.0008044613,0.000005759971,0.000037282414,0.0009819315],"genre_scores_gemma":[0.9980484,0.000018916431,0.00024897474,0.0013174136,0.00006584506,0.00010835988,0.00015255022,0.0000068437334,0.000032668922],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9819601,0.011599226,0.00073426455,0.00029529235,0.00514667,0.00026440824],"domain_scores_gemma":[0.9960219,0.0020249512,0.00028661243,0.00045423702,0.0011335921,0.00007870915],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13825716,0.00010317632,0.00014684604,0.0005444381,0.00074288796,0.00037753413,0.00042742686,0.000049805996,0.0009792569],"category_scores_gemma":[0.015215927,0.00007137193,0.000028885903,0.0025190008,0.00006713567,0.00072711764,0.00009688259,0.00033907578,0.00016766952],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017224129,0.00028075426,0.36624292,0.000022278027,0.000024382842,2.886971e-7,0.12129401,0.006656781,0.0004019657,0.011059261,0.016398873,0.4776013],"study_design_scores_gemma":[0.00052227866,0.00007558499,0.5369964,0.0000115540315,0.000005485696,0.000003178308,0.012528984,0.42126077,0.000015589412,0.026414683,0.0020947664,0.00007069174],"about_ca_topic_score_codex":0.00009899289,"about_ca_topic_score_gemma":0.0009051754,"teacher_disagreement_score":0.47753057,"about_ca_system_score_codex":0.0003440436,"about_ca_system_score_gemma":0.0008450732,"threshold_uncertainty_score":0.99993396},"labels":[],"label_agreement":null},{"id":"W4389672983","doi":"10.56645/jmde.v19i46.971","title":"Building Spaces for Dialogues to Rethink Evaluator Competencies: Lessons from the Webinars Organized by the Evaluation Centre for Complex Health Interventions","year":2023,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Psychological intervention; General partnership; Sustainability; Political science; Public relations; Capacity building; Diversity (politics); Sociology; Engineering ethics; Psychology; Engineering","score_opus":0.48782107023075144,"score_gpt":0.5796790978903889,"score_spread":0.09185802765963741,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389672983","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.59371746,0.0009798642,0.06203971,0.3342324,0.0023998101,0.0059649525,0.00059574813,0.000041285894,0.000028749773],"genre_scores_gemma":[0.97089833,0.00012593331,0.025886834,0.000873149,0.0007850747,0.00047245508,0.00056636403,0.00004302751,0.00034882207],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9880425,0.003295754,0.0022311574,0.00051438453,0.005463848,0.00045236733],"domain_scores_gemma":[0.9805071,0.0102375755,0.0023574638,0.0006663407,0.006035125,0.00019643568],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08628207,0.0002617324,0.0005913465,0.00037806336,0.0018351389,0.0005200599,0.0012747329,0.00009390596,0.00059633557],"category_scores_gemma":[0.017330427,0.00014511762,0.00057027803,0.0014047336,0.00011542993,0.00065312255,0.0002419302,0.0002642117,0.00008261446],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008063603,0.00037993246,0.003163186,0.000055621353,0.00032040878,3.781619e-7,0.04256512,0.061347988,0.01423991,0.0011346529,0.6319903,0.24399616],"study_design_scores_gemma":[0.004473466,0.0009183857,0.07942727,0.00036119996,0.00045135632,0.000005364103,0.033144064,0.8088829,0.00029972746,0.054630227,0.01717115,0.00023491791],"about_ca_topic_score_codex":0.000043155793,"about_ca_topic_score_gemma":0.00062917924,"teacher_disagreement_score":0.7475349,"about_ca_system_score_codex":0.0006926871,"about_ca_system_score_gemma":0.0016965808,"threshold_uncertainty_score":0.99946433},"labels":[],"label_agreement":null},{"id":"W4389686269","doi":"10.56645/jmde.v19i46.969","title":"Rethinking Evaluator Competencies in an Age of Discontinuity – Implications of Inequities, Sustainability and the Pandemic for Training Evaluators: An Introduction to a Special Volume","year":2023,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Pandemic; Sustainability; Coronavirus disease 2019 (COVID-19); Sociology; Psychology; Political science; Engineering ethics; Medicine; Engineering; Biology; Ecology","score_opus":0.2642530573592116,"score_gpt":0.5106165978136467,"score_spread":0.24636354045443504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389686269","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98515326,0.000050276896,0.0032827477,0.00918938,0.00049886573,0.0017650797,0.000028029035,0.000009902108,0.000022456994],"genre_scores_gemma":[0.99568963,0.000018994646,0.0030595388,0.000020097668,0.0009980089,0.0001132053,0.000041779753,0.000011404649,0.000047331192],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9921766,0.0023410767,0.0022804714,0.0003908828,0.0025593562,0.0002515939],"domain_scores_gemma":[0.991218,0.001786584,0.0016158052,0.0005604773,0.0047032055,0.00011596331],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08981225,0.0001582579,0.0006476411,0.00082723226,0.0002692367,0.00009795136,0.0005534426,0.00008795942,0.00011934169],"category_scores_gemma":[0.013254697,0.000105619205,0.00015877138,0.0012694956,0.00039252202,0.0013405839,0.00016291854,0.00022689199,0.0000011121123],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0031471094,0.0004273737,0.27991113,0.00010377578,0.00006027241,8.894615e-7,0.33932143,0.10991984,0.011998098,0.0058049955,0.0004692042,0.24883586],"study_design_scores_gemma":[0.0024201728,0.0007929274,0.5547088,0.000039083978,0.000088778055,0.0000065538457,0.05065106,0.21928023,0.000055150173,0.17177342,0.00009238653,0.0000914781],"about_ca_topic_score_codex":0.000024258694,"about_ca_topic_score_gemma":0.0013046855,"teacher_disagreement_score":0.2886704,"about_ca_system_score_codex":0.000389264,"about_ca_system_score_gemma":0.0015053024,"threshold_uncertainty_score":0.9950571},"labels":[],"label_agreement":null},{"id":"W4389686508","doi":"10.56645/jmde.v19i46.893","title":"In Plain Sight or Just Plain Obscured?: A Review of Professional Evaluation Associations’ Frameworks for Evaluation Practice Supporting Equity, Diversity and Inclusion (EDI)","year":2023,"lang":"en","type":"review","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Inclusion (mineral); Equity (law); Professional development; Diversity (politics); Presentation (obstetrics); Psychology; Medical education; Pedagogy; Political science; Medicine","score_opus":0.5524989813377544,"score_gpt":0.6559057552488365,"score_spread":0.1034067739110821,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389686508","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023558047,0.97348636,0.00092701206,0.0053871647,0.0044613234,0.012947388,0.00021320401,0.000018290282,0.00020346078],"genre_scores_gemma":[0.0039156186,0.9905691,0.00282873,0.00018070874,0.0008953361,0.0006753307,0.0006814814,0.000058316662,0.00019537257],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.95092255,0.014424432,0.008913349,0.0011288899,0.023932712,0.0006780382],"domain_scores_gemma":[0.94518626,0.020781595,0.017649569,0.00067679957,0.015484086,0.00022166282],"candidate_categories":["metaresearch","metaepi_narrow","sts","open_science"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.31691056,0.00056866766,0.002625308,0.0019089653,0.002522973,0.00012407046,0.001235999,0.0009848885,0.00088429655],"category_scores_gemma":[0.14731929,0.00039129274,0.00073849206,0.0026778728,0.00010456747,0.002784206,0.008485941,0.0015191116,0.000019102199],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043922724,0.00074793986,0.00027589835,0.015305371,0.0002969877,0.000008203097,0.011348998,0.0014194138,0.000004191086,0.00007849206,0.0058936453,0.96418166],"study_design_scores_gemma":[0.014767063,0.0023107608,0.006568525,0.2561881,0.022296961,0.00021069832,0.00989009,0.57657784,0.00000981687,0.03924856,0.070271775,0.0016598135],"about_ca_topic_score_codex":0.000014813881,"about_ca_topic_score_gemma":0.00015135073,"teacher_disagreement_score":0.9625218,"about_ca_system_score_codex":0.0029367865,"about_ca_system_score_gemma":0.009255413,"threshold_uncertainty_score":0.9998539},"labels":[],"label_agreement":null},{"id":"W4389686746","doi":"10.56645/jmde.v19i46.881","title":"Glocal Evaluation Competencies for Learning As We Go: Zooming in and zooming out to connect system-level solutions to local beneficiaries","year":2023,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Roads University; Canadian Evaluation Society","funders":"","keywords":"Glocalization; Perspective (graphical); Beneficiary; Zoom; Knowledge management; Adaptation (eye); Computer science; Psychology; Business; Artificial intelligence; Political science; Engineering; Globalization","score_opus":0.4029661667108118,"score_gpt":0.5222759465913903,"score_spread":0.1193097798805785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389686746","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88381404,0.0002803104,0.10382751,0.009085377,0.0011136907,0.0016276402,0.0000149621565,0.00002976219,0.00020668881],"genre_scores_gemma":[0.98980224,0.00003085094,0.009435663,0.00006489865,0.00022657774,0.00018347865,0.000020341951,0.000019961013,0.00021601004],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9920462,0.0011359656,0.0017799952,0.00046944065,0.0041228095,0.00044561614],"domain_scores_gemma":[0.9926208,0.0028839738,0.00078909984,0.00025402042,0.0032104491,0.00024165468],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04928083,0.00022563753,0.00053068716,0.0016113017,0.00078364555,0.0002892465,0.00036490214,0.000119790486,0.00010243789],"category_scores_gemma":[0.009994521,0.00018658458,0.00014985986,0.0013077897,0.000055601588,0.0008626751,0.00027057025,0.00027310182,0.00023491576],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004436224,0.00006876039,0.007457181,0.00004209575,0.000033938075,0.0000038629205,0.023582777,0.7740499,0.0053216303,0.0006949222,0.000732809,0.18756852],"study_design_scores_gemma":[0.0018057653,0.00075560616,0.0825835,0.00041493052,0.00008434526,0.000021100883,0.07144132,0.83811575,0.00015985416,0.0039765527,0.00043730414,0.00020397933],"about_ca_topic_score_codex":0.00002731569,"about_ca_topic_score_gemma":0.0013111486,"teacher_disagreement_score":0.18736453,"about_ca_system_score_codex":0.0009541228,"about_ca_system_score_gemma":0.0011220343,"threshold_uncertainty_score":0.9983447},"labels":[],"label_agreement":null},{"id":"W4389938261","doi":"10.5489/cuaj.8669","title":"Aiming to bridge the CUA diversity gap","year":2023,"lang":"en","type":"article","venue":"Canadian Urological Association Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Bridge (graph theory); Diversity (politics); Political science; Biology","score_opus":0.27535172734347274,"score_gpt":0.42317821002480166,"score_spread":0.14782648268132892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389938261","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7154948,0.0000119424,0.0003253213,0.2726098,0.000903626,0.00012617081,0.000022429746,0.000030194395,0.010475707],"genre_scores_gemma":[0.9785154,0.000014066358,0.0000319315,0.016663382,0.00042761918,0.0000034449527,0.0000030113758,0.0000030395531,0.004338108],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99695045,0.00044293192,0.0003533523,0.00018149275,0.0016353356,0.00043643432],"domain_scores_gemma":[0.9975362,0.0010122517,0.00022473183,0.00016318995,0.0005061924,0.0005574809],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.010386786,0.0000765577,0.00013159774,0.00031740984,0.0018202395,0.00047401883,0.00070382404,0.00009006177,0.0028784056],"category_scores_gemma":[0.0058777267,0.00004554088,0.00010642249,0.0012500356,0.000019492909,0.00020872174,0.00015943227,0.00036143794,0.0044192164],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000040364916,0.0000027832323,0.6669358,1.0540122e-7,0.000010770756,0.000010402699,0.00073787855,0.0013202939,0.0000049329424,0.00052992377,0.31345984,0.016983213],"study_design_scores_gemma":[0.00009352446,0.000033216522,0.7012017,8.696634e-7,0.000004729957,0.000006648828,0.0002738465,0.0015928944,0.0000010981147,0.00633824,0.29040307,0.000050161318],"about_ca_topic_score_codex":0.0007749066,"about_ca_topic_score_gemma":0.0037110944,"teacher_disagreement_score":0.2630206,"about_ca_system_score_codex":0.0005915913,"about_ca_system_score_gemma":0.0003993019,"threshold_uncertainty_score":0.99947923},"labels":[],"label_agreement":null},{"id":"W4390063387","doi":"10.3138/cjpe-2023-0009","title":"Employing Mixed-Methods Citation Analysis to Investigate Transnational Influence in Evaluation Theory","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Citation; Affordance; Co-citation; Citation analysis; Equity (law); Epistemology; Sociology; Computer science; Management science; Psychology; Political science; Library science; Cognitive psychology; Engineering","score_opus":0.42274354534197994,"score_gpt":0.6040932728385231,"score_spread":0.18134972749654316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390063387","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9741107,0.00009521019,0.018127846,0.005214405,0.00064983143,0.001349468,0.000009885438,0.00001945928,0.0004231458],"genre_scores_gemma":[0.98083174,0.0000034297766,0.018358387,0.00032531604,0.000065609864,0.00027547538,0.000070999675,0.00001190027,0.00005715309],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9888796,0.004398391,0.001618092,0.00037266887,0.004342473,0.00038876932],"domain_scores_gemma":[0.9906521,0.0013819396,0.00068343285,0.00032641902,0.0063880505,0.00056806346],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1153402,0.000161575,0.0003478362,0.007092511,0.00022561442,0.0005020689,0.0005370692,0.000107061176,0.0012389243],"category_scores_gemma":[0.020361125,0.00014278576,0.0001992242,0.012645658,0.000085632644,0.0012173826,0.000015072157,0.00024464444,0.00009881776],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013108234,0.000013601996,0.044141717,0.0000023026003,0.00006697612,0.0000019486674,0.0028562618,0.3743249,0.00019753717,0.0021663222,0.00020212555,0.5760132],"study_design_scores_gemma":[0.00047562868,0.00012387718,0.6083519,0.000018085499,0.00025849338,0.0000028862737,0.001555897,0.31773058,0.00010890442,0.07003208,0.0012260213,0.00011567205],"about_ca_topic_score_codex":0.00022070759,"about_ca_topic_score_gemma":0.03098234,"teacher_disagreement_score":0.5758975,"about_ca_system_score_codex":0.0008197234,"about_ca_system_score_gemma":0.005815459,"threshold_uncertainty_score":0.99982065},"labels":[],"label_agreement":null},{"id":"W4390063458","doi":"10.3138/cjpe-2023-0023","title":"The “What” and “Why” of (Un)Ethical Evaluation Practice: A Meta-Narrative Review and Ethical Awareness Framework","year":2023,"lang":"en","type":"review","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta; Ontario Council of University Libraries; Wilfrid Laurier University; University of Toronto; University Health Network; Centre for Addiction and Mental Health; The Wilson Centre; York University","funders":"","keywords":"Engineering ethics; Reflexivity; Beneficence; Meta-ethics; Stewardship (theology); Deliberation; Stakeholder; Psychology; Nursing ethics; Sociology; Autonomy; Political science; Public relations; Social science","score_opus":0.7245374058454952,"score_gpt":0.6765867511534138,"score_spread":0.047950654692081374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390063458","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000015676338,0.96384436,0.0002709942,0.030351868,0.00080589927,0.004594354,0.000017769396,0.000007443311,0.000091650116],"genre_scores_gemma":[0.00023456661,0.9953223,0.0018283941,0.001472348,0.00017558521,0.00087124034,0.000032880194,0.00003080875,0.000031917243],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9756916,0.013654107,0.0034450686,0.00056893565,0.0062390086,0.00040128522],"domain_scores_gemma":[0.9697052,0.013135863,0.0048336037,0.0006778727,0.01102675,0.00062069006],"candidate_categories":["metaresearch","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14897496,0.00041099006,0.0022665304,0.00068806915,0.00074264675,0.0012379948,0.0007608492,0.0010367518,0.0009205521],"category_scores_gemma":[0.10091639,0.00022834259,0.00059230725,0.0020644078,0.0005670407,0.00074323226,0.00007063391,0.002869944,0.000022581977],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006600183,0.000013391867,0.0000038158696,0.0013377118,0.00090109545,0.000004350697,0.0013140698,0.000020934058,1.0421344e-8,0.0016936717,0.0022903793,0.992414],"study_design_scores_gemma":[0.00032924136,0.00045679923,0.000060372764,0.013986586,0.029292688,0.0002645887,0.002744756,0.0026947751,1.6674504e-7,0.032844212,0.9170368,0.00028903282],"about_ca_topic_score_codex":0.00013612826,"about_ca_topic_score_gemma":0.0032374135,"teacher_disagreement_score":0.9921249,"about_ca_system_score_codex":0.00038988102,"about_ca_system_score_gemma":0.017980648,"threshold_uncertainty_score":0.9999927},"labels":[],"label_agreement":null},{"id":"W4390063483","doi":"10.3138/cjpe.75810","title":"Community-Based Evaluation When Localizing Sustainable Development Goals","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Centre for Community Based Research","funders":"","keywords":"Participatory evaluation; Stakeholder; Sustainable development; Citizen journalism; Key (lock); Process management; Evaluation methods; Sustainable community; Community development; Business; Environmental resource management; Environmental planning; Knowledge management; Management science; Computer science; Political science; Public relations; Public administration; Economics; Engineering; Geography","score_opus":0.5017879788631601,"score_gpt":0.5574306116824358,"score_spread":0.05564263281927573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390063483","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9719763,0.0004065289,0.0067844614,0.008587378,0.0012574637,0.0036633369,0.0000059261524,0.00007250836,0.0072461087],"genre_scores_gemma":[0.9936293,0.0000022777651,0.004777479,0.00045189794,0.00010996119,0.00024266199,0.00011663345,0.00001765011,0.00065213646],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9898707,0.00305211,0.0013817357,0.00020823296,0.00493413,0.0005530938],"domain_scores_gemma":[0.9882078,0.0005560784,0.0008632783,0.0004718197,0.009364788,0.0005361917],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.099131025,0.00016876649,0.00028808884,0.001974496,0.0010445687,0.00077853625,0.0007802155,0.00010889274,0.002730119],"category_scores_gemma":[0.007340849,0.00014157026,0.00012701895,0.0020798394,0.00009787946,0.0008645336,0.000033843502,0.00040426024,0.00039535572],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001963134,0.0000611585,0.013280076,0.000024320274,0.0000387399,0.000012503874,0.0062443274,0.049685504,0.000028149963,0.00037273194,0.02116461,0.9090682],"study_design_scores_gemma":[0.0022889548,0.00049175456,0.08274983,0.0001302984,0.00014787499,0.000013906038,0.019511065,0.42959568,0.00047410524,0.030287223,0.4339945,0.00031479652],"about_ca_topic_score_codex":0.00094399706,"about_ca_topic_score_gemma":0.01424585,"teacher_disagreement_score":0.90875345,"about_ca_system_score_codex":0.0015682804,"about_ca_system_score_gemma":0.021665888,"threshold_uncertainty_score":0.9981815},"labels":[],"label_agreement":null},{"id":"W4390063624","doi":"10.3138/cjpe-2023-0024","title":"Arts-Based Evaluation","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Victoria","funders":"Lawson Foundation","keywords":"The arts; Recreation; Arts in education; Painting; Narrative; Psychology; Sociology; Visual arts; Political science; Art","score_opus":0.6412074581239966,"score_gpt":0.6406298731733805,"score_spread":0.0005775849506161057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390063624","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96531266,0.00041695553,0.0021009415,0.012025829,0.0033885404,0.0027291789,0.000013664444,0.000057170422,0.013955038],"genre_scores_gemma":[0.99747604,0.0000040349178,0.0015452979,0.0003005405,0.00025249133,0.00014836303,0.000050000726,0.000012174703,0.00021107923],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9919808,0.0008629073,0.0010698449,0.00023332017,0.005507024,0.00034608413],"domain_scores_gemma":[0.9909841,0.00040689268,0.0007507324,0.00038007647,0.006973712,0.00050452614],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.054079473,0.00012579236,0.00022361515,0.0016933026,0.0002766247,0.00049466913,0.0004985392,0.000088594505,0.007026814],"category_scores_gemma":[0.008443646,0.000099412166,0.00016906457,0.0024111792,0.000079577614,0.0006323497,0.000009040995,0.00018718353,0.0009740839],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001057377,0.000020671412,0.01625752,0.0000024827286,0.000014759703,0.0000048433853,0.00039842387,0.03873305,0.000049316663,0.0002624975,0.016180906,0.92806494],"study_design_scores_gemma":[0.001285175,0.00034764665,0.15001616,0.000035524674,0.00010250969,0.000011224344,0.0007622966,0.7266079,0.00015010068,0.015221345,0.10532564,0.0001344755],"about_ca_topic_score_codex":0.00017954096,"about_ca_topic_score_gemma":0.009371943,"teacher_disagreement_score":0.9279305,"about_ca_system_score_codex":0.00056701485,"about_ca_system_score_gemma":0.01254243,"threshold_uncertainty_score":0.9999086},"labels":[{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"qualitative","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"qualitative","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W4390063627","doi":"10.3138/cjpe.75803","title":"Contribution Analysis of a Complex System During Disruptions","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Outreach; Occupational safety and health; Agriculture; Business; Coronavirus disease 2019 (COVID-19); Environmental planning; Environmental resource management; Political science; Environmental health; Geography; Environmental science; Medicine","score_opus":0.4378081056136442,"score_gpt":0.5552920873869361,"score_spread":0.11748398177329195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390063627","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9961111,0.000069354544,0.0013703277,0.0007982436,0.00037478717,0.00056748756,0.000050357685,0.00001837628,0.0006399423],"genre_scores_gemma":[0.99939257,0.0000037859534,0.00032174718,0.000012995054,0.00006571659,0.00003828939,0.00009185193,0.000004674053,0.000068346744],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99588466,0.0005055701,0.0011532287,0.000147902,0.0020766642,0.00023198985],"domain_scores_gemma":[0.9935427,0.00022752576,0.0009564211,0.0002627465,0.004701613,0.00030904257],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.013125517,0.00008298945,0.00035387537,0.0028479744,0.00024272117,0.00018072531,0.0003085265,0.000054835637,0.0010723589],"category_scores_gemma":[0.0021935909,0.000066387736,0.00027085902,0.0056132358,0.00006902678,0.00036005458,0.000011193618,0.000098211516,0.000077413446],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006425007,0.00009424471,0.4008028,0.00004319039,0.0014484285,0.000026988739,0.003913636,0.21091902,0.0018511481,0.006457801,0.0025825663,0.37179592],"study_design_scores_gemma":[0.0004297599,0.000084715,0.63373005,0.000024767423,0.0005576401,0.000007992104,0.0016553757,0.3613187,0.000065076965,0.00032576686,0.0017474015,0.00005271913],"about_ca_topic_score_codex":0.00036961256,"about_ca_topic_score_gemma":0.013774366,"teacher_disagreement_score":0.37174323,"about_ca_system_score_codex":0.00049583067,"about_ca_system_score_gemma":0.0016034062,"threshold_uncertainty_score":0.9998408},"labels":[],"label_agreement":null},{"id":"W4390104865","doi":"10.33524/cjar.v22i3.640","title":"ARNA Conference – Hosted by the Yellowhead Tribal College","year":2022,"lang":"en","type":"article","venue":"The Canadian Journal of Action Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Participatory action research; Social justice; Citizen journalism; Political science; Action (physics); Action research; Economic Justice; Sociology; Engineering ethics; Engineering; Pedagogy; Criminology; Law","score_opus":0.6877486907512952,"score_gpt":0.596748167511259,"score_spread":0.09100052324003616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390104865","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74408257,0.00038605608,0.00014774899,0.21823376,0.0016772613,0.0004755807,0.00014087187,0.000004326344,0.03485182],"genre_scores_gemma":[0.9737513,0.000021935233,0.000008893365,0.0005997457,0.00011615845,0.000012741544,0.0000017963671,0.0000048650422,0.025482532],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99274665,0.00255006,0.00046464914,0.0001200418,0.003783566,0.00033505113],"domain_scores_gemma":[0.9961796,0.0012214902,0.0002653525,0.00036657826,0.0016395565,0.0003274207],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02979935,0.00006141623,0.00012714176,0.0004814043,0.003102741,0.0004374201,0.0015565101,0.000028021648,0.014927179],"category_scores_gemma":[0.0013569524,0.00003174913,0.00007893972,0.0015769815,0.00033281368,0.0002434732,0.00006658709,0.00123941,0.00014052178],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008560537,0.000020572597,0.00121269,8.8224994e-7,0.000024555933,0.000019559013,0.001868345,0.00076070614,0.00062342355,0.0036713684,0.96989864,0.021813635],"study_design_scores_gemma":[0.00043613525,0.00032853233,0.0068727476,0.0000044857907,0.0000055246023,0.00018491103,0.025721168,0.0030132253,0.00034831342,0.005829019,0.9571998,0.000056122382],"about_ca_topic_score_codex":0.0064301775,"about_ca_topic_score_gemma":0.072434366,"teacher_disagreement_score":0.22966877,"about_ca_system_score_codex":0.0006112574,"about_ca_system_score_gemma":0.0070090215,"threshold_uncertainty_score":0.99902576},"labels":[],"label_agreement":null},{"id":"W4390104890","doi":"10.33524/cjar.v22i3.642","title":"Invitation to a Virtual Talk with Dr. Roula Hawa","year":2022,"lang":"en","type":"article","venue":"The Canadian Journal of Action Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Action research; Presentation (obstetrics); Participatory action research; Curriculum; Citizen journalism; Noon; Psychology; Pedagogy; Mathematics education; Media studies; Sociology; Computer science; Medicine; World Wide Web","score_opus":0.597681172439479,"score_gpt":0.5978460786209567,"score_spread":0.00016490618147768643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390104890","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.894684,0.000028010429,0.000831688,0.098724425,0.00050023344,0.00023965622,0.000009856931,0.0000025287768,0.0049795927],"genre_scores_gemma":[0.99206936,0.000002370284,0.00009155629,0.0011424797,0.00012644508,0.000016716462,0.0000011847412,0.000006085625,0.006543802],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9943338,0.0012058555,0.00034505056,0.00011838414,0.0037365658,0.00026034156],"domain_scores_gemma":[0.9969619,0.0006736129,0.00017020591,0.00025592485,0.0015058165,0.00043252017],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.019635322,0.000051182644,0.0001001778,0.0011920021,0.0016877914,0.00043313755,0.0007297958,0.000018177734,0.0075842156],"category_scores_gemma":[0.0010616665,0.000030373638,0.000040984713,0.0018909231,0.00010092326,0.00035746102,0.000044955126,0.00070717867,0.0001193191],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000740798,0.00006801966,0.012942579,0.0000030940669,0.00007440608,0.00014242076,0.018384736,0.16448918,0.0016655738,0.008227081,0.58965963,0.2036025],"study_design_scores_gemma":[0.00051292626,0.0020700074,0.040049013,0.000011373933,0.000006427034,0.00029157565,0.044946734,0.0025257682,0.00035416067,0.0059745302,0.9031614,0.00009610496],"about_ca_topic_score_codex":0.0070788655,"about_ca_topic_score_gemma":0.18147258,"teacher_disagreement_score":0.31350178,"about_ca_system_score_codex":0.00073201035,"about_ca_system_score_gemma":0.004295311,"threshold_uncertainty_score":0.99961185},"labels":[],"label_agreement":null},{"id":"W4390117787","doi":"10.33524/cjar.v23i2.671","title":"New Podcast: Episode #10 of Participatory Action Research Feminist Trailblazers &amp; Good Troublemakers","year":2023,"lang":"en","type":"article","venue":"The Canadian Journal of Action Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Demise; Action research; Participatory action research; Reflexivity; Feminism; Sociology; Citizen journalism; Action (physics); Masculinity; Gender studies; Political science; Pedagogy; Social science; Law; Anthropology","score_opus":0.8742878531723174,"score_gpt":0.6638912725671381,"score_spread":0.2103965806051793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390117787","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.937288,0.00011151805,0.00020187661,0.043257426,0.0011197658,0.00040545478,0.000021135389,0.000012723442,0.017582128],"genre_scores_gemma":[0.9631461,0.00006455729,0.000100897894,0.00007381788,0.00038164188,0.000010622876,0.000003094986,0.000016081043,0.036203217],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9893524,0.002725729,0.0010024132,0.0002538212,0.005820117,0.0008454981],"domain_scores_gemma":[0.9920253,0.0029906596,0.00039015152,0.00063329184,0.0029317953,0.0010287813],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0607407,0.00011209324,0.00027657195,0.0027951244,0.0012928958,0.00050414633,0.0011723341,0.00010944401,0.008633332],"category_scores_gemma":[0.004953524,0.00007608991,0.00017208644,0.0046755336,0.00060745457,0.0005219347,0.000057477642,0.0014158564,0.0017238947],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004485217,0.000042239357,0.01677317,0.00002383576,0.000101536854,0.000038162863,0.006723745,0.0025188783,0.0029831114,0.0027612518,0.84906596,0.118519574],"study_design_scores_gemma":[0.0009173348,0.0006806375,0.06602888,0.00008602463,0.000018313578,0.00009636493,0.030670071,0.00150655,0.0033934284,0.0132766245,0.88318026,0.00014552005],"about_ca_topic_score_codex":0.017040981,"about_ca_topic_score_gemma":0.29651076,"teacher_disagreement_score":0.27946976,"about_ca_system_score_codex":0.0007731909,"about_ca_system_score_gemma":0.009709452,"threshold_uncertainty_score":0.99905336},"labels":[],"label_agreement":null},{"id":"W4390120973","doi":"10.33524/cjar.v20i3.503","title":"Call for Article Submissions: Action Research and Indigenous Ways of Knowing","year":2019,"lang":"en","type":"article","venue":"The Canadian Journal of Action Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Nipissing University","funders":"","keywords":"Action research; Indigenous; Action (physics); Call to action; Sociology; Pedagogy; Psychology; Public relations; Political science; Ecology; Business; Biology; Marketing","score_opus":0.8200564594945607,"score_gpt":0.6381159504806944,"score_spread":0.18194050901386638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390120973","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97554404,0.00013591954,0.00019027358,0.021920925,0.00026068813,0.0004303759,0.000004026221,0.000001542018,0.0015122255],"genre_scores_gemma":[0.99674374,0.000050533552,0.00014260403,0.00016159908,0.00016329931,0.000007344781,5.3146016e-7,0.000006838832,0.0027235167],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9958649,0.0007181748,0.00049033,0.00014210831,0.0023587274,0.00042575257],"domain_scores_gemma":[0.9924888,0.0026844775,0.00018616082,0.00030247692,0.0039972113,0.00034087282],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03444231,0.000052819247,0.0001505782,0.0011448383,0.0009818216,0.00031079273,0.0004954457,0.00008177132,0.0007324862],"category_scores_gemma":[0.002825664,0.00003254382,0.00005596323,0.001041488,0.00024655077,0.00047329706,0.000031612475,0.00082317233,0.00008387263],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014019723,0.0002788889,0.211655,0.00017435878,0.0002024202,0.000029472789,0.039163478,0.0026852929,0.09537983,0.0113276215,0.17247981,0.46522185],"study_design_scores_gemma":[0.0027106314,0.005271798,0.22562407,0.00026076165,0.000023869243,0.00024772895,0.06252116,0.014080919,0.057403434,0.09923818,0.53232783,0.00028962438],"about_ca_topic_score_codex":0.0048447642,"about_ca_topic_score_gemma":0.028008722,"teacher_disagreement_score":0.46493223,"about_ca_system_score_codex":0.00035355444,"about_ca_system_score_gemma":0.003553533,"threshold_uncertainty_score":0.9942448},"labels":[],"label_agreement":null},{"id":"W4390343038","doi":"10.1080/1360144x.2023.2286983","title":"A complexity-informed examination of educational development services of a university’s teaching and learning centre","year":2023,"lang":"en","type":"article","venue":"The International Journal for Academic Development","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of Alberta","funders":"","keywords":"Context (archaeology); Psychology; Medical education; Computer science; Mathematics education; Medicine","score_opus":0.1704988529281381,"score_gpt":0.45922389032217115,"score_spread":0.28872503739403305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390343038","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9909524,0.00002891296,0.0007825962,0.005680386,0.0004923051,0.00015966129,0.000005525654,0.0000086163645,0.001889633],"genre_scores_gemma":[0.98085934,0.00008213253,0.0071990755,0.00013269088,0.00007737042,0.0000032726405,0.00004310086,0.000005408257,0.011597595],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.997195,0.00023265035,0.0007356216,0.00013213466,0.0015686293,0.00013596861],"domain_scores_gemma":[0.99604225,0.0023839003,0.0007129487,0.000062053725,0.0007424007,0.00005643056],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010158362,0.000086374515,0.00014129379,0.00049795763,0.0004713318,0.000056888774,0.0007932567,0.000046269844,0.00018768659],"category_scores_gemma":[0.00109849,0.00006093081,0.000043552616,0.00021463391,0.00006250701,0.00035021766,0.0002094326,0.00036906314,0.000025155068],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004143354,0.00011324679,0.07393209,0.00011318781,0.0005260038,0.000002066366,0.15114404,0.0037627732,0.0020898387,0.03596667,0.006068212,0.7258675],"study_design_scores_gemma":[0.0010499618,0.000032065807,0.5647305,0.00028855287,0.000015180408,0.000037766593,0.032503814,0.012135548,0.0016767742,0.0053102034,0.38206244,0.000157136],"about_ca_topic_score_codex":0.000006558741,"about_ca_topic_score_gemma":0.00003104595,"teacher_disagreement_score":0.7257104,"about_ca_system_score_codex":0.00019695603,"about_ca_system_score_gemma":0.0007880093,"threshold_uncertainty_score":0.3625151},"labels":[],"label_agreement":null},{"id":"W4390800683","doi":"10.1515/9780887552908-015","title":"Connections and Disconnections: A Review of the Regional Cumulative Effects Assessment in Northern Manitoba","year":2022,"lang":"en","type":"review","venue":"University of Manitoba Press eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Cumulative effects; Geography; Regional science; Biology; Ecology","score_opus":0.2845217984988502,"score_gpt":0.43334236653395475,"score_spread":0.14882056803510457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390800683","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00033303493,0.9743426,0.000095680065,0.000140317,0.00038512354,0.0023021088,0.00008367616,0.0000150041515,0.022302443],"genre_scores_gemma":[0.00022018017,0.99844635,0.00009916485,0.0000588458,0.000021805534,0.000018844756,0.00001631578,0.000011678128,0.0011068333],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957825,0.0016399404,0.0007210041,0.00044230136,0.0012642262,0.00015002907],"domain_scores_gemma":[0.99527276,0.0024824014,0.0012696328,0.00068617513,0.00023623378,0.000052808966],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019740206,0.00023760168,0.0010854853,0.00031732002,0.00033022324,0.00002601741,0.000904905,0.00009484993,0.00013788302],"category_scores_gemma":[0.00030930273,0.00017447477,0.00042596032,0.00026930711,0.00026459742,0.00013570496,0.0006404981,0.0004928072,0.0000033689291],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016269096,0.00017453391,0.0010549692,0.021895682,0.00024900053,0.000010968527,0.00071655394,0.000048317444,2.6562287e-7,0.010900902,0.0014828214,0.9634497],"study_design_scores_gemma":[0.00031762366,0.00006983931,0.0012127537,0.017259995,0.0004121311,0.00001391956,0.0021465383,0.00007406002,3.875422e-7,0.0003881456,0.97793305,0.00017153552],"about_ca_topic_score_codex":0.0024296374,"about_ca_topic_score_gemma":0.038399465,"teacher_disagreement_score":0.97645026,"about_ca_system_score_codex":0.0003266424,"about_ca_system_score_gemma":0.00068902125,"threshold_uncertainty_score":0.97914726},"labels":[],"label_agreement":null},{"id":"W4390828283","doi":"10.1515/9782760326538-005","title":"CHAPITRE 3 Deuxième étude de cas : changement de programme à l’Université de Sherbrooke","year":2019,"lang":"fr","type":"book-chapter","venue":"University of Ottawa Press eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.1118988515378043,"score_gpt":0.3236774616758091,"score_spread":0.21177861013800478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390828283","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038155686,0.0005806651,0.0029609888,0.0006329526,0.0003500183,0.0011784448,0.00016852717,0.00007808282,0.95589465],"genre_scores_gemma":[0.14189875,0.000753859,0.0056793364,0.0002768451,0.00011753348,0.0000016638999,0.000032437383,0.00005175792,0.8511878],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957919,0.00027399664,0.0005251196,0.00083055435,0.001582325,0.0009960646],"domain_scores_gemma":[0.99664307,0.00036266856,0.0008660459,0.0009810947,0.0005800338,0.0005670784],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0022859068,0.000535907,0.000739766,0.0004544087,0.0005770129,0.00009349695,0.0017338494,0.00063073344,0.0076959673],"category_scores_gemma":[0.00004943628,0.0006192634,0.0005037253,0.00004860085,0.00063500373,0.0002530185,0.0010695085,0.0005185649,0.00042608814],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004223685,0.00024249103,0.019353656,0.00054215966,0.0007138153,0.00042783847,0.029601976,0.0014381044,0.0007318755,0.81317645,0.0048035122,0.12854575],"study_design_scores_gemma":[0.0020383704,0.00047431554,0.010026585,0.00046480616,0.00047115624,0.00004929738,0.001991984,0.0066315313,0.001278771,0.0013576543,0.9745345,0.00068099494],"about_ca_topic_score_codex":0.0047664,"about_ca_topic_score_gemma":0.012422916,"teacher_disagreement_score":0.96973103,"about_ca_system_score_codex":0.0019447091,"about_ca_system_score_gemma":0.001356897,"threshold_uncertainty_score":0.99962586},"labels":[],"label_agreement":null},{"id":"W4390942690","doi":"10.5334/ijic.icic23669","title":"Evaluation Capacity Building for Integrated Care Models in Practice","year":2023,"lang":"en","type":"article","venue":"International Journal of Integrated Care","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Toronto East General Hospital; Trillium Health Centre; University of Toronto","funders":"","keywords":"General partnership; Capacity building; Knowledge management; Health care; Integrated care; Process (computing); Context (archaeology); Process management; Equity (law); Knowledge transfer; Business; Computer science; Political science","score_opus":0.3030801497522244,"score_gpt":0.5239616917149666,"score_spread":0.22088154196274223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390942690","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.946242,0.0007305858,0.036275383,0.0036704082,0.005043647,0.0006943683,0.00027607713,0.000048318554,0.0070192157],"genre_scores_gemma":[0.9924979,0.00010348559,0.006528628,0.00036206242,0.00021449209,0.000045694975,0.00013768172,0.00001676469,0.00009325623],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9927015,0.0005993994,0.0013772317,0.00030351637,0.004786506,0.0002318622],"domain_scores_gemma":[0.9642864,0.0012997652,0.0009519994,0.00021672415,0.03315095,0.00009418466],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0098588,0.00018612148,0.00031659598,0.0016021081,0.00008923043,0.00039670267,0.001091889,0.00013084122,0.00028619627],"category_scores_gemma":[0.013796616,0.00013446191,0.00023344859,0.001387226,0.000046073073,0.0018115598,0.00006436014,0.00045246162,0.000047548914],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008401964,0.00012496686,0.008093636,0.00001583515,0.00035630667,0.00005576104,0.023794385,0.38349864,0.0025305133,0.00632706,0.0073091267,0.56705356],"study_design_scores_gemma":[0.004191348,0.00044899838,0.003216839,0.0005048277,0.00016409474,0.00010026249,0.32626325,0.57988983,0.0046415366,0.02560524,0.05461787,0.00035589517],"about_ca_topic_score_codex":0.00027351393,"about_ca_topic_score_gemma":0.0005749781,"teacher_disagreement_score":0.56669766,"about_ca_system_score_codex":0.0025274043,"about_ca_system_score_gemma":0.002781234,"threshold_uncertainty_score":0.9945106},"labels":[],"label_agreement":null},{"id":"W4391134234","doi":"10.2139/ssrn.4703961","title":"Unveiling the Magic: Simplifying Evidence-Based Practice for Everyone","year":2024,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"MAGIC (telescope); Computer science; Astronomy; Physics","score_opus":0.2193683160275435,"score_gpt":0.5261762190490454,"score_spread":0.30680790302150196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391134234","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020612814,0.061207157,0.8219965,0.09096695,0.002012256,0.000635517,0.0000041199196,0.00008285898,0.002481796],"genre_scores_gemma":[0.98369324,0.002850254,0.0009868139,0.0019017498,0.0009571873,0.000023432889,0.0000013152234,0.000019166378,0.009566843],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956742,0.0004092652,0.0006236887,0.00031583168,0.0016868309,0.0012901615],"domain_scores_gemma":[0.99039626,0.008314396,0.00025595695,0.000323799,0.0006380702,0.000071535535],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0362145,0.00013752974,0.00015655777,0.00021420293,0.00055106165,0.0012291812,0.0007111919,0.00005169944,0.00042153784],"category_scores_gemma":[0.0061858417,0.00007449323,0.00021682677,0.00075493194,0.000048533493,0.0016827635,0.000038098704,0.0013755213,0.0004897898],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00053312135,0.00010362954,0.0010223612,0.000039204948,0.00034110414,0.000011367706,0.0012626984,0.019361869,0.0014402495,0.22607343,0.023476962,0.72633404],"study_design_scores_gemma":[0.00049726956,0.0005939071,0.0001837884,0.00017824546,0.00012243554,0.00038236319,0.008965769,0.16631833,0.00024209374,0.3130683,0.5092336,0.0002138941],"about_ca_topic_score_codex":0.000011491636,"about_ca_topic_score_gemma":0.00009970884,"teacher_disagreement_score":0.9630804,"about_ca_system_score_codex":0.00074097863,"about_ca_system_score_gemma":0.008259768,"threshold_uncertainty_score":0.99980766},"labels":[],"label_agreement":null},{"id":"W4391140116","doi":"10.2139/ssrn.4703699","title":"Risk of Bias in Cross-Sectional Studies: Protocol for a Scoping Review of Concepts and Tools","year":2024,"lang":"en","type":"review","venue":"SSRN Electronic Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Protocol (science); Computer science; Medicine; Alternative medicine","score_opus":0.5827840948920746,"score_gpt":0.6749741694278371,"score_spread":0.09219007453576245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391140116","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000013984811,0.9357882,0.00021862771,0.00003463819,0.00015912461,0.06365734,0.000030661864,0.0000038091632,0.00009361265],"genre_scores_gemma":[0.000007730143,0.9582778,0.000103368366,0.000020502865,0.00016054658,0.041090377,0.0000033314632,0.000016448608,0.00031989877],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.99360394,0.0007751433,0.0031724842,0.0003998854,0.0013215316,0.00072699034],"domain_scores_gemma":[0.9932846,0.0027240738,0.0027516237,0.00025970757,0.00093284587,0.000047145575],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.042249948,0.0002652899,0.0019013534,0.0004790872,0.0001034991,0.00016637925,0.00046857263,0.00012705495,0.000119086406],"category_scores_gemma":[0.007128762,0.00015349252,0.0006215766,0.00082699285,0.00014404488,0.00037653063,0.0001032962,0.001351682,0.0000120886825],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022781387,0.000025937803,0.0007548267,0.12712865,0.00030649404,3.9963902e-7,0.00006746664,0.000005158305,5.278153e-8,0.0035067457,0.00013270129,0.8680488],"study_design_scores_gemma":[0.001105617,0.00079289585,0.00008864537,0.6846081,0.00042949207,0.0001909017,0.00039161698,0.000040881652,7.751454e-7,0.050689157,0.26138353,0.00027837523],"about_ca_topic_score_codex":0.0000036300844,"about_ca_topic_score_gemma":0.00017210786,"teacher_disagreement_score":0.86777043,"about_ca_system_score_codex":0.00061606464,"about_ca_system_score_gemma":0.013681592,"threshold_uncertainty_score":0.9919099},"labels":[],"label_agreement":null},{"id":"W4391157879","doi":"10.7202/1108607ar","title":"La rigueur en recherche-développement : risques et tensions dans l’opérationnalisation de la démarche","year":2023,"lang":"fr","type":"article","venue":"Recherches qualitatives","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières; Université de Sherbrooke","funders":"","keywords":"Operationalization; Rigour; Process (computing); Process management; Engineering ethics; Epistemology; Management science; Political science; Psychology; Risk analysis (engineering); Computer science; Engineering; Business; Philosophy","score_opus":0.8037453369100962,"score_gpt":0.6763974219061654,"score_spread":0.12734791500393083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391157879","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2744713,0.0028642223,0.19861923,0.36576903,0.0015399475,0.0011943851,0.00017808407,0.0005612914,0.15480249],"genre_scores_gemma":[0.43989775,0.020808494,0.3571363,0.004070402,0.00071046816,0.00045349763,0.00027631046,0.00016342374,0.17648333],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.83147657,0.16263801,0.001806409,0.00092830823,0.0023505152,0.0008001727],"domain_scores_gemma":[0.8623628,0.13528445,0.0005494484,0.0005999731,0.0009021777,0.00030115814],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2266176,0.00043212285,0.0005548845,0.0007034531,0.00030910494,0.00064422155,0.0007819979,0.0010389725,0.0008908827],"category_scores_gemma":[0.08419998,0.00037369394,0.00030109994,0.0031381864,0.00070862,0.0013492946,0.00032408178,0.0017036296,0.0019514728],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000092231116,0.00037759542,0.00278517,0.00011093176,0.00019020631,0.000029894572,0.59328914,0.001935974,0.0053269947,0.10814115,0.027916653,0.2598041],"study_design_scores_gemma":[0.001015945,0.00032993776,0.09170947,0.00047484486,0.000110982706,0.00002537354,0.16912167,0.021954674,0.0022844414,0.46027604,0.2520851,0.0006115177],"about_ca_topic_score_codex":0.00042133103,"about_ca_topic_score_gemma":0.00035539232,"teacher_disagreement_score":0.42416745,"about_ca_system_score_codex":0.0024260976,"about_ca_system_score_gemma":0.0043176846,"threshold_uncertainty_score":0.9998715},"labels":[],"label_agreement":null},{"id":"W4391531407","doi":"10.31124/advance.24898458.v1","title":"PoliticalExistentialism","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Politics; Political science; Law","score_opus":0.41686425971900565,"score_gpt":0.5958206599209434,"score_spread":0.1789564002019377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391531407","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020967579,0.00028266813,0.0022235187,0.021807108,0.006213682,0.00021184528,0.000040407005,0.00016039639,0.9480928],"genre_scores_gemma":[0.79244065,0.000015642578,0.001597505,0.0015705938,0.0005027409,0.000029658546,0.000016811493,0.000011671399,0.20381473],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9960892,0.00012081977,0.0006815942,0.00060640124,0.0022994394,0.00020255428],"domain_scores_gemma":[0.99817616,0.0002969727,0.00009494017,0.0009444904,0.00036171527,0.00012571916],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003268076,0.00015489642,0.00025596964,0.0003257092,0.00004648649,0.0011249671,0.0007798142,0.00017906677,0.029747436],"category_scores_gemma":[0.00044458767,0.00009547043,0.00025065304,0.00023803492,0.000061144456,0.00004790688,0.0021870097,0.00053435774,0.02278641],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002402684,0.000021941662,0.00021183623,0.000031697702,0.000028059578,0.0000065869726,0.00025006605,0.00020423613,0.000011161055,0.7814573,0.1913383,0.026436377],"study_design_scores_gemma":[0.00003843936,0.000008633251,0.0007960713,0.00002779524,0.000018445675,0.0000023433536,0.00015895504,0.019325778,0.00006473515,0.83143175,0.14800231,0.00012471962],"about_ca_topic_score_codex":0.00005126618,"about_ca_topic_score_gemma":0.000029797517,"teacher_disagreement_score":0.77147305,"about_ca_system_score_codex":0.000060692902,"about_ca_system_score_gemma":0.00058411236,"threshold_uncertainty_score":0.99991196},"labels":[],"label_agreement":null},{"id":"W4391657081","doi":"10.18260/1-2--38449","title":"The Use of Mixed Methods in Academic Program Evaluation","year":2024,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"York University","keywords":"Computer science","score_opus":0.7821025008569673,"score_gpt":0.7203396528799191,"score_spread":0.06176284797704823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391657081","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84834784,0.0032267638,0.097296976,0.01942504,0.0043955464,0.004472038,0.00000525331,0.0002184983,0.022612056],"genre_scores_gemma":[0.89020157,0.00023724991,0.102385685,0.00016496384,0.000049895327,0.00040211694,0.000003579956,0.000007460697,0.006547451],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962078,0.001142017,0.00065609737,0.00020526287,0.0016665272,0.00012235006],"domain_scores_gemma":[0.99480325,0.004507308,0.00007956354,0.00027765782,0.00030631386,0.00002592238],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.030216573,0.00005382349,0.00009627452,0.00019179063,0.00004827611,0.00025158297,0.00027647332,0.00005300882,0.00096183526],"category_scores_gemma":[0.0035159467,0.000025620642,0.000051301085,0.0011262629,0.000055100507,0.00046504787,0.000053607087,0.00016484731,0.000120173216],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004337468,0.000009866066,0.0023556089,0.0000017180823,0.0000037183022,7.545143e-8,0.0002152822,0.00083002564,0.0003162768,0.005749638,0.005744752,0.9847687],"study_design_scores_gemma":[0.00007696381,0.000032468422,0.037055366,0.000012991299,0.000006418225,5.11232e-7,0.00031001086,0.66065264,0.0009910312,0.014186531,0.28664243,0.000032640073],"about_ca_topic_score_codex":0.000016666429,"about_ca_topic_score_gemma":0.0001298372,"teacher_disagreement_score":0.9847361,"about_ca_system_score_codex":0.000044481127,"about_ca_system_score_gemma":0.00028822434,"threshold_uncertainty_score":0.9999514},"labels":[],"label_agreement":null},{"id":"W4391686139","doi":"10.1093/reseval/rvae003","title":"Effective mission-oriented research: A new framework for systemic research impact assessment","year":2024,"lang":"en","type":"article","venue":"Research Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Research England; Leibniz-Gemeinschaft; Consortium of International Agricultural Research Centers; Ontario Agri-Food Innovation Alliance; Commonwealth Scientific and Industrial Research Organisation; International Livestock Research Institute; European Commission; Bundesministerium für Bildung und Forschung; FP7 International Cooperation; Strong; Stockholm Environment Institute; UK Research and Innovation; Overseas Development Institute; International Development Research Centre; University of Arizona; World Bank Group","keywords":"Knowledge management; Sociology; Process management; Business; Management science; Computer science; Engineering","score_opus":0.8249377954287089,"score_gpt":0.7852370493509188,"score_spread":0.03970074607779017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391686139","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.63402236,0.010103737,0.24428093,0.049584113,0.003133887,0.034876566,0.00008851809,0.0003991772,0.023510695],"genre_scores_gemma":[0.9840298,0.00020629741,0.004833025,0.000034575827,0.0015036585,0.0024368688,0.00009428356,0.00006387914,0.0067975638],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.92321545,0.027217204,0.0014949087,0.0021155968,0.043664165,0.0022927066],"domain_scores_gemma":[0.901672,0.07490498,0.00015144145,0.0019558584,0.020351253,0.00096447085],"candidate_categories":["metaresearch","sts","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.40534937,0.0002850837,0.00047185563,0.0052365516,0.0020436367,0.0029582835,0.0014580189,0.000395608,0.0052945437],"category_scores_gemma":[0.089870095,0.00019504587,0.00033590334,0.012187185,0.0004432184,0.0012289875,0.00046645955,0.003150561,0.0034972765],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.0005106367,0.0002493821,0.0013047662,0.0001769078,0.0001547216,0.000015146178,0.0062044146,0.0020673263,0.0051346766,0.08672649,0.33240294,0.5650526],"study_design_scores_gemma":[0.0008637587,0.001704995,0.007275739,0.0011485555,0.000020769206,0.00001853035,0.0051848083,0.4895765,0.00070975133,0.42934775,0.0639428,0.00020607557],"about_ca_topic_score_codex":0.000336158,"about_ca_topic_score_gemma":0.00004591451,"teacher_disagreement_score":0.5648465,"about_ca_system_score_codex":0.005280017,"about_ca_system_score_gemma":0.016150668,"threshold_uncertainty_score":0.99925554},"labels":[],"label_agreement":null},{"id":"W4391738934","doi":"10.1177/0013161x241230527","title":"Management Practices and Implementation Challenges in District Education Directorates in Ghana","year":2024,"lang":"en","type":"article","venue":"Educational Administration Quarterly","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University of Ottawa","funders":"Foreign, Commonwealth and Development Office","keywords":"Bureaucracy; Accountability; Incentive; Focus group; Context (archaeology); Public relations; Political science; Politics; Sociology; Public administration; Business; Economics; Marketing","score_opus":0.1776085598623689,"score_gpt":0.5356547615527024,"score_spread":0.3580462016903335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391738934","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90804833,0.0032243333,0.000046716836,0.070932046,0.0012411526,0.0005378612,0.00001364799,0.000027370854,0.015928518],"genre_scores_gemma":[0.995938,0.0003239973,0.0007587444,0.00009851621,0.00018868456,0.0003251715,0.00009804388,0.0000071286076,0.0022617239],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99754936,0.00022994648,0.0007010901,0.0004997886,0.0008531538,0.00016665827],"domain_scores_gemma":[0.9983933,0.0008949118,0.00029946127,0.00019558454,0.00014467638,0.00007206448],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0024906015,0.00012989715,0.00012754666,0.0006931298,0.000062910556,0.0006385538,0.00016188998,0.00004825761,0.0012249392],"category_scores_gemma":[0.00016679567,0.00011593964,0.000028051285,0.00078777585,0.000020906285,0.0013515104,0.000010849065,0.00012093549,0.00021372914],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023426464,0.00037268957,0.0546138,0.00007966424,0.000015190824,0.0000037989882,0.005963859,0.000004902129,0.000031792286,0.1080706,0.0024455513,0.82837474],"study_design_scores_gemma":[0.00026253803,0.00026130924,0.86645776,0.00009027696,0.000013174351,0.000014046011,0.057128962,0.0010379913,0.000058515645,0.033318132,0.041152295,0.00020499139],"about_ca_topic_score_codex":0.0000816433,"about_ca_topic_score_gemma":0.003216567,"teacher_disagreement_score":0.82816976,"about_ca_system_score_codex":0.00029782363,"about_ca_system_score_gemma":0.0011782219,"threshold_uncertainty_score":0.9996881},"labels":[],"label_agreement":null},{"id":"W4391790392","doi":"10.1177/20531680241233439","title":"Promoting Reproducibility and Replicability in Political Science","year":2024,"lang":"en","type":"article","venue":"Research & Politics","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Laura and John Arnold Foundation","keywords":"Reproducibility; Politics; Political science; Data science; Psychology; Computer science; Statistics; Mathematics; Law","score_opus":0.5427626271480739,"score_gpt":0.6652534810633781,"score_spread":0.12249085391530423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391790392","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95727533,0.0001485951,0.000031987158,0.023151128,0.00013518817,0.00036290096,0.000007792864,0.000042944914,0.018844126],"genre_scores_gemma":[0.99831474,0.000009672979,0.0003253799,0.00014102779,0.00014581333,0.000023920355,7.6676673e-7,0.0000067493625,0.0010319075],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99048537,0.0008822721,0.00075001846,0.0020756563,0.0043828236,0.0014238415],"domain_scores_gemma":[0.9915569,0.003998198,0.000028514773,0.002555364,0.0012525093,0.00060850586],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14922385,0.00009134643,0.00017996554,0.00083013216,0.00035606782,0.0010229275,0.0006336092,0.000055035805,0.00023838556],"category_scores_gemma":[0.081856795,0.00006637618,0.000037372865,0.0024710838,0.0019972823,0.000658947,0.00061316584,0.00063283404,0.00019834575],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000056380486,0.00010709342,0.17979506,0.00007710597,0.0000020575974,0.000013823033,0.002750179,0.0000025305292,0.001395801,0.7848968,0.0003171401,0.030636778],"study_design_scores_gemma":[0.000095114665,0.00010977819,0.4067348,0.0000616375,0.000001369988,0.000016887894,0.0013817414,0.056999065,0.0036907117,0.5231546,0.007654347,0.000099936464],"about_ca_topic_score_codex":0.00042836057,"about_ca_topic_score_gemma":0.00007676868,"teacher_disagreement_score":0.26174217,"about_ca_system_score_codex":0.0007914108,"about_ca_system_score_gemma":0.0030411694,"threshold_uncertainty_score":0.9864113},"labels":[],"label_agreement":null},{"id":"W4391885740","doi":"10.17483/2368-6669.1420","title":"Adaptation de l’instrument « Évaluation de l’environnement d’apprentissage clinique » : ajout de la composante de la dynamique de groupe","year":2024,"lang":"fr","type":"article","venue":"Quality Advancement in Nursing Education - Avancées en formation infirmière","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Université de Moncton","funders":"","keywords":"Humanities; Psychology; Art","score_opus":0.0944614982996397,"score_gpt":0.5061953327756262,"score_spread":0.41173383447598655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391885740","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32377186,0.0027982425,0.6383116,0.014274094,0.002364752,0.0011959259,0.0000629355,0.00014960952,0.017070962],"genre_scores_gemma":[0.909279,0.0055492804,0.08141495,0.00084702804,0.00037462375,0.0005992481,0.00043447647,0.000051189025,0.0014502197],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9863565,0.0080370195,0.0023996532,0.00070481206,0.0015290465,0.00097300054],"domain_scores_gemma":[0.99471444,0.0032622581,0.00082951266,0.0005825065,0.00026212947,0.0003491431],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.028541682,0.00048431917,0.0004611535,0.00081720424,0.00050785625,0.0010798966,0.0005121216,0.00050544104,0.0011272674],"category_scores_gemma":[0.0011200459,0.0005509243,0.00021989676,0.0008917105,0.00042676428,0.002736768,0.00006915818,0.0009041693,0.00014339157],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009617407,0.0015212137,0.008458074,0.00052026036,0.00003733289,0.000003102284,0.05766022,0.115956776,0.0012264556,0.19437853,0.0009714382,0.6191704],"study_design_scores_gemma":[0.0010789769,0.00021683754,0.046856094,0.0035485309,0.00011508434,0.000108782355,0.031185878,0.6543136,0.0014169115,0.15457653,0.10602179,0.000560967],"about_ca_topic_score_codex":0.00038818194,"about_ca_topic_score_gemma":0.00021731068,"teacher_disagreement_score":0.6186094,"about_ca_system_score_codex":0.009998745,"about_ca_system_score_gemma":0.004813797,"threshold_uncertainty_score":0.9999571},"labels":[],"label_agreement":null},{"id":"W4392059009","doi":"10.4337/9781839105722.00020","title":"Methods development in evidence synthesis: a dialogue between science and society","year":2024,"lang":"en","type":"book-chapter","venue":"Edward Elgar Publishing eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Stanford Bio-X; McGill University","keywords":"Engineering ethics; Political science; Epistemology; Engineering; Philosophy","score_opus":0.2674267436399957,"score_gpt":0.46999453915591877,"score_spread":0.20256779551592308,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392059009","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011532994,0.0013411137,0.0016612806,0.0027683282,0.0016502321,0.0007157594,0.00002667417,0.00016925564,0.99051404],"genre_scores_gemma":[0.08847827,0.00023852041,0.1029443,0.0020366446,0.0014249336,0.0003192116,0.000018834808,0.00018007364,0.8043592],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9905083,0.00021494388,0.0015504919,0.00166251,0.0054404084,0.0006233021],"domain_scores_gemma":[0.99137175,0.0056041162,0.00053315156,0.00093318254,0.0012146599,0.00034316673],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.061025366,0.00048479447,0.00080567674,0.0012617537,0.0004690108,0.007786747,0.0022364673,0.00047337753,0.00031497874],"category_scores_gemma":[0.011867327,0.00037935015,0.00019389049,0.00040225845,0.00072282413,0.002679407,0.0015182905,0.0013236448,0.00027941947],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008739828,0.0000068394847,0.0006344503,0.00010684181,0.00007905569,0.000010216828,0.007667249,0.0000050015647,0.000066285545,0.05786817,0.014598049,0.9189491],"study_design_scores_gemma":[0.00016918329,0.00003474182,0.0036007564,0.0016777145,0.00008051334,0.000007914701,0.00039691923,0.00064098387,0.0006657175,0.09849166,0.8935276,0.0007062719],"about_ca_topic_score_codex":0.00004698594,"about_ca_topic_score_gemma":0.00014944177,"teacher_disagreement_score":0.9182428,"about_ca_system_score_codex":0.0008643842,"about_ca_system_score_gemma":0.004842528,"threshold_uncertainty_score":0.99986583},"labels":[],"label_agreement":null},{"id":"W4392171788","doi":"10.1177/16094069241234187","title":"Premature Closure of Analysis in Qualitative Research: Identifying Features and Mitigation Strategies","year":2024,"lang":"en","type":"article","venue":"International Journal of Qualitative Methods","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland; University of Calgary","funders":"","keywords":"Closure (psychology); Qualitative research; Qualitative analysis; Computer science; Risk analysis (engineering); Data science; Management science; Process management; Political science; Sociology; Business; Engineering; Social science","score_opus":0.8653576621623321,"score_gpt":0.8002145646638936,"score_spread":0.0651430974984385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392171788","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69325596,0.0059899315,0.28885797,0.0077411043,0.001078661,0.00017032883,0.000058216454,0.000008219053,0.0028396195],"genre_scores_gemma":[0.88909733,0.00016487742,0.11016516,0.00004047584,0.000100332094,0.000004871957,0.000005821351,0.000005955463,0.0004151686],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9763196,0.017866563,0.0016255735,0.00028611545,0.0037486416,0.00015349548],"domain_scores_gemma":[0.97356117,0.021392832,0.0006865885,0.00013875174,0.0041545685,0.0000661151],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.111591816,0.00011629286,0.0004476869,0.0034155995,0.000051355837,0.0006050846,0.0005529847,0.00008312254,0.00027019088],"category_scores_gemma":[0.009774686,0.000079635334,0.00024577076,0.0024809076,0.0003050576,0.0015014353,0.000087521614,0.0005972998,0.000004328747],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022229037,0.00007642584,0.0019876903,0.000057727342,0.0014645192,0.000028505985,0.7790658,0.0015908141,0.006580409,0.1706106,0.0011631311,0.03715211],"study_design_scores_gemma":[0.00029230522,0.00013909653,0.033477318,0.00027112247,0.00007215581,0.000017921991,0.45688757,0.0021579177,0.0025368587,0.5033794,0.00068371906,0.000084592444],"about_ca_topic_score_codex":0.000057257083,"about_ca_topic_score_gemma":0.00014512739,"teacher_disagreement_score":0.3327688,"about_ca_system_score_codex":0.00012818743,"about_ca_system_score_gemma":0.00042037692,"threshold_uncertainty_score":0.9985664},"labels":[],"label_agreement":null},{"id":"W4392608258","doi":"10.56279/tjpsd.v30i2.221","title":"Opportunities and Challenges for Professionalizing Monitoring and Evaluation Practice: A Global Overview and Perspectives","year":2023,"lang":"en","type":"article","venue":"Tanzania Journal for Population studies and Development","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Engineering ethics; Political science; Engineering","score_opus":0.752449976007623,"score_gpt":0.5977017265390756,"score_spread":0.15474824946854737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392608258","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79792595,0.1772028,0.00041642206,0.022536866,0.00075222075,0.0009989908,0.000010724024,0.000027128935,0.0001288724],"genre_scores_gemma":[0.78402007,0.1984142,0.0165562,0.00012663654,0.00023168087,0.00024043821,0.000008374436,0.000011508481,0.00039090324],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9980831,0.00013752963,0.00050845486,0.0002722494,0.0008318662,0.00016676952],"domain_scores_gemma":[0.99743384,0.00093314314,0.0003436017,0.00005882567,0.001137511,0.0000930879],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0074713104,0.0001317711,0.00024832934,0.00014081452,0.001216069,0.00023706154,0.0000430876,0.000038674367,0.0000063199673],"category_scores_gemma":[0.0014618698,0.00009292332,0.000020836109,0.00012040417,0.000045588276,0.0006394843,0.00011076081,0.000051332245,6.695685e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013812551,0.000019971378,0.028311592,0.00020807397,0.00018293971,0.0000011461459,0.025909264,0.000030710744,0.000007373132,0.013606034,0.0006979627,0.9308868],"study_design_scores_gemma":[0.0012610772,0.00013921558,0.6298868,0.00025858174,0.00006729344,0.00006114179,0.2788911,0.0018748186,0.0000040682166,0.023623329,0.06375371,0.000178884],"about_ca_topic_score_codex":0.0000023654407,"about_ca_topic_score_gemma":0.000015641415,"teacher_disagreement_score":0.93070793,"about_ca_system_score_codex":0.00010006589,"about_ca_system_score_gemma":0.000138387,"threshold_uncertainty_score":0.9353143},"labels":[],"label_agreement":null},{"id":"W4392609533","doi":"10.12930/nacadajournal-d-22-31","title":"Academic Advising in Ontario: A Multiple Case Study","year":2023,"lang":"en","type":"article","venue":"NACADA Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"George Brown College","funders":"","keywords":"Academic advising; Higher education; Psychology; Pedagogy; Mathematics education; Sociology; Political science","score_opus":0.3930035173261196,"score_gpt":0.5456588985564538,"score_spread":0.15265538123033418,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392609533","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9971941,0.000034988527,0.00011076472,0.0007545741,0.00073382107,0.00019636027,7.9972057e-7,0.000021955528,0.0009526194],"genre_scores_gemma":[0.99664354,0.000014662495,0.00015502101,0.00019969298,0.00015416813,0.0000075453863,5.4123024e-7,0.0000072210714,0.0028176112],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99621147,0.0003550799,0.00089525996,0.00024154302,0.0019899434,0.0003066876],"domain_scores_gemma":[0.9983672,0.00081797695,0.0002555663,0.00020886913,0.00019907227,0.00015133701],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011984469,0.000103894185,0.00020386005,0.00075498456,0.00032812558,0.00024274726,0.0004066282,0.00007989062,0.0018962967],"category_scores_gemma":[0.0012123259,0.00007431944,0.00006783803,0.0012657508,0.000020182322,0.0006466219,0.00010629785,0.0013400532,0.00061640533],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019583029,0.000038667797,0.9401053,3.9681365e-7,0.0000066042135,0.002230459,0.009654512,0.0022087162,0.000070363574,0.000006393159,0.0028518287,0.04280718],"study_design_scores_gemma":[0.0022950347,0.00018450244,0.8904699,0.000028442135,0.000008953986,0.0040132203,0.059086557,0.020027157,0.000021268072,0.001629021,0.022073464,0.00016245928],"about_ca_topic_score_codex":0.0073826713,"about_ca_topic_score_gemma":0.20757198,"teacher_disagreement_score":0.2001893,"about_ca_system_score_codex":0.0002985587,"about_ca_system_score_gemma":0.000671522,"threshold_uncertainty_score":0.9992272},"labels":[],"label_agreement":null},{"id":"W4392681658","doi":"10.22318/icls2023.645029","title":"Situating Evaluation: Theory Driven Evaluation in Practice","year":2023,"lang":"en","type":"article","venue":"Proceedings.","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University; Trent University","funders":"","keywords":"Autoethnography; Knowledge management; Computer science; Sociology; Engineering ethics; Management science; Social science; Engineering","score_opus":0.3177210124840651,"score_gpt":0.5597948644746129,"score_spread":0.24207385199054782,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392681658","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6501712,0.0001259029,0.00019378464,0.0058037024,0.0005879386,0.0012255766,0.0000018855471,0.00014310858,0.3417469],"genre_scores_gemma":[0.99664605,0.00003523663,0.0013535909,0.0005445853,0.00017861224,0.00032555722,0.000014872841,0.000012251168,0.000889221],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9916617,0.00040668377,0.0007979491,0.00056793506,0.0062403968,0.00032529226],"domain_scores_gemma":[0.9945824,0.0012699238,0.00041591082,0.00020901376,0.0034493317,0.0000734308],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.07276905,0.00013150823,0.00018333133,0.0006313874,0.00020982423,0.00038731334,0.00043208277,0.00007791772,0.0024091324],"category_scores_gemma":[0.037350815,0.00010659929,0.000054129177,0.0031461846,0.000040607716,0.0018410685,0.00012756007,0.00020291422,0.0025770508],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000091940434,0.00011966961,0.067635044,0.000015963116,0.00003090562,0.0000020122623,0.018534034,0.009864305,0.0012328774,0.041413035,0.015519459,0.84554076],"study_design_scores_gemma":[0.00094944995,0.00005910199,0.08774962,0.000043230433,0.000057088608,0.00000488254,0.019975493,0.8069899,0.00020896502,0.0723581,0.011434051,0.00017011761],"about_ca_topic_score_codex":0.0000060598363,"about_ca_topic_score_gemma":0.000021561102,"teacher_disagreement_score":0.84537065,"about_ca_system_score_codex":0.00025653525,"about_ca_system_score_gemma":0.00047216384,"threshold_uncertainty_score":0.9985028},"labels":[],"label_agreement":null},{"id":"W4392736519","doi":"10.48550/arxiv.2403.05647","title":"Minor Issues Escalated to Critical Levels in Large Samples: A Permutation-Based Fix","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Michael Smith Health Research BC; Alliance de recherche numérique du Canada; Western Canada Research Grid","keywords":"Minor (academic); Permutation (music); Mathematics; Statistics; Political science; Philosophy; Law","score_opus":0.41361698413674314,"score_gpt":0.4140297358051339,"score_spread":0.00041275166839077615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392736519","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9526189,0.00009482997,0.03903263,0.0037365507,0.0008647781,0.00049743784,0.00033922493,0.00011704871,0.002698592],"genre_scores_gemma":[0.9929757,0.000010678925,0.0007897066,0.0006574522,0.0000785009,0.0000051183442,0.000046225843,0.000020595606,0.0054159956],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99663097,0.0004067715,0.0005936804,0.0013228545,0.00061390456,0.00043184153],"domain_scores_gemma":[0.9967809,0.0013432535,0.0001269152,0.00087265385,0.00062151864,0.00025477636],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0024342553,0.00030787193,0.00046538463,0.0011925426,0.00013004,0.00037917928,0.0010066853,0.0002959398,0.0045187036],"category_scores_gemma":[0.0017411051,0.00029459212,0.00022869847,0.001818616,0.000081954975,0.0002039053,0.00083018583,0.0006449954,0.0029596887],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020155706,0.00056594395,0.091805704,0.0002717183,0.00008710785,0.000612417,0.004705154,0.7743975,0.00011963967,0.11663172,0.0078621255,0.0027393987],"study_design_scores_gemma":[0.00064382015,0.000087437584,0.06878829,0.00029916546,0.000076628414,0.0000010732034,0.0019597914,0.8090769,0.00012313575,0.11245266,0.0059722373,0.0005188432],"about_ca_topic_score_codex":0.0002143099,"about_ca_topic_score_gemma":0.0011797207,"teacher_disagreement_score":0.04035682,"about_ca_system_score_codex":0.00033760726,"about_ca_system_score_gemma":0.0008626657,"threshold_uncertainty_score":0.99995065},"labels":[],"label_agreement":null},{"id":"W4392756290","doi":"10.1177/15586898241238875","title":"Fostering Equity and Diversity Through Essential Mixed Methods Research Inclusive Language Practices","year":2024,"lang":"en","type":"article","venue":"Journal of Mixed Methods Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Equity (law); Diversity (politics); Sociology; Multimethodology; Political science; Public relations; Pedagogy; Anthropology","score_opus":0.8054900074738737,"score_gpt":0.7893809467249846,"score_spread":0.01610906074888907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392756290","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46425658,0.013472099,0.4631007,0.020603962,0.0042493464,0.000697313,0.000017845674,0.000035239515,0.033566907],"genre_scores_gemma":[0.46466127,0.0014599054,0.5311249,0.00007082182,0.00078518066,0.000009116925,0.0000010958203,0.000021483349,0.0018662126],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9444444,0.041804653,0.0014216214,0.000760742,0.010628202,0.0009403685],"domain_scores_gemma":[0.94508797,0.04880711,0.00068720646,0.0006534165,0.004380142,0.00038416195],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.36111483,0.00018205632,0.0005709952,0.0017688647,0.0014908025,0.0018712993,0.0018918888,0.00019465764,0.001231477],"category_scores_gemma":[0.06317635,0.00012493652,0.00021927463,0.003048481,0.0005990665,0.0024484035,0.019379733,0.002724581,0.00008409832],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028207514,0.00008582018,0.00027305132,0.00009865621,0.00012310862,0.00018331791,0.015174168,0.000024150257,0.077479124,0.0018511969,0.009547931,0.8948774],"study_design_scores_gemma":[0.0016355289,0.0017470536,0.010466465,0.00053326046,0.00013003331,0.000560073,0.13043958,0.016027333,0.17687798,0.46602383,0.19507383,0.0004850411],"about_ca_topic_score_codex":0.00026760154,"about_ca_topic_score_gemma":0.00012276269,"teacher_disagreement_score":0.8943924,"about_ca_system_score_codex":0.0004126656,"about_ca_system_score_gemma":0.0014243079,"threshold_uncertainty_score":0.99980915},"labels":[],"label_agreement":null},{"id":"W4392775921","doi":"10.1177/10982140241234841","title":"Mapping Evaluation Use: A Scoping Review of Extant Literature (2005–2022)","year":2024,"lang":"en","type":"review","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; Queen's University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Extant taxon; Program evaluation; Management science; Evaluation methods; Psychology; Sociology; Political science; Engineering; Public administration","score_opus":0.39634967058603965,"score_gpt":0.6096230452322937,"score_spread":0.21327337464625407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392775921","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000047225232,0.99410397,0.00076650654,0.0005753961,0.0015928156,0.00248639,0.00003457269,0.00000987375,0.00038323013],"genre_scores_gemma":[0.00007774415,0.9972134,0.0014383523,0.00033727786,0.0004686073,0.00012360937,0.00010418015,0.000042311916,0.0001944651],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.97617716,0.0058172015,0.0057619554,0.0006198691,0.011292386,0.00033141996],"domain_scores_gemma":[0.9775426,0.0020879463,0.010425425,0.0008989124,0.008858827,0.00018633748],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08210161,0.0004954277,0.003228513,0.0022347497,0.000099798395,0.00047345928,0.00079279626,0.00015114101,0.003571033],"category_scores_gemma":[0.013857627,0.00031171687,0.0012804766,0.0053604445,0.00015733393,0.0012461083,0.00012556795,0.00084522355,0.0001614961],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000069015305,0.000032559125,0.000004615372,0.02486003,0.00017081601,0.0000046671103,0.0003594472,0.000053113843,0.0000017470636,0.000021729977,0.0040309858,0.9704534],"study_design_scores_gemma":[0.00022872418,0.00028628894,0.000022891936,0.7237769,0.0032567356,0.0002522659,0.00023331163,0.0031331268,8.0390106e-7,0.00042631428,0.2681032,0.0002794889],"about_ca_topic_score_codex":0.0000038114915,"about_ca_topic_score_gemma":0.000007560161,"teacher_disagreement_score":0.9701739,"about_ca_system_score_codex":0.0007985375,"about_ca_system_score_gemma":0.009483951,"threshold_uncertainty_score":0.9999335},"labels":[],"label_agreement":null},{"id":"W4392819524","doi":"","title":"Performance-based accountability systems: types, instrumental logics and effects on effectiveness and equity in educational systems in Europe and Canada. A comparative study using PISA 2012.","year":2017,"lang":"fr","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Accountability; Equity (law); Political science; Mathematics education; Accounting; Economics; Psychology; Law","score_opus":0.11704807524260268,"score_gpt":0.40231302057826684,"score_spread":0.28526494533566416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392819524","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98967296,0.0021464918,0.00030305624,0.0010636117,0.0007988712,0.002406897,0.00008075674,0.000012198596,0.0035151376],"genre_scores_gemma":[0.9985845,0.00031355332,0.0003920549,0.000033384826,0.00002310952,0.00017087687,0.000062371175,0.000016478369,0.0004036616],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98192936,0.01447719,0.00091045356,0.0011143078,0.001188902,0.00037981203],"domain_scores_gemma":[0.98898125,0.0069485847,0.00081706594,0.0012355966,0.0018027269,0.00021475583],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.022013936,0.00043448666,0.00081467966,0.00033397615,0.0006796319,0.0011849756,0.00076131895,0.0001869496,0.000028524515],"category_scores_gemma":[0.0016164839,0.00040141173,0.000031777945,0.00042899934,0.00045032898,0.0005540458,0.0011029094,0.0006443438,0.0000059523736],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000121644094,0.00097530946,0.96669674,0.0008788237,0.000041604668,0.000003988083,0.005307218,0.004348359,0.0001427616,0.004276035,0.000032075255,0.017175468],"study_design_scores_gemma":[0.0015013879,0.000008328753,0.7588389,0.003988177,0.000029808638,0.000008953525,0.001030213,0.23344748,0.00020210564,0.00009868247,0.00053505815,0.00031094602],"about_ca_topic_score_codex":0.3559349,"about_ca_topic_score_gemma":0.53649426,"teacher_disagreement_score":0.22909911,"about_ca_system_score_codex":0.0010720601,"about_ca_system_score_gemma":0.003274248,"threshold_uncertainty_score":0.9998519},"labels":[],"label_agreement":null},{"id":"W4392825504","doi":"10.29173/jaed262","title":"Program Evaluation In A Northern Aboriginal Setting: Assessing Impact and Benefit Agreements","year":2008,"lang":"en","type":"article","venue":"Journal of Aboriginal Economic Development","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Guelph","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Environmental planning; Environmental resource management; Business; Geography; Environmental science","score_opus":0.10738559755386341,"score_gpt":0.49886750775503147,"score_spread":0.39148191020116807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392825504","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99652606,0.00019529309,0.000154818,0.00041334255,0.0005167419,0.00039634632,0.0000017317803,0.0000072744506,0.0017883695],"genre_scores_gemma":[0.98460513,0.00016209816,0.014788258,0.000066434106,0.00014943758,0.000028990287,0.000004433784,0.000010482277,0.00018470884],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99612355,0.00011334114,0.0016800694,0.00029887393,0.001471754,0.00031243404],"domain_scores_gemma":[0.99748296,0.00019123561,0.001248158,0.00018125432,0.00069526554,0.00020110479],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008262853,0.00020611238,0.0004221958,0.00068151165,0.00019290492,0.00030511574,0.00035630792,0.000061131745,0.0005269881],"category_scores_gemma":[0.00007982965,0.00015286417,0.000094388284,0.00029141793,0.000060159527,0.0014260702,0.000025562522,0.00023957448,0.00009488072],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005401765,0.000106251486,0.71194106,0.0000029489122,0.00003931399,0.000016714655,0.001615844,0.0049899006,0.000022305514,0.00003362873,0.00017421854,0.28100377],"study_design_scores_gemma":[0.0016354198,0.0002029058,0.9197068,0.00006040898,0.00001614555,0.0002402835,0.00050805183,0.010082561,0.00009042737,0.0008006596,0.06647091,0.00018542915],"about_ca_topic_score_codex":0.000032885593,"about_ca_topic_score_gemma":0.00063644996,"teacher_disagreement_score":0.28081834,"about_ca_system_score_codex":0.0014964159,"about_ca_system_score_gemma":0.0053853835,"threshold_uncertainty_score":0.95534396},"labels":[],"label_agreement":null},{"id":"W4392959364","doi":"10.1177/10497323241237411","title":"The Use of Vignettes to Improve the Validity of Qualitative Interviews for Realist Evaluation","year":2024,"lang":"en","type":"article","venue":"Qualitative Health Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Rimouski; Université de Sherbrooke","funders":"","keywords":"Vignette; Data collection; Qualitative research; Context (archaeology); Focus group; Psychology; Perception; Focus (optics); Process (computing); Applied psychology; Computer science; Social psychology; Sociology","score_opus":0.9732759034260431,"score_gpt":0.8093841111144409,"score_spread":0.16389179231160222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392959364","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31538936,0.0050087203,0.12691848,0.52649873,0.0023294531,0.019605944,0.00229701,0.000053159492,0.0018991516],"genre_scores_gemma":[0.9807826,0.0004831705,0.009095514,0.0016363031,0.00020275622,0.0026649917,0.00005838859,0.000032035096,0.0050442214],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9259629,0.060497932,0.002951052,0.0008103237,0.008989201,0.0007885517],"domain_scores_gemma":[0.8467332,0.14408642,0.0005124914,0.0009002757,0.0076039685,0.0001636295],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.33252904,0.00013192695,0.00038734626,0.00041905095,0.00070679816,0.00036019678,0.0008201405,0.000050635885,0.00019476181],"category_scores_gemma":[0.060147155,0.00006257656,0.00017845692,0.002135939,0.0006527556,0.00039893997,0.00018229106,0.00036532723,0.00008439889],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019340956,0.000057776244,0.000019316418,0.00023733858,0.000040083607,5.615601e-8,0.48954165,0.00009616948,0.000360266,0.106049694,0.15507153,0.24833271],"study_design_scores_gemma":[0.00038199453,0.0027796282,0.0011686861,0.00028149958,0.000012410608,2.7800561e-7,0.4021434,0.05089292,0.0013819752,0.23113482,0.3097043,0.00011809794],"about_ca_topic_score_codex":0.00092601095,"about_ca_topic_score_gemma":0.0014929704,"teacher_disagreement_score":0.66539323,"about_ca_system_score_codex":0.00032800465,"about_ca_system_score_gemma":0.002267256,"threshold_uncertainty_score":0.94776964},"labels":[],"label_agreement":null},{"id":"W4392971412","doi":"10.1111/medu.15374","title":"‘Good’ evaluation: Methodological diversity may be empress, but sound methods remain queen","year":2024,"lang":"en","type":"letter","venue":"Medical Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Wilson Centre; University of Toronto; Centre for Addiction and Mental Health","funders":"","keywords":"Queen (butterfly); Diversity (politics); Sound (geography); Sociology; Anthropology; Biology; Ecology; Acoustics","score_opus":0.5639421722179152,"score_gpt":0.6388402463653121,"score_spread":0.07489807414739691,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392971412","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005428326,0.00083802314,0.021747287,0.9335989,0.011178155,0.00078170904,0.000033147102,0.00010946769,0.031170491],"genre_scores_gemma":[0.0013480571,0.00013728396,0.035606496,0.8965604,0.008431843,0.00030340455,0.0008526331,0.000039547765,0.056720387],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9725493,0.011413952,0.0014505935,0.0014549734,0.0126122,0.0005189349],"domain_scores_gemma":[0.9872571,0.008781968,0.00066476373,0.001387329,0.0016077998,0.0003010018],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity","insufficient_payload"],"category_scores_codex":[0.07136259,0.00044632377,0.00083002646,0.0006341794,0.0005380371,0.00055934035,0.0019961935,0.001681944,0.06489109],"category_scores_gemma":[0.04859901,0.00031121256,0.00039413915,0.0010981704,0.00039033106,0.00039266227,0.001096517,0.0029810662,0.0017141814],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007918303,0.00007572374,0.00057614467,0.000047574293,0.000052745352,0.000011311512,0.00064040185,0.000006851653,0.0000011198613,0.00063851295,0.87625927,0.12168241],"study_design_scores_gemma":[0.00020179623,0.00005878576,0.0016481105,0.000097208125,0.0002589775,0.000024103316,0.00054873805,0.0038148575,0.000013383064,0.13080224,0.8622056,0.0003261927],"about_ca_topic_score_codex":0.0003369135,"about_ca_topic_score_gemma":0.000045960627,"teacher_disagreement_score":0.13016373,"about_ca_system_score_codex":0.00062600453,"about_ca_system_score_gemma":0.0077291327,"threshold_uncertainty_score":0.999934},"labels":[],"label_agreement":null},{"id":"W4393032589","doi":"10.3819/ccbr.2024.190011","title":"Comparative Cognition Needs to Focus More on Outreach","year":2024,"lang":"en","type":"article","venue":"Comparative Cognition & Behavior Reviews","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Comparative cognition; Outreach; Focus (optics); Cognition; Psychology; Animal behavior; Cognitive science; Animal cognition; Cognitive psychology; Neuroscience; Zoology; Biology; Political science; Physics","score_opus":0.592033304971624,"score_gpt":0.592116662660835,"score_spread":0.0000833576892109722,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393032589","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7153431,0.014414109,0.02481851,0.0070743486,0.0039727255,0.0136826495,0.00086945907,0.0007013829,0.21912372],"genre_scores_gemma":[0.99107355,0.0003500013,0.0006297644,0.0016369994,0.0002470216,0.0020697603,0.00031646728,0.000022182203,0.0036542807],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99435425,0.0009775409,0.0015397212,0.0008883348,0.0018448032,0.00039537967],"domain_scores_gemma":[0.9966472,0.00090050977,0.0003530885,0.00060905324,0.0011475617,0.0003426018],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0029162215,0.0004921536,0.0011156081,0.0010486424,0.00035718628,0.0007856622,0.00050769217,0.00010574039,0.00663021],"category_scores_gemma":[0.00028670463,0.00035195082,0.0003892699,0.002718399,0.00016222867,0.000805103,0.000103786,0.00046767658,0.037308525],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028830417,0.0014752684,0.0012577544,0.00008362995,0.00011620307,0.00004376152,0.029301472,0.00012223101,0.008066504,0.0067497734,0.3531586,0.5993365],"study_design_scores_gemma":[0.001090894,0.0012045639,0.024937494,0.0014434342,0.00061555696,0.00003545816,0.008474895,0.0026057505,0.011936174,0.0028537582,0.9437306,0.0010714213],"about_ca_topic_score_codex":0.000005429122,"about_ca_topic_score_gemma":0.000053127937,"teacher_disagreement_score":0.5982651,"about_ca_system_score_codex":0.00016297284,"about_ca_system_score_gemma":0.0001758926,"threshold_uncertainty_score":0.99989325},"labels":[],"label_agreement":null},{"id":"W4393152943","doi":"10.1609/aaai.v38i17.29845","title":"Accelerating the Global Aggregation of Local Explanations","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Azrieli Foundation; German-Israeli Foundation for Scientific Research and Development; Deutsche Forschungsgemeinschaft; Open Philanthropy Project","keywords":"Economic geography; Economics","score_opus":0.3793026277643469,"score_gpt":0.48442412767895365,"score_spread":0.10512149991460673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393152943","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77650017,0.00018565558,0.058791496,0.03266884,0.0019781606,0.00094753184,0.00005358117,0.00009585273,0.12877871],"genre_scores_gemma":[0.99912834,0.000025061116,0.00027924278,0.00014822697,0.0000692812,0.000020821333,6.9258977e-7,0.0000045323677,0.0003238029],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971861,0.000037801972,0.0008308502,0.00029805664,0.0014865198,0.00016065309],"domain_scores_gemma":[0.9976784,0.0004667928,0.00036577205,0.00022156972,0.001227702,0.000039789415],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002542596,0.000121947654,0.00016807721,0.000106722066,0.00022099185,0.0004320232,0.0011562469,0.00005464391,0.0007792808],"category_scores_gemma":[0.0011544487,0.0000629208,0.00012084403,0.0013953358,0.0003552284,0.00044284732,0.00014411274,0.00018861447,0.00018483789],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016103468,0.00002781743,0.00059861795,0.000011551671,0.0000084305975,5.988192e-8,0.0009386697,0.0004916668,0.0015437477,0.73435354,0.00038980794,0.26162],"study_design_scores_gemma":[0.000015674615,0.0001054276,0.0012369136,0.0002491808,0.000019021158,0.0000032664773,0.00898544,0.33984733,0.17626056,0.4723663,0.000805316,0.000105579675],"about_ca_topic_score_codex":0.000040983035,"about_ca_topic_score_gemma":0.00006850935,"teacher_disagreement_score":0.33935565,"about_ca_system_score_codex":0.000064981796,"about_ca_system_score_gemma":0.000262479,"threshold_uncertainty_score":0.85325783},"labels":[],"label_agreement":null},{"id":"W4393164122","doi":"10.1162/qss_a_00304","title":"Evaluating approaches to identifying research supporting the United Nations Sustainable Development Goals","year":2024,"lang":"en","type":"article","venue":"Quantitative Science Studies","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Syddansk Universitet","keywords":"Sustainable development; Environmental resource management; Environmental planning; Political science; Process management; Management science; Computer science; Business; Geography; Environmental science; Engineering","score_opus":0.949022836235384,"score_gpt":0.7319454571991254,"score_spread":0.21707737903625857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393164122","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9334505,0.0018576321,0.010965532,0.027527116,0.0008346418,0.0014211319,0.0000033768645,0.00010944327,0.02383061],"genre_scores_gemma":[0.9625672,0.000052105068,0.025717655,0.0001616837,0.000049229922,0.00033209135,0.0000019075455,0.000009843418,0.0111082755],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9898106,0.0008994358,0.0009152647,0.0009027241,0.0065735565,0.00089842966],"domain_scores_gemma":[0.9799379,0.012673833,0.0002041071,0.0005765517,0.0064479113,0.00015971262],"candidate_categories":["metaresearch","bibliometrics","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11910436,0.00016160507,0.00022757518,0.006716428,0.0066707362,0.0023629586,0.001361139,0.000022592289,0.00013688527],"category_scores_gemma":[0.056620564,0.00009056928,0.000056899877,0.039412785,0.0014364227,0.0016138235,0.0011258352,0.00031614458,0.000923418],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007986477,0.00002706846,0.0009380445,0.000057702953,0.000054514843,0.0000066579637,0.18562846,0.004448491,0.0014006292,0.78697294,0.004189975,0.016267538],"study_design_scores_gemma":[0.00008659874,0.00019328688,0.0113186445,0.00017955639,0.000011977575,0.000002463413,0.8384319,0.06536562,0.0029061483,0.03904654,0.04224575,0.00021151692],"about_ca_topic_score_codex":0.000056604043,"about_ca_topic_score_gemma":0.00021577526,"teacher_disagreement_score":0.7479264,"about_ca_system_score_codex":0.00046818203,"about_ca_system_score_gemma":0.0021825624,"threshold_uncertainty_score":0.9998545},"labels":[],"label_agreement":null},{"id":"W4393535247","doi":"10.5281/zenodo.6797876","title":"Touché20-Argument-Retrieval-for-Comparative-Questions","year":2020,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Optech (Canada)","funders":"","keywords":"Argument (complex analysis); Computer science; Epistemology; Information retrieval; Philosophy; Biology","score_opus":0.27489454462019003,"score_gpt":0.4476513850146947,"score_spread":0.17275684039450467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393535247","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007506125,0.00006265615,0.0032183493,0.002731539,0.00053200487,0.0012330007,0.9774435,0.00035928484,0.01434458],"genre_scores_gemma":[0.0012081831,0.0002167617,0.00035028512,0.0007208345,0.00050876325,2.8028552e-7,0.99427396,0.00053299684,0.002187932],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9942778,0.0009482343,0.00094521866,0.0010140176,0.0023200864,0.0004946771],"domain_scores_gemma":[0.99511915,0.00034681408,0.0005719253,0.0012033656,0.00236779,0.000390953],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0038013777,0.0003373242,0.00051318604,0.00066201825,0.0031459029,0.0030217099,0.0033284414,0.00019465388,0.07025425],"category_scores_gemma":[0.004888222,0.00030339666,0.00019312545,0.001613769,0.00022706744,0.00050827634,0.0015507136,0.00061791006,0.0976819],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012699646,0.00011544594,3.0398976e-7,0.00004060446,0.000055358625,0.0000032893754,0.00031499108,0.000094116185,0.00009801886,0.0007141044,0.98868275,0.009754003],"study_design_scores_gemma":[0.00065019756,0.00055321614,0.00006792048,0.000040149833,0.00005056341,0.00001735038,0.0003566594,0.00085403264,0.00006797304,0.00072472706,0.9962803,0.00033689657],"about_ca_topic_score_codex":0.000010800258,"about_ca_topic_score_gemma":0.0000014139206,"teacher_disagreement_score":0.027427647,"about_ca_system_score_codex":0.00027829845,"about_ca_system_score_gemma":0.00004802394,"threshold_uncertainty_score":0.9999418},"labels":[],"label_agreement":null},{"id":"W4393569295","doi":"10.5281/zenodo.6797875","title":"Touché20-Argument-Retrieval-for-Comparative-Questions","year":2020,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Optech (Canada)","funders":"","keywords":"Argument (complex analysis); Computer science; Information retrieval; Epistemology; Philosophy; Chemistry","score_opus":0.27489454462019003,"score_gpt":0.4476513850146947,"score_spread":0.17275684039450467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393569295","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007506125,0.00006265615,0.0032183493,0.002731539,0.00053200487,0.0012330007,0.9774435,0.00035928484,0.01434458],"genre_scores_gemma":[0.0012081831,0.0002167617,0.00035028512,0.0007208345,0.00050876325,2.8028552e-7,0.99427396,0.00053299684,0.002187932],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9942778,0.0009482343,0.00094521866,0.0010140176,0.0023200864,0.0004946771],"domain_scores_gemma":[0.99511915,0.00034681408,0.0005719253,0.0012033656,0.00236779,0.000390953],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0038013777,0.0003373242,0.00051318604,0.00066201825,0.0031459029,0.0030217099,0.0033284414,0.00019465388,0.07025425],"category_scores_gemma":[0.004888222,0.00030339666,0.00019312545,0.001613769,0.00022706744,0.00050827634,0.0015507136,0.00061791006,0.0976819],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012699646,0.00011544594,3.0398976e-7,0.00004060446,0.000055358625,0.0000032893754,0.00031499108,0.000094116185,0.00009801886,0.0007141044,0.98868275,0.009754003],"study_design_scores_gemma":[0.00065019756,0.00055321614,0.00006792048,0.000040149833,0.00005056341,0.00001735038,0.0003566594,0.00085403264,0.00006797304,0.00072472706,0.9962803,0.00033689657],"about_ca_topic_score_codex":0.000010800258,"about_ca_topic_score_gemma":0.0000014139206,"teacher_disagreement_score":0.027427647,"about_ca_system_score_codex":0.00027829845,"about_ca_system_score_gemma":0.00004802394,"threshold_uncertainty_score":0.9999418},"labels":[],"label_agreement":null},{"id":"W4393756461","doi":"10.5281/zenodo.6873559","title":"Touché20-Argument-Retrieval-for-Comparative-Questions","year":2020,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Optech (Canada)","funders":"","keywords":"Argument (complex analysis); Computer science; Information retrieval; Medicine","score_opus":0.27489454462019003,"score_gpt":0.4476513850146947,"score_spread":0.17275684039450467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393756461","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007506125,0.00006265615,0.0032183493,0.002731539,0.00053200487,0.0012330007,0.9774435,0.00035928484,0.01434458],"genre_scores_gemma":[0.0012081831,0.0002167617,0.00035028512,0.0007208345,0.00050876325,2.8028552e-7,0.99427396,0.00053299684,0.002187932],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9942778,0.0009482343,0.00094521866,0.0010140176,0.0023200864,0.0004946771],"domain_scores_gemma":[0.99511915,0.00034681408,0.0005719253,0.0012033656,0.00236779,0.000390953],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0038013777,0.0003373242,0.00051318604,0.00066201825,0.0031459029,0.0030217099,0.0033284414,0.00019465388,0.07025425],"category_scores_gemma":[0.004888222,0.00030339666,0.00019312545,0.001613769,0.00022706744,0.00050827634,0.0015507136,0.00061791006,0.0976819],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012699646,0.00011544594,3.0398976e-7,0.00004060446,0.000055358625,0.0000032893754,0.00031499108,0.000094116185,0.00009801886,0.0007141044,0.98868275,0.009754003],"study_design_scores_gemma":[0.00065019756,0.00055321614,0.00006792048,0.000040149833,0.00005056341,0.00001735038,0.0003566594,0.00085403264,0.00006797304,0.00072472706,0.9962803,0.00033689657],"about_ca_topic_score_codex":0.000010800258,"about_ca_topic_score_gemma":0.0000014139206,"teacher_disagreement_score":0.027427647,"about_ca_system_score_codex":0.00027829845,"about_ca_system_score_gemma":0.00004802394,"threshold_uncertainty_score":0.9999418},"labels":[],"label_agreement":null},{"id":"W4393862188","doi":"10.3138/cjpe-2024-0012","title":"Strengthening Evaluation Capacity Building Practice Through Competition: The Max Bell School of Public Policy’s Evaluation Capacity Case Challenge","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Alberta; University of Ottawa; Queen's University; McGill University","funders":"","keywords":"Competition (biology); Capacity building; Political science; Architectural engineering; Economics; Engineering; Economic growth","score_opus":0.6298851995534387,"score_gpt":0.5347281576265688,"score_spread":0.09515704192686991,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393862188","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9290416,0.0061653145,0.00961997,0.03238584,0.0030334846,0.004896387,0.000072160365,0.000047567406,0.014737673],"genre_scores_gemma":[0.9911991,0.00008760161,0.00714907,0.00025829911,0.00093182107,0.0002777748,0.00003381633,0.000026775693,0.000035789966],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98209536,0.0063483478,0.0022269466,0.00053060724,0.008238618,0.00056014804],"domain_scores_gemma":[0.97926205,0.0019567003,0.0018024737,0.0007152905,0.01570233,0.0005611286],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10471569,0.00030120192,0.0004276051,0.0013389221,0.0008181958,0.0014472186,0.0007122868,0.00020344794,0.0056290403],"category_scores_gemma":[0.036452033,0.0002191361,0.00030206572,0.00258753,0.00033901332,0.0041589495,0.000040888957,0.0008102994,0.000117928896],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024783189,0.00015569296,0.0010447705,0.000050320385,0.00025962916,0.00003555239,0.009822521,0.017223231,0.00015279284,0.025102705,0.0016382027,0.9444898],"study_design_scores_gemma":[0.0019183402,0.00089408545,0.005100744,0.00042652586,0.001362845,0.0024480573,0.013285418,0.8111745,0.00030553274,0.083402,0.07925088,0.00043105625],"about_ca_topic_score_codex":0.004366387,"about_ca_topic_score_gemma":0.024770614,"teacher_disagreement_score":0.9440587,"about_ca_system_score_codex":0.0027867996,"about_ca_system_score_gemma":0.01966661,"threshold_uncertainty_score":0.9995894},"labels":[],"label_agreement":null},{"id":"W4393901164","doi":"10.3138/cjpe-2024-0003","title":"Evaluation Capacity Building: Experiential Learning Through Community–University Collaboratives","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa; McGill University; Queen's University; University of Alberta","funders":"","keywords":"Experiential learning; Capacity building; Experiential education; Psychology; Sociology; Knowledge management; Mathematics education; Computer science; Political science","score_opus":0.5508950277399596,"score_gpt":0.5316824930199557,"score_spread":0.019212534720003838,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393901164","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98029596,0.0011902438,0.0066042067,0.0013586681,0.001937109,0.0010086922,0.000009614301,0.000031477626,0.0075640273],"genre_scores_gemma":[0.99574685,0.000014763947,0.0037155969,0.000042952677,0.00020695297,0.000018845125,0.000014148915,0.000011045177,0.00022887245],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99001247,0.0050769732,0.0006840334,0.00022142747,0.0037377386,0.00026738388],"domain_scores_gemma":[0.9915107,0.00043056795,0.00044815335,0.00027007825,0.007037463,0.00030303572],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03949789,0.00014595901,0.00023136158,0.00076282944,0.00088288856,0.0009812068,0.0005234516,0.000106277665,0.0028551891],"category_scores_gemma":[0.005737506,0.00012693137,0.0001498408,0.0018579625,0.00019754932,0.0020225055,0.000024070567,0.000672362,0.00007038137],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032427055,0.00008303929,0.002886841,0.000016589805,0.00015258472,0.000012947645,0.05123376,0.016491164,0.0009519171,0.004976468,0.00413852,0.91902375],"study_design_scores_gemma":[0.0016039595,0.0010710165,0.010631112,0.00027402127,0.00055673806,0.00006759143,0.064639114,0.47493,0.0011256072,0.026741417,0.4179856,0.00037384385],"about_ca_topic_score_codex":0.00148613,"about_ca_topic_score_gemma":0.016099501,"teacher_disagreement_score":0.9186499,"about_ca_system_score_codex":0.0012847709,"about_ca_system_score_gemma":0.009537692,"threshold_uncertainty_score":0.99805635},"labels":[],"label_agreement":null},{"id":"W4393901296","doi":"10.3138/cjpe-2024-0001","title":"Capturing Evaluation Capacity: Findings from a Mapping of Evaluation Capacity Instruments","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McGill University; University of Ottawa","funders":"","keywords":"Rubric; Face validity; Construct validity; Content validity; Reliability (semiconductor); Concurrent validity; Construct (python library); Adaptation (eye); Psychology; Computer science; Applied psychology; Internal consistency; Process management; Psychometrics; Engineering; Clinical psychology","score_opus":0.5637636910939985,"score_gpt":0.48089635624878085,"score_spread":0.08286733484521763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393901296","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98911524,0.0011090428,0.0013924956,0.0011875934,0.0028971399,0.0022242141,0.000054210628,0.000020545971,0.0019995025],"genre_scores_gemma":[0.9949582,0.000013871208,0.0043175225,0.00007930424,0.0003207516,0.00017528831,0.000076873235,0.000022103628,0.000036068657],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9871926,0.0017209739,0.0020261935,0.00049537676,0.008145583,0.000419322],"domain_scores_gemma":[0.9905832,0.00046081026,0.0009927726,0.00047183462,0.007019793,0.00047158162],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.05105589,0.00025836317,0.00046299657,0.0019710467,0.0002745665,0.0008477197,0.00051750476,0.00019533292,0.0056477487],"category_scores_gemma":[0.0066099474,0.00022049698,0.00028345178,0.0017282292,0.00016240498,0.0018629215,0.00002710455,0.00045622565,0.00011388985],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015611124,0.000049057482,0.02371707,0.000027558688,0.0001680294,0.0000029137823,0.008715455,0.0048443233,0.0012407531,0.0003259237,0.000995545,0.95989776],"study_design_scores_gemma":[0.0016177904,0.0002958224,0.14744638,0.0006057118,0.0006482531,0.000039019793,0.0025872057,0.7869716,0.0017613715,0.050235398,0.007503207,0.0002881875],"about_ca_topic_score_codex":0.0035476182,"about_ca_topic_score_gemma":0.01496088,"teacher_disagreement_score":0.95960957,"about_ca_system_score_codex":0.0021454855,"about_ca_system_score_gemma":0.009221726,"threshold_uncertainty_score":0.99639505},"labels":[],"label_agreement":null},{"id":"W4393901340","doi":"10.3138/cjpe-2024-0006","title":"Meeting the Challenge: How the City of Kingston Is Working to Propel Evaluation Growth","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta; University of Ottawa; Kingston Health Sciences Centre; McGill University; Queen's University","funders":"","keywords":"Regional science; Engineering ethics; Sociology; Engineering","score_opus":0.5229101328012221,"score_gpt":0.5202649908847802,"score_spread":0.00264514191644194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393901340","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5616208,0.013111694,0.0027483525,0.4002824,0.004952333,0.005462877,0.000010223571,0.000026246018,0.011785111],"genre_scores_gemma":[0.9978519,0.000038875412,0.000794142,0.00044080435,0.0004611375,0.00013636134,0.0000026874277,0.00001259284,0.00026150426],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9927963,0.0012622287,0.0008545797,0.00026792454,0.00452314,0.00029582588],"domain_scores_gemma":[0.9933619,0.0006118956,0.0006305584,0.00038655216,0.004773546,0.0002355808],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.06303442,0.0001385897,0.00020703628,0.0005753449,0.0003785859,0.0010285072,0.00077676715,0.00007436399,0.0010859725],"category_scores_gemma":[0.0063451156,0.00007222768,0.00017655155,0.0017077669,0.00012422614,0.00058143475,0.000030192714,0.0003567265,0.000034626857],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008365625,0.000018293722,0.0032171283,0.00001101453,0.00004447133,0.0000015009758,0.009102309,0.0010009302,0.00004209589,0.0010700936,0.007835598,0.9776482],"study_design_scores_gemma":[0.0009883912,0.0011888491,0.06688341,0.0013299766,0.00076387206,0.00008985088,0.011891291,0.5147994,0.0012511464,0.06844746,0.33195195,0.0004143428],"about_ca_topic_score_codex":0.00057672535,"about_ca_topic_score_gemma":0.009090088,"teacher_disagreement_score":0.9772338,"about_ca_system_score_codex":0.00046726782,"about_ca_system_score_gemma":0.004764993,"threshold_uncertainty_score":0.99982715},"labels":[],"label_agreement":null},{"id":"W4393901348","doi":"10.3138/cjpe-2024-0014","title":"Exploring the Edges: Identifying the Next Generation of Evaluation Capacity Building Research and Practice Through Adjacency","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa; McGill University","funders":"","keywords":"Adjacency list; Computer science; Data science; Algorithm","score_opus":0.9617855589426995,"score_gpt":0.6449060188564266,"score_spread":0.31687954008627284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393901348","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9655131,0.0082459655,0.005379184,0.014876242,0.002530932,0.0019101141,0.0000033720448,0.000008431551,0.0015326764],"genre_scores_gemma":[0.99524474,0.0003584793,0.0034231923,0.000082694045,0.00063286716,0.00021269714,0.0000039967076,0.000010612894,0.000030699986],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9893242,0.0038933144,0.0010280098,0.00027629852,0.0051873475,0.00029083574],"domain_scores_gemma":[0.9876684,0.0032567258,0.00050612085,0.00037783204,0.00804322,0.0001476765],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.116730005,0.000111451554,0.0001632952,0.00056796387,0.0008444909,0.0019124174,0.00042697706,0.000051586372,0.00032248764],"category_scores_gemma":[0.021393515,0.00006293245,0.00008404123,0.0018015514,0.00029904337,0.0044364245,0.00003294631,0.000519515,0.000018598623],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001205139,0.000020025165,0.00028276775,0.000016485114,0.00004767217,0.0000021058556,0.01631584,0.0024683548,0.0018950098,0.005943912,0.0017088364,0.97128695],"study_design_scores_gemma":[0.0010360595,0.0010354796,0.023025084,0.00066337106,0.0006353957,0.00040929695,0.059913803,0.7177952,0.0053872494,0.09536388,0.0944412,0.00029400765],"about_ca_topic_score_codex":0.001181836,"about_ca_topic_score_gemma":0.006214315,"teacher_disagreement_score":0.9709929,"about_ca_system_score_codex":0.00052245625,"about_ca_system_score_gemma":0.0041448097,"threshold_uncertainty_score":0.9991237},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":["metaresearch"],"domain":"methods","study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W4393901512","doi":"10.3138/cjpe-2024-0002","title":"Evaluation Literacy and Use in Community Organizations: Insights and Implications for Evaluation Capacity Building","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Australian Government","keywords":"Capacity building; Literacy; Business; Capacity development; Environmental planning; Environmental resource management; Sociology; Economic growth; Economics; Pedagogy; Geography","score_opus":0.43190576373339495,"score_gpt":0.5397514135621242,"score_spread":0.10784564982872924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393901512","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98431116,0.0034389442,0.005913343,0.0026030203,0.00045135486,0.0031090658,0.000027004602,0.00001375117,0.00013233542],"genre_scores_gemma":[0.99227345,0.00005980814,0.006960983,0.000105082,0.00010344255,0.0004013668,0.00006688285,0.000015577916,0.000013385233],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9943124,0.0023666003,0.0010607613,0.00028613556,0.0017515483,0.0002225642],"domain_scores_gemma":[0.9880334,0.0016304437,0.00039600057,0.00031745122,0.009325968,0.0002967067],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04573313,0.00015236171,0.00023151637,0.0014816324,0.00053698407,0.001768249,0.00023724853,0.00011218752,0.00020068516],"category_scores_gemma":[0.018842781,0.000129928,0.000052973923,0.0017324836,0.00011652756,0.0027230964,0.00002134496,0.00033128296,0.0000040381556],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007749859,0.000046387275,0.028604189,0.000023068746,0.00003461379,3.0637315e-7,0.007133137,0.0028402118,0.00026199772,0.004498081,0.00032958068,0.9562207],"study_design_scores_gemma":[0.0009804512,0.00019590711,0.33614224,0.00015020343,0.0002616936,0.000030830903,0.0006250592,0.53201663,0.00004027535,0.12460427,0.004831209,0.00012122314],"about_ca_topic_score_codex":0.000982946,"about_ca_topic_score_gemma":0.03610286,"teacher_disagreement_score":0.95609945,"about_ca_system_score_codex":0.0009485052,"about_ca_system_score_gemma":0.005338861,"threshold_uncertainty_score":0.999268},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W4393902386","doi":"10.4324/9781003280422-16","title":"Reflecting on the how questions","year":2024,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"History","score_opus":0.6012019840012676,"score_gpt":0.5808121383806713,"score_spread":0.020389845620596314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393902386","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000014936117,0.00009793484,0.00021707482,0.05659515,0.00090191397,0.00016367786,0.0000077679215,0.0000688456,0.9419327],"genre_scores_gemma":[0.01355576,0.00005634299,0.00012877543,0.0021264364,0.0003048997,0.000011841809,0.0000034858015,0.00001749082,0.983795],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99741465,0.00003567192,0.0003060133,0.00037062616,0.0017608523,0.00011219406],"domain_scores_gemma":[0.9973599,0.0015395046,0.00014794979,0.0006533902,0.0002554325,0.000043830834],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0031526412,0.00016220954,0.0001617722,0.00023757305,0.00022991766,0.00073186005,0.0004581408,0.00011888897,0.03110274],"category_scores_gemma":[0.00048648307,0.0000732851,0.00015212092,0.0001004128,0.000053125677,0.00009125808,0.000095816766,0.0004704959,0.018029535],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010629485,0.0000016533756,0.000002288821,0.0000010894547,0.000010905127,0.0000012617031,0.00006223183,0.000013079314,0.0000027912536,0.85758406,0.12877777,0.013541801],"study_design_scores_gemma":[0.00001373203,0.000030273066,0.000009661987,0.000053762553,0.000009981579,0.0000019316171,0.00009946249,0.0008130452,0.0000109095745,0.35252792,0.6463575,0.00007184651],"about_ca_topic_score_codex":0.00000312346,"about_ca_topic_score_gemma":0.00011166939,"teacher_disagreement_score":0.51757973,"about_ca_system_score_codex":0.00006833025,"about_ca_system_score_gemma":0.00016319701,"threshold_uncertainty_score":0.98273504},"labels":[],"label_agreement":null},{"id":"W4393902965","doi":"10.3138/cjpe-2024-0004","title":"Developing Evaluation Capacity Building Competencies: Participant Reflections From the Evaluation Capacity Case Challenge","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"McGill University; University of Waterloo; University of Alberta","funders":"","keywords":"Capacity building; Capacity development; Psychology; Business; Environmental resource management; Environmental science; Economic growth; Economics","score_opus":0.8696201595344439,"score_gpt":0.5799551477667225,"score_spread":0.2896650117677214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393902965","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96294004,0.0038030364,0.011957769,0.012635565,0.0043057706,0.0030810076,0.000052217365,0.000046063356,0.0011785572],"genre_scores_gemma":[0.9875508,0.00003870948,0.010811464,0.00024567926,0.00078745786,0.00048854924,0.000036208647,0.000022947486,0.000018216651],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98727643,0.0037679966,0.0018075472,0.0005513091,0.006055476,0.0005412483],"domain_scores_gemma":[0.98787445,0.0016900696,0.00082884415,0.00060450804,0.008522372,0.00047978488],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07147564,0.0002795165,0.00038291013,0.0007960739,0.0011957957,0.0016192313,0.00061177433,0.00017222417,0.0032379269],"category_scores_gemma":[0.011263911,0.0001929784,0.00026229236,0.001887365,0.00023062337,0.00156341,0.00003104515,0.00064221845,0.00012304574],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012807484,0.000049188322,0.0014419579,0.000013114872,0.00021436698,0.00003771132,0.019247849,0.01597334,0.0002558626,0.004941018,0.0014733707,0.9563394],"study_design_scores_gemma":[0.00086552976,0.0003065201,0.015288252,0.00031970083,0.0011892236,0.00054954726,0.010808274,0.82988656,0.00018078763,0.089586645,0.05068807,0.00033092505],"about_ca_topic_score_codex":0.007024803,"about_ca_topic_score_gemma":0.22620298,"teacher_disagreement_score":0.9560085,"about_ca_system_score_codex":0.0029222893,"about_ca_system_score_gemma":0.014702817,"threshold_uncertainty_score":0.9995875},"labels":[],"label_agreement":null},{"id":"W4393902987","doi":"10.3138/cjpe-2024-0005","title":"Learning From Evaluation Data: Discoveries From the Inaugural Evaluation Capacity Case Challenge","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa; University of Alberta; McGill University; Queen's University","funders":"","keywords":"Data science; Computer science","score_opus":0.7100870622061499,"score_gpt":0.544183741665453,"score_spread":0.1659033205406969,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393902987","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9725843,0.00907597,0.0015290293,0.008627242,0.0040326426,0.0023979552,0.00021698045,0.00003087639,0.0015049775],"genre_scores_gemma":[0.9964861,0.00006537492,0.0010233687,0.00012223555,0.0013025751,0.00017812809,0.0007477723,0.00002299766,0.000051422907],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9867783,0.0042241137,0.0013997494,0.00063187437,0.0065950435,0.00037091647],"domain_scores_gemma":[0.9913881,0.0018837269,0.00080354855,0.0009767503,0.004570361,0.00037754863],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.058051515,0.00025334343,0.00033452516,0.00046488634,0.0007363304,0.0024559663,0.0010609981,0.0001530358,0.008664388],"category_scores_gemma":[0.0134063065,0.00016640764,0.00016847598,0.0010084622,0.00021015006,0.00345421,0.000072610754,0.0007291111,0.00019746566],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018446986,0.000028929388,0.0048581455,0.000003684158,0.00012801259,0.000041398966,0.008711324,0.010382223,0.000025711257,0.0001874857,0.0046105627,0.97100407],"study_design_scores_gemma":[0.0008474298,0.00030129543,0.02700274,0.00014462165,0.0008754138,0.00013132239,0.009872369,0.885741,0.000024251813,0.028960187,0.04588688,0.00021248742],"about_ca_topic_score_codex":0.014338784,"about_ca_topic_score_gemma":0.19765352,"teacher_disagreement_score":0.9707916,"about_ca_system_score_codex":0.001179679,"about_ca_system_score_gemma":0.009957348,"threshold_uncertainty_score":0.99857956},"labels":[],"label_agreement":null},{"id":"W4393955411","doi":"10.25035/jche.02.01.04","title":"Educational Evaluation as Hermes","year":2024,"lang":"en","type":"article","venue":"Journal of Contemplative and Holistic Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kwantlen Polytechnic University","funders":"","keywords":"Psychology","score_opus":0.3811328744922947,"score_gpt":0.6170466990209954,"score_spread":0.2359138245287007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393955411","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.910019,0.0060833986,0.002494063,0.017564066,0.004264928,0.00024059591,0.0000056319627,0.000006364396,0.05932195],"genre_scores_gemma":[0.99369055,0.000102902304,0.00035042985,0.000355632,0.00074576965,0.00001243021,0.0000068623863,0.000005085799,0.0047303224],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974592,0.0002594979,0.00067013333,0.00015698733,0.0013759201,0.00007831514],"domain_scores_gemma":[0.99564725,0.0016036652,0.00035538862,0.00011365881,0.002181139,0.00009891762],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0053189383,0.00008524162,0.0001693492,0.0004504275,0.00011321215,0.00040886775,0.00013934338,0.00003791856,0.0026833892],"category_scores_gemma":[0.0031120034,0.000058016914,0.00006844055,0.0003484529,0.000065783715,0.0009527769,0.000013370879,0.00014232259,0.0001675974],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006246532,0.00018432543,0.011846011,0.000028917451,0.00008092347,0.0000014000458,0.010094664,0.00006499835,0.000543714,0.31350553,0.05464326,0.6089438],"study_design_scores_gemma":[0.00038587963,0.0002728433,0.23051928,0.0002720578,0.00012784048,0.00021381173,0.010307828,0.00802904,0.000122253,0.6183651,0.13123833,0.00014575795],"about_ca_topic_score_codex":0.000019546505,"about_ca_topic_score_gemma":0.000013984403,"teacher_disagreement_score":0.608798,"about_ca_system_score_codex":0.000117923795,"about_ca_system_score_gemma":0.0041198903,"threshold_uncertainty_score":0.9982283},"labels":[],"label_agreement":null},{"id":"W4394011565","doi":"10.1007/978-3-031-55996-9_8","title":"The Quest for Impact Research: Position, Strategies and Future Directions","year":2024,"lang":"en","type":"book-chapter","venue":"World sustainability series","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Position (finance); Position paper; Political science; Regional science; Computer science; Sociology; Economics; World Wide Web; Finance","score_opus":0.13846701138775153,"score_gpt":0.5141254299600635,"score_spread":0.37565841857231197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394011565","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007730357,0.017755054,0.000049785944,0.19232844,0.0018642911,0.003214664,0.00029535717,0.00018907152,0.7835303],"genre_scores_gemma":[0.025606437,0.0018523167,0.00006515492,0.00006041254,0.0010436623,0.00024860326,0.00003911883,0.000035538444,0.9710488],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99652374,0.00020531367,0.00067580276,0.0006916341,0.0014766294,0.00042685252],"domain_scores_gemma":[0.9916852,0.002824593,0.00016267879,0.00090349047,0.004290927,0.00013310467],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.009409069,0.00029485504,0.00034695325,0.0005640421,0.0019416751,0.0035954693,0.00045253919,0.00016029438,0.0006472027],"category_scores_gemma":[0.0008325388,0.00016762484,0.00025272046,0.00042654655,0.00112773,0.0010066717,0.0002168919,0.0006689785,0.000047277405],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012481624,0.000009156134,0.00005718311,0.00008817013,0.00004624967,0.000002500248,0.0012357263,0.000011951993,3.969813e-7,0.9324889,0.026159056,0.039775874],"study_design_scores_gemma":[0.000037485373,0.0001208849,0.0006292798,0.000015807942,0.000014906185,0.0000042485967,0.012465567,0.000030573025,8.8693406e-7,0.48379079,0.5027932,0.00009636104],"about_ca_topic_score_codex":0.00006332213,"about_ca_topic_score_gemma":0.0076075103,"teacher_disagreement_score":0.47663414,"about_ca_system_score_codex":0.00072097726,"about_ca_system_score_gemma":0.0024840357,"threshold_uncertainty_score":0.99935764},"labels":[],"label_agreement":null},{"id":"W4394061729","doi":"10.7895/ijadr.453","title":"Organizational structure, capacity and reach of organizations involved in alcohol prevention: An assessment of stakeholders across five countries in East Africa","year":2024,"lang":"en","type":"article","venue":"The International Journal of Alcohol and Drug Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Organizational structure; Business; Capacity building; Political science; Economic growth; Environmental planning; Geography; Economics","score_opus":0.3549950905602557,"score_gpt":0.5423515220312097,"score_spread":0.18735643147095404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394061729","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9950599,0.00037363885,0.0002443883,0.0034625789,0.00018861514,0.00016494814,0.00010176186,0.0000024390959,0.00040173242],"genre_scores_gemma":[0.99877304,0.00030001035,0.00055569893,0.000026191983,0.000076862154,0.0000020352427,0.000012722846,0.0000065000427,0.00024691442],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99521255,0.0006011651,0.00089735986,0.00019567761,0.0029367697,0.00015648763],"domain_scores_gemma":[0.99454,0.0010997724,0.00027955577,0.00015689933,0.0038554778,0.00006833895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0108857555,0.000088896726,0.00022004584,0.0006900982,0.00009561729,0.00031176713,0.00063248316,0.00004677151,0.00048570693],"category_scores_gemma":[0.0011498227,0.00005706634,0.00002974072,0.0014537824,0.00036501285,0.0007160663,0.00016400682,0.00039900685,0.0000013623211],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023980105,0.0004075767,0.8795114,0.000081652826,0.0002455559,0.00003227489,0.05337237,0.0071138735,0.006178215,0.041033838,0.0011106642,0.01067274],"study_design_scores_gemma":[0.0018668189,0.00025317853,0.8212016,0.0004006142,0.000016390339,0.00006955162,0.034896944,0.031822473,0.0023386104,0.10635493,0.0006404614,0.0001384061],"about_ca_topic_score_codex":0.00019648153,"about_ca_topic_score_gemma":0.001619602,"teacher_disagreement_score":0.065321095,"about_ca_system_score_codex":0.00011445532,"about_ca_system_score_gemma":0.001007359,"threshold_uncertainty_score":0.53181505},"labels":[],"label_agreement":null},{"id":"W4394130160","doi":"10.6084/m9.figshare.23298966","title":"Additional file 2 of Defining re-implementation","year":2023,"lang":"en","type":"dataset","venue":"Figshare","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Database; Operating system; World Wide Web","score_opus":0.4110701987896556,"score_gpt":0.544034278483647,"score_spread":0.13296407969399143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394130160","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.5268144e-8,0.000005448226,2.6021407e-8,0.000038649374,0.00009010877,0.00013319617,0.99787056,0.000019390318,0.0018425877],"genre_scores_gemma":[5.0384095e-8,0.0000016700748,0.00010850141,0.00020529037,0.0001243192,0.0012068695,0.99644744,0.000008868651,0.0018970094],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967511,0.00009786718,0.0006413686,0.00031763548,0.0020406889,0.00015132793],"domain_scores_gemma":[0.9893788,0.008764996,0.00080907915,0.0004748967,0.00051943277,0.000052762993],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00030492796,0.00013262653,0.00022475245,0.00033512246,0.000093839655,0.0001118855,0.00059943314,0.00012185694,0.9999542],"category_scores_gemma":[0.01931645,0.000112195754,0.000115987794,0.00063475216,0.0000062288173,0.00018920316,0.00021040274,0.00016621193,0.46223128],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013798353,0.0000074925083,1.129061e-7,0.0000284094,0.000008625975,0.0000018424554,0.000012163343,0.000010268872,1.6639648e-8,3.3296502e-7,0.9977197,0.0022096466],"study_design_scores_gemma":[0.00007184862,0.000034344495,0.00050790096,0.0009905698,0.0000044599137,7.881986e-7,0.000319185,0.00008504961,0.0000010941114,0.00007587002,0.99779207,0.00011680703],"about_ca_topic_score_codex":0.000014769057,"about_ca_topic_score_gemma":0.00053509074,"teacher_disagreement_score":0.53772295,"about_ca_system_score_codex":0.000039270555,"about_ca_system_score_gemma":0.00064959435,"threshold_uncertainty_score":0.9889443},"labels":[],"label_agreement":null},{"id":"W4394147466","doi":"10.6084/m9.figshare.20438454","title":"Additional file 4 of Selecting implementation models, theories, and frameworks in which to integrate intersectional approaches","year":2022,"lang":"en","type":"dataset","venue":"Open MIND","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"George & Fay Yee Centre for Healthcare Innovation; University of Toronto; University of Manitoba; University of Calgary; Université Laval; University of Ottawa; McGill University; Research Institute for Aging; University of Waterloo; University of British Columbia; Public Health Ontario; York University; McMaster University; Research Canada; Ottawa Hospital","funders":"","keywords":"Computer science; Theoretical computer science; Data science","score_opus":0.27067259952341777,"score_gpt":0.4834897237657355,"score_spread":0.21281712424231775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394147466","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001587722,0.0000049590994,0.00012123896,0.00016608118,0.0001200102,0.00044997744,0.9969608,5.225996e-7,0.002017636],"genre_scores_gemma":[0.00037321582,0.000004258691,0.005379125,0.00009883038,0.000044153803,0.00065847475,0.9929634,0.0000058581663,0.00047273608],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972149,0.00032156712,0.0007063434,0.00052636355,0.0010753719,0.00015545123],"domain_scores_gemma":[0.996171,0.0027800302,0.00045144442,0.00028827123,0.00024947923,0.00005979807],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002512494,0.00015761153,0.0002942914,0.00046039335,0.00015322315,0.00036720725,0.0007477049,0.00014606031,0.99192816],"category_scores_gemma":[0.0015365627,0.00013385864,0.000034041757,0.0010661035,0.000032873086,0.00051540905,0.0006858468,0.0006522978,0.0001175036],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004196935,0.000042168773,0.0000085110505,0.0000028388981,0.000014842776,4.5234611e-7,0.00068426115,0.0013782007,1.8219032e-7,0.000036631056,0.94785225,0.04993768],"study_design_scores_gemma":[0.00015025093,0.0001114554,0.0001495867,0.00007105136,0.0000072150715,0.0000046237083,0.010110424,0.00472184,0.0000029101766,0.0030883986,0.9814391,0.00014311778],"about_ca_topic_score_codex":0.00029031356,"about_ca_topic_score_gemma":0.010755291,"teacher_disagreement_score":0.9918107,"about_ca_system_score_codex":0.0001325557,"about_ca_system_score_gemma":0.00081040215,"threshold_uncertainty_score":0.6001705},"labels":[],"label_agreement":null},{"id":"W4394212670","doi":"10.6084/m9.figshare.14269614","title":"How to translate scientific knowledge into practice? Concepts, models and application","year":2021,"lang":"en","type":"dataset","venue":"Figshare","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Data science; Scientific modelling; Sociology of scientific knowledge; Management science; Epistemology; Engineering; Philosophy","score_opus":0.2845236997664,"score_gpt":0.5327063468984754,"score_spread":0.24818264713207538,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394212670","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000002153034,0.0018387857,0.00021458561,0.00304489,0.0002783894,0.00064350775,0.99340135,0.000020907648,0.00055544626],"genre_scores_gemma":[0.00017001852,0.000033570606,0.00060334493,0.0005256617,0.00017053219,0.0005506139,0.9956614,0.000011907874,0.0022729742],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99635696,0.00027616427,0.00046180747,0.0010431092,0.0016251064,0.00023683088],"domain_scores_gemma":[0.9954166,0.0009899696,0.0003700739,0.0012284603,0.0017548337,0.00024008514],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001426913,0.00024794697,0.00034506788,0.00035096763,0.0003706912,0.0030128215,0.0008921297,0.00022770574,0.05423581],"category_scores_gemma":[0.0050262776,0.00020525126,0.00008543606,0.0011390903,0.000028574215,0.0011766303,0.0003186229,0.00030449062,0.007191662],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005250435,0.000037290472,1.1828958e-7,0.00008058827,0.0000096378335,0.0000023749221,0.0006306598,0.00013134677,0.0000075016083,0.000008978223,0.9613754,0.037710827],"study_design_scores_gemma":[0.00015594957,0.000030317298,0.000007048144,0.00037316373,0.00002178749,0.0000059887716,0.00060767174,0.0069514676,0.00003068203,0.00040374353,0.991159,0.0002531302],"about_ca_topic_score_codex":0.000008501624,"about_ca_topic_score_gemma":0.00049928046,"teacher_disagreement_score":0.047044147,"about_ca_system_score_codex":0.00007367969,"about_ca_system_score_gemma":0.00085487915,"threshold_uncertainty_score":0.99802214},"labels":[],"label_agreement":null},{"id":"W4394258873","doi":"10.6084/m9.figshare.23722278","title":"Additional file 3 of Aligning intuition and theory: a novel approach to identifying the determinants of behaviours necessary to support implementation of evidence into practice","year":2023,"lang":"en","type":"dataset","venue":"Open MIND","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital","funders":"","keywords":"Intuition; Computer science; Data science; Psychology; Cognitive science","score_opus":0.5074891195682348,"score_gpt":0.5898946231140129,"score_spread":0.08240550354577802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394258873","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011412814,0.000004288256,0.0003303401,0.00013084312,0.00008693243,0.000901443,0.9972699,5.393896e-7,0.00013440351],"genre_scores_gemma":[0.0011379115,0.0000120746145,0.018162724,0.00011923294,0.00003096449,0.0004433078,0.97984004,0.000008905352,0.0002448205],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99629956,0.00034409165,0.0010575376,0.00044689016,0.001713277,0.00013864266],"domain_scores_gemma":[0.9900569,0.0071408544,0.0014958489,0.0005234561,0.0007113778,0.000071620154],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0075577954,0.00014556933,0.0003662287,0.00037134113,0.00012724937,0.00022732912,0.0011475331,0.00007515815,0.1861711],"category_scores_gemma":[0.0067643523,0.00009807014,0.00005430166,0.0007918609,0.00008513407,0.0010702349,0.0008893392,0.00011889143,0.0002968186],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053457166,0.0000767385,0.0000415351,0.000025214791,0.000017248743,6.593105e-7,0.0012329924,0.000016384725,0.000039571718,0.0000038285943,0.93576336,0.062728986],"study_design_scores_gemma":[0.00034029013,0.00073057564,0.0074160197,0.0013539802,0.00020968335,0.000019888948,0.03565987,0.00014879127,0.0011312626,0.00035013122,0.9523617,0.00027779993],"about_ca_topic_score_codex":0.0006518058,"about_ca_topic_score_gemma":0.0012908748,"teacher_disagreement_score":0.18587428,"about_ca_system_score_codex":0.000042377727,"about_ca_system_score_gemma":0.00070046086,"threshold_uncertainty_score":0.8145729},"labels":[],"label_agreement":null},{"id":"W4394366550","doi":"10.6084/m9.figshare.20438460","title":"Additional file 6 of Selecting implementation models, theories, and frameworks in which to integrate intersectional approaches","year":2022,"lang":"en","type":"dataset","venue":"Figshare","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"George & Fay Yee Centre for Healthcare Innovation; University of Toronto; University of Manitoba; University of Calgary; Université Laval; University of Ottawa; McGill University; Research Institute for Aging; University of Waterloo; University of British Columbia; Public Health Ontario; York University; McMaster University; Research Canada; Ottawa Hospital","funders":"","keywords":"Computer science; Data science; Theoretical computer science","score_opus":0.26104989935573303,"score_gpt":0.4458443888476095,"score_spread":0.1847944894918765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394366550","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000025144775,0.000012366435,0.0000076206024,0.00007936872,0.000063949934,0.0002866799,0.99906445,0.000007476913,0.00047557958],"genre_scores_gemma":[0.00007407297,0.0000016704391,0.0003985959,0.00021912719,0.00007477494,0.0023984222,0.99670076,0.000008120062,0.00012443664],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972981,0.00023462447,0.0006064064,0.00045736195,0.0012354647,0.00016804787],"domain_scores_gemma":[0.9946428,0.004196045,0.000440434,0.0002679211,0.00039087923,0.000061899766],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00060220505,0.00017120434,0.00025364684,0.0005379906,0.00013447434,0.0001528165,0.00043636843,0.00018156352,0.99953634],"category_scores_gemma":[0.0075141606,0.0001495038,0.00004954706,0.0011664785,0.000007490014,0.00032643054,0.00037983037,0.0007827965,0.00029756775],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014798311,0.000024394743,0.0000012811232,0.000024590427,0.000011028565,5.0948114e-7,0.00031575258,0.0019150382,3.064764e-8,0.000019045752,0.9936136,0.004059908],"study_design_scores_gemma":[0.00008679587,0.0000751288,0.00018746962,0.00047687956,0.000003160601,0.000004046015,0.0036694293,0.0073674773,7.105407e-7,0.0020362793,0.98594415,0.00014847568],"about_ca_topic_score_codex":0.00005345204,"about_ca_topic_score_gemma":0.0027910802,"teacher_disagreement_score":0.9992387,"about_ca_system_score_codex":0.00014047428,"about_ca_system_score_gemma":0.0006305902,"threshold_uncertainty_score":0.89956945},"labels":[],"label_agreement":null},{"id":"W4394409877","doi":"10.6084/m9.figshare.23722275","title":"Additional file 2 of Aligning intuition and theory: a novel approach to identifying the determinants of behaviours necessary to support implementation of evidence into practice","year":2023,"lang":"en","type":"dataset","venue":"Figshare","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital","funders":"","keywords":"Intuition; Computer science; Data science; Management science; Psychology; Cognitive science; Engineering","score_opus":0.5079036135970103,"score_gpt":0.5613669653741327,"score_spread":0.05346335177712236,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394409877","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000026747746,0.000009665327,0.000031570788,0.0000682978,0.00004984898,0.00059581664,0.9991756,0.0000053892113,0.000037052927],"genre_scores_gemma":[0.00024314458,0.0000045615307,0.0016420314,0.00020096828,0.00004229786,0.0011167751,0.9966775,0.000009884907,0.00006283903],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9963839,0.00025647364,0.0009175297,0.00039103228,0.0019049045,0.0001461366],"domain_scores_gemma":[0.9868853,0.01003318,0.0014614075,0.00048703662,0.0010601251,0.00007296405],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002144618,0.00015533845,0.00031928177,0.00041875435,0.000113576796,0.000106078725,0.0007259197,0.00009043076,0.72093743],"category_scores_gemma":[0.026528347,0.00010681358,0.00007525182,0.0008548496,0.000023375207,0.0007121668,0.0005379325,0.00013830951,0.000647524],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021596148,0.000047468908,0.00000785521,0.00016797333,0.000013500161,7.027554e-7,0.0006736909,0.000022787302,0.0000066207213,0.0000022008091,0.9914649,0.0075706746],"study_design_scores_gemma":[0.00016104299,0.00041117627,0.007218258,0.005602243,0.00007906721,0.000013352524,0.010927379,0.00017812772,0.00023607415,0.00018791281,0.97476584,0.00021952859],"about_ca_topic_score_codex":0.000142579,"about_ca_topic_score_gemma":0.00038294558,"teacher_disagreement_score":0.72028995,"about_ca_system_score_codex":0.000044343727,"about_ca_system_score_gemma":0.00055651367,"threshold_uncertainty_score":0.98167163},"labels":[],"label_agreement":null},{"id":"W4394532023","doi":"10.6084/m9.figshare.20039813","title":"The Governance of Public Policy Evaluation Systems: Policy Effectiveness and Accountability","year":2022,"lang":"en","type":"dataset","venue":"Figshare","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Accountability; Corporate governance; Public administration; Business; Public policy; Political science; Finance","score_opus":0.28220152893438777,"score_gpt":0.520708851808889,"score_spread":0.23850732287450127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394532023","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014495,0.0027533213,2.3156986e-7,0.0004820921,0.00027201185,0.0011557562,0.99472857,0.000009962546,0.00045312426],"genre_scores_gemma":[0.008724817,0.00023433019,6.418536e-7,0.00009124632,0.0002670483,0.0014729461,0.9891121,0.000009530042,0.00008738562],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9910005,0.0026874226,0.000802109,0.000558845,0.0046644066,0.00028672314],"domain_scores_gemma":[0.9894212,0.005919685,0.0013691641,0.0015434609,0.0016474902,0.000098990524],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01178004,0.00023043627,0.0004143185,0.00027263945,0.00052446185,0.0006706286,0.0014590495,0.00015080435,0.3621691],"category_scores_gemma":[0.05923045,0.00014784302,0.00011141992,0.0014695234,0.00004675518,0.00045940635,0.00074826553,0.0003428421,0.0004690123],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011381383,0.00002669607,0.00005273705,0.00020034504,0.000019664278,1.9622645e-7,0.000028406277,0.00015387483,3.3789198e-7,0.00008675568,0.9711475,0.02827211],"study_design_scores_gemma":[0.00026974909,0.000059079317,0.029038005,0.00023817188,0.000014124907,0.000004315708,0.00016620767,0.0010904111,0.0000018306945,0.00037695657,0.9685976,0.0001435507],"about_ca_topic_score_codex":0.0008629685,"about_ca_topic_score_gemma":0.00037686597,"teacher_disagreement_score":0.3617001,"about_ca_system_score_codex":0.000707099,"about_ca_system_score_gemma":0.004784065,"threshold_uncertainty_score":0.94869405},"labels":[],"label_agreement":null},{"id":"W4394688120","doi":"10.3389/feduc.2024.1331293","title":"The impact of observers’ beliefs on the perceived contribution of a Research Lesson","year":2024,"lang":"en","type":"article","venue":"Frontiers in Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Agencia Nacional de Investigación y Desarrollo","keywords":"Psychology; Computer science; Mathematics education; Applied psychology","score_opus":0.2390425685814852,"score_gpt":0.5739276872918442,"score_spread":0.334885118710359,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394688120","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9859938,0.001218088,0.00030215536,0.0070430064,0.0018747582,0.00039237042,0.000007600216,0.000005801308,0.003162443],"genre_scores_gemma":[0.99812543,0.00030608574,0.0000975954,0.000023774954,0.00007409874,0.00004690757,0.000008037792,0.0000038812345,0.0013141645],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9973339,0.0006964562,0.0004154268,0.00017627291,0.001220594,0.0001573848],"domain_scores_gemma":[0.9969573,0.00175778,0.00011717433,0.00041408712,0.00072599837,0.00002762895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011074922,0.00006052442,0.00011999629,0.00033603387,0.00016579987,0.000126419,0.00043734032,0.000046788355,0.00018650512],"category_scores_gemma":[0.002636088,0.00002810668,0.000093826355,0.0013192705,0.00018220385,0.00018585147,0.000028575576,0.0002196601,0.00003369908],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001845894,0.0003800798,0.19062741,0.000017236627,0.00006399724,2.3895828e-7,0.02367374,0.0016033914,0.0014921265,0.043817356,0.5035878,0.23455204],"study_design_scores_gemma":[0.00013664982,0.00020975113,0.89772356,0.00016534059,0.0000046603996,4.1559716e-7,0.017845374,0.020826805,0.00060114666,0.04931768,0.013119047,0.000049563394],"about_ca_topic_score_codex":0.00025288356,"about_ca_topic_score_gemma":0.000052731568,"teacher_disagreement_score":0.70709616,"about_ca_system_score_codex":0.00036476567,"about_ca_system_score_gemma":0.0012839421,"threshold_uncertainty_score":0.38383693},"labels":[],"label_agreement":null},{"id":"W4394702948","doi":"10.25071/ddnwqb22","title":"Editorial: The politics of evidence","year":2015,"lang":"en","type":"editorial","venue":"Canada Watch","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Toronto Metropolitan University; Canadian Centre for Policy Alternatives; York University; University of Toronto","funders":"","keywords":"Politics; Political science; Law","score_opus":0.2908667989263498,"score_gpt":0.49923274723876454,"score_spread":0.20836594831241473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394702948","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000028770615,0.0003825855,0.000012414725,0.0154363215,0.98183143,0.00016944343,0.00022729754,0.000006929744,0.0019047776],"genre_scores_gemma":[0.0008871488,0.00009718518,0.000023087494,0.0001375892,0.96591043,0.0000142362405,0.00003349718,0.0000144813985,0.032882348],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98482054,0.00035905823,0.0008844043,0.00035713476,0.013284149,0.00029470853],"domain_scores_gemma":[0.9823121,0.009630424,0.0006716126,0.0012610075,0.0059283623,0.00019650867],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008848676,0.00019675915,0.00043830212,0.000052175958,0.00015441973,0.00015118197,0.002003289,0.0003390396,0.00046806643],"category_scores_gemma":[0.032491006,0.00009583813,0.00008161556,0.0004523647,0.00012616739,0.00017796463,0.00019242072,0.0006060974,0.000048863123],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006516507,0.0000042549245,0.00005879051,0.00001018748,0.000010643244,7.0677015e-7,0.00012830975,0.000047639194,0.0000011370025,0.00002844478,0.999123,0.0005803645],"study_design_scores_gemma":[0.000120216726,0.00004175623,0.000016730095,0.000064100495,0.000025789737,2.0948643e-7,0.00034979507,0.00008009857,0.00002156872,0.002137584,0.9970099,0.00013225923],"about_ca_topic_score_codex":0.46470556,"about_ca_topic_score_gemma":0.6643895,"teacher_disagreement_score":0.19968393,"about_ca_system_score_codex":0.00064678723,"about_ca_system_score_gemma":0.033883527,"threshold_uncertainty_score":0.9756587},"labels":[],"label_agreement":null},{"id":"W4394812653","doi":"10.1080/17457289.2024.2341127","title":"Using survey experiments for construct validation: “strong leader” questions and support for authoritarian leadership","year":2024,"lang":"en","type":"article","venue":"Journal of Elections Public Opinion and Parties","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Australian Research Council; Social Sciences and Humanities Research Council of Canada; Australian National University","keywords":"Construct (python library); Authoritarianism; Construct validity; Psychology; Survey research; Social psychology; Political science; Computer science; Applied psychology; Democracy; Psychometrics; Clinical psychology; Politics","score_opus":0.7541250149287131,"score_gpt":0.573723305629749,"score_spread":0.18040170929896404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394812653","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.166314,0.0076401406,0.7712038,0.037153766,0.014595614,0.0014021873,0.00022946231,0.00009778836,0.0013632382],"genre_scores_gemma":[0.9939687,0.00010703285,0.004142161,0.00006220549,0.00037792337,0.000025207552,0.000020117006,0.000009189689,0.0012874674],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983087,0.00020769023,0.0006815935,0.00018573829,0.00042103237,0.00019523472],"domain_scores_gemma":[0.9976791,0.0010092108,0.00023651804,0.00009587387,0.0008485398,0.00013074235],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.004899089,0.00010168894,0.00021283979,0.00050352677,0.000560069,0.0010411174,0.0001021197,0.00006677362,0.00017015527],"category_scores_gemma":[0.0012247538,0.00007926245,0.000088243956,0.00039759374,0.000121576086,0.0011984472,0.000015840475,0.0001282499,0.0000021523153],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00065578346,0.0005020534,0.2176988,0.0004914607,0.0011079365,0.0000024187425,0.011297531,0.0021856339,0.0036288116,0.44585037,0.14886889,0.16771032],"study_design_scores_gemma":[0.0032165174,0.0029926638,0.05136302,0.00037099567,0.00017997665,0.0009170435,0.035250176,0.20016056,0.0025424825,0.027470112,0.67477816,0.000758296],"about_ca_topic_score_codex":0.000010977513,"about_ca_topic_score_gemma":0.000039074188,"teacher_disagreement_score":0.8276547,"about_ca_system_score_codex":0.000051778505,"about_ca_system_score_gemma":0.00065310736,"threshold_uncertainty_score":0.9999959},"labels":[],"label_agreement":null},{"id":"W4394837005","doi":"10.1002/cl2.1401","title":"Unlocking the power of global collaboration: Building a stronger evidence ecosystem together","year":2024,"lang":"en","type":"editorial","venue":"Campbell Systematic Reviews","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cochrane; Campbell Scientific (Canada)","funders":"","keywords":"Power (physics); Ecosystem; Psychology; Environmental resource management; Environmental science; Ecology; Biology; Physics","score_opus":0.18860196282871255,"score_gpt":0.5064074530173462,"score_spread":0.3178054901886337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394837005","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00038042362,0.16485557,0.002606738,0.00063684856,0.81683713,0.010784606,0.00019140434,0.000048090125,0.0036591932],"genre_scores_gemma":[0.12682238,0.01607475,0.0023764402,0.00043940954,0.81747615,0.00797499,0.000067852525,0.0002633599,0.02850469],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9794776,0.0058655473,0.006166723,0.0010157401,0.0070790774,0.00039535086],"domain_scores_gemma":[0.97641546,0.012318398,0.005482702,0.0029521347,0.002696988,0.00013429504],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.055677317,0.0006074623,0.0030420055,0.00016607213,0.00022494141,0.0013025382,0.002536519,0.00049772166,0.0009295484],"category_scores_gemma":[0.040883534,0.00028556242,0.00075745815,0.0025232802,0.00008028614,0.00052767154,0.00033850942,0.00055540114,0.0030835054],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000062953177,0.000013093415,0.00003788652,0.047425393,0.000099908146,0.0000025931668,0.0010964787,0.000072832554,0.00000923114,0.0010130593,0.94990796,0.00031524143],"study_design_scores_gemma":[0.00010594155,0.000074209805,0.000002815295,0.095428094,0.0003985623,0.0000072250727,0.001803668,0.0010312997,0.0000059983245,0.00056096027,0.900289,0.0002922285],"about_ca_topic_score_codex":0.000013915996,"about_ca_topic_score_gemma":0.00020798258,"teacher_disagreement_score":0.14878082,"about_ca_system_score_codex":0.00079014746,"about_ca_system_score_gemma":0.0018260236,"threshold_uncertainty_score":0.9999837},"labels":[],"label_agreement":null},{"id":"W4394853659","doi":"10.11124/jbies-24-00073","title":"Unlocking the power of global collaboration: building a stronger evidence ecosystem together","year":2024,"lang":"en","type":"editorial","venue":"JBI Evidence Synthesis","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Campbell Scientific (Canada)","funders":"","keywords":"Ecosystem; Power (physics); Environmental resource management; Business; Environmental science; Ecology; Biology; Physics","score_opus":0.06666236805151937,"score_gpt":0.460328599035359,"score_spread":0.3936662309838396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394853659","genre_codex":"editorial","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012812528,0.014336894,0.0014430104,0.012529201,0.95387036,0.0015370672,0.0006201709,0.00014605679,0.0027046895],"genre_scores_gemma":[0.7710906,0.00091178867,0.0008592402,0.00010923883,0.22396445,0.00041058566,0.0000031095876,0.00006391597,0.0025870078],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98468673,0.0018361536,0.0021577938,0.0013318502,0.009461751,0.0005257207],"domain_scores_gemma":[0.94727945,0.045188323,0.0016929613,0.0022685768,0.0034127058,0.00015796669],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.02203958,0.0005610559,0.0010571966,0.00027346934,0.0003578418,0.0017572634,0.0031628897,0.00068322674,0.0029624025],"category_scores_gemma":[0.07587516,0.00033578725,0.00048443713,0.0029327206,0.0001983279,0.0017073149,0.0005699432,0.0007060294,0.0011926922],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008253509,0.000022761362,0.00097352255,0.0002001991,0.00012772917,0.00000865972,0.00081634184,0.0005491117,0.00011860919,0.00061330874,0.98936677,0.0071204365],"study_design_scores_gemma":[0.00009626745,0.00016791435,0.00047851301,0.012001025,0.000491776,0.000006065457,0.0041264473,0.0028179307,0.00073008455,0.0019746732,0.97648084,0.000628469],"about_ca_topic_score_codex":0.00010672815,"about_ca_topic_score_gemma":0.0007750661,"teacher_disagreement_score":0.75827813,"about_ca_system_score_codex":0.0009907864,"about_ca_system_score_gemma":0.0041926196,"threshold_uncertainty_score":0.9999094},"labels":[],"label_agreement":null},{"id":"W4394953955","doi":"10.1007/s10459-024-10331-5","title":"Group concept mapping for health professions education scholarship","year":2024,"lang":"en","type":"article","venue":"Advances in Health Sciences Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Wilson Centre; University of Toronto; McGill University","funders":"","keywords":"Conceptualization; Concept map; Computer science; Scholarship; Consistency (knowledge bases); Conceptual framework; Management science; Stakeholder; Data science; Sociology; Artificial intelligence; Social science; Political science; Engineering","score_opus":0.24563001762989425,"score_gpt":0.6242535704999903,"score_spread":0.3786235528700961,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394953955","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06762439,0.27579716,0.15555932,0.41173482,0.06263593,0.009779194,0.00007185238,0.0004508972,0.01634646],"genre_scores_gemma":[0.94076556,0.0034078925,0.040154904,0.011531678,0.0006421997,0.0010658903,0.00006779217,0.00001577248,0.0023483115],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99531907,0.0005626568,0.0013610955,0.0008624178,0.0013402073,0.0005545835],"domain_scores_gemma":[0.9971002,0.0014438261,0.0005200701,0.0003649323,0.00032479595,0.00024622472],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0160451,0.0001658794,0.000283164,0.0010449293,0.0009926558,0.000507138,0.00068361306,0.000057244193,0.00022188386],"category_scores_gemma":[0.0014902366,0.00012847222,0.000070076734,0.0033792553,0.00021289791,0.0036842653,0.00004731381,0.00026257482,0.00008657561],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004723334,0.00015441421,0.012095773,0.00020879963,9.729308e-7,2.4038306e-8,0.0043999366,0.0003691515,0.000008256707,0.12305765,0.006739894,0.8529604],"study_design_scores_gemma":[0.00015649255,0.00033719468,0.024519954,0.0014059885,0.0000013778817,0.0000051384554,0.018737229,0.008638083,0.000015969701,0.23256734,0.7134096,0.00020562428],"about_ca_topic_score_codex":0.0001407218,"about_ca_topic_score_gemma":0.00054659985,"teacher_disagreement_score":0.87314117,"about_ca_system_score_codex":0.0006672749,"about_ca_system_score_gemma":0.015215779,"threshold_uncertainty_score":0.99036705},"labels":[],"label_agreement":null},{"id":"W4396614620","doi":"10.1590/2526-8910.ctoar27953638","title":"Exploring professional theories, models, and frameworks for justice-oriented constructs: a scoping review","year":2024,"lang":"en","type":"review","venue":"Cadernos Brasileiros de Terapia Ocupacional ","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Engineering ethics; Sociology; Economic Justice; Management science; Epistemology; Knowledge management; Psychology; Political science; Computer science; Engineering; Law; Philosophy","score_opus":0.5526758705705631,"score_gpt":0.5671441697270805,"score_spread":0.014468299156517372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396614620","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000318263,0.97838795,0.013017465,0.00054614194,0.0030347037,0.0038911037,0.00062808587,0.00012560857,0.00033710233],"genre_scores_gemma":[0.000083471554,0.9891865,0.003925168,0.0013962743,0.00082560413,0.0032702966,0.00033415575,0.00009676902,0.0008817505],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9927139,0.0006592882,0.002344099,0.0014452543,0.0021171034,0.0007203358],"domain_scores_gemma":[0.99292547,0.0043677897,0.00092559424,0.0007836456,0.0005974941,0.0004000333],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0048983386,0.00084099977,0.002390505,0.0006261418,0.00051136594,0.0005270481,0.00082709064,0.0007289638,0.00084026693],"category_scores_gemma":[0.002221195,0.00056504423,0.0007392482,0.0010390751,0.00031569766,0.0011235344,0.0003912863,0.0018565994,0.00013096485],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003276338,0.00006497113,0.00006784118,0.15306866,0.00022608135,0.000014771653,0.00073001266,0.000011025656,3.8136463e-7,0.09971589,0.008854514,0.7372131],"study_design_scores_gemma":[0.0004517251,0.00008936615,0.000029840627,0.5777992,0.0020476526,0.00027586342,0.00041321313,0.0026938347,6.784107e-7,0.02357361,0.39172867,0.0008963601],"about_ca_topic_score_codex":0.0000011754058,"about_ca_topic_score_gemma":0.0000035152016,"teacher_disagreement_score":0.73631674,"about_ca_system_score_codex":0.0002727941,"about_ca_system_score_gemma":0.003427245,"threshold_uncertainty_score":0.9996801},"labels":[],"label_agreement":null},{"id":"W4396616775","doi":"10.1177/073491491904300204","title":"P-Values are not Sufficient but they are Necessary: Probing the Role and Application of Statistical Significance Testing in Public Administration Research","year":2019,"lang":"en","type":"article","venue":"Public Administration Quarterly","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École Nationale d'Administration Publique","funders":"","keywords":"Statistical hypothesis testing; Administration (probate law); Significance testing; Econometrics; Statistics; Political science; Mathematics; Law","score_opus":0.17841941646990322,"score_gpt":0.45156691234473073,"score_spread":0.2731474958748275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396616775","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9677189,0.00003644289,0.008048017,0.019101318,0.00011142022,0.0013685328,0.00006617249,0.000039485265,0.0035097133],"genre_scores_gemma":[0.9985161,0.000004182569,0.00069629087,0.00012480843,0.00007615338,0.00028479684,0.000052063555,0.000013766318,0.00023184647],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99381644,0.0010949224,0.0012520164,0.00075020787,0.0026254843,0.00046091285],"domain_scores_gemma":[0.99345785,0.0031155788,0.00091327773,0.0007410161,0.0016070906,0.0001651691],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.011709743,0.00019309341,0.00032234195,0.0004319382,0.00037286253,0.0011513252,0.00064198254,0.00011989829,0.00018455516],"category_scores_gemma":[0.0022787282,0.00014006557,0.000040189374,0.0013382863,0.00026880036,0.0011694916,0.000051195446,0.0003917015,0.00012173483],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020278501,0.0009643716,0.6093269,0.00009427696,0.000020791202,0.000004180702,0.005254522,0.00011936732,0.0047787568,0.22514218,0.0002791953,0.15381266],"study_design_scores_gemma":[0.0007718577,0.0020088765,0.6965722,0.000064623564,0.000009811596,0.000018499568,0.06975265,0.20228383,0.00095390587,0.02183629,0.0053792065,0.0003482496],"about_ca_topic_score_codex":0.000054130098,"about_ca_topic_score_gemma":0.0012819855,"teacher_disagreement_score":0.20330589,"about_ca_system_score_codex":0.000110723144,"about_ca_system_score_gemma":0.0011573564,"threshold_uncertainty_score":0.99988556},"labels":[],"label_agreement":null},{"id":"W4396707487","doi":"10.3138/cjpe-2024-0013","title":"Concluding Remarks: A Bright Future for Evaluation Capacity Building","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McGill University; University of Ottawa","funders":"","keywords":"Engineering ethics; Management science; Capacity building; Computer science; Political science; Engineering; Law","score_opus":0.4634754320822916,"score_gpt":0.5450116204168327,"score_spread":0.08153618833454113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396707487","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8842792,0.010270531,0.05553475,0.019739559,0.01683417,0.007507346,0.00007108438,0.00007293783,0.0056904387],"genre_scores_gemma":[0.98267025,0.00001714282,0.015043898,0.0001753322,0.0016694748,0.00024645796,0.000025075295,0.000019079831,0.00013327277],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9940431,0.0007384848,0.0011660373,0.00034935714,0.003340472,0.00036251018],"domain_scores_gemma":[0.99210423,0.0006291146,0.0005422503,0.00028104984,0.006000883,0.00044244464],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.048242357,0.00016873184,0.0002859178,0.0010963595,0.00038767303,0.0013069318,0.00044110997,0.00013795367,0.0023525523],"category_scores_gemma":[0.004999172,0.00012818984,0.0002700766,0.00112419,0.00007861318,0.0012900677,0.000010419978,0.00028572217,0.000042578326],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015452457,0.000013603873,0.0010523342,0.000020929472,0.00005660998,0.0000030156991,0.0014038712,0.0020999021,0.00017531023,0.0040172916,0.01357733,0.97756433],"study_design_scores_gemma":[0.0010514162,0.00030706023,0.00738551,0.00020380263,0.0002937847,0.00007712246,0.001096774,0.5994358,0.00028637718,0.048805684,0.34087327,0.00018340163],"about_ca_topic_score_codex":0.0001628309,"about_ca_topic_score_gemma":0.0063441354,"teacher_disagreement_score":0.97738093,"about_ca_system_score_codex":0.001214637,"about_ca_system_score_gemma":0.008695615,"threshold_uncertainty_score":0.9997298},"labels":[],"label_agreement":null},{"id":"W4396707874","doi":"10.3138/cjpe-2024-0011","title":"The Science and Practice of Evaluation Capacity Building","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa; McGill University","funders":"","keywords":"Capacity building; Architectural engineering; Political science; Engineering","score_opus":0.5353283803429555,"score_gpt":0.5759095146980391,"score_spread":0.04058113435508359,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396707874","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95738083,0.0077659893,0.001934958,0.016334267,0.003201207,0.0019187945,0.0000059448635,0.00001172041,0.011446261],"genre_scores_gemma":[0.99522144,0.000042983,0.004493799,0.00006605001,0.00011430831,0.000031832555,5.9813294e-7,0.000004673658,0.00002430116],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99187714,0.0009609808,0.00082280964,0.00020758707,0.0059053404,0.00022615468],"domain_scores_gemma":[0.9839262,0.0019633577,0.0005465417,0.0002442768,0.013043033,0.00027663462],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1488352,0.00007851487,0.00012755427,0.00071108754,0.00052526343,0.001299487,0.0003779135,0.0000392904,0.0002104704],"category_scores_gemma":[0.05493576,0.00004814404,0.000053422937,0.0018096846,0.00056800066,0.0018308095,0.000018213954,0.00019106145,0.000010488993],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009186798,0.000008628673,0.00038292498,0.000004771448,0.000016726952,0.0000012329784,0.0014021927,0.00088872894,0.0006823216,0.0063347835,0.00086990104,0.9893986],"study_design_scores_gemma":[0.00048439353,0.0004916078,0.021534728,0.00014729038,0.00029061333,0.0002826749,0.0041117296,0.7523365,0.0009838135,0.04317458,0.17603013,0.0001319397],"about_ca_topic_score_codex":0.00033211434,"about_ca_topic_score_gemma":0.0022900393,"teacher_disagreement_score":0.98926663,"about_ca_system_score_codex":0.0006180029,"about_ca_system_score_gemma":0.01473612,"threshold_uncertainty_score":0.99973726},"labels":[],"label_agreement":null},{"id":"W4396708036","doi":"10.3138/cjpe.38.3.ed-en","title":"Editor’s Remarks","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Philosophy","score_opus":0.23986684550211407,"score_gpt":0.53726516308728,"score_spread":0.29739831758516594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396708036","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40802038,0.031316463,0.02977652,0.08365179,0.2535668,0.0070697684,0.00006807716,0.00023124731,0.18629895],"genre_scores_gemma":[0.991924,0.000014370662,0.0025319273,0.00016733223,0.0044750264,0.00003175822,0.0000074488485,0.000009975775,0.000838153],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99599636,0.00034867862,0.0007634437,0.0001712244,0.0025084005,0.00021189549],"domain_scores_gemma":[0.99652624,0.00028781785,0.00023191837,0.00021919417,0.0023077265,0.00042709245],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.019522728,0.00008729533,0.00015133605,0.00085658184,0.00012858829,0.0010298449,0.0003767322,0.00007261011,0.0068802848],"category_scores_gemma":[0.0026851979,0.00006194687,0.00013877731,0.0009012755,0.00006105189,0.00081044494,0.0000071524605,0.00023540495,0.00043046143],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000029673306,0.000007654344,0.0016723007,0.0000036012727,0.00001651454,0.000010607311,0.0004852689,0.00046249697,0.000015470963,0.00071727793,0.181378,0.81522787],"study_design_scores_gemma":[0.00020631256,0.00024171131,0.009716845,0.00007642375,0.00005493559,0.00005469574,0.00047021595,0.092491984,0.000034297074,0.016600339,0.8799663,0.00008593234],"about_ca_topic_score_codex":0.00017835973,"about_ca_topic_score_gemma":0.007082405,"teacher_disagreement_score":0.8151419,"about_ca_system_score_codex":0.0003860287,"about_ca_system_score_gemma":0.008402396,"threshold_uncertainty_score":0.997219},"labels":[],"label_agreement":null},{"id":"W4396713285","doi":"10.2139/ssrn.4815131","title":"LogicalOutcomes Evaluation Planning Handbook","year":2024,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Social Innovation; LogicalOutcomes","funders":"","keywords":"Computer science","score_opus":0.2281378642438064,"score_gpt":0.5324886917360048,"score_spread":0.3043508274921984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396713285","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4557968,0.09188009,0.38038296,0.016712116,0.0045133014,0.0006580266,0.0000040025448,0.00023095026,0.049821727],"genre_scores_gemma":[0.98645616,0.0008278064,0.00013971818,0.00024109217,0.00051612145,0.000009968688,0.00000308635,0.000009534701,0.011796511],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9951931,0.00033280204,0.0005469301,0.00027777723,0.0025583215,0.0010910182],"domain_scores_gemma":[0.998784,0.00048727644,0.00012428015,0.00019676898,0.00033103797,0.00007662278],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.02799142,0.00011716171,0.0001603422,0.0003349668,0.00027455145,0.000729749,0.00040413236,0.00005838174,0.0024766983],"category_scores_gemma":[0.0007262512,0.00007179823,0.00014589929,0.00049922324,0.00003244053,0.0006141753,0.000036680598,0.0011489999,0.0011535279],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021391059,0.00001620751,0.007095189,0.0000021730734,0.000082386374,0.000006638548,0.0006676965,0.0025910153,0.00017194035,0.10912335,0.0022762446,0.8779458],"study_design_scores_gemma":[0.00036472984,0.00019356633,0.0033539147,0.000048103295,0.000040731044,0.00031256097,0.002383385,0.0651823,0.0000462504,0.86935526,0.058583107,0.0001361079],"about_ca_topic_score_codex":0.0000032174771,"about_ca_topic_score_gemma":0.00005237733,"teacher_disagreement_score":0.87780964,"about_ca_system_score_codex":0.0008469736,"about_ca_system_score_gemma":0.0044008074,"threshold_uncertainty_score":0.9996242},"labels":[],"label_agreement":null},{"id":"W4396818826","doi":"10.4000/11nru","title":"Un processus heuristique de l’écoformation pour une trans-formation des élèves et des pédagogues","year":2023,"lang":"fr","type":"article","venue":"Éducation relative à l environnement","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.2006076482582706,"score_gpt":0.4637485878494765,"score_spread":0.2631409395912059,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396818826","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6172249,0.001647332,0.22990306,0.118026614,0.0008628429,0.0011973865,0.000091323665,0.00020595024,0.030840624],"genre_scores_gemma":[0.9563577,0.0072591715,0.0088709025,0.0008443027,0.00015369199,0.0003398648,0.00044134693,0.000036935955,0.025696091],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99474,0.0013119276,0.0013092266,0.0005338378,0.0014407972,0.0006642267],"domain_scores_gemma":[0.9970897,0.0008891849,0.0007030675,0.0004301111,0.0006335025,0.0002544781],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0070372145,0.00039359345,0.00032973336,0.0005788827,0.0011612992,0.00035077377,0.00042354767,0.00023636152,0.0039033494],"category_scores_gemma":[0.0010636003,0.000366164,0.00016942114,0.0020459795,0.00057172234,0.004203186,0.00008898619,0.00039022954,0.0033634766],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007075253,0.0009796966,0.013908306,0.00056164846,0.00017418103,0.0000059003505,0.2809098,0.031438716,0.0012824209,0.095288575,0.012669358,0.56271064],"study_design_scores_gemma":[0.0015724989,0.00038318412,0.4122807,0.0005018135,0.00016211474,0.000027084472,0.058367185,0.10475892,0.0048129996,0.23263252,0.18382652,0.0006744436],"about_ca_topic_score_codex":0.0002106875,"about_ca_topic_score_gemma":0.00080862414,"teacher_disagreement_score":0.56203616,"about_ca_system_score_codex":0.0013867326,"about_ca_system_score_gemma":0.00095478387,"threshold_uncertainty_score":0.999879},"labels":[],"label_agreement":null},{"id":"W4396981416","doi":"10.69520/jipe.v5i.165","title":"Transformative Potential of Applied Research","year":2024,"lang":"en","type":"article","venue":"Journal of innovation in polytechnic education.","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Royal University","funders":"","keywords":"Transformative learning; Sociology; Engineering ethics; Engineering; Pedagogy","score_opus":0.19552990274807971,"score_gpt":0.5526039934204441,"score_spread":0.3570740906723644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396981416","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87005764,0.0009485254,0.04261147,0.014358533,0.0031499225,0.00053293817,0.000008197859,0.000022538215,0.06831021],"genre_scores_gemma":[0.9959594,0.000066854234,0.002991154,0.00014446846,0.00019777239,0.00001721025,0.00000340796,0.0000064641763,0.00061325886],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99501354,0.00013383615,0.0023719869,0.0001350912,0.0022053048,0.00014023922],"domain_scores_gemma":[0.99494916,0.0004932224,0.0005881668,0.00021633296,0.003721984,0.000031136547],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018701041,0.00007320495,0.00020158172,0.0045871795,0.00005840261,0.0001298956,0.0004634609,0.000075495926,0.00088532816],"category_scores_gemma":[0.0009682939,0.000053598887,0.000054223554,0.009142388,0.00010382397,0.00072703557,0.00002367711,0.0005144884,0.000052378626],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010712566,0.0003815026,0.0007133138,0.00006191614,0.000029071827,0.0000017540735,0.006724896,0.0011150212,0.033107813,0.54977256,0.04141531,0.3665697],"study_design_scores_gemma":[0.001095748,0.0005475358,0.05270107,0.00080828776,0.000026187254,0.00012013748,0.052069403,0.0063985465,0.04858343,0.7152981,0.12203974,0.00031181233],"about_ca_topic_score_codex":0.0000059931226,"about_ca_topic_score_gemma":0.000003162232,"teacher_disagreement_score":0.36625788,"about_ca_system_score_codex":0.00019379883,"about_ca_system_score_gemma":0.0034913593,"threshold_uncertainty_score":0.9693723},"labels":[],"label_agreement":null},{"id":"W4397008286","doi":"10.12688/f1000research.140810.2","title":"The SCOPE framework – implementing ideals of responsible research assessment","year":2024,"lang":"en","type":"preprint","venue":"F1000Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Public Health","funders":"Research England; Newcastle University; University of Alberta","keywords":"Scope (computer science); Plan (archaeology); Management science; Process (computing); Computer science; Engineering ethics; Process management; Knowledge management; Business; Engineering","score_opus":0.6811050588103094,"score_gpt":0.7363201011535562,"score_spread":0.05521504234324681,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4397008286","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27136645,0.0176778,0.0025053315,0.10675806,0.0060228296,0.0075127794,0.0005179227,0.00024679233,0.58739203],"genre_scores_gemma":[0.9234022,0.004503144,0.011075172,0.00012317851,0.00094182626,0.0010404021,0.00004377258,0.0001107337,0.058759578],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9615219,0.008489405,0.0029164604,0.0017324847,0.023362609,0.0019771461],"domain_scores_gemma":[0.9572769,0.03214589,0.0005185063,0.0038598706,0.005891768,0.00030707289],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","open_science","insufficient_payload"],"category_scores_codex":[0.20999196,0.00033984828,0.0006794319,0.002076913,0.0015832892,0.003694143,0.0057591577,0.00043913664,0.006303365],"category_scores_gemma":[0.019114388,0.00020432108,0.00038815985,0.004085585,0.00089942897,0.00017042144,0.01856515,0.0062529473,0.0023709908],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022537183,0.00014333214,0.006088166,0.00039071823,0.00023679569,0.000030257244,0.0020404211,0.00081575254,0.0016836994,0.41966295,0.36458126,0.2041013],"study_design_scores_gemma":[0.00013828243,0.0001779964,0.008714014,0.0006400782,0.000014364947,0.0000018115693,0.0033508902,0.009835283,0.0019114432,0.77071404,0.20430365,0.00019814297],"about_ca_topic_score_codex":0.00033912843,"about_ca_topic_score_gemma":0.00042712264,"teacher_disagreement_score":0.6520358,"about_ca_system_score_codex":0.0005260405,"about_ca_system_score_gemma":0.012001375,"threshold_uncertainty_score":0.9997165},"labels":[],"label_agreement":null},{"id":"W4397292890","doi":"10.31234/osf.io/fhk98","title":"Bestiary of Questionable Research Practices in Psychology","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; University of Toronto","funders":"","keywords":"Bestiary; Psychology; Epistemology; Psychoanalysis; Philosophy; Geography; Archaeology","score_opus":0.8011866590946499,"score_gpt":0.7477894020968091,"score_spread":0.053397256997840814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4397292890","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2007897,0.0029357928,0.00039499946,0.03996496,0.0022869746,0.0006414256,0.000019027013,0.000041054478,0.75292605],"genre_scores_gemma":[0.97501695,0.0007342634,0.005107105,0.00030719422,0.00013446549,0.000107027874,0.000013013003,0.000010616848,0.018569337],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9935682,0.0013733868,0.001035442,0.00078231376,0.0030030687,0.00023757767],"domain_scores_gemma":[0.99419826,0.003099641,0.0005048803,0.0009913509,0.0011495646,0.000056316432],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.038241554,0.00011467528,0.00031261198,0.0015888714,0.000039039303,0.00021050134,0.0010624984,0.0002831653,0.007067877],"category_scores_gemma":[0.0075881598,0.00008017721,0.00007151542,0.0012748429,0.00016187366,0.00016815978,0.0015937944,0.0015508027,0.0022044808],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019562166,0.0009752877,0.13582556,0.00055817753,0.00008226309,0.00006396205,0.0026356387,0.007844426,0.0006961018,0.16479348,0.46820405,0.21812545],"study_design_scores_gemma":[0.00013473896,0.000085408305,0.034330286,0.00019714808,0.000005655793,0.0000043242276,0.0007103465,0.01654442,0.00014234119,0.90620893,0.04152666,0.00010973721],"about_ca_topic_score_codex":0.00087552884,"about_ca_topic_score_gemma":0.0010429401,"teacher_disagreement_score":0.77422726,"about_ca_system_score_codex":0.00006647994,"about_ca_system_score_gemma":0.0015306753,"threshold_uncertainty_score":0.9985724},"labels":[],"label_agreement":null},{"id":"W4398133617","doi":"10.4337/9781035321100.00022","title":"Generative thinking in programme evaluation: Pawson in prison","year":2024,"lang":"en","type":"book-chapter","venue":"Edward Elgar Publishing eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Prison; Generative grammar; Epistemology; Sociology; Psychology; Cognitive science; Linguistics; Philosophy; Criminology","score_opus":0.23523795663791794,"score_gpt":0.43548306529383995,"score_spread":0.20024510865592202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398133617","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012342768,0.001056067,0.00015129389,0.00501256,0.0026213871,0.0016435114,0.000018911816,0.00013491872,0.98812705],"genre_scores_gemma":[0.059416465,0.000043559765,0.0027070208,0.0013510755,0.0014530497,0.00043500552,0.00020712071,0.00014588685,0.9342408],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9885762,0.00037836397,0.0019595982,0.0014597311,0.0069709783,0.000655133],"domain_scores_gemma":[0.9963476,0.0007627363,0.0006913361,0.0009857792,0.0010362536,0.00017629254],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.029490028,0.0005486868,0.000785578,0.0020325931,0.00018479062,0.0072855367,0.0014941761,0.000734961,0.0022492975],"category_scores_gemma":[0.00217527,0.00044713204,0.0002583546,0.00032646148,0.00010935324,0.0017803902,0.000494033,0.0020939226,0.00071154605],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033855744,0.000037014735,0.00089761225,0.00004537637,0.000056830904,0.000059716225,0.010898771,0.0005462455,0.000008821501,0.34417897,0.025777109,0.61745965],"study_design_scores_gemma":[0.000579085,0.00007536386,0.00049713446,0.00054870575,0.000032237287,0.0000059477466,0.0004964878,0.012403329,0.000023997703,0.49331066,0.49157956,0.00044749846],"about_ca_topic_score_codex":0.00013731752,"about_ca_topic_score_gemma":0.0054659015,"teacher_disagreement_score":0.6170122,"about_ca_system_score_codex":0.0012013112,"about_ca_system_score_gemma":0.0019527085,"threshold_uncertainty_score":0.99979806},"labels":[],"label_agreement":null},{"id":"W4398201568","doi":"10.5751/es-14768-290211","title":"A values-centered relational science model: supporting Indigenous rights and reconciliation in research","year":2024,"lang":"en","type":"article","venue":"Ecology and Society","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Indigenous; Environmental resource management; Political science; Environmental ethics; Sociology; Geography; Ecology; Environmental science; Biology","score_opus":0.38249969488274227,"score_gpt":0.5606096528298791,"score_spread":0.1781099579471368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398201568","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99531037,0.00013587617,0.0003840466,0.0010487402,0.00019673104,0.00016642919,0.0000034314412,0.0000150578,0.0027393315],"genre_scores_gemma":[0.9966524,0.0000579092,0.0013957724,0.00016625882,0.000031242882,0.000015415491,0.0000032822281,0.0000022604913,0.0016754053],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99803877,0.00018041513,0.00034768373,0.0003979961,0.0007726187,0.00026251897],"domain_scores_gemma":[0.9985718,0.0009634599,0.000051067924,0.0001098529,0.00024375664,0.000060029743],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021278767,0.000053792915,0.00010346889,0.00021317713,0.00067219045,0.00019442978,0.00013109982,0.00009428923,0.00017230008],"category_scores_gemma":[0.0004968537,0.000040801,0.000028428974,0.00073295616,0.0004472252,0.0006177533,0.00009968876,0.00029160434,0.000037895705],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035142602,0.00013627629,0.63607514,0.000044920598,0.000033715023,0.000013257293,0.2552229,0.00360665,0.0011086027,0.058677,0.009515403,0.03553101],"study_design_scores_gemma":[0.00017581244,0.000046972607,0.27460226,0.000009562508,0.0000018177037,0.0000054935085,0.0014295187,0.5744438,0.000029570348,0.14868343,0.00052440993,0.00004732744],"about_ca_topic_score_codex":0.000022443195,"about_ca_topic_score_gemma":0.00017435978,"teacher_disagreement_score":0.57083714,"about_ca_system_score_codex":0.0001528421,"about_ca_system_score_gemma":0.00078265794,"threshold_uncertainty_score":0.73748386},"labels":[],"label_agreement":null},{"id":"W4398272487","doi":"10.7910/dvn/mrlhno","title":"Survey responses about review, tenure, and promotion","year":2020,"lang":"en","type":"dataset","venue":"Harvard Dataverse","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Promotion (chess); Business; Political science","score_opus":0.24246385110605972,"score_gpt":0.46477219530384994,"score_spread":0.22230834419779022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398272487","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000027830165,0.00007098074,0.000045679553,0.00022143907,0.00059122825,0.00061283587,0.99826765,0.000026009364,0.00013633564],"genre_scores_gemma":[0.000017912424,0.024821265,0.00011556119,0.0030671966,0.00014499041,0.000039262293,0.9704454,0.000012153405,0.0013362544],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99387705,0.0017017083,0.000980202,0.000880283,0.0023120213,0.00024873565],"domain_scores_gemma":[0.9957134,0.0011488482,0.00067201135,0.0016966498,0.0005243271,0.0002447636],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.010828277,0.0003127702,0.0006483011,0.00026315113,0.00018193982,0.00041040243,0.0008905002,0.00018670574,0.043069646],"category_scores_gemma":[0.01698886,0.00023183509,0.00009265522,0.000700221,0.00012692972,0.0006339119,0.0005736586,0.00042327875,0.20739634],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006392915,0.000039542356,0.0003116687,0.00021232477,0.000019845875,0.000021007061,0.000012381169,4.516358e-7,0.0000018513476,0.000004822342,0.9948209,0.00449127],"study_design_scores_gemma":[0.00027440538,0.00012101344,0.01763776,0.00050355145,0.00007859944,0.000013841853,0.000018989938,0.00009285875,0.0000022931533,0.000039376067,0.9809522,0.00026510935],"about_ca_topic_score_codex":0.00013704796,"about_ca_topic_score_gemma":0.00050404895,"teacher_disagreement_score":0.16432668,"about_ca_system_score_codex":0.000047407626,"about_ca_system_score_gemma":0.00051839865,"threshold_uncertainty_score":0.99129146},"labels":[],"label_agreement":null},{"id":"W4398762519","doi":"10.29173/mlj874","title":"Anatomy of a Public Inquiry","year":2013,"lang":"en","type":"article","venue":"Manitoba Law Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Anatomy; Medicine","score_opus":0.30107566738571523,"score_gpt":0.4821927072333304,"score_spread":0.18111703984761518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398762519","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9522386,0.00009185135,0.0021834539,0.005149679,0.00096647395,0.00011891981,0.0000010072254,0.000011724179,0.039238278],"genre_scores_gemma":[0.9978175,0.000017979892,0.0010148899,0.00061682315,0.0003976976,0.0000059108056,6.171025e-7,0.0000052779087,0.00012329729],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969896,0.00025531455,0.0006946685,0.00013361344,0.0017132142,0.00021361017],"domain_scores_gemma":[0.99782276,0.00022999369,0.00039342392,0.00029607496,0.0010833666,0.00017436992],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0040684054,0.000081086,0.00017793334,0.00022177194,0.00026345515,0.0006358596,0.00061124476,0.000042701813,0.011731897],"category_scores_gemma":[0.00034939515,0.000052424213,0.00010113561,0.0003952874,0.00012895498,0.0012412752,0.00008193614,0.00020024639,0.001530068],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000061597157,0.00010125492,0.08434552,0.000004269933,0.00003816865,0.000006714374,0.00079085137,0.00006140866,0.00043610216,0.05360537,0.038179126,0.82242507],"study_design_scores_gemma":[0.001390297,0.00029605313,0.31504092,0.000032464806,0.000017246643,0.0003079145,0.067747205,0.004370001,0.00097065035,0.18469907,0.42481947,0.00030870092],"about_ca_topic_score_codex":0.0005260046,"about_ca_topic_score_gemma":0.004005759,"teacher_disagreement_score":0.8221164,"about_ca_system_score_codex":0.000046709367,"about_ca_system_score_gemma":0.00011574138,"threshold_uncertainty_score":0.9992474},"labels":[],"label_agreement":null},{"id":"W4399068220","doi":"10.1080/10705511.2024.2350023","title":"Investigating Structural Model Fit Evaluation","year":2024,"lang":"en","type":"article","venue":"Structural Equation Modeling A Multidisciplinary Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Structural equation modeling; Econometrics; Goodness of fit; Psychology; Statistics; Computer science; Mathematics","score_opus":0.42721309084629544,"score_gpt":0.5352635135144597,"score_spread":0.10805042266816423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399068220","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78742105,0.0005969009,0.2060662,0.0029766632,0.0019262495,0.00034636122,0.000017881943,0.00011314373,0.0005355445],"genre_scores_gemma":[0.96705663,0.000020119347,0.031386603,0.000070329,0.00095274835,0.000024610006,0.0000508209,0.000035419216,0.0004026888],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9912606,0.000592903,0.0018045864,0.0007519607,0.0050902604,0.0004997299],"domain_scores_gemma":[0.99639994,0.00049250433,0.0004557328,0.0004840922,0.0018384573,0.00032928592],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010450722,0.00036262991,0.00035148044,0.00078701077,0.0015171204,0.0021373923,0.0007111184,0.000158431,0.0014520745],"category_scores_gemma":[0.0018858217,0.00025214395,0.00029847978,0.000978922,0.00009852132,0.0033314459,0.000206956,0.00089841627,0.0001836765],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014298221,0.0000024316073,0.0012803003,0.000010255055,0.000025786847,0.0000027817598,0.0043858327,0.90495056,0.001063701,0.0016828169,0.000104565035,0.0864767],"study_design_scores_gemma":[0.0004001418,0.000047451074,0.0010239368,0.000089156536,0.00004738425,0.0001312842,0.0012745621,0.70221716,0.00003547797,0.29448006,0.000010049668,0.0002433433],"about_ca_topic_score_codex":0.000013796808,"about_ca_topic_score_gemma":0.00002189567,"teacher_disagreement_score":0.29279724,"about_ca_system_score_codex":0.00052136875,"about_ca_system_score_gemma":0.0015409392,"threshold_uncertainty_score":0.9999931},"labels":[],"label_agreement":null},{"id":"W4399070358","doi":"10.1016/j.jogc.2024.102481","title":"Looking in the Mirror: Challenges with Identifying One’s Own Role in Poor Outcomes and Behaviour, and the Impact on Quality Improvement Initiatives","year":2024,"lang":"en","type":"article","venue":"Journal of Obstetrics and Gynaecology Canada","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Quality (philosophy); Psychology; Quality management; Process management; Social psychology; Business; Marketing; Epistemology","score_opus":0.11752812365442276,"score_gpt":0.42943419151786477,"score_spread":0.311906067863442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399070358","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.984772,0.00786474,0.0000041554226,0.0060330504,0.0006381701,0.00015021581,0.000005578521,9.025921e-7,0.0005311849],"genre_scores_gemma":[0.9985115,0.00094338396,0.000031575528,0.00048192844,0.0000053986446,0.0000055759087,2.4831033e-7,0.000003284399,0.00001713632],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99796164,0.0003830279,0.0005568925,0.00015340431,0.0007954997,0.00014955548],"domain_scores_gemma":[0.9894109,0.010025501,0.0002896331,0.00010509562,0.000115659175,0.000053237844],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005772531,0.00010178739,0.00029846345,0.00033957112,0.000102738595,0.00022493755,0.00017888048,0.000039366365,0.000053037194],"category_scores_gemma":[0.0017563241,0.000041515792,0.000031499294,0.000329511,0.000092517774,0.00024557672,0.0000443966,0.00034597627,1.7660234e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020139472,0.000049237147,0.8568328,0.000012626262,0.00004917751,0.0001244815,0.0047667674,0.000034311746,0.0000025895802,0.001827122,0.000024440313,0.13625629],"study_design_scores_gemma":[0.0014135399,0.0002777833,0.97968715,0.000014566059,0.000017425864,0.000010405418,0.0153193185,0.00045699038,0.000004223419,0.0026217396,0.00012050737,0.00005633598],"about_ca_topic_score_codex":0.01272643,"about_ca_topic_score_gemma":0.17898926,"teacher_disagreement_score":0.16626284,"about_ca_system_score_codex":0.00025432595,"about_ca_system_score_gemma":0.00059331476,"threshold_uncertainty_score":0.9938479},"labels":[],"label_agreement":null},{"id":"W4399100676","doi":"10.23941/ejpe.v17i1.849","title":"The Challenge of Choosing Well","year":2024,"lang":"en","type":"article","venue":"Erasmus Journal for Philosophy and Economics","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.20906842203831233,"score_gpt":0.4478009860038947,"score_spread":0.23873256396558235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399100676","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5865501,0.022929061,0.0032729222,0.17068478,0.0151557,0.0006523234,0.0000829839,0.000036201047,0.20063592],"genre_scores_gemma":[0.99332637,0.004843723,0.00023850932,0.0001662774,0.0007609388,0.000004119541,8.916013e-7,0.0000072494045,0.0006519408],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99900305,0.000035190325,0.0005339435,0.00014580261,0.00015870115,0.00012333776],"domain_scores_gemma":[0.9986589,0.0008523109,0.00016725317,0.00014868709,0.00010469083,0.00006816102],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036069073,0.00007208339,0.00013893694,0.00010998889,0.00043732073,0.0005229498,0.00022911756,0.000034518354,0.00018209232],"category_scores_gemma":[0.000110462795,0.000041807176,0.00012333805,0.00007053985,0.00006343571,0.00040049583,0.000031327927,0.000146725,0.000040734085],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010476567,0.000028238537,0.00033888666,0.000030635965,0.00009645034,0.0000014160723,0.0015189276,0.0012502645,0.000018468476,0.6895122,0.0059673116,0.30113244],"study_design_scores_gemma":[0.00017177404,0.000097260745,0.00010386374,0.000020996507,0.000008015487,0.000021276095,0.00016158045,0.024198052,0.00003777455,0.65708995,0.31804144,0.00004799477],"about_ca_topic_score_codex":6.0903386e-7,"about_ca_topic_score_gemma":0.000006052793,"teacher_disagreement_score":0.40677625,"about_ca_system_score_codex":0.000027595765,"about_ca_system_score_gemma":0.00009700602,"threshold_uncertainty_score":0.5042817},"labels":[],"label_agreement":null},{"id":"W4399172241","doi":"10.4324/9781032669618","title":"Theories of Change in Reality","year":2024,"lang":"en","type":"book","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"European Commission; McGill University","keywords":"Framing (construction); Bureaucracy; Nothing; Citizen journalism; Theory of change; Political science; Psychological intervention; Sociology; Public relations; Management science; Engineering; Epistemology; Psychology; Politics; Law; Civil engineering","score_opus":0.5655627609808765,"score_gpt":0.5828572229131757,"score_spread":0.01729446193229911,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399172241","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000094210525,0.00039418324,0.000054749566,0.0016772338,0.00054343994,0.0002020846,0.000040689705,0.000015915106,0.9969775],"genre_scores_gemma":[0.02379176,0.00013984529,0.00006394811,0.00033723016,0.00014793285,0.000021609585,0.000019018362,0.0000071540544,0.9754715],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99738675,0.00009314869,0.0006677749,0.00028007076,0.001478822,0.000093439965],"domain_scores_gemma":[0.99857146,0.00055251474,0.00018013861,0.00046621752,0.00020212977,0.000027571628],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.005475357,0.00010826348,0.000319005,0.00038806495,0.000012768735,0.00006379969,0.000379586,0.00013258768,0.013013915],"category_scores_gemma":[0.0002154028,0.0000650949,0.000092824295,0.00027137314,0.00007796705,0.00014886253,0.00012556175,0.00017631477,0.0012217023],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000073149517,0.000012014584,0.000703351,0.00003959347,0.0000072886305,0.0000021319865,0.0013283384,0.000002331981,7.364191e-7,0.81226194,0.13210337,0.053531613],"study_design_scores_gemma":[0.000045396195,0.000023460432,0.0022607327,0.00007276041,0.000004829919,3.4472248e-7,0.00011088811,0.0003824146,0.00001032833,0.5585043,0.4385214,0.00006317711],"about_ca_topic_score_codex":0.00008538032,"about_ca_topic_score_gemma":0.0014257276,"teacher_disagreement_score":0.30641803,"about_ca_system_score_codex":0.00007473266,"about_ca_system_score_gemma":0.00053633464,"threshold_uncertainty_score":0.99955595},"labels":[],"label_agreement":null},{"id":"W4399186559","doi":"10.1515/9782760547971-fm","title":"Front Matter","year":2017,"lang":"fr","type":"paratext","venue":"Presses de l'Université du Québec eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec; Bibliothèque et Archives nationales du Québec; Université du Québec à Montréal","funders":"","keywords":"Front (military); Physics; Meteorology","score_opus":0.05658611853439106,"score_gpt":0.3343479149476997,"score_spread":0.27776179641330867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399186559","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024936186,0.00398852,0.0047216844,0.0068473686,0.0031688665,0.0006337231,0.00019390571,0.00005368709,0.9554561],"genre_scores_gemma":[0.11078146,0.00066340755,0.0005505781,0.0016305828,0.00076156436,0.000030515923,0.000054446158,0.000059875492,0.8854676],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9948605,0.0005921021,0.0008320256,0.0011203472,0.0017123716,0.00088267744],"domain_scores_gemma":[0.99429315,0.0010094205,0.0012440605,0.0021056482,0.0008389896,0.00050872465],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0014016975,0.0007205863,0.00092574226,0.00042331056,0.001575333,0.0013459407,0.0038042301,0.0006155826,0.7614831],"category_scores_gemma":[0.00027552986,0.00066286104,0.0005172617,0.000057434874,0.0007238016,0.00071790593,0.0012522247,0.00083810283,0.60551417],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001410564,0.00007478678,0.038429566,0.000115504285,0.00019222623,0.00007825281,0.00684814,0.00047054345,0.00010432847,0.000053231335,0.8246047,0.1288877],"study_design_scores_gemma":[0.00094496924,0.000119504955,0.021698449,0.000317777,0.00028665486,0.00006117254,0.0010346128,0.00336177,0.00042027934,0.000276332,0.9707423,0.0007361884],"about_ca_topic_score_codex":0.04409652,"about_ca_topic_score_gemma":0.05404535,"teacher_disagreement_score":0.15596887,"about_ca_system_score_codex":0.0010390824,"about_ca_system_score_gemma":0.0059751263,"threshold_uncertainty_score":0.9997245},"labels":[],"label_agreement":null},{"id":"W4399271928","doi":"","title":"Étude de l'adoption d'outils d'IA pour le profilage et la prédiction de la réussite par les enseignants du postsecondaire","year":2024,"lang":"fr","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Université Laval","funders":"","keywords":"Diction; Humanities; Philosophy; Political science; Linguistics; Poetry","score_opus":0.04137162854704738,"score_gpt":0.35319851823824966,"score_spread":0.31182688969120226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399271928","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6274553,0.0048632757,0.18308835,0.05133269,0.0006441002,0.0005563535,0.000115627205,0.00033885892,0.13160546],"genre_scores_gemma":[0.930555,0.0029041308,0.020808825,0.00044572493,0.000081957085,0.00008188141,0.0001497362,0.000057913796,0.04491483],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97690856,0.019483242,0.00093499257,0.000899513,0.0011400125,0.00063367304],"domain_scores_gemma":[0.9907741,0.005623517,0.000424107,0.0011864747,0.0016522513,0.00033953786],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.037133038,0.00039386298,0.00037205947,0.0004311262,0.0009883328,0.0022961805,0.0010077205,0.0004540115,0.0016062246],"category_scores_gemma":[0.0028136382,0.0003844531,0.00029682193,0.0011260264,0.000577045,0.0012345233,0.00037491455,0.0008175137,0.0005319923],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004642012,0.0012332924,0.030670127,0.00026311158,0.00012879707,0.000059897455,0.048859846,0.0006237763,0.02598417,0.26492962,0.010264406,0.61693656],"study_design_scores_gemma":[0.0014831286,0.0000068050363,0.27208593,0.004146646,0.0001573995,0.00036368228,0.0040537366,0.362901,0.057793994,0.017936034,0.27820987,0.0008617592],"about_ca_topic_score_codex":0.001627596,"about_ca_topic_score_gemma":0.0018436499,"teacher_disagreement_score":0.6160748,"about_ca_system_score_codex":0.00036583358,"about_ca_system_score_gemma":0.0028758838,"threshold_uncertainty_score":0.99986076},"labels":[],"label_agreement":null},{"id":"W4399305464","doi":"10.1097/cxa.0000000000000204","title":"Reporting on Diverse Current Practices","year":2024,"lang":"en","type":"article","venue":"The Canadian Journal of Addiction","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Current (fluid); Computer science; Geology; Oceanography","score_opus":0.4241677502304784,"score_gpt":0.5369974780365094,"score_spread":0.11282972780603101,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399305464","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8759695,0.0043084486,0.0010932618,0.049876455,0.021430872,0.00023772809,0.000021118749,0.000026685431,0.04703589],"genre_scores_gemma":[0.9984593,0.000048653015,0.000038171434,0.0001931811,0.00056694896,8.6712123e-7,8.0300407e-7,0.0000034361174,0.0006886485],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978517,0.00015816503,0.000840157,0.000093716844,0.00094558985,0.00011061416],"domain_scores_gemma":[0.9967677,0.00045718698,0.0020514177,0.00016175654,0.00038764754,0.00017429498],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0105639845,0.000050801078,0.00009026434,0.0003822148,0.00034420195,0.0005936435,0.00023716918,0.00002178775,0.0016978161],"category_scores_gemma":[0.005601691,0.000026785608,0.00008797662,0.0004147417,0.000040763276,0.00055328046,0.0000067492333,0.00033184915,0.00031512033],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019996702,0.000009445174,0.007311914,0.000003289003,0.000041969946,0.00008353113,0.002317774,0.0024719415,0.000034727884,0.003935586,0.19068821,0.7930816],"study_design_scores_gemma":[0.00007727823,0.00013096114,0.034997422,0.00012348653,0.00003994085,0.00017691849,0.0010480983,0.006404609,0.00005856719,0.004001658,0.9528916,0.000049492042],"about_ca_topic_score_codex":0.00096722896,"about_ca_topic_score_gemma":0.023507368,"teacher_disagreement_score":0.7930321,"about_ca_system_score_codex":0.00021181827,"about_ca_system_score_gemma":0.0020488848,"threshold_uncertainty_score":0.99921477},"labels":[],"label_agreement":null},{"id":"W4399318766","doi":"10.22329/jtl.v18i1.8066","title":"Where Research Begins: Choosing a Research Project That Matters to You (and the World)","year":2024,"lang":"en","type":"article","venue":"Journal of Teaching and Learning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Data science; Management science; Engineering","score_opus":0.44392387005953354,"score_gpt":0.6160897126705749,"score_spread":0.17216584261104134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399318766","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8051305,0.0072972006,0.001354899,0.1709211,0.00048001012,0.00030272207,4.7615322e-7,0.000021710008,0.014491375],"genre_scores_gemma":[0.97377765,0.0002668016,0.0015319583,0.00039258722,0.00032612373,0.000005452444,1.1993163e-7,0.000011704324,0.023687582],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98960775,0.006441798,0.0004444623,0.00024052965,0.00295454,0.00031093237],"domain_scores_gemma":[0.9908589,0.00838991,0.00011712686,0.00016047893,0.0003604256,0.00011314254],"candidate_categories":["metaresearch","sts","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.14431214,0.00008231978,0.00020876362,0.0015465704,0.0016458732,0.002622401,0.0003759562,0.000031945197,0.00011236489],"category_scores_gemma":[0.005548554,0.000041491905,0.00006875864,0.0009054771,0.0001888471,0.0005626726,0.00021441793,0.004250566,0.000044053966],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034428513,0.000029667848,0.01912314,0.00008575595,0.00007684239,0.000047303347,0.10850061,0.0014021337,0.00060234143,0.0042820303,0.16147894,0.70402694],"study_design_scores_gemma":[0.00047297674,0.0002234116,0.0042533944,0.0010388559,0.000011018524,0.00013066422,0.0591319,0.014539589,0.000015250941,0.0018719722,0.91823226,0.000078676334],"about_ca_topic_score_codex":0.00017663695,"about_ca_topic_score_gemma":0.00007927177,"teacher_disagreement_score":0.7567533,"about_ca_system_score_codex":0.00008030859,"about_ca_system_score_gemma":0.00027609852,"threshold_uncertainty_score":0.9996539},"labels":[],"label_agreement":null},{"id":"W4399410473","doi":"10.1007/978-981-19-6056-7_100","title":"Marcia Rioux: A Voice for Impact","year":2024,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Linguistics; Philosophy","score_opus":0.30916988473459545,"score_gpt":0.5552553324465476,"score_spread":0.24608544771195212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399410473","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000032716198,0.0003731038,0.001769648,0.0019960431,0.0010248495,0.0005446555,0.0001821176,0.00006956563,0.9940073],"genre_scores_gemma":[0.003051831,0.00006185021,0.00081633276,0.00070066366,0.00039949533,0.000030795534,0.000045514116,0.000037594284,0.99485594],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967983,0.000012063564,0.00068491057,0.0005647291,0.0017250065,0.00021500832],"domain_scores_gemma":[0.99758625,0.000944625,0.00021401267,0.0006313362,0.0004960846,0.00012768494],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0027328513,0.00027329577,0.00039278134,0.00043454074,0.0000903612,0.00048907223,0.0005484605,0.00021950321,0.05216803],"category_scores_gemma":[0.0001981678,0.00015962748,0.0005398144,0.00008454812,0.0000453516,0.00018423889,0.00012398553,0.00022717247,0.024643606],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026456046,0.0000064153974,0.000037835478,0.000017258302,0.00007682913,0.0000026469534,0.000098210614,0.00002732931,0.0000051396437,0.42531037,0.5224686,0.051922858],"study_design_scores_gemma":[0.000109544075,0.00009628064,0.00010988539,0.00003108051,0.00003296531,0.0000031808804,0.000020071071,0.0033904926,0.0000036916322,0.34781474,0.6482353,0.0001527465],"about_ca_topic_score_codex":0.000013210791,"about_ca_topic_score_gemma":0.00019481734,"teacher_disagreement_score":0.1257667,"about_ca_system_score_codex":0.00013812579,"about_ca_system_score_gemma":0.00051167124,"threshold_uncertainty_score":0.9761158},"labels":[],"label_agreement":null},{"id":"W4399455523","doi":"10.18806/tesl.v40i2/1392","title":"EAP Practitioners in Canada","year":2023,"lang":"en","type":"article","venue":"TESL Canada Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Waterloo; York University","funders":"Social Sciences and Humanities Research Council of Canada; University of Waterloo; York University","keywords":"Linguistics; Psychology; Pedagogy; Sociology; Philosophy","score_opus":0.18762891323451958,"score_gpt":0.4616068913340979,"score_spread":0.2739779780995783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399455523","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92017573,0.0006626349,0.000069913534,0.061626934,0.00360919,0.00013330241,0.000030626765,0.000016994889,0.013674674],"genre_scores_gemma":[0.9715985,0.000033299864,0.00006545729,0.02624744,0.00015790357,0.0000037091395,0.0000043818986,0.0000055185697,0.0018837932],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99620664,0.00013554016,0.0004987098,0.00013332948,0.0027477215,0.00027805485],"domain_scores_gemma":[0.99863416,0.0005419824,0.00020825546,0.00016912428,0.0002529988,0.0001934497],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002830585,0.00006990322,0.00012765058,0.00021918581,0.00018516554,0.0001270859,0.0003407116,0.000015465723,0.042560533],"category_scores_gemma":[0.0009567964,0.000053305317,0.000021501843,0.001113154,0.000010258934,0.00028843776,0.00002969806,0.0002644126,0.00007780894],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000059311637,0.0000027789629,0.017929126,8.571586e-7,0.0000052223995,0.00020802527,0.000084335465,0.008840338,0.000023196282,0.00013081908,0.9586464,0.014122977],"study_design_scores_gemma":[0.0003441671,0.000013676935,0.27600423,0.000011360963,0.0000023391283,0.00008550164,0.0042920094,0.011168697,0.000036942216,0.00151216,0.70641285,0.00011604165],"about_ca_topic_score_codex":0.9953947,"about_ca_topic_score_gemma":0.9999324,"teacher_disagreement_score":0.25807512,"about_ca_system_score_codex":0.0017785786,"about_ca_system_score_gemma":0.036169343,"threshold_uncertainty_score":0.96929467},"labels":[],"label_agreement":null},{"id":"W4399460746","doi":"10.4102/aej.v12i2.731","title":"Decolonising national evaluation systems","year":2024,"lang":"en","type":"article","venue":"African Evaluation Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Francophone University Association","funders":"","keywords":"Computer science","score_opus":0.44198206295271253,"score_gpt":0.5874928836967103,"score_spread":0.14551082074399774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399460746","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33432665,0.015610088,0.10713662,0.0422672,0.03163862,0.003778156,0.000063824955,0.00036123645,0.4648176],"genre_scores_gemma":[0.9961607,0.000035959503,0.0005729193,0.00021025863,0.0015229443,0.00010816328,0.0000210954,0.000018230901,0.0013497662],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98024625,0.002194042,0.0013145526,0.0004758487,0.015456325,0.0003129748],"domain_scores_gemma":[0.9901211,0.001436946,0.00045627003,0.00028958396,0.0074878423,0.0002082334],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.08764315,0.00017992561,0.0002331193,0.0010917492,0.0005971898,0.003174657,0.0004931608,0.00008718738,0.012736401],"category_scores_gemma":[0.0073227407,0.00013291134,0.00017465273,0.001658806,0.000066620116,0.0017149596,0.000046588706,0.00037966314,0.0019821755],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029185743,0.000057660498,0.0015690564,0.000009786726,0.00013020534,0.0000071168743,0.0028391432,0.21016243,0.00042317543,0.013974771,0.082427464,0.68837],"study_design_scores_gemma":[0.00048598927,0.00007679149,0.00629492,0.000056972196,0.00010107231,0.00021794789,0.0019624615,0.83395666,0.000024629593,0.052520975,0.10414657,0.00015503235],"about_ca_topic_score_codex":0.0000054778434,"about_ca_topic_score_gemma":0.000013030159,"teacher_disagreement_score":0.68821496,"about_ca_system_score_codex":0.0014178687,"about_ca_system_score_gemma":0.005412766,"threshold_uncertainty_score":0.9987949},"labels":[],"label_agreement":null},{"id":"W4399627079","doi":"10.1075/ld.00175.let","title":"Different levels of co-construction in dialogue","year":2024,"lang":"en","type":"article","venue":"Language and Dialogue","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Normative; Dimension (graph theory); Context (archaeology); Action (physics); Adaptation (eye); Work (physics); Sociology; Epistemology; Psychology; Engineering; Geography; Mathematics","score_opus":0.10507307032279171,"score_gpt":0.4405329134610869,"score_spread":0.3354598431382952,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399627079","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99088657,0.00073480327,0.00082138134,0.00028562103,0.0004362831,0.00009896013,0.00008086251,0.000019929186,0.0066355877],"genre_scores_gemma":[0.9992553,0.000051021896,0.00016332374,0.00009534006,0.00009247059,0.000007865644,0.000021566953,0.000004106959,0.00030899033],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9987959,0.00010649762,0.00035093783,0.00021236748,0.00042349202,0.00011079942],"domain_scores_gemma":[0.999241,0.00046168154,0.000049937837,0.00017196244,0.000033162305,0.000042238178],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009498098,0.000077027194,0.0001785808,0.00026111418,0.000026743868,0.00009711333,0.000108284934,0.00005142963,0.0009363533],"category_scores_gemma":[0.00021672003,0.000050491915,0.00004328176,0.00028905002,0.000068199755,0.00019665105,0.00003178436,0.000087186345,0.0000738836],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036119836,0.00007450106,0.124626756,0.00006537937,0.000021958478,0.000046903086,0.021713108,0.000051993382,0.0131715415,0.02505065,0.0011730168,0.81396806],"study_design_scores_gemma":[0.0012478268,0.00020590404,0.91115415,0.00017698102,0.000027746577,0.000035969362,0.0106487125,0.007950919,0.019964973,0.042996854,0.0052267876,0.00036315573],"about_ca_topic_score_codex":0.00011444247,"about_ca_topic_score_gemma":0.00063229684,"teacher_disagreement_score":0.8136049,"about_ca_system_score_codex":0.000016789954,"about_ca_system_score_gemma":0.000051721163,"threshold_uncertainty_score":0.99997693},"labels":[],"label_agreement":null},{"id":"W4399652816","doi":"10.1111/capa.12571","title":"Navigating the challenges of policy evaluation","year":2024,"lang":"en","type":"article","venue":"Canadian Public Administration","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Accountability; Work (physics); Rationality; Political science; Management science; Engineering ethics; Public relations; Public administration; Engineering","score_opus":0.30864401936753194,"score_gpt":0.5311292359529306,"score_spread":0.22248521658539866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399652816","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1828386,0.0020373089,0.00049404375,0.74998033,0.0007971847,0.000529464,0.00004133045,0.00003960128,0.06324217],"genre_scores_gemma":[0.9989862,0.000036143363,0.000054906865,0.0003579533,0.00027025922,0.000043871052,0.000023716522,0.000006160892,0.00022078284],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974661,0.0002671021,0.00045541578,0.00023810379,0.001382956,0.00019031146],"domain_scores_gemma":[0.9981876,0.00050305633,0.000117431744,0.00036880537,0.00064064516,0.00018245542],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0075016953,0.00007790691,0.00008988748,0.00021694312,0.00019770811,0.00051157083,0.00034269528,0.000059940092,0.0015018907],"category_scores_gemma":[0.0030534745,0.000050911287,0.000055746645,0.000983043,0.00007391582,0.0006133865,0.000013383484,0.00017386387,0.00021943607],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[6.6392874e-7,0.000003745206,0.00019561268,0.000004239656,0.000006162869,6.392454e-7,0.0005292247,0.000007982188,0.000017023558,0.5249663,0.0011863736,0.47308204],"study_design_scores_gemma":[0.00025908597,0.00025648114,0.022623166,0.00012113712,0.000034595287,0.000045028202,0.011060711,0.23649092,0.0005000148,0.13273229,0.5955983,0.00027833044],"about_ca_topic_score_codex":0.0007458447,"about_ca_topic_score_gemma":0.14796856,"teacher_disagreement_score":0.8161476,"about_ca_system_score_codex":0.00027572399,"about_ca_system_score_gemma":0.011488598,"threshold_uncertainty_score":0.99941087},"labels":[],"label_agreement":null},{"id":"W4399663009","doi":"10.55016/ojs/ajer.v60i3.55838","title":"Essentials of a Qualitative Doctorate (2012) by Immy Holloway &amp; Lorraine Brown","year":2015,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Qualitative research; Psychology; Pedagogy; Sociology; Social science","score_opus":0.7195985490511484,"score_gpt":0.6816349388327946,"score_spread":0.037963610218353816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399663009","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90333474,0.0012818662,0.00025567922,0.044365574,0.00077354687,0.0001910135,0.000021143307,4.108896e-7,0.049776044],"genre_scores_gemma":[0.8473717,0.0000962038,0.00082528207,0.00012562459,0.00030786946,0.000010676374,0.000020641548,0.0000094973875,0.15123248],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99065256,0.0021755178,0.0013922513,0.00022640689,0.005235369,0.000317907],"domain_scores_gemma":[0.95325834,0.03614321,0.00087392936,0.00038736226,0.008907894,0.00042926738],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.028524378,0.000115574185,0.00035976476,0.000755806,0.00013611335,0.00018910551,0.0009602317,0.00006507595,0.03813714],"category_scores_gemma":[0.06315709,0.00007927478,0.00013904952,0.0014005055,0.0003247088,0.0010857597,0.000106064545,0.00036781817,0.0016999688],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026858906,0.00062590523,0.010491107,0.000011205093,0.000096847245,2.3582326e-7,0.019426662,0.0001837683,0.0049883327,0.012728945,0.9501015,0.0010768797],"study_design_scores_gemma":[0.0022776953,0.00088845135,0.012041001,0.00013206998,0.00003442023,0.000056637975,0.025401028,0.0002245427,0.00277223,0.057054892,0.8988265,0.0002905722],"about_ca_topic_score_codex":0.00043642372,"about_ca_topic_score_gemma":0.0005604187,"teacher_disagreement_score":0.10145645,"about_ca_system_score_codex":0.00016412341,"about_ca_system_score_gemma":0.0045606545,"threshold_uncertainty_score":0.9990773},"labels":[],"label_agreement":null},{"id":"W4399737277","doi":"10.24095/hpcdp.44.6.07f","title":"Prescription sociale à l’intention des personnes noires : l’importance d’une approche afrocentrique","year":2024,"lang":"fr","type":"article","venue":"Promotion de la santé et prévention des maladies chroniques au Canada","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"LogicalOutcomes","funders":"","keywords":"Political science; Humanities; Medical prescription; Art; Medicine","score_opus":0.047416088798972196,"score_gpt":0.3803430704859747,"score_spread":0.3329269816870025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399737277","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.705298,0.034687582,0.090772554,0.012291897,0.0048667556,0.0016893817,0.00025921897,0.0005321225,0.14960249],"genre_scores_gemma":[0.848725,0.016528372,0.0052836076,0.00024639769,0.0009356263,0.00031311056,0.00018275375,0.00007454586,0.12771057],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9930347,0.002039626,0.0012546544,0.0009874312,0.0017188891,0.0009646549],"domain_scores_gemma":[0.9971445,0.0006767252,0.0004955126,0.0004185058,0.00095666136,0.00030805392],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0066229748,0.00053664873,0.00048673077,0.00037901266,0.00095261534,0.0015227626,0.0004816506,0.0003832829,0.029577538],"category_scores_gemma":[0.0010601509,0.00052486657,0.00037265048,0.0013312533,0.0011314132,0.0029746753,0.00014009523,0.00065274397,0.000099854835],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00018326749,0.001135638,0.08017933,0.010909662,0.0006112842,0.00027456955,0.04174383,0.0015614607,0.0035218035,0.051651042,0.25345567,0.55477244],"study_design_scores_gemma":[0.0011272228,0.0007197665,0.13500068,0.008391382,0.00041735632,0.00046216138,0.02002044,0.105465345,0.005031629,0.116590485,0.6054281,0.0013454086],"about_ca_topic_score_codex":0.0806625,"about_ca_topic_score_gemma":0.90001523,"teacher_disagreement_score":0.81935275,"about_ca_system_score_codex":0.0057169297,"about_ca_system_score_gemma":0.0065435665,"threshold_uncertainty_score":0.9997203},"labels":[],"label_agreement":null},{"id":"W4399755831","doi":"10.62477/jkmp.v24i2.398","title":"Evidence-based Management in a Domain of Contested Information: Public Managers, Climate Change, and the Precursor of Knowledge Management","year":2024,"lang":"en","type":"article","venue":"Journal of Knowledge Management and Practice","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Climate change; Knowledge management; Public domain; Domain (mathematical analysis); Business; Data management; Environmental resource management; Political science; Computer science; Geography; Environmental science; Ecology; Data mining; Biology","score_opus":0.2844879896912839,"score_gpt":0.46623188821656864,"score_spread":0.18174389852528472,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399755831","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014758099,0.08327934,0.008542819,0.035841912,0.0021557873,0.0041450975,0.000015742562,0.00004224668,0.85121894],"genre_scores_gemma":[0.9538284,0.03776639,0.006202,0.0004943171,0.00009788766,0.00010749338,0.00000279116,0.0000140098755,0.0014866984],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99511385,0.0011972861,0.0018258526,0.00026789954,0.0013142343,0.00028085188],"domain_scores_gemma":[0.99341184,0.0040672594,0.0012640749,0.0004206721,0.00073196675,0.00010416778],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024732895,0.00022899419,0.0005169354,0.0018011539,0.00012527956,0.0005292671,0.00065070036,0.00005733822,0.00011944339],"category_scores_gemma":[0.0006428325,0.00014384593,0.00015478062,0.001906924,0.00025129635,0.004376291,0.0005029466,0.00025864725,0.000055563254],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015640038,0.0003247407,0.0014016181,0.0022042345,0.0005446293,0.00005533483,0.006629158,0.000028919909,0.000002084035,0.3451685,0.005029734,0.63704705],"study_design_scores_gemma":[0.010724459,0.0007316898,0.035252683,0.0063271243,0.0013353457,0.000082307095,0.052360512,0.018985175,0.000025258005,0.010260952,0.863457,0.00045744097],"about_ca_topic_score_codex":0.0000030693564,"about_ca_topic_score_gemma":0.00002397714,"teacher_disagreement_score":0.9390703,"about_ca_system_score_codex":0.000087174696,"about_ca_system_score_gemma":0.00006717408,"threshold_uncertainty_score":0.8571977},"labels":[],"label_agreement":null},{"id":"W4399822254","doi":"10.1515/9782760526884-006","title":"Analyse de l’argumentation de la validité des inférences d’évaluation dans les politiques institutionnelles d’évaluation des apprentissages des établissements d’enseignement collégial québécois","year":2011,"lang":"fr","type":"book-chapter","venue":"Presses de l'Université du Québec eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Humanities; Art","score_opus":0.10170538456131176,"score_gpt":0.33717002100351073,"score_spread":0.23546463644219898,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399822254","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75122154,0.0012972013,0.07900264,0.000105634885,0.00019749845,0.00083525456,0.000101564096,0.000139247,0.16709945],"genre_scores_gemma":[0.9639383,0.0058993166,0.014204417,0.00011167868,0.00023971336,0.00011853979,0.00016009506,0.000069858965,0.015258095],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9925117,0.002123977,0.0013872756,0.00103398,0.0020031135,0.00093993894],"domain_scores_gemma":[0.99408054,0.0017594538,0.0012590751,0.0006668468,0.0017369164,0.0004971435],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["sts"],"category_scores_codex":[0.0056445054,0.00088505493,0.0007394491,0.0010412605,0.0029563096,0.00085889926,0.0012294825,0.0005793781,0.012150031],"category_scores_gemma":[0.0010869172,0.00089959765,0.0004693338,0.00026618186,0.0030703938,0.0017117925,0.0004423421,0.0005076565,0.00021550253],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00031692928,0.0003283178,0.29389122,0.0003150387,0.0006674889,0.000050196104,0.1889325,0.00640133,0.004627795,0.010105768,0.00035562296,0.49400783],"study_design_scores_gemma":[0.004465692,0.0015114682,0.62863636,0.0027433124,0.0048805177,0.00027407636,0.09730397,0.022986177,0.032652162,0.13653015,0.065295584,0.0027205271],"about_ca_topic_score_codex":0.34147507,"about_ca_topic_score_gemma":0.5445228,"teacher_disagreement_score":0.4912873,"about_ca_system_score_codex":0.005867751,"about_ca_system_score_gemma":0.009465386,"threshold_uncertainty_score":0.99964267},"labels":[],"label_agreement":null},{"id":"W4399826863","doi":"10.1007/978-3-031-52501-8_8","title":"Connecting to Decision-Making","year":2024,"lang":"en","type":"book-chapter","venue":"Natural resource management and policy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Computer science","score_opus":0.08055714173560455,"score_gpt":0.46258566174511256,"score_spread":0.38202852000950804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399826863","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00078436354,0.0021983578,0.00018225951,0.0058433027,0.00055551564,0.0004721216,0.000016637641,0.00009174674,0.9898557],"genre_scores_gemma":[0.13401897,0.00015267718,0.0012710677,0.0037275085,0.0008161974,0.000008521814,0.000009210013,0.000045996014,0.8599498],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961183,0.000025065152,0.0006866877,0.0007927822,0.002043947,0.00033320894],"domain_scores_gemma":[0.99783903,0.0010286212,0.00021522552,0.0006015405,0.00015506324,0.00016048664],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0018082089,0.00035673636,0.00039135647,0.0018193289,0.00027483425,0.00093928404,0.00066403736,0.0001694095,0.0017635789],"category_scores_gemma":[0.0005676687,0.00025875823,0.00018227471,0.0003865691,0.000034989578,0.00012178437,0.001075214,0.0004942961,0.0032113034],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002438335,0.0000016151357,0.000005301359,0.000022000782,0.000041281975,0.000017055532,0.00031713367,0.00007670422,3.9703795e-7,0.39083692,0.031855408,0.5768018],"study_design_scores_gemma":[0.00010743498,0.000034836354,0.00014290898,0.0004915463,0.000041686082,0.000007129665,0.0002848087,0.0009454101,4.909326e-7,0.20904304,0.78865397,0.000246714],"about_ca_topic_score_codex":0.0000075227576,"about_ca_topic_score_gemma":0.000051430616,"teacher_disagreement_score":0.75679857,"about_ca_system_score_codex":0.00015658735,"about_ca_system_score_gemma":0.00004873553,"threshold_uncertainty_score":0.99998647},"labels":[],"label_agreement":null},{"id":"W4399841649","doi":"10.1515/9782760523470-002","title":"Des systèmes de classification des modèles d’évaluation de programmes d’intervention psychosociale à une proposition de modèle intégrateur","year":2009,"lang":"fr","type":"book-chapter","venue":"Presses de l'Université du Québec eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Mod; Humanities; Mathematics; Philosophy; Combinatorics","score_opus":0.09664103683754736,"score_gpt":0.3344611646091716,"score_spread":0.2378201277716242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399841649","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60379463,0.0028731523,0.26546028,0.0017610673,0.00025141868,0.0018786121,0.00006547585,0.00035349064,0.12356185],"genre_scores_gemma":[0.9441865,0.0013623133,0.020794911,0.0001939442,0.00027955283,0.00011449875,0.00012583594,0.00007593301,0.03286653],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9948571,0.0010275719,0.001048973,0.00089364493,0.0012900849,0.00088265224],"domain_scores_gemma":[0.99590975,0.0005150085,0.0011550256,0.00062142103,0.0013989352,0.00039986058],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003634559,0.0006533261,0.00060601364,0.00060564885,0.001390238,0.00073245546,0.0009745886,0.0006758089,0.0026392508],"category_scores_gemma":[0.0003267496,0.00068001694,0.0005490946,0.00022223339,0.0011031368,0.0009198785,0.00015803504,0.00057017605,0.0003991238],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041097435,0.00034873126,0.03063981,0.0003827227,0.00022075955,0.000025506182,0.016623856,0.00333115,0.005742295,0.016887782,0.0006585208,0.9247279],"study_design_scores_gemma":[0.0035530308,0.0018430597,0.28876242,0.0039401664,0.0019571527,0.0003315128,0.013638941,0.27454308,0.008058972,0.33885786,0.06252445,0.001989339],"about_ca_topic_score_codex":0.018520962,"about_ca_topic_score_gemma":0.054979328,"teacher_disagreement_score":0.92273855,"about_ca_system_score_codex":0.0044115665,"about_ca_system_score_gemma":0.0035968751,"threshold_uncertainty_score":0.9999098},"labels":[],"label_agreement":null},{"id":"W4399843209","doi":"10.1515/9782760535190-004","title":"Conflits entre les exigences de la méthodologie de la théorisation enracinée (MTE) et les exigences institutionnelles en matière de recherche scientifique","year":2012,"lang":"fr","type":"book-chapter","venue":"Presses de l'Université du Québec eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Political science","score_opus":0.3093598769213688,"score_gpt":0.42183598903782893,"score_spread":0.11247611211646014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399843209","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16411568,0.0075068055,0.10547391,0.0021945164,0.0004891946,0.00075325806,0.00009003412,0.0002105906,0.719166],"genre_scores_gemma":[0.78737813,0.013551328,0.035277843,0.000554925,0.0006064409,0.00006400211,0.00006342621,0.00006878188,0.1624351],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9860418,0.010080839,0.00085855124,0.0009017701,0.0012663638,0.0008506708],"domain_scores_gemma":[0.97633743,0.020928286,0.0008416607,0.00063367037,0.0006708454,0.0005881231],"candidate_categories":["metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.022237783,0.00068344834,0.00064006663,0.000569262,0.001330472,0.0008126269,0.0017939499,0.001744699,0.019976506],"category_scores_gemma":[0.005683133,0.000626504,0.0003577209,0.00015914944,0.0024742652,0.00089696614,0.00056320126,0.0016130412,0.00049140345],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025022883,0.00014223768,0.13399503,0.00031077396,0.00023807172,0.00007904605,0.10149798,0.002526567,0.0020282664,0.26480058,0.0018321449,0.49229908],"study_design_scores_gemma":[0.0007345513,0.00015396097,0.008606899,0.0009979474,0.00039318544,0.00023801962,0.03474736,0.00324994,0.007846042,0.06671235,0.87530446,0.0010152712],"about_ca_topic_score_codex":0.018015027,"about_ca_topic_score_gemma":0.018377304,"teacher_disagreement_score":0.87347233,"about_ca_system_score_codex":0.0022270158,"about_ca_system_score_gemma":0.011672371,"threshold_uncertainty_score":0.99996966},"labels":[],"label_agreement":null},{"id":"W4399874412","doi":"10.1515/9782760523470-003","title":"Le développement de l’évaluation de programme","year":2009,"lang":"fr","type":"book-chapter","venue":"Presses de l'Université du Québec eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École Nationale d'Administration Publique","funders":"","keywords":"Political science","score_opus":0.1009068780511702,"score_gpt":0.3270011954918782,"score_spread":0.22609431744070801,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399874412","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06752113,0.0015123069,0.035946164,0.024579126,0.00039374165,0.0015737442,0.00003870883,0.00024602428,0.86818904],"genre_scores_gemma":[0.65974045,0.0017359136,0.024464564,0.0037084739,0.00059102627,0.00006858336,0.00008206242,0.00011820656,0.30949074],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9950099,0.00045098667,0.0008681932,0.00085766526,0.0018200733,0.0009931662],"domain_scores_gemma":[0.99618244,0.00080327713,0.00076925213,0.0008285938,0.00085281505,0.0005636263],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0037601811,0.00061022415,0.00060629786,0.0004718426,0.0008784853,0.00046645224,0.0013731658,0.00051983824,0.017226847],"category_scores_gemma":[0.0003639462,0.00064488756,0.00041625282,0.0000956714,0.0004255461,0.00037360867,0.0003877882,0.00062243576,0.001902221],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016850143,0.00014044456,0.012740211,0.00006448643,0.0001822808,0.00009310432,0.011817953,0.0016469602,0.00050975604,0.028987493,0.0055122147,0.9381366],"study_design_scores_gemma":[0.0016598239,0.00045096758,0.014622321,0.0003177769,0.00043232465,0.00010977815,0.0017845521,0.0137041835,0.0014135202,0.028139863,0.9365564,0.00080851646],"about_ca_topic_score_codex":0.011708325,"about_ca_topic_score_gemma":0.037854053,"teacher_disagreement_score":0.9373281,"about_ca_system_score_codex":0.002122535,"about_ca_system_score_gemma":0.014309441,"threshold_uncertainty_score":0.99960023},"labels":[],"label_agreement":null},{"id":"W4399874436","doi":"10.1515/9782760523470-010","title":"Les apports de la recherche qualitative en évaluation de programmes","year":2009,"lang":"fr","type":"book-chapter","venue":"Presses de l'Université du Québec eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Political science","score_opus":0.33666981579820476,"score_gpt":0.45924087922669504,"score_spread":0.12257106342849028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399874436","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0804374,0.0022248328,0.04962807,0.00406202,0.0001722851,0.0011898705,0.000046916033,0.00021666332,0.8620219],"genre_scores_gemma":[0.6299523,0.0020815213,0.06421844,0.00096849166,0.00044072582,0.000071942486,0.000073636074,0.000110965084,0.302082],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9887051,0.0073421304,0.000861628,0.00083817093,0.0015499577,0.0007030314],"domain_scores_gemma":[0.97996837,0.017392827,0.0008505064,0.0005863731,0.00081122795,0.000390686],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.023345217,0.00061160873,0.0006479148,0.00045444752,0.0005884335,0.00043313796,0.0010576927,0.0012539095,0.015741196],"category_scores_gemma":[0.0036600565,0.0006016705,0.00041419207,0.000107167805,0.0007621114,0.00038885704,0.00027999055,0.0013836232,0.0006670108],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016214012,0.00009170368,0.0054319287,0.00006953507,0.00017843759,0.00007698414,0.13414747,0.00056288857,0.00024925315,0.015824903,0.0017696028,0.84143513],"study_design_scores_gemma":[0.0011496381,0.00048008974,0.012580326,0.0005155625,0.0006463661,0.00015311387,0.022353014,0.008115498,0.0009266145,0.097578235,0.854562,0.0009395561],"about_ca_topic_score_codex":0.020462567,"about_ca_topic_score_gemma":0.018177409,"teacher_disagreement_score":0.8527924,"about_ca_system_score_codex":0.003028915,"about_ca_system_score_gemma":0.008688984,"threshold_uncertainty_score":0.9997383},"labels":[],"label_agreement":null},{"id":"W4399874895","doi":"10.1515/9782760523470-012","title":"Les ressources disponibles en évaluation de programme","year":2009,"lang":"fr","type":"book-chapter","venue":"Presses de l'Université du Québec eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Political science; Valuation (finance); Geography; Economics; Finance","score_opus":0.09216941575874829,"score_gpt":0.33096504485629996,"score_spread":0.23879562909755167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399874895","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21484321,0.003238642,0.006699079,0.0069896844,0.00035182186,0.001253429,0.000071000235,0.00027851728,0.76627463],"genre_scores_gemma":[0.726345,0.001431301,0.004649425,0.00064633903,0.0005628669,0.000032731175,0.00006445171,0.00008591003,0.26618198],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99437237,0.0007924161,0.00093024876,0.00096819276,0.0020644446,0.00087230816],"domain_scores_gemma":[0.99457926,0.0023452141,0.00089389796,0.0008996917,0.00081820536,0.0004637643],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0039308956,0.00071660423,0.00072703126,0.00062197295,0.0012566834,0.0006195896,0.0016842333,0.0006921341,0.027968772],"category_scores_gemma":[0.00069044717,0.0006793898,0.0004831866,0.000106164465,0.0007729362,0.00047498482,0.0003450647,0.00075915706,0.0016062027],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024290702,0.00008895327,0.024710458,0.000084999054,0.00017806725,0.00007953352,0.022713514,0.0015466842,0.00033284625,0.01719054,0.0013718114,0.93145967],"study_design_scores_gemma":[0.0010120459,0.00042333096,0.031228947,0.0005171527,0.0005635785,0.00008537862,0.0030731875,0.009474167,0.0007274045,0.0099317515,0.9421581,0.00080495456],"about_ca_topic_score_codex":0.021635847,"about_ca_topic_score_gemma":0.051377565,"teacher_disagreement_score":0.9407863,"about_ca_system_score_codex":0.0014303591,"about_ca_system_score_gemma":0.003068887,"threshold_uncertainty_score":0.9995657},"labels":[],"label_agreement":null},{"id":"W4399921253","doi":"10.56645/jmde.v20i47.999","title":"Canadian Evaluation Society Tribute to Dr. Michael Scriven","year":2024,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Canadian Evaluation Society","funders":"","keywords":"Tribute; Political science; Sociology; Art; Media studies; Law","score_opus":0.23073699912654302,"score_gpt":0.5334483235436518,"score_spread":0.3027113244171088,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399921253","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8708482,0.0024226618,0.01210067,0.10523491,0.0054885736,0.0015768494,0.000058750407,0.000031067826,0.0022383514],"genre_scores_gemma":[0.99329364,0.00006377081,0.003452295,0.0003512015,0.0007438724,0.000050627386,0.000039989976,0.000021334386,0.0019832822],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98955035,0.00095481647,0.0015377916,0.0004396861,0.0071595013,0.0003578263],"domain_scores_gemma":[0.9926752,0.00067293766,0.0004839338,0.0004313539,0.0052410965,0.0004954989],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.054276433,0.00020882023,0.00034435466,0.0010938637,0.0003798104,0.0005440928,0.00062385475,0.00013599495,0.0027846438],"category_scores_gemma":[0.002488826,0.00015393565,0.00040740482,0.0016261303,0.00003851164,0.0015215776,0.00010015877,0.0003594007,0.0008924501],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014801796,0.00015546878,0.00734065,0.000028977205,0.00022418647,0.000019931427,0.021356843,0.12648906,0.010633682,0.00027297353,0.27827808,0.5550521],"study_design_scores_gemma":[0.0009935123,0.00038589467,0.068212554,0.00017312358,0.00026235988,0.00005694952,0.0035419255,0.8697288,0.0004615483,0.0116965445,0.04426735,0.00021941884],"about_ca_topic_score_codex":0.00055206654,"about_ca_topic_score_gemma":0.00963334,"teacher_disagreement_score":0.74323976,"about_ca_system_score_codex":0.002290449,"about_ca_system_score_gemma":0.0069305543,"threshold_uncertainty_score":0.9998855},"labels":[],"label_agreement":null},{"id":"W4400411952","doi":"10.22329/il.v44i2.8372","title":"Systemic Means of Persuasion and Argument Evaluation","year":2024,"lang":"en","type":"article","venue":"Informal Logic","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Persuasion; Argument (complex analysis); Epistemology; Psychology; Social psychology; Philosophy; Medicine","score_opus":0.2364615027996044,"score_gpt":0.49278444667138294,"score_spread":0.25632294387177856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400411952","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9287796,0.0019031274,0.0032293608,0.00057303323,0.0007400996,0.0004126809,0.000008725323,0.000043375756,0.06431],"genre_scores_gemma":[0.9988304,0.000110475274,0.0002703034,0.00012920296,0.000035601883,0.000019217154,0.000006481541,0.000002551647,0.0005957869],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974509,0.00008488672,0.00053778844,0.00015946722,0.0016548596,0.00011210311],"domain_scores_gemma":[0.99915415,0.00018897295,0.00011088947,0.00019194359,0.0003082785,0.00004577286],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006221317,0.000075988704,0.00013220902,0.00023473211,0.000060885162,0.0001553192,0.0001537503,0.000046688594,0.0014399294],"category_scores_gemma":[0.00030127974,0.000046686808,0.000050183815,0.00033755577,0.00004313702,0.00064058707,0.00006307385,0.00007110426,0.00033932202],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004120112,0.000029029174,0.0067397095,0.0001253174,0.000029492896,0.000002159353,0.0057273847,0.006586009,0.0016876798,0.037197225,0.0018690513,0.9399657],"study_design_scores_gemma":[0.0005360509,0.00037758364,0.038848758,0.00018071131,0.000050673185,0.00006071479,0.0041628256,0.923595,0.0008153863,0.011092825,0.020108694,0.00017074161],"about_ca_topic_score_codex":0.00000854341,"about_ca_topic_score_gemma":0.000006028194,"teacher_disagreement_score":0.939795,"about_ca_system_score_codex":0.000045757588,"about_ca_system_score_gemma":0.00017612582,"threshold_uncertainty_score":0.9994729},"labels":[],"label_agreement":null},{"id":"W4400411984","doi":"10.22329/il.v44i2.8397","title":"Argument Evaluation: If your Snark be a Boojum…","year":2024,"lang":"fr","type":"article","venue":"Informal Logic","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Argument (complex analysis); Epistemology; Philosophy; Sociology","score_opus":0.34861245878554586,"score_gpt":0.5253473424824049,"score_spread":0.17673488369685902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400411984","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.059903212,0.039749116,0.0043973005,0.09553939,0.023962788,0.0017634387,0.00017148031,0.0002754586,0.7742378],"genre_scores_gemma":[0.8216441,0.0015764566,0.0020048136,0.009448443,0.0012888128,0.00022247544,0.00010775148,0.000025482857,0.16368163],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9923838,0.0003192118,0.0014006678,0.0005624399,0.0046104672,0.0007234307],"domain_scores_gemma":[0.9974165,0.00054489117,0.00023460279,0.0006840761,0.00082057196,0.00029938298],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.011824934,0.00036746808,0.00036059914,0.00046616822,0.00037318715,0.0016297889,0.00074475544,0.00027393253,0.0969118],"category_scores_gemma":[0.0006463056,0.00027940265,0.00031245287,0.0013824473,0.00023572167,0.003033147,0.00027968385,0.0005183228,0.022739789],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043813176,0.00011801345,0.0010229679,0.00011150004,0.000094991505,0.000040874693,0.005167688,0.010543992,0.00001972882,0.101586744,0.10746882,0.7737809],"study_design_scores_gemma":[0.00040584683,0.00032089616,0.004055239,0.00013309343,0.00008941905,0.000063467356,0.0014080011,0.33564946,0.000054789383,0.012688824,0.6448675,0.00026346452],"about_ca_topic_score_codex":0.000057117737,"about_ca_topic_score_gemma":0.000040781724,"teacher_disagreement_score":0.77351743,"about_ca_system_score_codex":0.00041518986,"about_ca_system_score_gemma":0.002343146,"threshold_uncertainty_score":0.9999658},"labels":[],"label_agreement":null},{"id":"W4400441485","doi":"10.5465/amproc.2024.17521symposium","title":"Frontiers of Hierarchy Research: Status, Power, and Inequality","year":2024,"lang":"en","type":"article","venue":"Academy of Management Proceedings","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kellogg's (Canada)","funders":"","keywords":"Inequality; Hierarchy; Power (physics); Mathematics; Mathematical economics; Sociology; Econometrics; Economics; Mathematical analysis; Physics","score_opus":0.31534350699317293,"score_gpt":0.534745235096413,"score_spread":0.2194017281032401,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400441485","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9086439,0.002666374,0.00048495576,0.010534974,0.00020033774,0.00057175494,0.000014043453,0.000049444872,0.07683423],"genre_scores_gemma":[0.9915613,0.0016550274,0.0029274626,0.00019161396,0.000025826022,0.000020007687,9.5504e-7,0.000008632475,0.0036091649],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99576867,0.00006517832,0.00073110504,0.00044820053,0.0026798756,0.00030699105],"domain_scores_gemma":[0.9991046,0.0002837114,0.00016165279,0.000098187,0.00024793434,0.00010389923],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013875214,0.00010467806,0.00024024122,0.0010119965,0.00008410978,0.0001687941,0.0005047997,0.0000737574,0.00025048823],"category_scores_gemma":[0.00039870356,0.00007932783,0.00005750015,0.0015170317,0.00029698896,0.0008619179,0.0004154181,0.00030585795,0.000033072112],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000804746,0.00006300168,0.04657055,0.00049709924,0.00012580602,9.258422e-7,0.004175157,0.000004963112,0.0006251395,0.44323802,0.3287433,0.17587556],"study_design_scores_gemma":[0.0004055444,0.00018925339,0.15868679,0.00016757868,0.000031289463,9.46151e-7,0.010946747,0.0029091225,0.0019098409,0.15907848,0.66551596,0.00015843639],"about_ca_topic_score_codex":0.000007406905,"about_ca_topic_score_gemma":2.8016896e-7,"teacher_disagreement_score":0.33677268,"about_ca_system_score_codex":0.000042720985,"about_ca_system_score_gemma":0.000036921483,"threshold_uncertainty_score":0.48089},"labels":[],"label_agreement":null},{"id":"W4400444347","doi":"10.5465/amproc.2024.13429abstract","title":"A Theory of Time-Based Discrimination in Evaluation","year":2024,"lang":"en","type":"article","venue":"Academy of Management Proceedings","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Psychology","score_opus":0.17824285051654468,"score_gpt":0.47494816385743704,"score_spread":0.29670531334089234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400444347","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8551995,0.0004426854,0.002627466,0.0071837488,0.00013568393,0.001224228,0.0000047550393,0.00005303966,0.13312888],"genre_scores_gemma":[0.9968776,0.000040586154,0.00075464306,0.00018454455,0.000019710056,0.00006529122,0.0000033781105,0.000006808788,0.0020474412],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99661267,0.00006623323,0.0006964644,0.000309962,0.00219119,0.0001234803],"domain_scores_gemma":[0.9992217,0.00028185133,0.00022242605,0.000067863635,0.00018242894,0.000023732426],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.015972773,0.00009080496,0.00016799952,0.00095326,0.000023973367,0.000069504684,0.00037534654,0.00005853582,0.0012398072],"category_scores_gemma":[0.00033186722,0.000069817186,0.0000641131,0.0012146491,0.00006197418,0.0007093307,0.000072367264,0.00010648191,0.00010713737],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000081122475,0.00011147605,0.004178854,0.00043015124,0.000037820388,2.8922585e-7,0.0017286518,0.0009175127,0.0020226934,0.29793477,0.0072932844,0.6852634],"study_design_scores_gemma":[0.0010061385,0.000119159595,0.1562098,0.00064957654,0.00014684645,4.8360636e-7,0.0028687927,0.49683315,0.010907318,0.31978095,0.011283071,0.00019472005],"about_ca_topic_score_codex":0.0000013779877,"about_ca_topic_score_gemma":3.934708e-7,"teacher_disagreement_score":0.68506867,"about_ca_system_score_codex":0.00007019646,"about_ca_system_score_gemma":0.00004222142,"threshold_uncertainty_score":0.9996732},"labels":[],"label_agreement":null},{"id":"W4400445972","doi":"10.5465/amproc.2024.17173symposium","title":"Centering the Margins: Methodological Challenges and Opportunities of Studying the Understudied","year":2024,"lang":"en","type":"article","venue":"Academy of Management Proceedings","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Quest University Canada","funders":"","keywords":"Political science","score_opus":0.7987630461674443,"score_gpt":0.5329475065447259,"score_spread":0.2658155396227184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400445972","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47728875,0.044841696,0.0012026343,0.29974848,0.000418751,0.0015313296,0.0000039799543,0.00011025442,0.1748541],"genre_scores_gemma":[0.96186,0.03591058,0.00050760567,0.0006155053,0.00004130386,0.00003491168,1.1073967e-7,0.0000055051046,0.0010244768],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979721,0.0000867809,0.00048557518,0.0002695049,0.0010398931,0.00014617012],"domain_scores_gemma":[0.9987066,0.0009382804,0.00018685867,0.00007964977,0.000064167354,0.00002446196],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011685019,0.00010571273,0.00020681375,0.00016659277,0.00015777469,0.00011317357,0.00059217145,0.000038117287,0.00006917382],"category_scores_gemma":[0.00017223465,0.00004788521,0.00005925985,0.00022758904,0.0002472245,0.00033741794,0.0005383218,0.0001667693,0.000004459084],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001633412,0.000016869622,0.0002645648,0.0002804274,0.00015131083,5.063224e-7,0.007228582,0.000007487937,0.000080129335,0.58185196,0.002390469,0.40771136],"study_design_scores_gemma":[0.00044379974,0.00019261996,0.13721065,0.0004920536,0.00022338609,0.000008374712,0.3414824,0.005436626,0.0004891955,0.1458977,0.36789814,0.00022505932],"about_ca_topic_score_codex":7.83559e-7,"about_ca_topic_score_gemma":3.302725e-7,"teacher_disagreement_score":0.48457125,"about_ca_system_score_codex":0.000014145773,"about_ca_system_score_gemma":0.00000753253,"threshold_uncertainty_score":0.4049818},"labels":[],"label_agreement":null},{"id":"W4400449407","doi":"10.55016/ojs/ajer.v52i1.55108","title":"Establishing Performance Standards and Setting Cut-Scores","year":2006,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"University of Alberta; American Educational Research Association","keywords":"Psychology; Mathematics education; Statistics; Mathematics","score_opus":0.19738312749585904,"score_gpt":0.5540258457336474,"score_spread":0.35664271823778837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400449407","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9046844,0.00045194835,0.000024059947,0.017976806,0.00030235935,0.00007469859,0.0000040624523,3.55287e-7,0.076481305],"genre_scores_gemma":[0.9741285,0.00012461362,0.0006081704,0.00009690843,0.00067746156,0.000004521472,0.0000035994394,0.000007184779,0.02434904],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99385816,0.00036578937,0.00078810984,0.00019590776,0.004492214,0.0002998277],"domain_scores_gemma":[0.96588004,0.029577352,0.0003363943,0.00020749224,0.0038544252,0.00014427162],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01623145,0.00008468695,0.0001702323,0.0006650792,0.00046058052,0.00068675546,0.0005461297,0.000042766627,0.010386289],"category_scores_gemma":[0.02877859,0.00005940202,0.00005331717,0.00078153796,0.00016936612,0.0014634507,0.00010312992,0.0004089609,0.00011005897],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007220198,0.00011002774,0.8404229,0.00001498899,0.000014067911,4.305467e-7,0.00070807344,0.00061954104,0.0003170454,0.01431919,0.12918335,0.014218165],"study_design_scores_gemma":[0.00054889655,0.00026467856,0.7837577,0.00012929631,0.000010003826,0.00012510901,0.0013076074,0.0033523738,0.0006649663,0.014914456,0.19478303,0.00014192316],"about_ca_topic_score_codex":0.00035470413,"about_ca_topic_score_gemma":0.0009346041,"teacher_disagreement_score":0.06944409,"about_ca_system_score_codex":0.00018842539,"about_ca_system_score_gemma":0.0026543743,"threshold_uncertainty_score":0.99051833},"labels":[],"label_agreement":null},{"id":"W4400453371","doi":"10.1136/bmjebm-2024-sdc.56","title":"057 Barriers and facilitators in implementing training in shared decision-making based on reflexivity strategies: a qualitative approach","year":2024,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université Laval; Centres Intégré Universitaires de Santé et de Services Sociaux","funders":"","keywords":"Reflexivity; Training (meteorology); Computer science; Qualitative research; Knowledge management; Human–computer interaction; Process management; Sociology; Engineering","score_opus":0.3117313219169021,"score_gpt":0.5868476074641994,"score_spread":0.2751162855472973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400453371","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8830002,0.00006766705,0.052826896,0.0005146611,0.00015575084,0.0004228925,0.000042917676,0.000061788225,0.06290725],"genre_scores_gemma":[0.9867063,0.0000020163711,0.0128329685,0.00026848508,0.000013710322,0.00006206534,0.000005981992,0.000008981929,0.00009944973],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958742,0.00068924564,0.0009106453,0.0007239222,0.0014123765,0.0003895956],"domain_scores_gemma":[0.9933384,0.0061138966,0.0000913551,0.00026775323,0.00008212953,0.000106460866],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.019607982,0.00018073591,0.0003004322,0.0010410359,0.00013287594,0.0008528102,0.00026060775,0.000068157446,0.0020506864],"category_scores_gemma":[0.0027847248,0.00013122502,0.00006533672,0.0016124264,0.00007028916,0.0010334871,0.00007575113,0.00027950548,0.0000304152],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021575081,0.000055682875,0.017400153,0.000065374115,0.000019819634,0.000027281343,0.40872765,0.0398598,0.00008671291,0.039377954,0.00061040185,0.4935534],"study_design_scores_gemma":[0.0003709296,0.00007761788,0.0067381756,0.00019265934,0.0000018841775,6.305947e-7,0.39471748,0.56449085,0.000004928127,0.032562613,0.0006968924,0.00014533594],"about_ca_topic_score_codex":0.00007240958,"about_ca_topic_score_gemma":0.0012287331,"teacher_disagreement_score":0.5246311,"about_ca_system_score_codex":0.0001651325,"about_ca_system_score_gemma":0.00082654384,"threshold_uncertainty_score":0.99886155},"labels":[],"label_agreement":null},{"id":"W4400458560","doi":"10.7202/1111663ar","title":"La démarche d’évaluation au coeur de la stratégie d’optimisation des ressources pour les professionnels de l’information","year":2024,"lang":"fr","type":"article","venue":"Documentation et bibliothèques","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.1478055804942593,"score_gpt":0.5008885205897201,"score_spread":0.3530829400954608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400458560","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7291701,0.006705307,0.1869558,0.01625671,0.0010738662,0.00082792336,0.000088550805,0.00031669615,0.058605086],"genre_scores_gemma":[0.9515233,0.01779285,0.015994605,0.00079268194,0.0003688186,0.00020102288,0.00021324339,0.00003702435,0.013076454],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9899703,0.005822419,0.0011955947,0.0004624549,0.001986227,0.0005630009],"domain_scores_gemma":[0.9930441,0.0052691367,0.00045253843,0.00032169928,0.00068792165,0.00022464276],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.023710066,0.00035196956,0.0002769195,0.0033766967,0.0007215341,0.013308728,0.00042821935,0.00043688278,0.015242421],"category_scores_gemma":[0.0019252852,0.00031411645,0.0001750952,0.0039489027,0.0005583168,0.025424885,0.00008339815,0.00062731776,0.0006764867],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009773175,0.00018777899,0.016889807,0.0005503254,0.0000989516,0.000010634105,0.11627419,0.013458299,0.0031243588,0.043865062,0.016852727,0.78859013],"study_design_scores_gemma":[0.0016808159,0.00035238892,0.13109379,0.0021824092,0.0002589873,0.00013066248,0.0619181,0.25869173,0.0095098475,0.15238225,0.38100988,0.0007891227],"about_ca_topic_score_codex":0.0015136586,"about_ca_topic_score_gemma":0.00032536377,"teacher_disagreement_score":0.787801,"about_ca_system_score_codex":0.0013127042,"about_ca_system_score_gemma":0.004361984,"threshold_uncertainty_score":0.9999311},"labels":[],"label_agreement":null},{"id":"W4400482763","doi":"10.55016/ojs/cpai.v6i1.76623","title":"Creative evaluation","year":2023,"lang":"en","type":"article","venue":"Canadian Perspectives on Academic Integrity","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Assiniboine Community College","funders":"","keywords":"Computer science; Psychology","score_opus":0.3184331467128143,"score_gpt":0.5352887859850761,"score_spread":0.2168556392722618,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400482763","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6143446,0.0001584323,0.00009736933,0.027418526,0.0007581932,0.0006583198,0.000107878295,0.00012591675,0.35633078],"genre_scores_gemma":[0.9885948,0.00011703885,0.000052853917,0.0015998178,0.00024539465,0.000080997204,0.000027823016,0.000012558461,0.00926876],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99544734,0.00062782766,0.00045391868,0.00067416194,0.0023290247,0.0004677005],"domain_scores_gemma":[0.99682,0.0007396151,0.00015410453,0.00050424907,0.0013169104,0.00046514167],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.011693145,0.00017707885,0.00022354176,0.0013811608,0.00037471086,0.00012120532,0.00071140606,0.00027116548,0.010517597],"category_scores_gemma":[0.011535354,0.00013885988,0.00011214423,0.0021656223,0.00016100203,0.00041474923,0.00003837194,0.0015050843,0.010220047],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000073991076,0.000043148997,0.026167357,0.0000033901852,0.0000673307,0.000013993562,0.051020514,0.0014809658,0.00021742914,0.287743,0.46307373,0.17009516],"study_design_scores_gemma":[0.0008054408,0.00019670169,0.46933162,0.00005305474,0.000028747874,0.0000067253695,0.18744445,0.093965165,0.0003220358,0.11415387,0.13320498,0.0004872174],"about_ca_topic_score_codex":0.012189188,"about_ca_topic_score_gemma":0.028543139,"teacher_disagreement_score":0.44316426,"about_ca_system_score_codex":0.0017746432,"about_ca_system_score_gemma":0.0028531093,"threshold_uncertainty_score":0.9967909},"labels":[],"label_agreement":null},{"id":"W4400570810","doi":"10.5539/hes.v14n3p73","title":"Insights in Flexible Assessment from Students’ and Teachers’ Perspectives: A Focus Group Study","year":2024,"lang":"en","type":"article","venue":"Higher Education Studies","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Flexibility (engineering); Context (archaeology); Psychology; Focus group; Perspective (graphical); Medical education; Mathematics education; Pedagogy; Computer science; Medicine; Sociology","score_opus":0.2544257134724276,"score_gpt":0.5732626474560618,"score_spread":0.3188369339836342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400570810","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96379566,0.02662226,0.00005597045,0.0028533307,0.0019489237,0.0005107826,0.0000032194341,0.00007076901,0.0041391063],"genre_scores_gemma":[0.9889258,0.00048257993,0.00044347346,0.00019117339,0.00025452755,0.0003973295,0.0000040275645,0.000012595893,0.009288487],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9965825,0.0004033192,0.0005793013,0.0007416315,0.0015299835,0.00016324289],"domain_scores_gemma":[0.9982631,0.00084367563,0.00010195472,0.00037828373,0.00033986056,0.00007312871],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00158136,0.00019586983,0.0003354687,0.00054534484,0.0001871179,0.0006495888,0.00031152627,0.0000424839,0.00079844135],"category_scores_gemma":[0.00006978306,0.00013621851,0.0000478916,0.001006455,0.00009216225,0.0006541145,0.00021572933,0.00021127584,0.00018449298],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014196427,0.001877946,0.7493191,0.000009026519,0.0003012401,0.0000054669563,0.1980197,0.0000101173655,0.000070526345,0.022383222,0.013938631,0.014050878],"study_design_scores_gemma":[0.0003169888,0.00011335707,0.66099656,0.000045508805,0.000029445633,2.7835063e-7,0.29745266,0.000025556299,0.0000034372954,0.013795758,0.027105544,0.0001148886],"about_ca_topic_score_codex":0.00029808257,"about_ca_topic_score_gemma":0.0005595427,"teacher_disagreement_score":0.09943296,"about_ca_system_score_codex":0.00037836403,"about_ca_system_score_gemma":0.00029033195,"threshold_uncertainty_score":0.8742373},"labels":[],"label_agreement":null},{"id":"W4400583940","doi":"10.56105/cjsae.v30i1.5366","title":"Learning and Teaching Community-Based Research","year":2016,"lang":"en","type":"article","venue":"Canadian Journal for the Study of Adult Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Sociology; Learning community; Media studies; Library science; Teaching and learning center; Pedagogy; Teaching method; Computer science","score_opus":0.4038722337981145,"score_gpt":0.5763522597226716,"score_spread":0.17248002592455708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400583940","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98463345,0.00003246714,0.000446259,0.0121891955,0.0005306829,0.00033433866,0.000002292139,0.0000017302217,0.0018296111],"genre_scores_gemma":[0.9959937,0.0000054382426,0.0001280365,0.00014390601,0.00010838103,0.000023307168,6.5168973e-7,0.000004513355,0.003592082],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9975681,0.0013242518,0.00029136406,0.0000818461,0.00056974683,0.00016470307],"domain_scores_gemma":[0.9943039,0.003627733,0.00015748166,0.00021037961,0.0015103191,0.00019022383],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.015992912,0.000046724657,0.00008069417,0.0004034567,0.0032988084,0.00020736971,0.0003954786,0.00001914898,0.0001822672],"category_scores_gemma":[0.006774397,0.000023183573,0.000027387425,0.00015019797,0.00010295172,0.00017704119,0.000012675073,0.0004277604,0.000007634044],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028382838,0.00014293086,0.22634572,0.0000048811976,0.000020867077,1.3105355e-7,0.031155283,0.0001243021,0.00012285465,0.0021756587,0.012543529,0.72733545],"study_design_scores_gemma":[0.0015574136,0.00213247,0.17700903,0.00016211685,0.000028357377,0.000014335319,0.5873038,0.0011713561,0.00009003355,0.014178686,0.21621951,0.00013286577],"about_ca_topic_score_codex":0.006836692,"about_ca_topic_score_gemma":0.052408304,"teacher_disagreement_score":0.7272026,"about_ca_system_score_codex":0.00010928214,"about_ca_system_score_gemma":0.002108933,"threshold_uncertainty_score":0.99977684},"labels":[],"label_agreement":null},{"id":"W4400673484","doi":"10.15453/2168-6408.2290","title":"Letter to the Editor: The COPM: Culturally Sensitive by Design","year":2024,"lang":"en","type":"letter","venue":"The Open Journal of Occupational Therapy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; McMaster University; University of Toronto","funders":"","keywords":"Occupational therapy; Psychology; Physical medicine and rehabilitation; Medicine; Physical therapy","score_opus":0.3409748659366059,"score_gpt":0.51789094694133,"score_spread":0.17691608100472406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400673484","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00027186822,0.00050702156,0.0046152063,0.9836684,0.008265678,0.0011110347,0.00009980984,0.0000054699226,0.0014555083],"genre_scores_gemma":[0.0022498996,0.00022854577,0.0005264607,0.93496037,0.04257079,0.000051487477,0.000027849204,0.000030281215,0.019354317],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99120617,0.0024619452,0.0011283541,0.00031443805,0.004615439,0.00027363288],"domain_scores_gemma":[0.99124634,0.0050757006,0.0011019363,0.00072361756,0.001789446,0.00006296758],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.016921906,0.0003140658,0.00042365154,0.00014009727,0.0006676537,0.0027943433,0.005068837,0.00018529934,0.0019744074],"category_scores_gemma":[0.00041007443,0.00009895533,0.0003120251,0.0006194563,0.00017367068,0.00056334987,0.00027515754,0.0019890408,0.0012991031],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035381372,0.000013021382,0.000012367076,8.1121675e-7,0.00018800785,0.000012692147,0.0018733625,0.00084269384,0.000051998224,0.000042360694,0.9913809,0.0052279886],"study_design_scores_gemma":[0.00032517995,0.0002309103,0.00048521184,0.000056530615,0.000037864353,0.00008531969,0.00030179386,0.00025516818,0.00015350319,0.002398644,0.9955038,0.00016609818],"about_ca_topic_score_codex":0.000017616596,"about_ca_topic_score_gemma":0.0000068693007,"teacher_disagreement_score":0.048708033,"about_ca_system_score_codex":0.00013269657,"about_ca_system_score_gemma":0.0009253388,"threshold_uncertainty_score":0.9994785},"labels":[],"label_agreement":null},{"id":"W4400735838","doi":"10.1109/mbits.2024.3410588","title":"People, Ideas, Impact","year":2023,"lang":"en","type":"article","venue":"IEEE BITS the Information Theory Magazine","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science","score_opus":0.07998784799050072,"score_gpt":0.4422307343520779,"score_spread":0.36224288636157714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400735838","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7973469,0.00004782774,0.014824305,0.007685944,0.0020910494,0.0007905501,0.0001044845,0.0004818723,0.17662705],"genre_scores_gemma":[0.98345053,0.000052079176,0.00004152027,0.0017010783,0.00014097436,0.000043352316,0.000058484813,0.000008563108,0.014503432],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99646133,0.00038030697,0.0008682914,0.00014244206,0.001831754,0.00031589277],"domain_scores_gemma":[0.99627537,0.0019100258,0.00040108326,0.0007621863,0.00054803386,0.00010329809],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.013342509,0.00016508748,0.00019905817,0.000539198,0.00035941834,0.00048542346,0.000868658,0.000061009592,0.0044218386],"category_scores_gemma":[0.0020297281,0.00008422294,0.00015620796,0.0025941026,0.00008037331,0.002553304,0.00010011419,0.00016912894,0.075881325],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021414633,0.00003069147,0.004212647,0.000014435728,0.000059181504,0.0000014223373,0.008480151,0.033398453,0.0003364013,0.095124796,0.6076897,0.250438],"study_design_scores_gemma":[0.0010847044,0.00016808796,0.28114328,0.000021348693,0.000026201613,0.000038025035,0.0033801552,0.10870236,0.0005081795,0.22575076,0.3787787,0.0003982174],"about_ca_topic_score_codex":0.000007024024,"about_ca_topic_score_gemma":0.000030848452,"teacher_disagreement_score":0.27693063,"about_ca_system_score_codex":0.000066508655,"about_ca_system_score_gemma":0.00021298756,"threshold_uncertainty_score":0.9964883},"labels":[],"label_agreement":null},{"id":"W4400768939","doi":"10.1016/j.evalprogplan.2024.102469","title":"Use of research evidence in U.S. federal policymaking: A reflexive report on intra-stage mixed methods","year":2024,"lang":"en","type":"article","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Wilson Centre; University of Toronto; St. Michael's Hospital","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute on Drug Abuse; Huck Institutes of the Life Sciences; William T. Grant Foundation; National Science Foundation","keywords":"Reflexivity; Stage (stratigraphy); Political science; Public administration; Psychology; Sociology; Social science","score_opus":0.8332736446318545,"score_gpt":0.7462299680044214,"score_spread":0.08704367662743306,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400768939","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9823844,0.0018254018,0.0027316855,0.0035818832,0.00069956476,0.0015761177,0.0000052940227,0.000104527615,0.0070911516],"genre_scores_gemma":[0.9723012,0.000052136234,0.0258498,0.00012483729,0.00008378169,0.00020473172,0.000015570917,0.00001070566,0.0013572758],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9914175,0.003297912,0.0009749113,0.0006344655,0.00336181,0.0003133738],"domain_scores_gemma":[0.9916448,0.0067629227,0.00020666444,0.0004052577,0.00088674243,0.000093637726],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07016274,0.00012993913,0.00024775346,0.001113944,0.00018124381,0.0009644955,0.0002032813,0.0000992419,0.00043611097],"category_scores_gemma":[0.016877173,0.00009745599,0.00005754706,0.001976874,0.00014369636,0.0008400513,0.00009730977,0.00043600815,0.000031910848],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000124851,0.00006278998,0.03281581,0.00004537222,0.000016712034,0.000061314866,0.0047497046,0.0032980698,0.00045299073,0.0027551856,0.0017088973,0.9539083],"study_design_scores_gemma":[0.00042072902,0.0008779852,0.20215929,0.0019358428,0.000016784048,0.000062467516,0.0033727093,0.6981424,0.0013909966,0.010940261,0.08043454,0.0002460237],"about_ca_topic_score_codex":0.00010725263,"about_ca_topic_score_gemma":0.00006083342,"teacher_disagreement_score":0.9536623,"about_ca_system_score_codex":0.00013914553,"about_ca_system_score_gemma":0.0006578994,"threshold_uncertainty_score":0.9914041},"labels":[],"label_agreement":null},{"id":"W4400821843","doi":"10.3102/2093677","title":"Measuring Post-Pandemic Education Sector Recovery After a Canadian Mental Health Association Intervention","year":2024,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Pandemic; Intervention (counseling); Association (psychology); Mental health; Coronavirus disease 2019 (COVID-19); Medicine; Psychology; Psychiatry; Psychotherapist","score_opus":0.1474428151814682,"score_gpt":0.46245823158917854,"score_spread":0.31501541640771036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400821843","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9215362,0.0016734306,0.0010966905,0.041200645,0.008152706,0.0006334248,0.0001200864,0.00014714638,0.025439661],"genre_scores_gemma":[0.9657715,0.000055963843,0.00020529829,0.0028831856,0.0001648761,0.00004642401,0.00007872901,0.000008243861,0.03078577],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977528,0.00022359042,0.00049215736,0.00029136328,0.0010163755,0.00022375604],"domain_scores_gemma":[0.9991022,0.00013617794,0.00011817267,0.00016876335,0.00029775707,0.00017696439],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.005209013,0.00008662434,0.00011377891,0.0005583963,0.0001351603,0.00056783156,0.00014087357,0.000058393845,0.009546925],"category_scores_gemma":[0.0003566137,0.000068651316,0.00011544962,0.00046221633,0.0000058725186,0.00083624595,0.000022023773,0.00012516594,0.0017598986],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003379931,0.000063183,0.09946568,0.00003176065,0.00004346796,5.5671785e-7,0.0025960216,0.00002822269,0.00015395573,0.0005878535,0.098242655,0.79875284],"study_design_scores_gemma":[0.0003586333,0.00031739622,0.43948394,0.0003642893,0.000015887239,0.000014694349,0.004186332,0.011203975,0.00010046249,0.0042405087,0.5393885,0.00032537605],"about_ca_topic_score_codex":0.04537039,"about_ca_topic_score_gemma":0.48293176,"teacher_disagreement_score":0.79842746,"about_ca_system_score_codex":0.002756867,"about_ca_system_score_gemma":0.002993873,"threshold_uncertainty_score":0.99901736},"labels":[],"label_agreement":null},{"id":"W4400920634","doi":"10.36315/2024v1end028","title":"The contribution of a collaborative approach in understanding resistance factors when implementing change","year":2024,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Resistance (ecology); Computer science; Process management; Human–computer interaction; Knowledge management; Business","score_opus":0.4261536050827622,"score_gpt":0.5045879513493663,"score_spread":0.07843434626660412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400920634","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3688873,0.0050210236,0.39139473,0.01767635,0.0014870587,0.0031331214,0.00010275214,0.00014709927,0.21215056],"genre_scores_gemma":[0.99866223,0.0000470847,0.00027289303,0.000036294874,0.000022906706,0.000034991874,0.000007171133,0.0000030719114,0.0009133408],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99802744,0.0002003923,0.00047296265,0.00019961515,0.00089050486,0.00020909212],"domain_scores_gemma":[0.99822456,0.0012582763,0.000119730415,0.00016490504,0.00020930938,0.000023222603],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006958513,0.000067169494,0.00012578773,0.00016534145,0.00020582514,0.00028401572,0.00019939904,0.000026662134,0.0002430631],"category_scores_gemma":[0.00033374343,0.00003484191,0.00003614592,0.0011101426,0.000052813368,0.0004297962,0.00005865711,0.00007544409,0.000008839158],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021050451,0.000013993733,0.034960736,0.0000073584,0.000014867458,4.1631083e-7,0.011056431,0.00001032295,0.000092093855,0.94913816,0.0030382907,0.0016462746],"study_design_scores_gemma":[0.00096500537,0.00010331813,0.06653859,0.00016406488,0.000020629028,5.6185115e-7,0.28720334,0.07589874,0.0016140413,0.43684494,0.13034256,0.0003042339],"about_ca_topic_score_codex":0.000026826136,"about_ca_topic_score_gemma":0.0027824834,"teacher_disagreement_score":0.6297749,"about_ca_system_score_codex":0.00019985216,"about_ca_system_score_gemma":0.00015172848,"threshold_uncertainty_score":0.27387702},"labels":[],"label_agreement":null},{"id":"W4401022060","doi":"10.1016/j.jneb.2024.05.184","title":"Development of a Single Evaluation Plan for SNAP-Ed Texas","year":2024,"lang":"en","type":"article","venue":"Journal of Nutrition Education and Behavior","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Snap; Plan (archaeology); Computer science; Geography; Archaeology; Computer graphics (images)","score_opus":0.27666514441386925,"score_gpt":0.5228347066389685,"score_spread":0.24616956222509923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401022060","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9928124,0.0011795283,0.0024780117,0.001131425,0.0016736552,0.00047212408,0.000008996484,0.0000055101164,0.00023836728],"genre_scores_gemma":[0.9719995,0.000049407598,0.027184375,0.000069349844,0.00025771832,0.00011134897,0.000023743229,0.0000054940024,0.00029905047],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978206,0.00007696124,0.00087864307,0.00012610534,0.0010247619,0.00007292989],"domain_scores_gemma":[0.997704,0.00023384922,0.00039163727,0.000088409295,0.0015091511,0.00007292809],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003609455,0.0000693685,0.00015619546,0.00048995815,0.00007135113,0.00016350672,0.000112877984,0.000046460787,0.00064915745],"category_scores_gemma":[0.0002739182,0.000051555784,0.00007919691,0.000272113,0.000024673647,0.00044873488,0.000009219408,0.00006575197,0.0000134308575],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004201033,0.004620159,0.0023417224,0.00010369461,0.00001917768,3.8440072e-7,0.0027348655,0.000006037713,0.023207705,0.0005267823,0.01679781,0.9495996],"study_design_scores_gemma":[0.003171147,0.0010920144,0.207901,0.0010557802,0.00057928363,0.00021081473,0.023374941,0.0026472434,0.035364922,0.008137297,0.71611226,0.0003533094],"about_ca_topic_score_codex":6.613692e-7,"about_ca_topic_score_gemma":0.000005807642,"teacher_disagreement_score":0.94924635,"about_ca_system_score_codex":0.00011492711,"about_ca_system_score_gemma":0.0011216569,"threshold_uncertainty_score":0.7107819},"labels":[],"label_agreement":null},{"id":"W4401022221","doi":"10.1016/j.jneb.2024.05.138","title":"Exploring Response Shift Bias, Reliability and Validity by Using Retrospective Pretests-Posttests in EFNEP Evaluations","year":2024,"lang":"en","type":"article","venue":"Journal of Nutrition Education and Behavior","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Reliability (semiconductor); Psychology; Validity; Clinical psychology; Psychometrics","score_opus":0.42655711240884725,"score_gpt":0.5292730830177823,"score_spread":0.10271597060893506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401022221","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9939374,0.00089389,0.00017884288,0.0035024327,0.0011039895,0.00032668357,0.000021097772,0.000010745169,0.00002494916],"genre_scores_gemma":[0.9975139,0.00052093127,0.0015614463,0.00007453879,0.0001620235,0.00008283075,0.0000047501935,0.0000075965017,0.0000720142],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9970626,0.0007107021,0.0008599504,0.00026979385,0.0009779503,0.000118984346],"domain_scores_gemma":[0.99771005,0.0009776101,0.00029692994,0.00016689955,0.00071634544,0.00013214257],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008932491,0.000110155495,0.00021351877,0.00065616454,0.0001357814,0.00040755558,0.00011050164,0.000057963403,0.00018072022],"category_scores_gemma":[0.0021911287,0.00008948857,0.000066583176,0.0007200358,0.00007201618,0.0018108637,0.000025397554,0.00027876176,0.0000060364177],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029051927,0.0060287104,0.8400688,0.00009060362,0.000013103485,0.000010187148,0.008521004,0.000050574516,0.016099341,0.00020788761,0.004556508,0.12406274],"study_design_scores_gemma":[0.0004982722,0.00030092054,0.9873574,0.00028383223,0.00007069256,0.00008926358,0.0030271197,0.001247944,0.0007134685,0.0024813227,0.0038156267,0.00011413231],"about_ca_topic_score_codex":0.0000189501,"about_ca_topic_score_gemma":0.000013536348,"teacher_disagreement_score":0.14728859,"about_ca_system_score_codex":0.0003433552,"about_ca_system_score_gemma":0.0006498375,"threshold_uncertainty_score":0.3930068},"labels":[],"label_agreement":null},{"id":"W4401108160","doi":"10.15620/cdc/159012","title":"Findings from a Cognitive Interview Study of SurveyQuestions Administered with Adults with Intellectual and Development Disabilities","year":2024,"lang":"en","type":"report","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Quest University Canada","funders":"","keywords":"Intellectual disability; Psychology; Cognition; Cognitive interview; Developmental psychology; Population; Survey research; Clinical psychology; Applied psychology; Medicine; Psychiatry; Environmental health","score_opus":0.4298288816165486,"score_gpt":0.5052539548395397,"score_spread":0.07542507322299113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401108160","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9789349,0.00040137657,0.0011383013,0.00010075738,0.00023263675,0.001201748,0.00018250529,0.000040909046,0.017766878],"genre_scores_gemma":[0.9866133,0.00013304566,0.00059332384,0.00003207683,0.000024735382,0.0002209936,0.00015085754,0.00002665038,0.012205023],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9939019,0.00043690111,0.0012600021,0.00087543944,0.0033420508,0.00018368146],"domain_scores_gemma":[0.99096465,0.005883923,0.00035829237,0.00040253488,0.002272251,0.000118368036],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0045550265,0.00036947263,0.00082555244,0.0004132594,0.00010024943,0.00031986297,0.000311556,0.000106769185,0.004658811],"category_scores_gemma":[0.0031861986,0.00019374241,0.00004634246,0.0005629299,0.00025922284,0.00019718675,0.00028212543,0.00031802527,0.000135544],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015770402,0.0020608366,0.35339046,0.0008079618,0.0022374801,0.000048187983,0.4010605,0.0000071831882,9.674766e-7,0.000043701206,0.009991769,0.22877395],"study_design_scores_gemma":[0.0026473326,0.007851987,0.2158699,0.008988811,0.0005354928,0.00006786582,0.744338,0.00016494635,0.00013728224,0.0001791747,0.018237319,0.0009819323],"about_ca_topic_score_codex":0.0008024069,"about_ca_topic_score_gemma":0.035001755,"teacher_disagreement_score":0.34327748,"about_ca_system_score_codex":0.00014498133,"about_ca_system_score_gemma":0.0032901391,"threshold_uncertainty_score":0.99625105},"labels":[],"label_agreement":null},{"id":"W4401363452","doi":"10.3138/cjpe.39.1.rr-en","title":"Roots and Relations: Celebrating Good Medicine in Indigenous Evaluation","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Indigenous; Engineering ethics; Traditional medicine; Sociology; History; Anthropology; Medicine; Engineering; Biology; Ecology","score_opus":0.27093444104940484,"score_gpt":0.5361930289587907,"score_spread":0.2652585879093859,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401363452","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9633284,0.013666122,0.00096954807,0.010101052,0.0016477577,0.0022198802,0.000004527486,0.000018532115,0.008044182],"genre_scores_gemma":[0.9980743,0.000037075813,0.0012797036,0.000097878146,0.00024569602,0.00009156017,0.000017323357,0.000010403612,0.00014606418],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99468344,0.00086291175,0.0012094696,0.00025526705,0.0027436218,0.0002452929],"domain_scores_gemma":[0.99659127,0.0005525803,0.00039711528,0.00018632469,0.001970099,0.00030258516],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03907019,0.00012194851,0.00022733015,0.0017073682,0.00019393348,0.00047445117,0.00021966282,0.00009615277,0.0025375937],"category_scores_gemma":[0.004763488,0.00009153673,0.000052224324,0.0015247625,0.000092554976,0.0010447956,0.000009362625,0.00031109626,0.00005654545],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004005096,0.000012702478,0.04446691,0.000007525721,0.000015257189,0.000008552444,0.0057650534,0.0032582579,0.000042759853,0.00070559216,0.00096419815,0.9447492],"study_design_scores_gemma":[0.0012188304,0.0006398524,0.3752596,0.00043947485,0.0001644779,0.000109367465,0.0031793304,0.54462606,0.000018909897,0.05145658,0.022717379,0.00017011493],"about_ca_topic_score_codex":0.0010093543,"about_ca_topic_score_gemma":0.054856278,"teacher_disagreement_score":0.94457906,"about_ca_system_score_codex":0.00073940115,"about_ca_system_score_gemma":0.0067357277,"threshold_uncertainty_score":0.99889517},"labels":[],"label_agreement":null},{"id":"W4401363543","doi":"10.3138/cjpe-2023-0021","title":"Breaking the Mould? Expanding our Conceptualization of Evaluator Competencies","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Conceptualization; Psychology; Engineering ethics; Sociology; Computer science; Engineering; Artificial intelligence","score_opus":0.40402035861867575,"score_gpt":0.5589097674439346,"score_spread":0.15488940882525887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401363543","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9558064,0.00813821,0.013606777,0.010137781,0.005654345,0.0022067358,0.00002594653,0.000036866037,0.0043869503],"genre_scores_gemma":[0.9982228,0.00001763726,0.0011611439,0.00011547873,0.0002787496,0.000036810983,0.000008188823,0.000010786032,0.0001484004],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9948405,0.00078209117,0.001113961,0.00017910906,0.0028615983,0.00022272299],"domain_scores_gemma":[0.9953874,0.00040762027,0.0006356931,0.0002594069,0.0031040753,0.0002058579],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.020877294,0.00011679464,0.00023100486,0.0006766078,0.00024511895,0.0006441518,0.00050740794,0.00006605505,0.0011073576],"category_scores_gemma":[0.0029150282,0.0000711175,0.00016725856,0.0012240978,0.00011075696,0.0007439646,0.000015313482,0.00020236221,0.00004446034],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011155339,0.000020368267,0.010338623,0.000020432775,0.000073972966,0.0000052788914,0.009593023,0.009002294,0.00058323547,0.0065380284,0.00611918,0.9576944],"study_design_scores_gemma":[0.0011276344,0.00084529014,0.04374561,0.00062838424,0.00046275376,0.00017007384,0.046133924,0.75823677,0.0014929437,0.024363505,0.12246422,0.0003288928],"about_ca_topic_score_codex":0.00032597163,"about_ca_topic_score_gemma":0.0039175176,"teacher_disagreement_score":0.9573655,"about_ca_system_score_codex":0.00033430345,"about_ca_system_score_gemma":0.0055391826,"threshold_uncertainty_score":0.99980575},"labels":[],"label_agreement":null},{"id":"W4401363915","doi":"10.3138/cjpe-2024-0008","title":"Nora F. Murphy Johnson &amp; A. Rafael Johnson (2021). <i>Creative Evaluation and Engagement Essentials (Vol. 1)</i>","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Art; Art history","score_opus":0.3043823667836116,"score_gpt":0.5217967985992583,"score_spread":0.21741443181564674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401363915","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9108886,0.03215453,0.013079768,0.0098992,0.009351686,0.006986124,0.000072331015,0.000067737164,0.017499993],"genre_scores_gemma":[0.9930037,0.00047522137,0.004320862,0.00023415194,0.0008333015,0.00026851965,0.00007920684,0.00002972985,0.0007553037],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99031967,0.002331931,0.0014888176,0.0005436799,0.004867529,0.00044836162],"domain_scores_gemma":[0.99062127,0.00060234894,0.00071168196,0.0004293353,0.0069733034,0.00066203874],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.05000189,0.00027439988,0.00041821276,0.0016199852,0.000454755,0.0019088483,0.00043237742,0.00014797234,0.012995031],"category_scores_gemma":[0.006777088,0.00021719735,0.00020694171,0.0015372413,0.0001715705,0.0015098441,0.00003497474,0.00045770855,0.0003831525],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024096964,0.000047222453,0.0017392363,0.000020262334,0.0001093917,0.000008595059,0.0027187064,0.0020124502,0.00025641854,0.00037836115,0.038050815,0.9546344],"study_design_scores_gemma":[0.0016079256,0.0006087543,0.025916506,0.00033624037,0.00075830705,0.000055843164,0.0016573318,0.18287408,0.0004261805,0.01706526,0.7682866,0.0004069687],"about_ca_topic_score_codex":0.00092215516,"about_ca_topic_score_gemma":0.014221024,"teacher_disagreement_score":0.95422745,"about_ca_system_score_codex":0.00092166674,"about_ca_system_score_gemma":0.007992235,"threshold_uncertainty_score":0.99912727},"labels":[],"label_agreement":null},{"id":"W4401363971","doi":"10.3138/cjpe-2024-0126","title":"Reinhard Stockmann, Wolfgang Meyer, &amp; Laszlo Szentmarjay. (Eds.) (2022). <i>The Institutionalisation of Evaluation in the Americas</i>","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Institutionalisation; Political science; Sociology; Humanities; Philosophy; Law","score_opus":0.31244695241803505,"score_gpt":0.5200390598074937,"score_spread":0.2075921073894586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401363971","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9310779,0.01853623,0.005760088,0.028611612,0.0044370415,0.0054322397,0.00004225591,0.000026718786,0.0060759173],"genre_scores_gemma":[0.9979202,0.00010943092,0.00072880543,0.00046917432,0.00031863636,0.00023997614,0.00006008405,0.00001110781,0.00014258498],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9901634,0.0023500656,0.0014860987,0.00028398298,0.0054253936,0.00029107626],"domain_scores_gemma":[0.9945388,0.00091505767,0.00075621123,0.0004920117,0.0031308045,0.00016713492],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.053720083,0.00016338163,0.0002565108,0.0010059107,0.00028711578,0.00062561204,0.00069462106,0.00009170949,0.002058992],"category_scores_gemma":[0.0054448918,0.000095454896,0.00019715508,0.0026552575,0.00024972882,0.0009735943,0.00001818433,0.00043854193,0.00011193437],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001906672,0.000052809854,0.0044223866,0.000013672497,0.000041972897,0.0000057328257,0.0043979175,0.021103822,0.00013391243,0.0025661485,0.017370516,0.949872],"study_design_scores_gemma":[0.0011904619,0.00041871765,0.085209064,0.00028387722,0.00037668977,0.00016329785,0.003099465,0.21034686,0.00012893825,0.036737062,0.66178983,0.00025571277],"about_ca_topic_score_codex":0.00093154114,"about_ca_topic_score_gemma":0.029435609,"teacher_disagreement_score":0.9496163,"about_ca_system_score_codex":0.00067845284,"about_ca_system_score_gemma":0.008181767,"threshold_uncertainty_score":0.99885327},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W4401363982","doi":"10.3138/cjpe-2023-0025","title":"E-Eval: Learnings from a Community-Based Evaluation Capacity Building Initiative","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Concordia University of Edmonton; University of Alberta","funders":"","keywords":"Capacity building; Geography; Forestry; Political science","score_opus":0.6622962955102082,"score_gpt":0.5664147753741403,"score_spread":0.09588152013606788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401363982","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97849685,0.00084223214,0.010966413,0.003471186,0.0019187639,0.0013608694,0.000042111125,0.00004100137,0.002860566],"genre_scores_gemma":[0.9914756,0.0000041651047,0.007441659,0.00052370556,0.00030020188,0.0001184968,0.000086713546,0.000020755753,0.000028708217],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9889382,0.004841674,0.0011792794,0.00027821766,0.0044324393,0.00033019515],"domain_scores_gemma":[0.99100435,0.0017975147,0.0007019207,0.00041305987,0.005601824,0.0004813388],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05627129,0.00019658037,0.0003152913,0.0013424868,0.0005847486,0.0014055566,0.0006446693,0.00013868831,0.0049282513],"category_scores_gemma":[0.008720417,0.00016080371,0.00022630443,0.0014721156,0.00016823426,0.0013183252,0.00001826127,0.0009795686,0.00017931525],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021243073,0.000054164233,0.0070004077,0.000013971942,0.00008634123,0.0000069833304,0.007055054,0.018911455,0.0002930355,0.00046718298,0.0034402232,0.96264994],"study_design_scores_gemma":[0.0011727574,0.00062375667,0.044756267,0.00035386955,0.0003835688,0.000017132543,0.0034093459,0.82541806,0.0005444987,0.052909646,0.07016111,0.00025001206],"about_ca_topic_score_codex":0.0031258613,"about_ca_topic_score_gemma":0.019666402,"teacher_disagreement_score":0.9623999,"about_ca_system_score_codex":0.0013422393,"about_ca_system_score_gemma":0.011958282,"threshold_uncertainty_score":0.9996311},"labels":[],"label_agreement":null},{"id":"W4401364631","doi":"10.3138/cjpe-2023-0020","title":"Developing an Evaluation Training Program for Community-Based Organizations: A Participatory Curriculum Development Approach","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Training (meteorology); Curriculum; Citizen journalism; Curriculum development; Medical education; Sociology; Computer science; Political science; Pedagogy; Geography; Medicine","score_opus":0.6931025557856326,"score_gpt":0.5773742074883836,"score_spread":0.11572834829724898,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401364631","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7084437,0.0011849356,0.27510384,0.0019614985,0.002198257,0.009618494,0.00001820668,0.00016873781,0.0013023025],"genre_scores_gemma":[0.8272568,0.0000015378249,0.17023078,0.00020879303,0.00018953273,0.001731904,0.000333898,0.000028542512,0.00001824298],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99277306,0.0021085937,0.0014686016,0.00031981972,0.0028740305,0.00045588397],"domain_scores_gemma":[0.98927474,0.00044421406,0.0005383983,0.00036290078,0.008857516,0.00052221684],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.053629883,0.00021555634,0.00030908862,0.0012049073,0.0009272837,0.0014585787,0.00062299427,0.0001303319,0.000428193],"category_scores_gemma":[0.0049893777,0.00017703553,0.000115730574,0.0022500749,0.000103337436,0.0011926523,0.000014056768,0.00038915878,0.00002720965],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000068038366,0.00016715586,0.0022323441,0.000051852796,0.00005413679,0.0000010420893,0.010105342,0.0150132,0.000012065604,0.001544409,0.0005076145,0.970304],"study_design_scores_gemma":[0.0009354303,0.0006090317,0.005005686,0.00019934379,0.00022176141,0.00002121013,0.009867447,0.8951361,0.00012356331,0.0072043864,0.08040471,0.0002713188],"about_ca_topic_score_codex":0.000134473,"about_ca_topic_score_gemma":0.0066735526,"teacher_disagreement_score":0.9700327,"about_ca_system_score_codex":0.0014823256,"about_ca_system_score_gemma":0.04093181,"threshold_uncertainty_score":0.999578},"labels":[],"label_agreement":null},{"id":"W4401364750","doi":"10.3138/cjpe-2023-0047","title":"Expert Panels in Evaluation: An Update From the Field Using the DATA Model","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Government of Canada; Agriculture and Agri-Food Canada; University of Prince Edward Island","funders":"","keywords":"Field (mathematics); Computer science; Data science; Mathematics","score_opus":0.7706233405746606,"score_gpt":0.6311445631645073,"score_spread":0.13947877741015335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401364750","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85417444,0.0124906255,0.037636425,0.0864676,0.004574502,0.0034177962,0.000112659756,0.00002377352,0.0011021608],"genre_scores_gemma":[0.9938583,0.000041475716,0.0035113576,0.0019259651,0.0005167878,0.00004710441,0.00006803881,0.000010309581,0.000020681397],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99426967,0.0013752173,0.0008683562,0.0003137165,0.002940367,0.00023266386],"domain_scores_gemma":[0.99613523,0.0010787928,0.0002852363,0.0009917762,0.0013085838,0.00020035187],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.037724517,0.00011802684,0.0001586325,0.00028840126,0.0002810685,0.001400119,0.0016001563,0.00007364102,0.0026808265],"category_scores_gemma":[0.0038226338,0.00006206725,0.00006713003,0.0008583246,0.000075286225,0.0017538992,0.00004812617,0.00034507984,0.00003330539],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009043076,0.0000151084405,0.0014663325,8.1242854e-7,0.000021690077,0.000003995698,0.004290626,0.063283935,0.000030857827,0.00021624433,0.009654232,0.9210071],"study_design_scores_gemma":[0.00027289218,0.00006756321,0.0036943015,0.000067200315,0.00008571979,0.000012461629,0.0025782906,0.94654477,0.00002617278,0.02103949,0.02553062,0.000080531914],"about_ca_topic_score_codex":0.0033009548,"about_ca_topic_score_gemma":0.061384503,"teacher_disagreement_score":0.9209266,"about_ca_system_score_codex":0.00034305025,"about_ca_system_score_gemma":0.009094842,"threshold_uncertainty_score":0.99963653},"labels":[],"label_agreement":null},{"id":"W4401364911","doi":"10.3138/cjpe-2024-0023","title":"Marthe Hurteau &amp; Thomas Archibald (Eds.). (2023). <i>Practical Wisdom for an Ethical Evaluation Practice</i> .","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Philosophy; Environmental ethics; Engineering ethics; Engineering","score_opus":0.4952909679291251,"score_gpt":0.6140363416331979,"score_spread":0.11874537370407279,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401364911","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1650718,0.02062413,0.21269801,0.47024062,0.029418632,0.02751974,0.00032413495,0.0003136494,0.073789276],"genre_scores_gemma":[0.9105394,0.000099902594,0.08251535,0.0029311504,0.0020391752,0.0007439676,0.00023622818,0.000061595405,0.0008332102],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98744816,0.0035619454,0.001660511,0.000574232,0.006197195,0.00055795314],"domain_scores_gemma":[0.98492134,0.0037015392,0.00078388996,0.00060558267,0.008983868,0.0010037941],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09691397,0.00025474108,0.00038157514,0.000984504,0.00047154844,0.0021390563,0.0005670024,0.00035360674,0.0031737764],"category_scores_gemma":[0.038688753,0.000196477,0.00030117124,0.001250417,0.0002248244,0.0026623916,0.000021732327,0.0011287981,0.00034007253],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012671061,0.00011211114,0.00021232662,0.000016074231,0.00009174035,0.00000994376,0.0017277424,0.0022223764,0.00010995125,0.0056116143,0.06956732,0.92019206],"study_design_scores_gemma":[0.00087423716,0.0010123844,0.0010628615,0.00008188403,0.0004996216,0.00026493717,0.0010594773,0.2771444,0.000025913225,0.045309864,0.6724683,0.0001961156],"about_ca_topic_score_codex":0.00037655936,"about_ca_topic_score_gemma":0.026456768,"teacher_disagreement_score":0.91999596,"about_ca_system_score_codex":0.00069715164,"about_ca_system_score_gemma":0.021535395,"threshold_uncertainty_score":0.99889684},"labels":[],"label_agreement":null},{"id":"W4401375525","doi":"10.1177/10982140241270011","title":"Book Review: Policy Evaluation in the Era of COVID-19","year":2024,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Centre for Disease Control","funders":"","keywords":"Pearl; Coronavirus disease 2019 (COVID-19); Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); 2019-20 coronavirus outbreak; Political science; Virology; Geography; Medicine","score_opus":0.19986347767528487,"score_gpt":0.5871476618453196,"score_spread":0.38728418417003474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401375525","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.147267,0.39099473,0.008882572,0.44158393,0.0012565148,0.002534146,0.000016120302,0.000017927816,0.0074470644],"genre_scores_gemma":[0.94870603,0.01298112,0.00027504427,0.03755402,0.00029484404,0.000044276916,0.000008122796,0.000008253793,0.00012831758],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98712826,0.003899792,0.0016113508,0.0002059854,0.007007598,0.00014701393],"domain_scores_gemma":[0.99414986,0.002147844,0.0012427684,0.00038906094,0.001976645,0.000093823655],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07934207,0.00010844768,0.0003560693,0.0006793414,0.000063066655,0.00011397709,0.00048620315,0.000023782306,0.006224033],"category_scores_gemma":[0.016094755,0.00006176788,0.00018127974,0.0029069297,0.00015809,0.0007257789,0.000023649984,0.00030117904,0.00009106063],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003727634,0.00005679907,0.0006570757,0.000046171263,0.000026230953,0.0000028385537,0.0039832266,0.0081918705,0.00009626506,0.0004368124,0.20840982,0.7780556],"study_design_scores_gemma":[0.0014924032,0.0015590324,0.03590489,0.0014058675,0.00050510524,0.0002480333,0.0067783226,0.24626489,0.00008886047,0.02553803,0.6799645,0.00025006186],"about_ca_topic_score_codex":0.000059734746,"about_ca_topic_score_gemma":0.000021887328,"teacher_disagreement_score":0.801439,"about_ca_system_score_codex":0.0004844193,"about_ca_system_score_gemma":0.0061335247,"threshold_uncertainty_score":0.99950075},"labels":[],"label_agreement":null},{"id":"W4402053863","doi":"10.1108/978-1-80262-713-820241006","title":"Facilitating Change Making – In Practice","year":2024,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The King's University; Western University","funders":"","keywords":"Computer science","score_opus":0.5415435852893723,"score_gpt":0.5749160621140961,"score_spread":0.033372476824723774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402053863","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000015276653,0.0007503932,0.00021910599,0.0041158833,0.00071910204,0.00029159596,0.000014222454,0.00004477306,0.99382967],"genre_scores_gemma":[0.00862966,0.00011178627,0.0026449233,0.002475541,0.00021578032,0.000029091203,0.0000070465658,0.000020039693,0.9858661],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964859,0.000046607714,0.00075379264,0.0005218957,0.0020225737,0.00016926596],"domain_scores_gemma":[0.9964837,0.0025019965,0.00026270485,0.00041596766,0.00029646035,0.000039169536],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0053738654,0.0001904948,0.0002728501,0.00060530816,0.000049062717,0.00033707905,0.00034488618,0.00016388608,0.014478197],"category_scores_gemma":[0.0012607144,0.00013607087,0.000101037476,0.00014688628,0.00003112906,0.0006340992,0.00018370501,0.00044094067,0.0146657815],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008576678,0.0000066668413,0.000046283338,0.00001835533,0.000016899863,0.000037098802,0.0034130132,0.000021365839,0.0000011125018,0.7454267,0.004705689,0.24629825],"study_design_scores_gemma":[0.000068232795,0.000030297468,0.000049979295,0.0001932118,0.000015303734,0.0000072242988,0.0021238457,0.0045645414,5.668919e-7,0.1014941,0.89128613,0.00016653615],"about_ca_topic_score_codex":0.00002320599,"about_ca_topic_score_gemma":0.00038872493,"teacher_disagreement_score":0.88658047,"about_ca_system_score_codex":0.00012128466,"about_ca_system_score_gemma":0.00012986503,"threshold_uncertainty_score":0.9864227},"labels":[],"label_agreement":null},{"id":"W4402099750","doi":"10.31235/osf.io/9yq38","title":"Incentivising, excluding, and enduring: Insular policy feedback in Lithuanian research assessment","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Dynamics (music); Political science; Regional science; Psychology; Geography; Pedagogy","score_opus":0.5216111994312206,"score_gpt":0.6451508677722928,"score_spread":0.12353966834107222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402099750","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74348253,0.0008076982,0.00020686425,0.013929714,0.00089983706,0.0008815332,0.000022514241,0.00008509518,0.23968421],"genre_scores_gemma":[0.97926164,0.0006971756,0.0022436527,0.00027656645,0.0004197633,0.00012592037,0.000015761249,0.00003730225,0.016922198],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98986316,0.0011805508,0.0014272656,0.0016843472,0.0050785635,0.0007661284],"domain_scores_gemma":[0.9965942,0.000778265,0.00024976846,0.001347846,0.0007477602,0.0002821759],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.024781808,0.000392799,0.0006391116,0.0038137762,0.00026202115,0.0028971685,0.0012611015,0.0003995609,0.0018473424],"category_scores_gemma":[0.0014337297,0.00029716291,0.00013998785,0.0024322055,0.00028374317,0.00030176356,0.0071586864,0.0027634022,0.0007633206],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007038475,0.000735399,0.2952104,0.00082084147,0.00017946288,0.00016337805,0.013054156,0.0015553273,0.0009274478,0.34579962,0.02858383,0.3128998],"study_design_scores_gemma":[0.0006426887,0.00012185474,0.32931066,0.00080648693,0.000013526788,0.000009555782,0.0031066418,0.039682906,0.00028303373,0.56002533,0.065435074,0.0005622405],"about_ca_topic_score_codex":0.0020901274,"about_ca_topic_score_gemma":0.0015599894,"teacher_disagreement_score":0.31233755,"about_ca_system_score_codex":0.0009995518,"about_ca_system_score_gemma":0.0034944462,"threshold_uncertainty_score":0.999948},"labels":[],"label_agreement":null},{"id":"W4402109925","doi":"10.55016/ojs/jet.v22i3.44241","title":"Competence, Curriculum, and Control","year":2018,"lang":"en","type":"article","venue":"Journal of educational thought.","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Competence (human resources); Curriculum; Psychology; Mathematics education; Pedagogy; Social psychology","score_opus":0.09096601388774617,"score_gpt":0.49247874825905535,"score_spread":0.4015127343713092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402109925","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93016374,0.0005286114,0.0026489669,0.035734084,0.0026731836,0.00009523837,0.0000052487662,0.0000027752344,0.028148174],"genre_scores_gemma":[0.98630863,0.00003105924,0.008003584,0.0011481028,0.001739939,0.0000015797267,5.337923e-7,0.0000029780144,0.002763571],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99794,0.00013135995,0.0006005218,0.000109102766,0.0011197573,0.000099238525],"domain_scores_gemma":[0.99637794,0.0009844501,0.0005397756,0.00013557673,0.0018400049,0.00012225068],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0029009613,0.00006486423,0.00016775237,0.00021545033,0.00014051454,0.000136422,0.00029103947,0.00002624729,0.0045892275],"category_scores_gemma":[0.0015257283,0.000040340863,0.00006121168,0.00035521775,0.00014005095,0.00048519822,0.000020123536,0.00010279198,0.00026729968],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000759928,0.00038607637,0.6123544,0.0000042859206,0.00006436565,0.0000013847414,0.0008920041,0.000053842556,0.0006681193,0.20107299,0.15637966,0.028046897],"study_design_scores_gemma":[0.0008217408,0.000316418,0.551191,0.00002914408,0.00002252791,0.00017789657,0.00083513214,0.0017695109,0.00014858705,0.07160221,0.3729839,0.000101928206],"about_ca_topic_score_codex":0.000002347815,"about_ca_topic_score_gemma":0.000007794652,"teacher_disagreement_score":0.21660425,"about_ca_system_score_codex":0.000029555225,"about_ca_system_score_gemma":0.0005365122,"threshold_uncertainty_score":0.9963207},"labels":[],"label_agreement":null},{"id":"W4402110049","doi":"10.55016/ojs/jet.v19i3.52784","title":"Getting Started on Social Analysis in Canada","year":2018,"lang":"en","type":"article","venue":"Journal of educational thought.","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.18637758697805007,"score_gpt":0.515114714599559,"score_spread":0.328737127621509,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402110049","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.967164,0.000023516024,0.00008885841,0.023498641,0.00084298244,0.00003092079,0.0000049246487,6.1203934e-7,0.008345544],"genre_scores_gemma":[0.99492055,0.0000032453393,0.0012891704,0.0013167871,0.0011624852,0.0000011594046,0.0000025150118,0.0000027712933,0.0013013105],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99697083,0.00018957106,0.00078340044,0.0001172217,0.0018101031,0.00012885255],"domain_scores_gemma":[0.9970095,0.0011060475,0.000635536,0.0001182405,0.0010598269,0.000070844944],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002893022,0.00006460536,0.00021003488,0.0005852563,0.00013226786,0.00006931386,0.0003253976,0.00002138393,0.006473415],"category_scores_gemma":[0.0011827791,0.000046015295,0.00009817067,0.0017556776,0.000030661082,0.00023560967,0.000015060255,0.00014791434,0.00006075062],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013782209,0.0002670232,0.7814343,0.0000021887204,0.00025130814,0.000003672798,0.0019674953,0.003642904,0.00016814804,0.013958458,0.17200707,0.026159588],"study_design_scores_gemma":[0.00021085382,0.00004531978,0.9644796,0.000007451752,0.00003012775,0.0000029979865,0.0014231256,0.001887436,0.000110747,0.0048034685,0.026935656,0.00006322036],"about_ca_topic_score_codex":0.020372797,"about_ca_topic_score_gemma":0.5187637,"teacher_disagreement_score":0.4983909,"about_ca_system_score_codex":0.0005360952,"about_ca_system_score_gemma":0.0055236127,"threshold_uncertainty_score":0.9944348},"labels":[],"label_agreement":null},{"id":"W4402110255","doi":"10.55016/ojs/jet.v10i3.43890","title":"From Quantitative to Qualitative Change in Ontario Education, Gamet McDiarmid (Editor)","year":2018,"lang":"en","type":"article","venue":"Journal of educational thought.","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Geography; Mathematics education; Statistics; Mathematics","score_opus":0.36925181006582514,"score_gpt":0.6046730916550659,"score_spread":0.23542128158924075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402110255","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93308175,0.00018263586,0.00038310254,0.044474825,0.01520559,0.00024347338,0.000019837988,0.0000024354288,0.006406332],"genre_scores_gemma":[0.8875296,0.000016196384,0.080269024,0.0045174425,0.017459627,0.000064617845,0.000021683074,0.000014680361,0.010107087],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9959667,0.00057798286,0.0012053397,0.00027792205,0.0017833497,0.00018871653],"domain_scores_gemma":[0.99171954,0.0034368758,0.00086247176,0.00028780656,0.0034624804,0.00023083473],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.005298306,0.00014333741,0.0003243628,0.0008012983,0.000105654144,0.00015873768,0.00061726535,0.00006153471,0.013114143],"category_scores_gemma":[0.0046426686,0.000108684064,0.00010661929,0.0010464657,0.0000981739,0.0011606361,0.00005012255,0.00027540798,0.0012342781],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003075222,0.001115058,0.14155056,0.0000027621043,0.000059711154,7.616552e-7,0.36889023,0.00005306946,0.00021266656,0.044067454,0.4347864,0.008953803],"study_design_scores_gemma":[0.00030845666,0.0003815951,0.5131225,0.000095748255,0.000011513758,0.000004917082,0.03043143,0.000054214775,0.00014881283,0.118560694,0.33673155,0.00014853933],"about_ca_topic_score_codex":0.008817899,"about_ca_topic_score_gemma":0.07414357,"teacher_disagreement_score":0.37157196,"about_ca_system_score_codex":0.00059546105,"about_ca_system_score_gemma":0.005564305,"threshold_uncertainty_score":0.99954337},"labels":[],"label_agreement":null},{"id":"W4402110671","doi":"10.55016/ojs/jet.v36i1.52736","title":"Fenwick, T. &amp; Parsons, J. (2000). The Art of Evaluation: A Handbookfor Educators and Trainers. Toronto: Thompson Educational Publishers. Softcover, 246 pages.","year":2018,"lang":"en","type":"article","venue":"Journal of educational thought.","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Sociology; Gerontology; Library science; Media studies; Medicine; Computer science","score_opus":0.14492954093688148,"score_gpt":0.4737681638893039,"score_spread":0.3288386229524224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402110671","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45039973,0.017641712,0.0008546309,0.39569733,0.014643705,0.0012406523,0.000060714905,0.000012405135,0.119449124],"genre_scores_gemma":[0.9143627,0.0006848373,0.018403526,0.0032396961,0.008025675,0.00008512837,0.000061575236,0.000035094217,0.055101708],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9936928,0.0005653583,0.0014997416,0.00034746007,0.003610754,0.0002838909],"domain_scores_gemma":[0.98987186,0.0031104146,0.0016683443,0.000559739,0.004534138,0.00025547657],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011603859,0.00022884851,0.000404621,0.0002783912,0.00039601466,0.00054458616,0.00075037434,0.00010474588,0.03137606],"category_scores_gemma":[0.00646275,0.00014219388,0.000227236,0.0006839392,0.00046512167,0.0023552908,0.000070228474,0.00026307753,0.00017688009],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000994066,0.0004489908,0.014659077,0.000010253166,0.00010931174,1.06570575e-7,0.004565695,0.000047513615,0.00012827234,0.013296077,0.94083226,0.025803035],"study_design_scores_gemma":[0.00087749405,0.00023858256,0.16554664,0.00008899035,0.00012618027,0.00015796421,0.0053876876,0.00031065944,0.00014561851,0.037441224,0.78946257,0.00021640278],"about_ca_topic_score_codex":0.000025938534,"about_ca_topic_score_gemma":0.00046969348,"teacher_disagreement_score":0.463963,"about_ca_system_score_codex":0.00042103408,"about_ca_system_score_gemma":0.008376747,"threshold_uncertainty_score":0.99724483},"labels":[],"label_agreement":null},{"id":"W4402297732","doi":"10.1016/j.evalprogplan.2024.102496","title":"Arts-based evaluation of the Communities ChooseWell program","year":2024,"lang":"en","type":"article","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Victoria","funders":"","keywords":"The arts; Context (archaeology); Program evaluation; Space (punctuation); Process (computing); Sociology; Psychology; Public relations; Computer science; Political science; Geography; Public administration","score_opus":0.49517830828719495,"score_gpt":0.6325703300095291,"score_spread":0.13739202172233417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402297732","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96411854,0.0038811846,0.00054552325,0.002352125,0.0009983592,0.0033131072,0.000010895931,0.00020958195,0.024570704],"genre_scores_gemma":[0.9972837,0.000011131175,0.0015484411,0.00018422792,0.00007117588,0.0006604817,0.000052580515,0.000010933418,0.0001773269],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9927703,0.0014058714,0.000644748,0.00026787937,0.004720675,0.00019052911],"domain_scores_gemma":[0.9969019,0.0008302433,0.00023333411,0.00049838366,0.001476748,0.000059363523],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.028873445,0.00014824461,0.0001827399,0.00026840167,0.0003231955,0.0006591325,0.0003524359,0.0000764945,0.0015841397],"category_scores_gemma":[0.0009291445,0.000090680354,0.000107013875,0.0009700432,0.00017052982,0.00037007217,0.000070001784,0.00022736688,0.000044399858],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000129604,0.00008705395,0.019803986,0.000025176583,0.000020696265,1.3319756e-7,0.0027735073,0.012620205,0.000032558524,0.0005715488,0.001059394,0.9629928],"study_design_scores_gemma":[0.0005330156,0.00016871314,0.08181464,0.00022948094,0.00013011016,0.000002612869,0.0025010468,0.86703414,0.00022550892,0.004424233,0.04282956,0.00010693815],"about_ca_topic_score_codex":0.00002140998,"about_ca_topic_score_gemma":0.00004704657,"teacher_disagreement_score":0.96288586,"about_ca_system_score_codex":0.00007722374,"about_ca_system_score_gemma":0.0008211358,"threshold_uncertainty_score":0.99997914},"labels":[],"label_agreement":null},{"id":"W4402405798","doi":"10.23889/ijpds.v9i5.2587","title":"The employment, retention and exit of public school teachers in New Brunswick, Canada: an analysis using linked administrative data","year":2024,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Psychology; Business; Mathematics education; Demographic economics; Public administration; Political science; Economics","score_opus":0.6082030703870391,"score_gpt":0.5889861933433733,"score_spread":0.019216877043665814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402405798","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.936767,0.00026428417,0.054057106,0.0063075577,0.0019110771,0.00024346609,0.00035531097,0.00000859671,0.00008560612],"genre_scores_gemma":[0.99518746,0.0000979099,0.003748459,0.00006643308,0.00016653788,7.4794235e-7,0.00039286262,0.0000039497136,0.00033566734],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955694,0.00016346546,0.0008757672,0.0005227489,0.0026899904,0.0001786355],"domain_scores_gemma":[0.99738896,0.00048275618,0.00043851117,0.00078192266,0.000709726,0.00019810685],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.013679689,0.00008537734,0.00013601487,0.0010650858,0.00036342477,0.0022397398,0.0032933864,0.00002637232,0.000112265145],"category_scores_gemma":[0.004659514,0.000056940153,0.000032498698,0.0020573058,0.00013598106,0.007328051,0.00045253188,0.00016390589,0.0000011670141],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041942272,0.00003649636,0.8748063,0.0000020754853,0.00017875084,0.000004679275,0.0003906744,0.0037693516,0.00028321848,0.014387618,0.0026333209,0.10346558],"study_design_scores_gemma":[0.000126961,0.000019158715,0.4214977,0.00001667879,0.000030355353,0.000011167576,0.00082249433,0.5693114,0.0000059210633,0.0016587904,0.0064490554,0.00005033226],"about_ca_topic_score_codex":0.10838022,"about_ca_topic_score_gemma":0.7990129,"teacher_disagreement_score":0.6906327,"about_ca_system_score_codex":0.00033456282,"about_ca_system_score_gemma":0.009873149,"threshold_uncertainty_score":0.99879605},"labels":[],"label_agreement":null},{"id":"W4402406478","doi":"10.23889/ijpds.v9i5.2860","title":"Building access to linked data for program evaluation: lessons and opportunities from the evaluation of a pan-Canadian skills training initiative","year":2024,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Training (meteorology); Computer science; Medical education; Data science; Medicine; Geography","score_opus":0.8689239634490931,"score_gpt":0.6757502367984896,"score_spread":0.1931737266506035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402406478","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.530537,0.0013421035,0.26061788,0.15847363,0.0149279125,0.0094226,0.023628602,0.00007261344,0.0009776655],"genre_scores_gemma":[0.97890884,0.00006171238,0.017651621,0.00079393137,0.00058491173,0.00020069767,0.0017648172,0.000009436452,0.000024010276],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99309707,0.00023379881,0.0008652464,0.0006783147,0.0048871543,0.00023841532],"domain_scores_gemma":[0.9916089,0.0022262859,0.00043169074,0.000846199,0.0046900637,0.00019682599],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.043027993,0.0001231875,0.00016682732,0.00076899724,0.00067116605,0.0038322143,0.0048137223,0.00004173966,0.0002570527],"category_scores_gemma":[0.015298864,0.000084752886,0.000044259647,0.0006356353,0.00016695194,0.007935572,0.0006828477,0.00013289753,0.0000036707522],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017339875,0.000019024774,0.0012698676,0.0000021085132,0.00004610923,3.681348e-7,0.0011117744,0.001983925,0.000054732616,0.0059336713,0.0043115956,0.98524946],"study_design_scores_gemma":[0.0003977869,0.000049193484,0.084866226,0.00014417685,0.00009566598,0.000010572754,0.0012705153,0.8021897,0.000016097294,0.041623894,0.06923282,0.0001033486],"about_ca_topic_score_codex":0.0011395444,"about_ca_topic_score_gemma":0.010342628,"teacher_disagreement_score":0.9851461,"about_ca_system_score_codex":0.00029862515,"about_ca_system_score_gemma":0.004410879,"threshold_uncertainty_score":0.9972019},"labels":[],"label_agreement":null},{"id":"W4402454591","doi":"10.4212/cjhp.3679","title":"Embracing Our Future: A Revised Name for CSHP","year":2024,"lang":"en","type":"article","venue":"The Canadian Journal of Hospital Pharmacy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Canadian Science Publishing","funders":"","keywords":"Library science; Political science; Computer science","score_opus":0.1362797885178079,"score_gpt":0.4824075735994329,"score_spread":0.346127785081625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402454591","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.360283,0.017975835,0.002738312,0.57183546,0.03504026,0.0010675987,0.00010674773,0.000033533015,0.0109192515],"genre_scores_gemma":[0.99391454,0.000052289026,0.00024554523,0.0013353875,0.002845309,0.00000643779,0.0000013233347,0.000013867677,0.0015852913],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99803036,0.0001167846,0.0006211502,0.00014860963,0.0008093153,0.0002737621],"domain_scores_gemma":[0.9983017,0.00023634927,0.0002389619,0.0002049304,0.0006030507,0.00041504734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005196473,0.000113641036,0.00019249979,0.00031069978,0.00036179982,0.0009819308,0.0007601588,0.00002362802,0.0005792085],"category_scores_gemma":[0.0005047441,0.000063517575,0.0002535196,0.00045158534,0.000031674386,0.00069981907,0.000014992384,0.00031082166,0.00022708048],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007528198,0.000023370956,0.0013942897,0.00003901441,0.00017387449,0.00013612471,0.0065439,0.0008410537,0.00013838049,0.00932169,0.7129303,0.2683827],"study_design_scores_gemma":[0.000695645,0.00025028523,0.0013407929,0.00009543848,0.000073024836,0.00008890842,0.0032747118,0.0066796932,0.0002541023,0.028427925,0.95865154,0.00016793066],"about_ca_topic_score_codex":0.00031090569,"about_ca_topic_score_gemma":0.0019725992,"teacher_disagreement_score":0.6336315,"about_ca_system_score_codex":0.00017610294,"about_ca_system_score_gemma":0.0030724506,"threshold_uncertainty_score":0.9468781},"labels":[],"label_agreement":null},{"id":"W4402456713","doi":"10.7202/1113331ar","title":"L’évaluation formative : pratiques d’évaluation en classe et dilemmes du personnel enseignant dans la mise en oeuvre","year":2023,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Formative assessment; Valuation (finance); Political science; Humanities; Sociology; Business; Philosophy; Pedagogy; Accounting","score_opus":0.16356083020665513,"score_gpt":0.4644599927674716,"score_spread":0.30089916256081645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402456713","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8382136,0.00048564453,0.04620002,0.09306856,0.0053596823,0.0029887003,0.00019744824,0.00043499842,0.013051297],"genre_scores_gemma":[0.9641256,0.0033533962,0.006204426,0.001456032,0.0009345332,0.00094248715,0.002966191,0.00012213728,0.019895231],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.93569845,0.051926713,0.0029351036,0.001649638,0.0067905323,0.000999541],"domain_scores_gemma":[0.9799051,0.013830449,0.0017349081,0.001197248,0.0030319416,0.00030031527],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.16031535,0.0008689574,0.0008674074,0.0015404989,0.0010205582,0.0012632124,0.0009310231,0.00090896775,0.0033130294],"category_scores_gemma":[0.018539954,0.0008371632,0.00045368652,0.0031114805,0.0002653714,0.005449141,0.00025199255,0.0010347005,0.004075328],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008289633,0.000488436,0.004659205,0.00011610687,0.00013649168,0.000004914965,0.7996119,0.024138093,0.0017147593,0.012448233,0.020641653,0.13595727],"study_design_scores_gemma":[0.001562126,0.0003454032,0.44741148,0.00034622283,0.00031704153,0.00003675164,0.1308161,0.38044244,0.0007598173,0.013430272,0.02383504,0.00069729995],"about_ca_topic_score_codex":0.00070851896,"about_ca_topic_score_gemma":0.0028338197,"teacher_disagreement_score":0.6687958,"about_ca_system_score_codex":0.0019286384,"about_ca_system_score_gemma":0.010391769,"threshold_uncertainty_score":0.99977356},"labels":[],"label_agreement":null},{"id":"W4402596271","doi":"10.33524/cjar.v24i2.720","title":"Clausen, K., &amp; Black, G. (2020). The Future of Action Research in Education: A Canadian Perspective. McGill-Queen’s University Press.","year":2024,"lang":"en","type":"article","venue":"The Canadian Journal of Action Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Queen (butterfly); Action research; Perspective (graphical); Action (physics); Action learning; Sociology; Media studies; Pedagogy; Art; Visual arts; Teaching method; Cooperative learning; Physics","score_opus":0.42139326991485904,"score_gpt":0.5585900632977435,"score_spread":0.13719679338288449,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402596271","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30397156,0.0023736106,0.000025410038,0.59502584,0.0039567514,0.0010827779,0.00010194736,0.000010676408,0.09345145],"genre_scores_gemma":[0.98074216,0.0012834637,0.000029865821,0.00011579576,0.0007172559,0.0000037610498,0.000001994035,0.000010538872,0.017095169],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9930377,0.0029676924,0.00045730284,0.0002595037,0.0027599973,0.0005178097],"domain_scores_gemma":[0.99237686,0.0014184186,0.0001415944,0.0005365968,0.0049131014,0.0006134249],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.024689168,0.00009679864,0.00016614911,0.0026523746,0.0013141711,0.00050351047,0.001197791,0.00013243948,0.0018016037],"category_scores_gemma":[0.0009396887,0.0000596842,0.00010700991,0.0038990064,0.0005881731,0.00072233856,0.00004669817,0.0022030983,0.00017180528],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00019842593,0.000062063926,0.0024936707,0.000040804105,0.000100500525,0.00008645611,0.012120911,0.0017145551,0.00016839472,0.13097636,0.7673778,0.08466003],"study_design_scores_gemma":[0.00012213978,0.00008280797,0.0150807705,0.00007099662,0.000007693102,0.00005339726,0.08048593,0.00042242045,0.00007915942,0.008166782,0.89537024,0.00005767509],"about_ca_topic_score_codex":0.6817477,"about_ca_topic_score_gemma":0.9581241,"teacher_disagreement_score":0.6767706,"about_ca_system_score_codex":0.0048898784,"about_ca_system_score_gemma":0.030800777,"threshold_uncertainty_score":0.999986},"labels":[],"label_agreement":null},{"id":"W4402827753","doi":"10.1007/s10459-024-10376-6","title":"Navigating discourses of feedback: developing a pattern system of feedback","year":2024,"lang":"en","type":"article","venue":"Advances in Health Sciences Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Foothills Medical Centre; University of Calgary","funders":"Canadian Institutes of Health Research","keywords":"Computer science; Mathematics education; Medical education; Psychology; Medicine","score_opus":0.10808484659388805,"score_gpt":0.5555459206233194,"score_spread":0.44746107402943136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402827753","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93965155,0.022721909,0.015946321,0.010488383,0.0058863545,0.00067841104,0.000015059332,0.00004837144,0.0045636185],"genre_scores_gemma":[0.9912533,0.0007193754,0.0076274285,0.00018364972,0.00009216254,0.000039499104,0.000004277721,0.0000054670427,0.00007483386],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9959855,0.00025958903,0.0014911804,0.00046420397,0.0015155893,0.000283958],"domain_scores_gemma":[0.99760914,0.0010239026,0.0007252292,0.00025992218,0.00031002972,0.000071807095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007960054,0.00011790958,0.0003116924,0.00030738232,0.00017867885,0.000120395016,0.0005738396,0.000033298704,0.00007573706],"category_scores_gemma":[0.00044771543,0.00008595438,0.000050921397,0.0027355102,0.00028429276,0.0016058293,0.000058280926,0.00015066325,0.000029204824],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000033473514,0.000041753963,0.10462116,0.000920193,0.0000018471907,1.4991554e-7,0.0045731976,0.0031843279,0.000032322532,0.018483276,0.00010546473,0.868033],"study_design_scores_gemma":[0.0007855363,0.0011641558,0.28938773,0.041827075,0.000020630041,0.000055899323,0.3245997,0.24043626,0.0046655205,0.053172197,0.04283575,0.0010495138],"about_ca_topic_score_codex":0.00047766493,"about_ca_topic_score_gemma":0.00043877552,"teacher_disagreement_score":0.8669835,"about_ca_system_score_codex":0.00025025805,"about_ca_system_score_gemma":0.0035234732,"threshold_uncertainty_score":0.625049},"labels":[],"label_agreement":null},{"id":"W4402850333","doi":"10.32388/1xscnd","title":"Review of: \"Bridging Empirical Evidence and Diverse Epistemologies in Public Policy: Evidence-Based Policy and the Issue of Subjugated Knowledges\"","year":2024,"lang":"en","type":"peer-review","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Bridging (networking); Empirical evidence; Public policy; Political science; Sociology; Epistemology; Computer science; Law; Philosophy; Computer security","score_opus":0.560817005071267,"score_gpt":0.575252520860634,"score_spread":0.014435515789367082,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402850333","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00025214444,0.52043104,0.000033512817,0.4751176,0.00031668498,0.0009518331,0.000038162645,0.000020419615,0.0028386186],"genre_scores_gemma":[0.016515465,0.9043551,0.00019769568,0.03630153,0.00027524575,0.00012472553,0.000021976331,0.000019285968,0.042188983],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9913696,0.0024951913,0.0024764433,0.00088700885,0.002376424,0.00039530627],"domain_scores_gemma":[0.98123044,0.0141638275,0.0011919643,0.0012728557,0.0019714767,0.00016944211],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.028039575,0.0004320844,0.001967315,0.0013196474,0.00010535243,0.00025583102,0.0013034377,0.00021009111,0.0017206033],"category_scores_gemma":[0.09437817,0.00022346545,0.00031223294,0.0043436293,0.0011607999,0.0006573001,0.0009454776,0.00054573704,0.00013336266],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034110795,0.000035085617,0.0026074871,0.03651751,0.00003655147,0.0000034354,0.00020132663,0.0000035787673,0.0000022468466,0.0019781564,0.85244876,0.10613173],"study_design_scores_gemma":[0.0005070983,0.00014830219,0.0029757684,0.21272662,0.00023251252,0.000018977995,0.00015317701,0.003188108,0.000021251615,0.0020846357,0.7776007,0.00034283576],"about_ca_topic_score_codex":0.002168442,"about_ca_topic_score_gemma":0.0006167754,"teacher_disagreement_score":0.43881607,"about_ca_system_score_codex":0.00021666265,"about_ca_system_score_gemma":0.005459789,"threshold_uncertainty_score":0.99919194},"labels":[],"label_agreement":null},{"id":"W4402918007","doi":"10.26443/mje/rsem.v58i2.10240","title":"Creating a virtual equity, diversity, and inclusion community of practice","year":2024,"lang":"en","type":"article","venue":"McGill Journal of Education / Revue des sciences de l éducation de McGill","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Toronto; Vancouver Island University; Camosun College","funders":"","keywords":"Equity (law); Inclusion (mineral); Diversity (politics); Sociology; Political science; Anthropology; Law","score_opus":0.6789010317892197,"score_gpt":0.5902945124475407,"score_spread":0.08860651934167896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402918007","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9519007,0.0005367348,0.0020402728,0.004818188,0.0016645667,0.0001370504,0.000020128724,0.000016157133,0.03886619],"genre_scores_gemma":[0.98585874,0.00034163354,0.011911209,0.0011147261,0.0001179461,0.0000036341194,0.0000016893781,0.0000069364664,0.00064348953],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99574023,0.0013247851,0.0009435925,0.00022556027,0.0015411242,0.00022471936],"domain_scores_gemma":[0.9931644,0.0035399909,0.0009683673,0.00026745762,0.0018523982,0.0002073379],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.028722467,0.0001288828,0.00024720991,0.0008404337,0.007902048,0.00020993805,0.0010915963,0.000073679046,0.00022659235],"category_scores_gemma":[0.010349875,0.00010492518,0.00010621224,0.0015505182,0.00051023107,0.0024351492,0.0034954092,0.00039079634,0.000010788595],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013580463,0.0016253877,0.014173548,0.0003284067,0.00009787558,0.000008582834,0.26366898,0.005988194,0.0055586305,0.15757294,0.00528968,0.54555196],"study_design_scores_gemma":[0.00081084936,0.003145838,0.06064271,0.0022147682,0.00038860508,0.0036938502,0.23319615,0.040182862,0.004902132,0.50153387,0.14858066,0.0007077359],"about_ca_topic_score_codex":0.00039769645,"about_ca_topic_score_gemma":0.00013331568,"teacher_disagreement_score":0.5448442,"about_ca_system_score_codex":0.0009225516,"about_ca_system_score_gemma":0.0012110455,"threshold_uncertainty_score":0.9979864},"labels":[],"label_agreement":null},{"id":"W4403034213","doi":"10.7202/1113340ar","title":"Preparing for ‘intelligent and thoughtful practice’","year":2024,"lang":"en","type":"article","venue":"Ontario History","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Psychology; Computer science; Engineering ethics; Cognitive science; Engineering","score_opus":0.2468460518027375,"score_gpt":0.48430570829920827,"score_spread":0.23745965649647077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403034213","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.053718045,0.016310005,0.04040251,0.004784832,0.009516383,0.0009660987,0.000006817469,0.00019674434,0.87409854],"genre_scores_gemma":[0.42061707,0.00012999585,0.0204359,0.0019314949,0.00035405467,0.00014553237,0.0000089795285,0.00002523483,0.5563517],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99856627,0.000048357168,0.00030031454,0.0003423146,0.0006171403,0.00012561162],"domain_scores_gemma":[0.9985932,0.00085872493,0.00006995242,0.00025118235,0.00015992316,0.00006699863],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0030124327,0.00007996649,0.00011392124,0.00013525711,0.000085702704,0.00014734545,0.00015002779,0.00003914803,0.0019310603],"category_scores_gemma":[0.0005194122,0.00006129664,0.000063282336,0.00007545549,0.00004110145,0.00057354744,0.000044261036,0.00011482461,0.00029385884],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008257815,0.00005785486,0.0021441553,0.00002818694,0.000044254564,0.0000063198177,0.029926961,0.000107585794,0.00013859512,0.025922466,0.65327656,0.28826448],"study_design_scores_gemma":[0.00007890149,0.000069145026,0.0011852706,0.000015572925,0.00002258544,0.000011254024,0.00040987076,0.0035485756,0.00003479779,0.0023737878,0.99216706,0.00008315424],"about_ca_topic_score_codex":0.0020165353,"about_ca_topic_score_gemma":0.046078686,"teacher_disagreement_score":0.36689904,"about_ca_system_score_codex":0.0011902447,"about_ca_system_score_gemma":0.00092762173,"threshold_uncertainty_score":0.9989813},"labels":[],"label_agreement":null},{"id":"W4403070808","doi":"10.54337/nlc.v11.8767","title":"Communities of Practice","year":2018,"lang":"en","type":"article","venue":"Proceedings of the International Conference on Networked Learning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université TÉLUQ","funders":"","keywords":"Geography","score_opus":0.22295537669390175,"score_gpt":0.4714407095022655,"score_spread":0.24848533280836377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403070808","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5128588,0.000006819628,0.00013843113,0.0056435345,0.0005204808,0.00008373524,0.0000012711454,0.000013046691,0.4807339],"genre_scores_gemma":[0.9944166,0.00003057771,0.0007986606,0.0003908317,0.0001462919,0.000005012845,8.6620315e-7,0.0000050987787,0.004206075],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99758345,0.000060064376,0.00047282866,0.00012555762,0.0016515441,0.00010653416],"domain_scores_gemma":[0.9940928,0.0007011434,0.00093912333,0.0001277377,0.0041139903,0.00002521004],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0035152985,0.00008101865,0.00014515415,0.00012934611,0.0001681485,0.00013807364,0.0013900942,0.000037621365,0.001745162],"category_scores_gemma":[0.0026966848,0.000051379746,0.00006801395,0.00032688715,0.000252159,0.0004296711,0.00026389907,0.00027690892,0.000052361742],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00069177436,0.00019996926,0.16679628,0.000013516983,0.00015661071,1.2135094e-7,0.012607355,0.0037966126,0.009059398,0.74011236,0.012153043,0.054412972],"study_design_scores_gemma":[0.0012152398,0.0012554895,0.05212489,0.0008874968,0.000055388835,0.000017643351,0.07457003,0.55411655,0.01920005,0.051950064,0.24422175,0.00038540346],"about_ca_topic_score_codex":0.000036648235,"about_ca_topic_score_gemma":0.000016081714,"teacher_disagreement_score":0.68816227,"about_ca_system_score_codex":0.000028032378,"about_ca_system_score_gemma":0.000092662034,"threshold_uncertainty_score":0.9991674},"labels":[],"label_agreement":null},{"id":"W4403097997","doi":"10.1007/978-3-031-72430-5_8","title":"From Satisfaction to Impact: Evolving Evaluation Practices in Executive Education at the Ivey Academy","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Psychology; Medical education; Medicine","score_opus":0.1474180301134153,"score_gpt":0.4801587569579043,"score_spread":0.33274072684448897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403097997","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20465977,0.2595189,0.019948421,0.021558795,0.02742323,0.016449835,0.00024852762,0.00015591446,0.45003662],"genre_scores_gemma":[0.98326427,0.0005916993,0.00003250063,0.0003861937,0.0014719737,0.00016602548,0.000075652715,0.000029269384,0.013982407],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959115,0.0004395307,0.0009417305,0.0007813363,0.0016900989,0.00023580482],"domain_scores_gemma":[0.9945074,0.0037275394,0.0009669315,0.00039071476,0.00032033288,0.00008713133],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006944995,0.0003260484,0.00046194528,0.00046487738,0.00015809361,0.00073758676,0.00025414248,0.0005330008,0.00097428676],"category_scores_gemma":[0.0014113793,0.00019479272,0.00009018693,0.0003554337,0.00004386682,0.0003461488,0.00013846217,0.0008806014,0.00013943162],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000115657676,0.000015421103,0.026986126,0.000033601,0.000090993555,0.0000023682555,0.0072168014,0.6262666,0.00003147843,0.0019946387,0.012001475,0.32524484],"study_design_scores_gemma":[0.0003073655,0.00009858279,0.058481384,0.0018007477,0.00014049833,0.000017931696,0.00074862334,0.80638736,0.0000033740305,0.088180356,0.043343436,0.0004903478],"about_ca_topic_score_codex":0.002523322,"about_ca_topic_score_gemma":0.008620785,"teacher_disagreement_score":0.7786045,"about_ca_system_score_codex":0.0009496221,"about_ca_system_score_gemma":0.00039634045,"threshold_uncertainty_score":0.99993896},"labels":[],"label_agreement":null},{"id":"W4403147711","doi":"10.22230/ijepl.2024v20n2a1337","title":"Teacher Induction Policy Development and Implementation: A Case of Ontario’s New Teacher Induction Program (NTIP)","year":2024,"lang":"en","type":"article","venue":"International Journal of Education Policy and Leadership","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Saskatchewan; Carleton University; Queen's University","funders":"","keywords":"Teacher induction; Mathematics education; Computer science; Political science; Psychology; Pedagogy; Professional development","score_opus":0.416813624792624,"score_gpt":0.565963445946398,"score_spread":0.149149821153774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403147711","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95717984,0.00065292034,0.0004907752,0.03808417,0.0016093453,0.00019628923,0.0000022191552,0.00001339187,0.0017710656],"genre_scores_gemma":[0.9821538,0.000027905664,0.00320478,0.0005484648,0.0022137752,0.000013078999,0.000009365882,0.000009070216,0.011819807],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99774575,0.00012633692,0.0009002984,0.00020726318,0.0008774166,0.0001429604],"domain_scores_gemma":[0.998467,0.00011787011,0.00048055025,0.00010383609,0.0006657882,0.00016489938],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018420393,0.00012941041,0.00016446422,0.0014141916,0.000085331194,0.00040468623,0.00019297535,0.00008063092,0.0008946295],"category_scores_gemma":[0.0005040192,0.00010267222,0.00006632821,0.00047977277,0.00007649689,0.0010635111,0.000034456938,0.00028764037,0.000012319227],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041849984,0.00016438818,0.009097766,0.000016087404,0.00010073692,0.000007513999,0.049137183,0.000011444103,0.00009334338,0.009960318,0.007962699,0.92340666],"study_design_scores_gemma":[0.0012067094,0.00042024086,0.1629644,0.0002911365,0.000079138255,0.0057828757,0.08619654,0.00019834166,0.001395855,0.021825122,0.7193183,0.0003213808],"about_ca_topic_score_codex":0.0077440883,"about_ca_topic_score_gemma":0.0059371805,"teacher_disagreement_score":0.9230853,"about_ca_system_score_codex":0.000688209,"about_ca_system_score_gemma":0.009660867,"threshold_uncertainty_score":0.99886346},"labels":[],"label_agreement":null},{"id":"W4403249784","doi":"10.1515/9782760555396-019","title":"Chapter 14 Evaluating and monitoring the implementation of the first Child Advocacy Centre in the Quebec City region : When evaluation goes hand-in-hand with the institution’s activities","year":2023,"lang":"en","type":"book-chapter","venue":"Presses de l'Université du Québec eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Institution; Political science; Public administration; Law","score_opus":0.07493241372702934,"score_gpt":0.329581971802263,"score_spread":0.25464955807523365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403249784","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92812616,0.00051029696,0.00019946366,0.017007353,0.00025874475,0.002438346,0.000017894587,0.000021872893,0.051419843],"genre_scores_gemma":[0.9887891,0.00011541582,0.000010733279,0.00015087494,0.00009757539,0.00004244667,0.000004188781,0.000015735448,0.010773949],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99684256,0.0003750409,0.00042857867,0.0003715444,0.0017741842,0.00020809492],"domain_scores_gemma":[0.99698967,0.001368864,0.000661794,0.00059727655,0.00035445538,0.000027934397],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034678904,0.00025324777,0.00024480966,0.0001953443,0.0011305889,0.00034541907,0.0008153227,0.000095322175,0.0004378385],"category_scores_gemma":[0.00015990443,0.00011774733,0.00010082496,0.000088113215,0.0005088833,0.00033205756,0.00029031376,0.00040400954,0.000008617541],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003825938,0.00003692984,0.28392985,0.00009511006,0.00023288268,0.000011059881,0.405651,0.004376193,0.00006962492,0.00756576,0.0016602299,0.29598874],"study_design_scores_gemma":[0.0038260508,0.00023052478,0.7549853,0.0016248332,0.00082474295,0.000045922105,0.14531516,0.006770177,0.001148567,0.008623599,0.07593718,0.0006679864],"about_ca_topic_score_codex":0.03060558,"about_ca_topic_score_gemma":0.691793,"teacher_disagreement_score":0.66118747,"about_ca_system_score_codex":0.00036539233,"about_ca_system_score_gemma":0.0010031943,"threshold_uncertainty_score":0.9758497},"labels":[],"label_agreement":null},{"id":"W4403250772","doi":"10.1002/ev.20615","title":"Using contribution analysis to assess evaluation capacity outcomes in community organizations","year":2024,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; University of Ottawa","funders":"","keywords":"Evaluation methods; Capacity building; Program evaluation; Process management; Business; Political science; Public administration; Economic growth; Economics; Engineering","score_opus":0.538010031454944,"score_gpt":0.5850516251312451,"score_spread":0.04704159367630112,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403250772","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6357742,0.00007385741,0.35830238,0.0015973938,0.0011988044,0.0019515802,0.00007559378,0.00010114634,0.0009250299],"genre_scores_gemma":[0.9932098,0.0000061050723,0.0051238067,0.00015875477,0.000118300406,0.0004079335,0.00038061323,0.00001832878,0.00057639665],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99297214,0.002189526,0.0010415817,0.00052166707,0.0029958952,0.00027917096],"domain_scores_gemma":[0.99182653,0.002260649,0.00020936821,0.0006749226,0.004878069,0.0001504596],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.031351037,0.00020067222,0.0004017927,0.002616893,0.0007694029,0.00070138124,0.00032238226,0.00013322102,0.0021422023],"category_scores_gemma":[0.018385787,0.00017777407,0.00022039514,0.0117064705,0.000030590563,0.0011165452,0.00005686581,0.0002654117,0.00015739731],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039143637,0.00040045963,0.11956669,0.0000137535435,0.00062750577,1.6486634e-7,0.0051685954,0.735638,0.0037271937,0.0059494907,0.0027402118,0.12612881],"study_design_scores_gemma":[0.00069763244,0.000053140902,0.2391568,0.000019520548,0.001082934,0.000001079018,0.0006029268,0.73930687,0.0005010961,0.01564433,0.00277178,0.00016191676],"about_ca_topic_score_codex":0.0013326773,"about_ca_topic_score_gemma":0.014989953,"teacher_disagreement_score":0.35743555,"about_ca_system_score_codex":0.0017428473,"about_ca_system_score_gemma":0.0015896104,"threshold_uncertainty_score":0.99877},"labels":[],"label_agreement":null},{"id":"W4403289536","doi":"10.1139/as-2023-0078","title":"Conducting research “in a good way”: relationships as the foundation of research","year":2024,"lang":"en","type":"article","venue":"Arctic Science","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Division of Arctic Sciences; Office of Polar Programs; Andrew W. Mellon Foundation; Doris Duke Charitable Foundation","keywords":"Foundation (evidence); Psychology; Political science; Law","score_opus":0.8928374838922593,"score_gpt":0.6929234119872743,"score_spread":0.199914071904985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403289536","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8637391,0.00022298264,0.0002488309,0.020786943,0.0006616572,0.00042211328,6.3142573e-7,0.000019300634,0.11389845],"genre_scores_gemma":[0.9968434,0.000031132997,0.00042126304,0.00003670395,0.000056259454,0.00003576425,4.4948328e-7,0.0000038813128,0.0025711402],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9892639,0.0017304335,0.00056756596,0.0005551689,0.007422618,0.0004603341],"domain_scores_gemma":[0.9812627,0.015815904,0.00006763698,0.00071791426,0.002056411,0.00007943719],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.17538343,0.00005465241,0.000091299036,0.0012726261,0.0011558678,0.0009171879,0.0012709764,0.000033615797,0.00058683386],"category_scores_gemma":[0.026546087,0.00003215865,0.000031578824,0.011827791,0.001968325,0.0013256208,0.00030194048,0.00082871533,0.0013672384],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013925908,0.000056126726,0.03199024,0.000027210759,0.0000036045485,0.0000054825678,0.017282058,0.00061829656,0.0049710353,0.8738343,0.00052477134,0.070672914],"study_design_scores_gemma":[0.00022321058,0.00023766849,0.10283393,0.00035158946,0.000003658551,0.000036694266,0.04712884,0.15001379,0.004003688,0.67077833,0.024258161,0.00013041108],"about_ca_topic_score_codex":0.00065623503,"about_ca_topic_score_gemma":0.000226092,"teacher_disagreement_score":0.20305598,"about_ca_system_score_codex":0.0002616904,"about_ca_system_score_gemma":0.0017465255,"threshold_uncertainty_score":0.99941033},"labels":[],"label_agreement":null},{"id":"W4403340319","doi":"10.1017/s0008423924000234","title":"Replicating “Language Matters”: Taking Baselines into Account","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Political Science","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université Laval; Western University; Université de Montréal","funders":"","keywords":"Computer science; Law and economics; Economics","score_opus":0.12314938954835856,"score_gpt":0.5038126145455223,"score_spread":0.3806632249971637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403340319","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9020489,0.00065440027,0.008837473,0.074837886,0.0028024472,0.00009629106,0.000012188556,0.000018043978,0.010692365],"genre_scores_gemma":[0.9922906,0.0000010620892,0.002057499,0.0049273404,0.000416954,0.0000010348695,2.3516301e-7,0.0000050814483,0.00030017426],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9967662,0.00007331026,0.00066845096,0.00026975872,0.0015696541,0.0006526027],"domain_scores_gemma":[0.9967289,0.0006874234,0.00017037225,0.00030977768,0.00067214476,0.0014313764],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010947875,0.00008517324,0.00014864601,0.0008439442,0.00034273238,0.001401621,0.0010802657,0.000025038953,0.0024101373],"category_scores_gemma":[0.008191736,0.000056570138,0.00008707975,0.0014865776,0.0005383299,0.0010674611,0.000039900606,0.00023693059,0.0002982775],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003359081,0.000010527886,0.015233236,0.000022145447,0.000009659202,0.00029891307,0.0053545334,0.0001525401,0.006876952,0.8129202,0.016247315,0.14287059],"study_design_scores_gemma":[0.000528625,0.00044272016,0.46153566,0.0011805912,0.000074049625,0.0020661042,0.035988253,0.15801881,0.010154162,0.14635548,0.18264966,0.0010058985],"about_ca_topic_score_codex":0.011842748,"about_ca_topic_score_gemma":0.012513657,"teacher_disagreement_score":0.66656476,"about_ca_system_score_codex":0.0005822051,"about_ca_system_score_gemma":0.006823979,"threshold_uncertainty_score":0.99963504},"labels":[],"label_agreement":null},{"id":"W4403423835","doi":"10.1007/978-3-031-67604-8_1","title":"Evaluation and Decision in Times of Crisis","year":2024,"lang":"en","type":"book-chapter","venue":"Contributions to economics","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec en Outaouais","funders":"","keywords":"Psychology; Business","score_opus":0.1071133609451431,"score_gpt":0.45706817440130704,"score_spread":0.34995481345616397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403423835","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019048402,0.0040807715,0.002714614,0.0076030833,0.0016953738,0.0019274905,0.0020477276,0.000033839216,0.9608487],"genre_scores_gemma":[0.8146999,0.002125053,0.0019707603,0.0006893467,0.00030793695,0.0001363201,0.00020011734,0.000060813265,0.1798098],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975598,0.00003518911,0.001127685,0.00050561543,0.0006296166,0.00014213084],"domain_scores_gemma":[0.9971184,0.0007772123,0.000289881,0.00051007,0.0012032072,0.00010123095],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.007844349,0.00017873645,0.0004685835,0.00095815584,0.0000572332,0.00016726575,0.0002719233,0.00021253571,0.0052892338],"category_scores_gemma":[0.001082447,0.00016008496,0.000115175,0.00012400067,0.00004924346,0.00019884252,0.00018208263,0.00017651611,0.0013561725],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026119384,0.000013286033,0.00010076166,0.000005119179,0.000042305015,6.117863e-7,0.00016238204,0.0036027078,0.0000028474133,0.7764737,0.014480484,0.20508969],"study_design_scores_gemma":[0.000315176,0.000050377595,0.000388968,0.000077357334,0.00007667678,0.000001886622,0.00006718971,0.031428024,0.000020773648,0.73933387,0.22809893,0.00014075462],"about_ca_topic_score_codex":0.000012140927,"about_ca_topic_score_gemma":0.00044911448,"teacher_disagreement_score":0.79565144,"about_ca_system_score_codex":0.00051384006,"about_ca_system_score_gemma":0.000626565,"threshold_uncertainty_score":0.99942136},"labels":[],"label_agreement":null},{"id":"W4403423938","doi":"10.1007/978-3-031-67604-8","title":"Public Policy Evaluation and Analysis","year":2024,"lang":"en","type":"book","venue":"Contributions to economics","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Universidade Federal de Viçosa; Employment and Social Development Canada; Universidade Federal do Rio Grande do Norte; Université Laval","keywords":"Political science; Computer science","score_opus":0.20624305178601193,"score_gpt":0.4955287573432082,"score_spread":0.2892857055571963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403423938","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031996728,0.0021582255,0.010130406,0.0633374,0.0013305306,0.0016833968,0.005621541,0.000111005895,0.91242784],"genre_scores_gemma":[0.08184823,0.00053980487,0.00021798248,0.0019356398,0.0010738132,0.00023406479,0.0018159625,0.000033385782,0.9123011],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99700767,0.00016632934,0.0010192157,0.0007944801,0.0007072524,0.00030503358],"domain_scores_gemma":[0.99584675,0.00067263644,0.00034440236,0.000887448,0.0019246333,0.00032410817],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008550884,0.0002513963,0.0006249568,0.00333264,0.00025412193,0.0014965818,0.0004933731,0.00026993628,0.0035952951],"category_scores_gemma":[0.0038403906,0.00022531391,0.0003186754,0.0013288751,0.000084415115,0.00037329196,0.00028506515,0.00025814527,0.006104103],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000071372538,0.00002026579,0.0005530003,0.0000059625263,0.0009309482,5.8766176e-7,0.00016330439,0.0030041873,9.829034e-7,0.66311496,0.17407955,0.1581191],"study_design_scores_gemma":[0.00016709183,0.000025573325,0.0014990332,0.000007707565,0.0006555354,0.0000017950537,0.000018453378,0.07267451,0.0000013838934,0.22682938,0.6979228,0.0001967169],"about_ca_topic_score_codex":0.00001323004,"about_ca_topic_score_gemma":0.0004811877,"teacher_disagreement_score":0.5238433,"about_ca_system_score_codex":0.002298308,"about_ca_system_score_gemma":0.0068468447,"threshold_uncertainty_score":0.99954},"labels":[],"label_agreement":null},{"id":"W4403691997","doi":"10.4324/9781003388227-9","title":"The Long and Winding Road to Meaningful Public Participation in Impact Assessment","year":2024,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Fundação de Amparo à Pesquisa do Estado de Minas Gerais; Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"Environmental science; Environmental planning; Business","score_opus":0.288502917140246,"score_gpt":0.5567152622253309,"score_spread":0.26821234508508485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403691997","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024411196,0.00027260292,0.0008761826,0.0085627325,0.00061320636,0.0005822291,0.0000066791013,0.000040763905,0.9646344],"genre_scores_gemma":[0.6319376,0.000079454236,0.000108030756,0.00021339906,0.000078998164,0.000030494659,0.0000068676686,0.000016152399,0.36752898],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9963587,0.0000705824,0.0008308443,0.00050996756,0.0019341011,0.0002958137],"domain_scores_gemma":[0.99817085,0.00073006604,0.00020321921,0.00047095778,0.00024554005,0.00017934687],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0073493565,0.00022929834,0.00028678292,0.0005785418,0.00020932779,0.001796234,0.00037138592,0.00011983862,0.0034553173],"category_scores_gemma":[0.00033225727,0.00012059501,0.00010156838,0.0002385388,0.000048259233,0.00040113335,0.00024776944,0.00033445755,0.00088438235],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014856402,0.000018006427,0.022421,0.000008845959,0.00007285784,0.000010099675,0.0011576521,0.00041549717,0.000009343587,0.5250781,0.0071891355,0.44360456],"study_design_scores_gemma":[0.00046234718,0.00042889194,0.39521173,0.00029243165,0.00006431669,0.0000110950305,0.00095495454,0.057717305,0.00001215276,0.21939927,0.32470685,0.00073865213],"about_ca_topic_score_codex":0.000034237084,"about_ca_topic_score_gemma":0.002403126,"teacher_disagreement_score":0.6075264,"about_ca_system_score_codex":0.00033310143,"about_ca_system_score_gemma":0.0003809771,"threshold_uncertainty_score":0.99989355},"labels":[],"label_agreement":null},{"id":"W4403692227","doi":"10.1177/10982140241287936","title":"Streamlining Complex Intervention Evaluation Through Participatory Systems Mapping and Contribution Analysis: A Comprehensive Framework for Actionable Complexity Evaluation","year":2024,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École Nationale d'Administration Publique","funders":"","keywords":"Participatory evaluation; Intervention (counseling); Citizen journalism; Computer science; Management science; Evaluation methods; Program evaluation; Process management; Risk analysis (engineering); Engineering; Sociology; Business; Political science; Psychology; Public administration; Reliability engineering; Social science","score_opus":0.5525892727434512,"score_gpt":0.5892092362444481,"score_spread":0.036619963500996944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403692227","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5252204,0.0022279348,0.46916083,0.0009638118,0.0010321555,0.0012569363,0.000031125925,0.000021597109,0.00008522534],"genre_scores_gemma":[0.98815924,0.00007054201,0.010712041,0.00012984178,0.00039199376,0.00028109137,0.00022754313,0.000016250282,0.000011478663],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.987675,0.0037417067,0.0021299892,0.0005419746,0.0056056078,0.0003057007],"domain_scores_gemma":[0.9825975,0.003146724,0.0023491066,0.0003612688,0.011415599,0.00012985153],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04410046,0.00024276678,0.00076903345,0.0010585159,0.0003693887,0.00076493726,0.00022009882,0.00009306822,0.0008826406],"category_scores_gemma":[0.0057014143,0.00020110687,0.00041470834,0.0024398416,0.00025375743,0.0016452558,0.000045239103,0.00029316783,0.000021396983],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045175847,0.000253033,0.010289513,0.00009045735,0.002610592,0.0000015599466,0.006749615,0.30554366,0.001062126,0.022520877,0.001399612,0.6490272],"study_design_scores_gemma":[0.0012560256,0.00057254,0.06698834,0.00026774203,0.0028552958,0.000019858564,0.0135461325,0.8376714,0.000042319614,0.0748289,0.0017752161,0.00017621028],"about_ca_topic_score_codex":0.00008411087,"about_ca_topic_score_gemma":0.000047255995,"teacher_disagreement_score":0.648851,"about_ca_system_score_codex":0.0009504101,"about_ca_system_score_gemma":0.00088062085,"threshold_uncertainty_score":0.9842997},"labels":[],"label_agreement":null},{"id":"W4403764005","doi":"10.24908/pceea.2023.17146","title":"Working with Others – An Analysis of Collaborative Research Likelihood","year":2024,"lang":"en","type":"article","venue":"Proceedings of the Canadian Engineering Education Association (CEEA)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa; Concordia University","funders":"","keywords":"Psychology","score_opus":0.0873151367951162,"score_gpt":0.4226850961927657,"score_spread":0.33536995939764946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403764005","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97525734,0.00019436171,0.000065077984,0.007471248,0.0010124136,0.00042270176,0.000032903354,0.000042116364,0.015501826],"genre_scores_gemma":[0.9965293,0.000008556386,0.0007200981,0.00007727274,0.00008062778,0.000039120303,0.00000646694,0.000014716951,0.002523849],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99723446,0.000041795458,0.0004099696,0.0002678588,0.0017897529,0.0002561382],"domain_scores_gemma":[0.9957819,0.0003863539,0.0003018104,0.00017069154,0.0031817344,0.00017753016],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0061144033,0.00009703403,0.00021036126,0.0019497023,0.00017348479,0.0004304427,0.00048911717,0.000089762325,0.0001969239],"category_scores_gemma":[0.0019302255,0.00007086773,0.000082580125,0.008684745,0.000035530444,0.0004609219,0.00002098478,0.00022713617,0.000010872048],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014327319,0.000118900156,0.85416275,0.00009144839,0.0011654659,1.3915528e-7,0.025817117,0.020355266,0.0023642066,0.056795347,0.02560999,0.013505018],"study_design_scores_gemma":[0.00020452851,0.00013056387,0.6973352,0.00038192756,0.0004748586,9.2705267e-7,0.019944657,0.17632584,0.002769668,0.0018489377,0.10023923,0.0003436832],"about_ca_topic_score_codex":0.0037779554,"about_ca_topic_score_gemma":0.04768143,"teacher_disagreement_score":0.1568276,"about_ca_system_score_codex":0.0016299363,"about_ca_system_score_gemma":0.002977615,"threshold_uncertainty_score":0.9696959},"labels":[],"label_agreement":null},{"id":"W4403785657","doi":"10.1080/28338073.2024.2421131","title":"Evolving Maintenance of Certification in Canada: A Collaborative Journey","year":2024,"lang":"en","type":"article","venue":"Journal of CME","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa; Royal College of Physicians and Surgeons of Canada","funders":"","keywords":"Certification; Maintenance of Certification; Business; Process management; Engineering management; Engineering; Management; Economics","score_opus":0.15522537616634066,"score_gpt":0.4609264752324451,"score_spread":0.30570109906610443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403785657","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9697543,0.0025184697,0.003927124,0.015014434,0.0015896125,0.00011616917,0.0000120221075,0.0000027333458,0.0070651397],"genre_scores_gemma":[0.99852467,0.000112338035,0.0006964093,0.00010192654,0.00005872172,9.583474e-7,2.034622e-7,0.0000029039822,0.00050185574],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99746543,0.00013316699,0.0009298349,0.00008414516,0.0012955413,0.00009189307],"domain_scores_gemma":[0.99764127,0.0005062012,0.00047926087,0.00011336621,0.0012069765,0.0000529358],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037965584,0.00004936335,0.00019117708,0.00030169875,0.000021369355,0.00008934527,0.00024496013,0.00001826904,0.0006727466],"category_scores_gemma":[0.0009358472,0.000031340212,0.000043834112,0.0010020313,0.000019127994,0.0005188037,0.0000142839735,0.00015958952,0.000012556482],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032068326,0.00017848816,0.24440937,0.0001007312,0.00015691883,0.00028088526,0.017454002,0.025617152,0.018220631,0.016867744,0.442285,0.2341084],"study_design_scores_gemma":[0.00079804513,0.00023501416,0.71264136,0.0008361404,0.000025075344,0.00009770587,0.01689954,0.09745081,0.0042895745,0.013939825,0.15260756,0.00017935676],"about_ca_topic_score_codex":0.0118089095,"about_ca_topic_score_gemma":0.25761285,"teacher_disagreement_score":0.46823198,"about_ca_system_score_codex":0.0004790259,"about_ca_system_score_gemma":0.005943151,"threshold_uncertainty_score":0.9996922},"labels":[],"label_agreement":null},{"id":"W4403873460","doi":"10.4324/9781003457077-11","title":"Lessons from realist evaluations in Canada","year":2024,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Political science","score_opus":0.37615300039476307,"score_gpt":0.5234789253540757,"score_spread":0.14732592495931263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403873460","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001136334,0.0003711025,0.00011551794,0.014706671,0.001206508,0.0002171093,0.00054861174,0.000020681893,0.98270017],"genre_scores_gemma":[0.02964136,0.0001292116,0.00022808464,0.0011774555,0.00014962826,0.00001900356,0.00021998459,0.000022679,0.9684126],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9950586,0.000043186206,0.0009293593,0.0006146622,0.003182518,0.00017170796],"domain_scores_gemma":[0.99764585,0.0009849519,0.0001954073,0.0007608249,0.00030630804,0.00010662833],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0018544187,0.00021944493,0.00036623093,0.00035449534,0.00006694067,0.00022544607,0.00056896935,0.00012731575,0.084180735],"category_scores_gemma":[0.00019347531,0.00016036243,0.00009571144,0.0001502267,0.00003348964,0.00012668526,0.0001330367,0.0003763548,0.004054374],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000036598663,0.0000046488494,0.0003566238,0.0000029531086,0.0000289873,0.000021113265,0.00012978628,0.0004764371,0.0000021818214,0.68342674,0.26671377,0.048833117],"study_design_scores_gemma":[0.00008614453,0.000005965133,0.0021444336,0.000061600585,0.000022352033,6.740075e-7,0.00019141419,0.0068752985,0.0000030861122,0.41078806,0.57966036,0.0001606108],"about_ca_topic_score_codex":0.8938958,"about_ca_topic_score_gemma":0.9990106,"teacher_disagreement_score":0.3129466,"about_ca_system_score_codex":0.0010891698,"about_ca_system_score_gemma":0.0083773695,"threshold_uncertainty_score":0.99724424},"labels":[],"label_agreement":null},{"id":"W4404017730","doi":"10.33137/tijih.v1i4.41128","title":"Indigenous evaluation","year":2024,"lang":"en","type":"article","venue":"Turtle Island Journal of Indigenous Health","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"First Nations University of Canada; University of Saskatchewan","funders":"Saskatchewan Health Research Foundation","keywords":"Indigenous; Geography; Biology; Ecology","score_opus":0.15480458022876326,"score_gpt":0.5225409671835659,"score_spread":0.36773638695480265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404017730","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95899713,0.021363055,0.0062717022,0.0032912449,0.0034587125,0.00062794413,0.000029121138,0.000031538333,0.005929544],"genre_scores_gemma":[0.99581265,0.0011210134,0.0004921298,0.0007942445,0.00070631906,0.000004912844,0.000007921922,0.000015953086,0.0010448609],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99369586,0.0005931685,0.0014963038,0.00023421449,0.0035854613,0.0003949738],"domain_scores_gemma":[0.99717015,0.0005263451,0.00069673697,0.0003016124,0.0010696253,0.00023555227],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.023706125,0.00014527535,0.00040247932,0.00081175327,0.00038087787,0.0004495927,0.0004940833,0.00007537229,0.0021705457],"category_scores_gemma":[0.00036210968,0.00009121076,0.0001758133,0.0008460498,0.000034529246,0.0005576263,0.000026146834,0.00041495587,0.0005541349],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048673406,0.00011853486,0.007150247,0.0000459106,0.0000723789,0.00003946731,0.07295808,0.001581137,0.000045989764,0.00020454837,0.019021062,0.89871395],"study_design_scores_gemma":[0.0033492167,0.0060662013,0.10895178,0.0007881472,0.00018363133,0.002907636,0.011309586,0.01970626,0.0005069579,0.06869341,0.7767305,0.0008066774],"about_ca_topic_score_codex":0.00011150144,"about_ca_topic_score_gemma":0.00062057865,"teacher_disagreement_score":0.8979073,"about_ca_system_score_codex":0.00050144247,"about_ca_system_score_gemma":0.007969432,"threshold_uncertainty_score":0.9987416},"labels":[],"label_agreement":null},{"id":"W4404134255","doi":"10.4018/979-8-3693-1164-6.ch006","title":"A Culturally Responsive Framework for Critically Examining Priorities in Approximations of Practice","year":2024,"lang":"en","type":"book-chapter","venue":"Advances in educational marketing, administration, and leadership book series","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Critically ill; Computer science; Sociology; Psychology; Medicine; Intensive care medicine","score_opus":0.18331060232667812,"score_gpt":0.46688502052211805,"score_spread":0.28357441819543994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404134255","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007188891,0.06988026,0.0022726173,0.09863477,0.001979548,0.0024710563,0.0002940755,0.000060206978,0.82368857],"genre_scores_gemma":[0.052060653,0.011903946,0.10015508,0.0024373143,0.00088807975,0.0006785906,0.00026339287,0.00008037025,0.8315326],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9962588,0.00024782727,0.0014922041,0.00067951204,0.0010556394,0.00026604414],"domain_scores_gemma":[0.9774155,0.020004362,0.0006900516,0.00031255992,0.0014935858,0.00008393736],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004850056,0.0003231151,0.00047506177,0.0005495618,0.00016557986,0.00029487236,0.00030385194,0.00027190652,0.0007398677],"category_scores_gemma":[0.027025728,0.00029885885,0.00008578518,0.00020827648,0.0005715146,0.0027110102,0.00004068893,0.00047123112,0.000014795354],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006331365,0.000052286305,0.00060841907,0.00050948147,0.00002050476,0.0000022685174,0.0059179906,0.000032223794,0.0000038229064,0.9893846,0.0006773069,0.0021579617],"study_design_scores_gemma":[0.00018440506,0.00026183683,0.0031907926,0.0015583095,0.00004101322,0.000031056534,0.033494413,0.00006008152,0.000011890692,0.5277612,0.43309128,0.0003136837],"about_ca_topic_score_codex":0.0000020094024,"about_ca_topic_score_gemma":0.00038957683,"teacher_disagreement_score":0.46162337,"about_ca_system_score_codex":0.0001251014,"about_ca_system_score_gemma":0.002042762,"threshold_uncertainty_score":0.99994636},"labels":[],"label_agreement":null},{"id":"W4404181489","doi":"10.32920/27637761.v1","title":"Increasing literacy in quantitative methods: The key to the future of Canadian psychology.","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada; National Institutes of Health","keywords":"Key (lock); Literacy; Psychology; Political science; Computer science; Pedagogy","score_opus":0.323933385730249,"score_gpt":0.624293240674635,"score_spread":0.300359854944386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404181489","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27647594,0.005185461,0.0067443117,0.46530733,0.0076671415,0.0017792343,0.00013624477,0.000030339706,0.23667401],"genre_scores_gemma":[0.76476234,0.0005253436,0.2089974,0.02062141,0.00045719687,0.00018857849,0.000016596416,0.000025261694,0.0044058994],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9948666,0.0025633993,0.0008744795,0.00054428494,0.00091358385,0.00023763953],"domain_scores_gemma":[0.9951114,0.0028820843,0.00022197796,0.0011554823,0.0005145387,0.00011448847],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02631594,0.00017735483,0.00032837948,0.0015364994,0.00011489974,0.00043024207,0.001576431,0.0001624299,0.0017179772],"category_scores_gemma":[0.0016625475,0.000075117576,0.00013403564,0.0025166285,0.000077414166,0.00008813928,0.0006359285,0.0008879908,0.00049778406],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000853597,0.000038211532,0.007818887,0.00003312964,0.00008984171,0.00000706994,0.10269894,0.004241813,0.00008994726,0.10977811,0.09520697,0.67991173],"study_design_scores_gemma":[0.00009307688,0.000047739177,0.07246332,0.00013742626,0.000020292231,0.0000070369556,0.012208774,0.0140633695,0.000033705215,0.14320865,0.7575446,0.00017200646],"about_ca_topic_score_codex":0.08519976,"about_ca_topic_score_gemma":0.54612863,"teacher_disagreement_score":0.6797397,"about_ca_system_score_codex":0.00009527074,"about_ca_system_score_gemma":0.0010986961,"threshold_uncertainty_score":0.99919456},"labels":[],"label_agreement":null},{"id":"W4404182370","doi":"10.32920/27637761","title":"Increasing literacy in quantitative methods: The key to the future of Canadian psychology.","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Key (lock); Literacy; Psychology; Management science; Sociology; Computer science; Pedagogy; Economics","score_opus":0.323933385730249,"score_gpt":0.624293240674635,"score_spread":0.300359854944386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404182370","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27647594,0.005185461,0.0067443117,0.46530733,0.0076671415,0.0017792343,0.00013624477,0.000030339706,0.23667401],"genre_scores_gemma":[0.76476234,0.0005253436,0.2089974,0.02062141,0.00045719687,0.00018857849,0.000016596416,0.000025261694,0.0044058994],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9948666,0.0025633993,0.0008744795,0.00054428494,0.00091358385,0.00023763953],"domain_scores_gemma":[0.9951114,0.0028820843,0.00022197796,0.0011554823,0.0005145387,0.00011448847],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02631594,0.00017735483,0.00032837948,0.0015364994,0.00011489974,0.00043024207,0.001576431,0.0001624299,0.0017179772],"category_scores_gemma":[0.0016625475,0.000075117576,0.00013403564,0.0025166285,0.000077414166,0.00008813928,0.0006359285,0.0008879908,0.00049778406],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000853597,0.000038211532,0.007818887,0.00003312964,0.00008984171,0.00000706994,0.10269894,0.004241813,0.00008994726,0.10977811,0.09520697,0.67991173],"study_design_scores_gemma":[0.00009307688,0.000047739177,0.07246332,0.00013742626,0.000020292231,0.0000070369556,0.012208774,0.0140633695,0.000033705215,0.14320865,0.7575446,0.00017200646],"about_ca_topic_score_codex":0.08519976,"about_ca_topic_score_gemma":0.54612863,"teacher_disagreement_score":0.6797397,"about_ca_system_score_codex":0.00009527074,"about_ca_system_score_gemma":0.0010986961,"threshold_uncertainty_score":0.99919456},"labels":[],"label_agreement":null},{"id":"W4404232315","doi":"10.1177/15586898241298996","title":"Media Review: The Handbook of Teaching Qualitative and Mixed Research Methods: A Step-by-Step Guide for Instructors RuthAWutichABernardH. R. (2023). The Handbook of Teaching Qualitative and Mixed Research Methods: A Step-by-Step Guide for Instructors. Milton Park, Abingdon, Oxfordshire: Routledge, 372 p. ISBN: 9781032100272, $55.99.","year":2024,"lang":"en","type":"article","venue":"Journal of Mixed Methods Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Multimethodology; Qualitative research; Mathematics education; Sociology; Computer science; Management science; Psychology; Engineering; Social science","score_opus":0.4377993658594084,"score_gpt":0.6786566395829021,"score_spread":0.24085727372349375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404232315","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009927864,0.21300976,0.7585554,0.009957776,0.0015484206,0.005274588,0.0004807678,0.000028738305,0.0012166767],"genre_scores_gemma":[0.001018417,0.03382769,0.9576137,0.00020039533,0.0005574776,0.0008083813,0.000032838914,0.00017185575,0.0057692653],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.69973457,0.26887757,0.00986199,0.0026502213,0.015672728,0.0032029408],"domain_scores_gemma":[0.6467906,0.3332117,0.002745376,0.0021305827,0.01415584,0.00096588663],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","research_integrity"],"consensus_categories":["metaresearch","sts"],"category_scores_codex":[0.6620842,0.00091310026,0.0032108848,0.0032695641,0.0029795803,0.0013294155,0.004196308,0.000629928,0.0002077392],"category_scores_gemma":[0.2862576,0.000532602,0.0010287429,0.0038990644,0.004233962,0.0015757137,0.0019283233,0.0069231326,0.000010216757],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009798424,0.00016243084,0.000044030585,0.0014435556,0.0007045791,0.00000459771,0.037948813,0.0000043969585,0.0305051,0.0033733824,0.4878954,0.43693388],"study_design_scores_gemma":[0.0030607206,0.0020938613,0.0001045444,0.006951857,0.00029714074,0.00007387549,0.20537949,0.00690166,0.02967631,0.022613259,0.7222937,0.00055363204],"about_ca_topic_score_codex":0.0011222946,"about_ca_topic_score_gemma":0.00050918484,"teacher_disagreement_score":0.43638024,"about_ca_system_score_codex":0.0009900403,"about_ca_system_score_gemma":0.0034910238,"threshold_uncertainty_score":0.9997125},"labels":[],"label_agreement":null},{"id":"W4404308159","doi":"10.7202/1114565ar","title":"Le travail collectif des enseignants pour l’évaluation des apprentissages comme norme professionnelle ? Une revue de la littérature pour interroger cette tendance émergente","year":2024,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Political science; Sociology","score_opus":0.19776485315484063,"score_gpt":0.4586518624624211,"score_spread":0.26088700930758046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404308159","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6944709,0.020939507,0.154021,0.09611829,0.007636708,0.0019871038,0.00013215555,0.00030138623,0.02439294],"genre_scores_gemma":[0.7707938,0.00401698,0.009876286,0.00046309098,0.00069546176,0.00031670093,0.00028071535,0.000082940394,0.21347405],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9802192,0.014445031,0.0015303139,0.0011290997,0.0019633507,0.00071300095],"domain_scores_gemma":[0.9936442,0.003173788,0.0005891863,0.0007251898,0.0016302357,0.00023742106],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.04493611,0.0005444235,0.00054463884,0.00089129334,0.0012606112,0.001518054,0.0006246205,0.00059336727,0.0047802827],"category_scores_gemma":[0.004242693,0.00052693236,0.0003190448,0.0035570092,0.0005039057,0.0020456663,0.00012842784,0.000969513,0.0014923338],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009800616,0.0009198648,0.007017236,0.00063042203,0.00019338414,0.0000097599,0.32668805,0.007713272,0.012672463,0.0034014403,0.111545876,0.52911025],"study_design_scores_gemma":[0.001976226,0.00027159904,0.4629434,0.004473571,0.00048746946,0.00022877075,0.044919,0.31112608,0.0053939004,0.07069547,0.09644789,0.0010366079],"about_ca_topic_score_codex":0.00066960166,"about_ca_topic_score_gemma":0.0045288587,"teacher_disagreement_score":0.5280736,"about_ca_system_score_codex":0.0012864355,"about_ca_system_score_gemma":0.010814432,"threshold_uncertainty_score":0.99971825},"labels":[],"label_agreement":null},{"id":"W4404308176","doi":"10.7202/1114566ar","title":"Entre jeux de pouvoir et intérêts : retour à la raison d’être de l’évaluation","year":2024,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; Cégep de Sorel-Tracy","funders":"","keywords":"Humanities; Philosophy; Political science","score_opus":0.17573907761614516,"score_gpt":0.5276697148517477,"score_spread":0.3519306372356026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404308176","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46499944,0.005715367,0.14270583,0.30208513,0.010412574,0.0016474109,0.00010195187,0.00040146755,0.071930856],"genre_scores_gemma":[0.9359704,0.0022942428,0.008885653,0.002399699,0.00091095455,0.00021881948,0.0005163107,0.00007924934,0.048724625],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97056806,0.022292197,0.0015590631,0.0011590878,0.0036718978,0.00074970955],"domain_scores_gemma":[0.9910779,0.006071946,0.00050561986,0.0008028301,0.0012680878,0.00027361212],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.121226475,0.00049578183,0.00044345736,0.0008891704,0.00034179736,0.0016769782,0.0005843656,0.00063239515,0.011878724],"category_scores_gemma":[0.008616622,0.00048310388,0.00030428488,0.0018837963,0.00013192781,0.0025528825,0.00011218309,0.0009422169,0.0033260079],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055016386,0.00040909727,0.010132942,0.00021905986,0.00012620918,0.000011188117,0.293571,0.023123102,0.0022266845,0.0344496,0.15078992,0.48488617],"study_design_scores_gemma":[0.0008355941,0.0001838231,0.2353356,0.0007945042,0.00034567257,0.00010775935,0.011017816,0.42791083,0.0010311236,0.054519873,0.26733533,0.0005820936],"about_ca_topic_score_codex":0.00024977428,"about_ca_topic_score_gemma":0.0009262426,"teacher_disagreement_score":0.4843041,"about_ca_system_score_codex":0.002150111,"about_ca_system_score_gemma":0.014940091,"threshold_uncertainty_score":0.99976206},"labels":[],"label_agreement":null},{"id":"W4404690134","doi":"10.4102/aej.v12i1.758","title":"A rocky road to evidence: Evaluating literacy programmes using a trust-based approach in a context of fragility","year":2024,"lang":"en","type":"article","venue":"African Evaluation Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Context (archaeology); Computer science; Data collection; Fragility; Quality (philosophy); Baseline (sea); Data science; Knowledge management; Political science","score_opus":0.4099295910482118,"score_gpt":0.576455307169125,"score_spread":0.16652571612091316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404690134","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94577813,0.0017824395,0.047832098,0.002287688,0.00046177924,0.0011756697,0.00000809087,0.000026270562,0.0006478071],"genre_scores_gemma":[0.9773336,0.00000702179,0.021955607,0.00028500188,0.00019502535,0.00012418823,0.0000044662634,0.000016237924,0.00007881736],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98805773,0.002588638,0.0020327722,0.0006215371,0.0062921387,0.000407204],"domain_scores_gemma":[0.99397343,0.0014909434,0.00062815635,0.0004991202,0.003156674,0.00025164455],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.057091985,0.00022610465,0.00046891617,0.0014538119,0.00021788398,0.0010111394,0.0006221046,0.00008510676,0.0015431201],"category_scores_gemma":[0.010734718,0.00016834024,0.00023571894,0.0036277664,0.00008132522,0.0014588863,0.00007911719,0.00046718522,0.00006195584],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016630274,0.00013489011,0.027537499,0.000035496,0.000026172398,0.0000033724796,0.01808261,0.08217331,0.00086680683,0.00007948736,0.00021146468,0.8706826],"study_design_scores_gemma":[0.0007729633,0.0004101442,0.03448946,0.0005218298,0.000074046315,0.000033539727,0.009231961,0.9509021,0.00018136555,0.002444317,0.0007553648,0.00018290734],"about_ca_topic_score_codex":0.00006312559,"about_ca_topic_score_gemma":0.000039005172,"teacher_disagreement_score":0.8704997,"about_ca_system_score_codex":0.0006843295,"about_ca_system_score_gemma":0.0040109796,"threshold_uncertainty_score":0.9993696},"labels":[],"label_agreement":null},{"id":"W4404694781","doi":"10.1080/1389224x.2024.2429498","title":"Embracing pluralism: assessing the perceptions of different stakeholders on the effectiveness of advisory methods in Ontario","year":2024,"lang":"en","type":"article","venue":"The Journal of Agricultural Education and Extension","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Guelph","funders":"Ontario Ministry of Agriculture, Food and Rural Affairs","keywords":"Perception; Advisory committee; Pluralism (philosophy); Public relations; Business; Political science; Public administration; Psychology","score_opus":0.20543812021525926,"score_gpt":0.49094931791974433,"score_spread":0.2855111977044851,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404694781","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9932841,0.00034335337,0.00024343684,0.0043835524,0.0008236641,0.00017513814,4.4532322e-7,0.0000021278997,0.000744204],"genre_scores_gemma":[0.9992766,0.000089917005,0.00018568728,0.0001268946,0.000051506646,0.0000031269244,0.0000013916275,0.0000025186573,0.000262354],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9965993,0.0020071466,0.0005724563,0.00009609704,0.00064674404,0.00007825655],"domain_scores_gemma":[0.9940993,0.004845704,0.0003622102,0.00017135893,0.0004903479,0.00003108631],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010000821,0.00009097319,0.00020002924,0.00013568261,0.00017018603,0.00012568118,0.00022969951,0.000030423294,0.00015736507],"category_scores_gemma":[0.00056518853,0.000026286674,0.00009897875,0.00038581277,0.000090325455,0.00033902482,0.0000342555,0.00034441712,0.0000032404587],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003964553,0.0007126407,0.025338173,0.0001192368,0.00013339664,7.8790936e-7,0.086088024,0.011111922,0.6939488,0.012348519,0.0066311955,0.16317087],"study_design_scores_gemma":[0.00009463981,0.00009206288,0.94319487,0.0005199616,0.00004015643,0.000036292062,0.04971785,0.0004343819,0.0023717429,0.0033035036,0.00015427511,0.000040247945],"about_ca_topic_score_codex":0.00061242224,"about_ca_topic_score_gemma":0.0007067433,"teacher_disagreement_score":0.9178567,"about_ca_system_score_codex":0.000109081666,"about_ca_system_score_gemma":0.00027710377,"threshold_uncertainty_score":0.3466105},"labels":[],"label_agreement":null},{"id":"W4404840672","doi":"10.32920/27931788.v1","title":"Program evaluation: An educator's portal into academic scholarship","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact; Royal College of Physicians and Surgeons of Canada; University of Ottawa; McMaster University","funders":"","keywords":"Scholarship; Sociology; Political science; Psychology; Mathematics education","score_opus":0.5059844233206742,"score_gpt":0.6504454096660965,"score_spread":0.14446098634542237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404840672","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84627795,0.002084039,0.00013809517,0.010264351,0.009121339,0.0038125457,0.00001715641,0.000557576,0.12772696],"genre_scores_gemma":[0.97768074,0.00007601316,0.008070898,0.0009389974,0.0013782063,0.001932181,0.00023644367,0.00004113382,0.0096453605],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98783654,0.00088257407,0.0015939974,0.001646379,0.0076464186,0.0003940857],"domain_scores_gemma":[0.99511963,0.0002833558,0.00048946356,0.0018406654,0.0018532772,0.00041357943],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.029055271,0.0004236385,0.00048010724,0.0008003284,0.00020747873,0.0020383152,0.00210979,0.00071110646,0.027052661],"category_scores_gemma":[0.0017429208,0.0003022615,0.000281706,0.0009663108,0.00012377767,0.0007878918,0.0016977128,0.0028443339,0.00664378],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011592433,0.00016956773,0.011161027,0.000049051883,0.000051481064,0.0000035902792,0.0017935546,0.00079529453,0.000026948963,0.0068810172,0.024847735,0.95420915],"study_design_scores_gemma":[0.00027927937,0.00020134718,0.02811228,0.00017869225,0.0001827271,0.000016289796,0.0026585045,0.09887344,0.00020682233,0.76744443,0.10117097,0.00067520945],"about_ca_topic_score_codex":0.000045545003,"about_ca_topic_score_gemma":0.00026327305,"teacher_disagreement_score":0.95353395,"about_ca_system_score_codex":0.00029447398,"about_ca_system_score_gemma":0.0068551633,"threshold_uncertainty_score":0.99994296},"labels":[],"label_agreement":null},{"id":"W4404840745","doi":"10.32920/27931788","title":"Program evaluation: An educator's portal into academic scholarship","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact; Royal College of Physicians and Surgeons of Canada; University of Ottawa; McMaster University","funders":"","keywords":"Scholarship; Sociology; Political science","score_opus":0.5059844233206742,"score_gpt":0.6504454096660965,"score_spread":0.14446098634542237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404840745","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84627795,0.002084039,0.00013809517,0.010264351,0.009121339,0.0038125457,0.00001715641,0.000557576,0.12772696],"genre_scores_gemma":[0.97768074,0.00007601316,0.008070898,0.0009389974,0.0013782063,0.001932181,0.00023644367,0.00004113382,0.0096453605],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98783654,0.00088257407,0.0015939974,0.001646379,0.0076464186,0.0003940857],"domain_scores_gemma":[0.99511963,0.0002833558,0.00048946356,0.0018406654,0.0018532772,0.00041357943],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.029055271,0.0004236385,0.00048010724,0.0008003284,0.00020747873,0.0020383152,0.00210979,0.00071110646,0.027052661],"category_scores_gemma":[0.0017429208,0.0003022615,0.000281706,0.0009663108,0.00012377767,0.0007878918,0.0016977128,0.0028443339,0.00664378],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011592433,0.00016956773,0.011161027,0.000049051883,0.000051481064,0.0000035902792,0.0017935546,0.00079529453,0.000026948963,0.0068810172,0.024847735,0.95420915],"study_design_scores_gemma":[0.00027927937,0.00020134718,0.02811228,0.00017869225,0.0001827271,0.000016289796,0.0026585045,0.09887344,0.00020682233,0.76744443,0.10117097,0.00067520945],"about_ca_topic_score_codex":0.000045545003,"about_ca_topic_score_gemma":0.00026327305,"teacher_disagreement_score":0.95353395,"about_ca_system_score_codex":0.00029447398,"about_ca_system_score_gemma":0.0068551633,"threshold_uncertainty_score":0.99994296},"labels":[],"label_agreement":null},{"id":"W4404981512","doi":"10.1177/16094069241306284","title":"Bridging Perspectives: Utilizing Interpretative Phenomenological Analysis (IPA) to Inform and Enhance Social Interventions","year":2024,"lang":"en","type":"article","venue":"International Journal of Qualitative Methods","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Interpretative phenomenological analysis; Bridging (networking); Psychological intervention; Psychology; Epistemology; Psychotherapist; Sociology; Computer science; Qualitative research; Social science; Philosophy","score_opus":0.80663421725288,"score_gpt":0.7665079156715062,"score_spread":0.04012630158137376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404981512","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14582644,0.0009397366,0.8404674,0.007589841,0.0006270672,0.00008560385,0.000038030354,0.000014449252,0.0044114357],"genre_scores_gemma":[0.8815717,0.000039951272,0.11699857,0.00023660848,0.0001940165,0.000009994195,0.0000023959378,0.00000671337,0.0009400165],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9938466,0.0026210719,0.0013882904,0.00033034838,0.0016482135,0.00016549217],"domain_scores_gemma":[0.9921295,0.004447644,0.0006057051,0.00010542086,0.0025910877,0.0001206152],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.025491439,0.00016094555,0.00048590082,0.0021801372,0.00014010504,0.00068880094,0.0006411817,0.00004879559,0.0019482005],"category_scores_gemma":[0.006237411,0.00011022755,0.00072155474,0.001927238,0.0001958208,0.0010199792,0.00021276511,0.00036573826,0.000042930234],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017278982,0.000081961996,0.0004381456,0.000011075471,0.0030206745,0.000015493062,0.5148382,0.0005424753,0.0004914821,0.085809454,0.00047112134,0.39410713],"study_design_scores_gemma":[0.00047348632,0.00081328826,0.017331114,0.00031491538,0.0004320343,0.000040350635,0.85904837,0.052347504,0.0007104528,0.05933332,0.00878445,0.00037070076],"about_ca_topic_score_codex":0.000012815276,"about_ca_topic_score_gemma":0.000017473274,"teacher_disagreement_score":0.7357453,"about_ca_system_score_codex":0.00050643843,"about_ca_system_score_gemma":0.00017959678,"threshold_uncertainty_score":0.99896413},"labels":[],"label_agreement":null},{"id":"W4405013031","doi":"10.1177/15586898241305657","title":"Media Review: Philosophical Foundations of Mixed Methods Research: Dialogues between Researchers and Philosophers ShanY. (Ed.) (2024). Philosophical Foundations of Mixed Methods Research: Dialogues between Researchers and Philosophers. Routledge.","year":2024,"lang":"en","type":"article","venue":"Journal of Mixed Methods Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Multimethodology; Epistemology; Sociology; Engineering ethics; Management science; Social science; Philosophy; Engineering","score_opus":0.8334287360136173,"score_gpt":0.6923099243927741,"score_spread":0.14111881162084328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405013031","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.097126104,0.197079,0.16836643,0.49372584,0.0069662123,0.01120052,0.0015544023,0.00027451568,0.023706969],"genre_scores_gemma":[0.4075278,0.0617891,0.52322054,0.00011964297,0.0055949176,0.00028128945,0.00018536735,0.00031014587,0.0009712023],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.748224,0.20640323,0.009680429,0.0036233661,0.027805831,0.0042631235],"domain_scores_gemma":[0.7272863,0.24401906,0.0016029957,0.00305735,0.020827582,0.0032067373],"candidate_categories":["metaresearch","metaepi_narrow","bibliometrics","sts","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","sts","research_integrity"],"category_scores_codex":[0.5256828,0.001023192,0.004154665,0.011358441,0.0021470215,0.0016854418,0.0052451673,0.0013398848,0.0019153196],"category_scores_gemma":[0.29236126,0.00080178,0.0012142308,0.016277393,0.0121758,0.002775675,0.004166959,0.012466058,0.00016492872],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012266275,0.00082765066,0.003692629,0.002932441,0.0023205513,0.0001396888,0.0065483763,0.0000334879,0.02093143,0.04488431,0.037473936,0.87898886],"study_design_scores_gemma":[0.0022011537,0.0030994222,0.0147255715,0.003695826,0.00047969652,0.00007460569,0.005210377,0.0012850189,0.009045743,0.89199215,0.06735191,0.0008385221],"about_ca_topic_score_codex":0.00023958343,"about_ca_topic_score_gemma":0.00009717045,"teacher_disagreement_score":0.87815034,"about_ca_system_score_codex":0.0012802669,"about_ca_system_score_gemma":0.0066128713,"threshold_uncertainty_score":0.9999566},"labels":[],"label_agreement":null},{"id":"W4405018354","doi":"10.2139/ssrn.5043501","title":"Layered Policy Analysis in Program Evaluation Using the Marginal Treatment Effect","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Economics; Econometrics","score_opus":0.16847313246044734,"score_gpt":0.5553809299607939,"score_spread":0.38690779750034654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405018354","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97777075,0.0063790376,0.002702724,0.007883309,0.0007804395,0.0025959662,0.000012270808,0.000042695527,0.0018328325],"genre_scores_gemma":[0.99581844,0.0016040182,0.00017961231,0.00004494915,0.0008834965,0.00033668315,0.000026942911,0.000023113515,0.0010827499],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99039733,0.0024466605,0.0011680598,0.00070411223,0.0035269826,0.0017568612],"domain_scores_gemma":[0.9973948,0.0005029616,0.00071471115,0.0007920016,0.0004998721,0.00009564709],"candidate_categories":["metaresearch","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.04247339,0.00041276315,0.00070613896,0.0023984564,0.00029613095,0.0012399429,0.00094793714,0.00021382433,0.0003625108],"category_scores_gemma":[0.00062368606,0.00021135392,0.00085117726,0.0035111704,0.00006505701,0.00015251723,0.00034017407,0.0032194448,0.00010130137],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00008917401,0.00010970877,0.012984081,0.0000079827105,0.0016565035,0.000004240681,0.0006922971,0.18894018,0.000020165264,0.004119246,0.000028093105,0.79134834],"study_design_scores_gemma":[0.0008296062,0.0006860239,0.006867259,0.000052587755,0.001802999,0.00007850129,0.0010837937,0.6308821,0.000022502581,0.35604715,0.0014100021,0.00023747473],"about_ca_topic_score_codex":0.001046104,"about_ca_topic_score_gemma":0.0138661405,"teacher_disagreement_score":0.7911109,"about_ca_system_score_codex":0.0104179075,"about_ca_system_score_gemma":0.023994919,"threshold_uncertainty_score":0.99979687},"labels":[],"label_agreement":null},{"id":"W4405099173","doi":"10.22215/etd/2024-16207","title":"Performance Measurement in the Public Universities in the Province of Ontario, Canada","year":2024,"lang":"en","type":"dissertation","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Library science; Geography; Public administration; Computer science","score_opus":0.1406225270700838,"score_gpt":0.38491376224244744,"score_spread":0.24429123517236365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405099173","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75815403,0.00013029035,0.000001612198,0.002618687,0.0005117113,0.00038585125,0.0000036598956,0.0000030867402,0.23819104],"genre_scores_gemma":[0.956886,0.00001968755,0.00001135165,0.00037603336,0.000015675561,0.000028024622,0.000036533642,0.000003951759,0.042622738],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9940379,0.00026414797,0.00059865584,0.00025515966,0.0046619005,0.00018221817],"domain_scores_gemma":[0.9986562,0.0002722815,0.0002068145,0.00044247851,0.00040418492,0.000018031305],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008058059,0.00014283396,0.00020096541,0.00032032636,0.000085553955,0.00019657961,0.001285496,0.00006336734,0.0013061633],"category_scores_gemma":[0.000092080445,0.000067083616,0.000050718874,0.00082290487,0.000026093961,0.00029232557,0.000025518728,0.00039804238,0.000023612483],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030508038,0.0005592671,0.14211406,0.0007852435,0.00013831849,0.00014075798,0.30252957,0.0025819973,0.000037877566,0.056129538,0.41346818,0.08121011],"study_design_scores_gemma":[0.0002675999,0.00009553916,0.4313372,0.00019497328,0.000023414246,0.00000286977,0.30793425,0.0028752873,0.000057529032,0.0005097219,0.25648683,0.00021475855],"about_ca_topic_score_codex":0.8076891,"about_ca_topic_score_gemma":0.99984896,"teacher_disagreement_score":0.28922313,"about_ca_system_score_codex":0.0015729056,"about_ca_system_score_gemma":0.02818428,"threshold_uncertainty_score":0.9996068},"labels":[],"label_agreement":null},{"id":"W4405189958","doi":"10.1080/08982112.2024.2434019","title":"A Conversation with Christine M. Anderson-Cook","year":2024,"lang":"en","type":"article","venue":"Quality Engineering","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Conversation; Management; Engineering; Marketing; Sociology; Operations research; Advertising; Business; Economics; Communication","score_opus":0.21817104021291212,"score_gpt":0.5007267483288038,"score_spread":0.2825557081158917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405189958","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49806827,0.00041449812,0.48895025,0.00451451,0.0008126896,0.00021729255,0.000009177802,0.00039176486,0.0066215503],"genre_scores_gemma":[0.9971638,0.000006526899,0.0015571419,0.000096618656,0.00009396805,0.000010474432,0.0000062999375,0.00000770129,0.0010575063],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985049,0.000039862764,0.00028641094,0.00021496556,0.00083392666,0.00011994277],"domain_scores_gemma":[0.99917156,0.0004436053,0.000035349094,0.00020309816,0.00009349273,0.000052922063],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025863235,0.000079997386,0.00011640202,0.00014303523,0.00003317311,0.00024005224,0.0001173458,0.00002734631,0.0008768426],"category_scores_gemma":[0.00026399986,0.000054833177,0.000034269684,0.00045702638,0.000014893423,0.00033788756,0.000015532887,0.00009571659,0.00032914086],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002158225,0.00018413244,0.054345608,0.00095077715,0.00040618228,0.000096574244,0.041824006,0.30744797,0.015618826,0.23574747,0.034651622,0.308511],"study_design_scores_gemma":[0.0003581807,0.000077128505,0.038715158,0.00008681823,0.000012294303,0.000010425407,0.0012454275,0.87320966,0.0010351529,0.0005473946,0.084464744,0.00023762872],"about_ca_topic_score_codex":0.000021395597,"about_ca_topic_score_gemma":0.000014478951,"teacher_disagreement_score":0.5657617,"about_ca_system_score_codex":0.000051709452,"about_ca_system_score_gemma":0.00008450591,"threshold_uncertainty_score":0.96008116},"labels":[],"label_agreement":null},{"id":"W4405330878","doi":"10.1201/9781003564966-33","title":"Factors influencing sustainability and potential challenges in Canada","year":2024,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Sustainability; Business; Environmental planning; Environmental resource management; Geography; Environmental science; Ecology; Biology","score_opus":0.20691708012302226,"score_gpt":0.4156366512710805,"score_spread":0.20871957114805825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405330878","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09694897,0.0025500217,0.000009770452,0.0043409425,0.00069871556,0.00034485973,0.000021540593,0.000023623661,0.89506155],"genre_scores_gemma":[0.7168789,0.00039561454,0.000006737361,0.00008088415,0.000034887824,0.0000031397533,0.000003069043,0.0000104338915,0.28258634],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9970608,0.00002947086,0.00061947317,0.00055844494,0.0015438712,0.00018794488],"domain_scores_gemma":[0.99872065,0.00035680912,0.00012341786,0.00037382226,0.0003233758,0.000101919184],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014808999,0.00022110115,0.00034796775,0.00030722257,0.00004856069,0.00013815798,0.0002510311,0.00012203464,0.0032023774],"category_scores_gemma":[0.00019214953,0.00014350424,0.00005665108,0.000055392964,0.000046164027,0.00017444954,0.00019139431,0.00031556265,0.000033774435],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021997339,0.000014107827,0.024779301,0.00030818957,0.0000797342,0.0001276531,0.003199729,0.0012340036,0.0000023930695,0.6771349,0.0036700955,0.28942794],"study_design_scores_gemma":[0.00021073723,0.00005771247,0.085303254,0.00010605263,0.000029752191,0.0000047547114,0.020367917,0.0031476412,0.000009104776,0.6277617,0.2624315,0.00056988024],"about_ca_topic_score_codex":0.31880856,"about_ca_topic_score_gemma":0.96784884,"teacher_disagreement_score":0.6490402,"about_ca_system_score_codex":0.0011085579,"about_ca_system_score_gemma":0.00395775,"threshold_uncertainty_score":0.99770886},"labels":[],"label_agreement":null},{"id":"W4405365784","doi":"10.3138/cjpe.76851","title":"Veronica G. Thomas and Patricia B. Campbell (2021). <i>Evaluation in today’s world: Respecting diversity, improving quality, and promoting usability</i>","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Diversity (politics); Usability; Quality (philosophy); Sociology; Library science; Computer science; Philosophy; Anthropology; Epistemology; Human–computer interaction","score_opus":0.3843085190255128,"score_gpt":0.5217906207117903,"score_spread":0.1374821016862775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405365784","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9928129,0.0006125193,0.000054140186,0.003166204,0.00044690754,0.0015192932,0.000004755029,0.000013314818,0.0013699825],"genre_scores_gemma":[0.9987467,0.000029690753,0.0008597363,0.00007933294,0.00014016459,0.00004007328,0.000008582292,0.000009823285,0.000085928514],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99310833,0.0018763165,0.0012965145,0.00042298643,0.002878156,0.00041768412],"domain_scores_gemma":[0.9954674,0.001050706,0.0009055187,0.0002707716,0.0019176144,0.0003879886],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07861734,0.00015297087,0.00032090902,0.0017051494,0.00060851016,0.0005908658,0.00031923022,0.0000850016,0.0003402686],"category_scores_gemma":[0.012235839,0.00013561004,0.000069800735,0.0023945302,0.00011682094,0.0009692717,0.00017562648,0.0003362116,0.00001643965],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012279833,0.000017690507,0.3766063,0.000014321147,0.000008042904,0.0000043066634,0.003832413,0.00061573467,0.00006370031,0.00011263625,0.00016614006,0.6185464],"study_design_scores_gemma":[0.0016826236,0.00028214345,0.7919185,0.00010084595,0.00008684169,0.000016389311,0.0046178126,0.18109009,0.000044997865,0.018140938,0.0018186732,0.00020011413],"about_ca_topic_score_codex":0.0029036514,"about_ca_topic_score_gemma":0.1590468,"teacher_disagreement_score":0.61834633,"about_ca_system_score_codex":0.0008252806,"about_ca_system_score_gemma":0.0033967993,"threshold_uncertainty_score":0.9960845},"labels":[],"label_agreement":null},{"id":"W4405365972","doi":"10.3138/cjpe.76834","title":"Gail Vallance Barrington &amp; Beverly Triana-Tremain. (2022). <i>Evaluation time: A practical guide for evaluation</i>","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Environmental science","score_opus":0.4077939034852666,"score_gpt":0.576833651242932,"score_spread":0.16903974775766534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405365972","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81174207,0.0035356625,0.025616355,0.07760708,0.012914771,0.03773558,0.00027707094,0.00034235316,0.030229082],"genre_scores_gemma":[0.95800245,0.000095656535,0.027078645,0.0017669647,0.002136348,0.0033981404,0.0009610782,0.00012365812,0.0064370455],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98373646,0.0027147431,0.0024872315,0.0006835185,0.009570373,0.000807666],"domain_scores_gemma":[0.9779643,0.0019289101,0.0018540778,0.0007975938,0.016558964,0.00089615467],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.12750241,0.00032402013,0.00058321,0.001727806,0.0006571253,0.0009484202,0.0007808233,0.000238205,0.0096024675],"category_scores_gemma":[0.04797655,0.0002807167,0.00040440942,0.00277029,0.00013850817,0.0015330835,0.000033640626,0.00038315795,0.0013282644],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012570343,0.000069594294,0.0018949875,0.000012469026,0.00010230653,0.000003935464,0.0009954749,0.014130671,0.00028575462,0.0003464018,0.2737108,0.7083219],"study_design_scores_gemma":[0.004726415,0.00064827077,0.013579928,0.0000637884,0.0005629666,0.000051010935,0.00079221005,0.5570961,0.0000747299,0.02260119,0.39948946,0.00031393132],"about_ca_topic_score_codex":0.00024959305,"about_ca_topic_score_gemma":0.012447807,"teacher_disagreement_score":0.708008,"about_ca_system_score_codex":0.001778877,"about_ca_system_score_gemma":0.024835592,"threshold_uncertainty_score":0.9999645},"labels":[],"label_agreement":null},{"id":"W4405366000","doi":"10.3138/cjpe-2023-0011","title":"When we say evaluation, it isn’t the same thing","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sociology; Computer science","score_opus":0.5162236582112425,"score_gpt":0.5551123995560459,"score_spread":0.03888874134480336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405366000","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39471072,0.0037541883,0.0026594154,0.5453715,0.009123754,0.007657325,0.000033182718,0.000112718604,0.036577243],"genre_scores_gemma":[0.9927279,0.000067421635,0.0013997488,0.002078971,0.00063285505,0.0002142577,0.000032658096,0.00002096427,0.0028252224],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.990172,0.0017622599,0.0012893107,0.00027663622,0.0060614115,0.00043832595],"domain_scores_gemma":[0.9915784,0.0008549698,0.0009217213,0.00054639013,0.0056623803,0.0004361093],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.07333303,0.00016152431,0.00025166108,0.0009754174,0.00065800495,0.000977325,0.0009983879,0.00009847059,0.012458819],"category_scores_gemma":[0.009676247,0.00010147099,0.00019298618,0.0018061794,0.00013127543,0.00096768903,0.000029714312,0.00035055078,0.0010146267],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000067732653,0.000012666391,0.004104524,0.0000025900283,0.000033478496,0.000003047554,0.0077784294,0.010509758,0.000018263476,0.0004230048,0.18906865,0.7880388],"study_design_scores_gemma":[0.0009510927,0.00025391494,0.04707082,0.00008079245,0.00018813474,0.000038546477,0.0101824775,0.38251233,0.000034427034,0.0789678,0.47953853,0.0001811185],"about_ca_topic_score_codex":0.0005210097,"about_ca_topic_score_gemma":0.027597908,"teacher_disagreement_score":0.7878577,"about_ca_system_score_codex":0.0006170236,"about_ca_system_score_gemma":0.009163156,"threshold_uncertainty_score":0.9997632},"labels":[],"label_agreement":null},{"id":"W4405366177","doi":"10.3138/cjpe-2023-0012","title":"Examining Youth Sector Stakeholders’ Experiences in an Online Program Evaluation Certificate","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"York University; Youth Research and Evaluation eXchange; Brock University","funders":"","keywords":"Certificate; Business; Public relations; Political science; Computer science","score_opus":0.9339822613619181,"score_gpt":0.581308825436659,"score_spread":0.3526734359252591,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405366177","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99436516,0.00018516122,0.00007188006,0.0007213355,0.0012342961,0.0029245382,0.000018489025,0.000050089246,0.00042906235],"genre_scores_gemma":[0.9968215,0.000009124609,0.0018019546,0.00008396574,0.00025823835,0.0007197795,0.00022569502,0.000020601448,0.00005913871],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9911465,0.0016459336,0.0016183223,0.00047178377,0.0045535145,0.0005639161],"domain_scores_gemma":[0.994144,0.00023507273,0.000937588,0.00047295756,0.003571895,0.0006384538],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03396134,0.0002106657,0.00034876,0.0020779548,0.00026852,0.0008795586,0.00074401964,0.00013211228,0.0022671022],"category_scores_gemma":[0.0037836994,0.00017155163,0.00010360034,0.0032890085,0.00014559661,0.0016508942,0.000019361501,0.00031996475,0.00008056897],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019853222,0.00012726535,0.04696091,0.0000034843733,0.000011588325,0.0000079043675,0.036784373,0.009406613,0.00006583357,0.00001208567,0.00031089052,0.9062892],"study_design_scores_gemma":[0.0013383396,0.0012869802,0.34067336,0.00007755812,0.000074939715,0.000010026845,0.16984648,0.48259002,0.00007376269,0.0012093225,0.0025844418,0.00023475292],"about_ca_topic_score_codex":0.0005627401,"about_ca_topic_score_gemma":0.05345097,"teacher_disagreement_score":0.90605444,"about_ca_system_score_codex":0.00065632217,"about_ca_system_score_gemma":0.006035719,"threshold_uncertainty_score":0.99959916},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"opus","categories":["metaresearch"],"domain":"incentives","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"low"}],"label_agreement":"split"},{"id":"W4405517287","doi":"10.7202/1114680ar","title":"Rendons l’évaluation plus inclusive","year":2024,"lang":"fr","type":"article","venue":"Apprendre et enseigner aujourd’hui Revue du Conseil pédagogique interdisciplinaire du Québec","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Valuation (finance); Economics; Accounting","score_opus":0.06320444833850127,"score_gpt":0.40520742591763803,"score_spread":0.3420029775791368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405517287","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20561783,0.023166718,0.05718127,0.63927835,0.020152617,0.0020578918,0.0005145427,0.00091601326,0.051114775],"genre_scores_gemma":[0.81298536,0.002038497,0.0013254678,0.0028672481,0.0030234787,0.0004409321,0.00018937823,0.00020982401,0.17691982],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9861554,0.0037601423,0.0034092355,0.0026262868,0.0025830022,0.0014659323],"domain_scores_gemma":[0.98691523,0.007351402,0.0009996498,0.0020992286,0.001846714,0.00078779826],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","insufficient_payload"],"category_scores_codex":[0.012965318,0.0014057893,0.0016418138,0.0014069987,0.0014413379,0.002586651,0.0021628714,0.0009872984,0.009548322],"category_scores_gemma":[0.0043033822,0.0012819722,0.0013509963,0.0022195028,0.0014534356,0.0027725305,0.0025102347,0.0023481336,0.008631777],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028769838,0.0003882561,0.0006777575,0.00053556706,0.00053078565,0.001144505,0.19780304,0.0053575314,0.00021156929,0.015571246,0.30983248,0.46765956],"study_design_scores_gemma":[0.001756143,0.0007472161,0.002242803,0.0035266625,0.00056982756,0.0028330889,0.022727191,0.24086191,0.00032616412,0.015297727,0.70751876,0.0015925368],"about_ca_topic_score_codex":0.009255624,"about_ca_topic_score_gemma":0.06977475,"teacher_disagreement_score":0.6364111,"about_ca_system_score_codex":0.0035041277,"about_ca_system_score_gemma":0.03054199,"threshold_uncertainty_score":0.9999535},"labels":[],"label_agreement":null},{"id":"W4405650869","doi":"10.1177/10784535241306773","title":"Choosing an Analytical Approach in Case Study Research","year":2024,"lang":"en","type":"editorial","venue":"Creative Nursing","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; Memorial University of Newfoundland","funders":"","keywords":"Qualitative research; Phenomenon; Grounded theory; Phenomenology (philosophy); Narrative; Epistemology; Context (archaeology); Management science; Focus (optics); Computer science; Qualitative analysis; Data science; Sociology; Social science; Engineering; Linguistics","score_opus":0.5672455620062431,"score_gpt":0.6730034726611266,"score_spread":0.10575791065488349,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405650869","genre_codex":"editorial","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.156062,0.00043677224,0.00062927505,0.0003078925,0.69276595,0.0017825435,0.000056057073,0.000081454775,0.14787807],"genre_scores_gemma":[0.5085364,0.000012567981,0.0006707343,0.000009825035,0.48195755,0.00012395687,0.000103771046,0.00007015407,0.008515043],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.98609054,0.0035294637,0.0010701545,0.0015213559,0.007189522,0.00059893914],"domain_scores_gemma":[0.991987,0.0048336852,0.00017192002,0.0009628247,0.0018056623,0.00023890148],"candidate_categories":["metaresearch","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.029609712,0.00032551694,0.00070523354,0.0022934326,0.00047125356,0.001828027,0.00078763266,0.0004712279,0.00044217124],"category_scores_gemma":[0.0055623576,0.00024459037,0.00011230023,0.003308735,0.00040564826,0.00066027575,0.00014955552,0.0028029722,0.00027313558],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008505969,0.0013373625,0.0012931717,0.000019775363,0.00003424245,0.0011996499,0.039815675,0.00020902528,0.0000013600387,0.00019378557,0.90456426,0.05124663],"study_design_scores_gemma":[0.0015243201,0.0018198618,0.0019907034,0.0011098409,0.00017930212,0.00014548305,0.6292316,0.18314815,0.0000051257666,0.0075918967,0.17246588,0.0007878682],"about_ca_topic_score_codex":0.0005623483,"about_ca_topic_score_gemma":0.0002736464,"teacher_disagreement_score":0.7320984,"about_ca_system_score_codex":0.0013342422,"about_ca_system_score_gemma":0.0016773924,"threshold_uncertainty_score":0.9994976},"labels":[],"label_agreement":null},{"id":"W4405894699","doi":"10.20899/jpna.nsb51y51","title":"French-Language Public Administration Research on Social Equity: A Systematic Literature Review","year":2024,"lang":"en","type":"article","venue":"Journal of Public and Nonprofit Affairs","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École Nationale d'Administration Publique","funders":"","keywords":"Equity (law); Scholarship; Sociology; Public relations; Political science; Positive economics; Economics; Law","score_opus":0.40892361306121183,"score_gpt":0.5749626439278334,"score_spread":0.16603903086662153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405894699","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.078341804,0.4797264,0.0016076005,0.32611668,0.0034513471,0.0022392035,0.000058310263,0.00010682323,0.10835185],"genre_scores_gemma":[0.98891205,0.007075486,0.00012257787,0.0003877048,0.00060116255,0.000024448706,0.000007092437,0.0000104722,0.002859032],"study_design_codex":"not_applicable","study_design_gemma":"systematic_review","domain_scores_codex":[0.99274117,0.0012051397,0.0012678782,0.00029189445,0.004153765,0.00034014168],"domain_scores_gemma":[0.9962035,0.0010285166,0.00046369346,0.00027532896,0.0017777184,0.0002512811],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.040357176,0.00014660695,0.00050376705,0.0010851012,0.00029285028,0.0031360334,0.00060455286,0.00012225831,0.00086134527],"category_scores_gemma":[0.0033811126,0.000087881424,0.00020797178,0.0023781417,0.000106005835,0.0016314263,0.00012862496,0.0007621344,0.00015619653],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000616794,0.00037011137,0.00081038964,0.049654506,0.0003112921,0.00064154086,0.008676093,7.4438384e-7,0.00019406647,0.16353561,0.48306265,0.29268134],"study_design_scores_gemma":[0.0049363966,0.009800159,0.03423742,0.37365884,0.0008354288,0.0051931757,0.1331007,0.012033995,0.0003272265,0.0643046,0.35900953,0.002562516],"about_ca_topic_score_codex":8.129174e-7,"about_ca_topic_score_gemma":0.000022270373,"teacher_disagreement_score":0.9105702,"about_ca_system_score_codex":0.00014703108,"about_ca_system_score_gemma":0.0011227002,"threshold_uncertainty_score":0.9978988},"labels":[],"label_agreement":null},{"id":"W4405920204","doi":"10.5339/difi.2024.3","title":"Toward a conceptual framework for policy implementation inquiry: A multi-perspective approach","year":2024,"lang":"en","type":"article","venue":"Doha International Family Institute Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Perspective (graphical); Conceptual framework; Computer science; Management science; Sociology; Engineering; Artificial intelligence; Social science","score_opus":0.48711269548868524,"score_gpt":0.5991450540670336,"score_spread":0.11203235857834831,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405920204","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029547641,0.00036100324,0.93485236,0.01636327,0.010562226,0.0004615141,0.00015206513,0.00006787537,0.007632056],"genre_scores_gemma":[0.9088561,0.0001491166,0.08263425,0.0022094715,0.0053314636,0.00010240279,0.00006845682,0.000019794466,0.00062895933],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962244,0.000111136054,0.0008968519,0.0004679971,0.001997885,0.00030175416],"domain_scores_gemma":[0.9974509,0.00042557216,0.0002854366,0.00019939331,0.0014694228,0.00016930046],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0026530165,0.00020543965,0.00023333679,0.0009419947,0.00030244834,0.001599732,0.00086118915,0.000109943714,0.000530962],"category_scores_gemma":[0.0015870759,0.0001543755,0.00028863113,0.00070992653,0.00024429229,0.0019878964,0.00010441221,0.00047278233,0.0002267058],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000062862026,0.00009157936,0.00050102564,0.0000047870167,0.00019004913,0.000011253539,0.012828988,0.0013709405,0.00018332593,0.93388945,0.010176619,0.040689103],"study_design_scores_gemma":[0.0021588667,0.0003021032,0.007991545,0.000109272885,0.000048267535,0.0002606995,0.08655157,0.065497965,0.00012775236,0.32129803,0.5152488,0.0004051511],"about_ca_topic_score_codex":0.00010053828,"about_ca_topic_score_gemma":0.000021162115,"teacher_disagreement_score":0.87930846,"about_ca_system_score_codex":0.0009791099,"about_ca_system_score_gemma":0.0016421888,"threshold_uncertainty_score":0.9994367},"labels":[],"label_agreement":null},{"id":"W4405952547","doi":"10.3389/978-2-8325-5746-4","title":"Learning for Action in Policy Implementation","year":2024,"lang":"en","type":"book","venue":"Frontiers research topics","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Mental Health; Centers for Disease Control and Prevention; National Institutes of Health; Pierre Elliott Trudeau Foundation; National Institute of Diabetes and Digestive and Kidney Diseases; National Heart, Lung, and Blood Institute; Bill and Melinda Gates Foundation","keywords":"Action (physics); Computer science; Political science; Physics","score_opus":0.5527894107550396,"score_gpt":0.6734924314881021,"score_spread":0.1207030207330625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405952547","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00057489035,0.0022824546,0.023075862,0.088376954,0.0057164743,0.004066421,0.000097838136,0.0001125265,0.8756966],"genre_scores_gemma":[0.000365861,0.00049253827,0.00086591457,0.00007584004,0.0015691301,0.00019113539,0.00019947621,0.00002635631,0.99621373],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99531096,0.00040112046,0.0006222959,0.00052468514,0.0026911285,0.0004498336],"domain_scores_gemma":[0.9985559,0.00018624633,0.00013708792,0.00033140977,0.0006991637,0.000090223235],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009718951,0.00014440632,0.00027918295,0.0024305854,0.00022206019,0.00052310474,0.0004896601,0.00023207038,0.00065297267],"category_scores_gemma":[0.0015053713,0.00012279858,0.0001310947,0.0007545119,0.00007683087,0.0002917317,0.00015474758,0.0010204026,0.0003943905],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014281155,0.0000050373983,0.00033565957,0.00003459492,0.000011146771,0.000001221634,0.00054383883,0.00011780393,0.0000024703245,0.0050308015,0.63583106,0.3580721],"study_design_scores_gemma":[0.00022829036,0.000153092,0.0005320602,0.000029251367,0.000004595822,2.8079629e-7,0.0022072885,0.0077143162,0.000016638582,0.15262419,0.83639175,0.00009825969],"about_ca_topic_score_codex":0.000068587025,"about_ca_topic_score_gemma":0.00049966143,"teacher_disagreement_score":0.35797384,"about_ca_system_score_codex":0.0016449603,"about_ca_system_score_gemma":0.0034654122,"threshold_uncertainty_score":0.71495926},"labels":[],"label_agreement":null},{"id":"W4405953970","doi":"","title":"Understanding of evaluation capacity building in practice: a case study of a national medical education organization","year":2017,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medical education; Capacity building; Political science; Medicine; Law","score_opus":0.8408918433422927,"score_gpt":0.7325208759513173,"score_spread":0.1083709673909754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405953970","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9919713,0.00022616798,0.00217154,0.0005423779,0.00056679425,0.0007867971,0.00000653094,0.0000044260446,0.0037240335],"genre_scores_gemma":[0.99913245,0.00024757575,0.00039601125,0.00009154225,0.00006956942,0.000026180436,0.0000038920953,0.00001236665,0.000020384416],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9902135,0.0012369779,0.0016994581,0.00036482362,0.00633599,0.00014922561],"domain_scores_gemma":[0.9890383,0.0015122201,0.0038223239,0.00056003756,0.004930705,0.00013644558],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.029598111,0.00014743609,0.00049310335,0.001419129,0.00046761663,0.0010719321,0.0018155898,0.00009840031,0.008149582],"category_scores_gemma":[0.04594239,0.0001259864,0.00005678819,0.0015148888,0.00013855544,0.006110411,0.00053139083,0.00026508578,0.0000032400897],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000075497774,0.0016264092,0.97665006,0.000022602302,0.00007648174,0.000016611315,0.0034909775,0.0017226136,0.0023909998,0.0011948654,0.0019102899,0.0108225765],"study_design_scores_gemma":[0.0019300798,0.000044629014,0.93177724,0.00039993066,0.00010718868,0.00016898233,0.01943008,0.01667971,0.0017872956,0.027340217,0.00011308355,0.00022153716],"about_ca_topic_score_codex":0.0026663002,"about_ca_topic_score_gemma":0.0013348681,"teacher_disagreement_score":0.04487281,"about_ca_system_score_codex":0.00048551877,"about_ca_system_score_gemma":0.0029567475,"threshold_uncertainty_score":0.9999651},"labels":[],"label_agreement":null},{"id":"W4406089582","doi":"","title":"Keynote: What We Talk About When We Talk About Evidence","year":2013,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Data science; History","score_opus":0.5974596579464728,"score_gpt":0.6540836632870419,"score_spread":0.056624005340569106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406089582","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81607556,0.14936958,0.0022577199,0.014751242,0.004270924,0.0019705214,0.000032913937,0.00009959852,0.011171956],"genre_scores_gemma":[0.83827484,0.14848982,0.0009473476,0.00223209,0.00043863326,0.00018858322,0.0000068427307,0.000060879218,0.009360963],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9885881,0.0010941961,0.0027165986,0.0011177993,0.0056551844,0.00082812126],"domain_scores_gemma":[0.98979926,0.0029905583,0.002467521,0.0017471821,0.002270381,0.0007250802],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["scholarly_communication","insufficient_payload"],"category_scores_codex":[0.010408159,0.0005896707,0.0012968001,0.0015631018,0.0006883226,0.017623758,0.008910684,0.00023928247,0.26329038],"category_scores_gemma":[0.0025610772,0.00043733427,0.00045517017,0.002220911,0.0003533547,0.031916987,0.00201608,0.000772195,0.0022745216],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013801962,0.00025821588,0.11269348,0.00007087194,0.00012907424,0.00002918079,0.0015812423,0.0005304327,0.027120553,0.0001330404,0.32699135,0.5303245],"study_design_scores_gemma":[0.00094588764,0.00004740104,0.66241324,0.0032859803,0.00008844095,0.0000441501,0.0018589994,0.003824122,0.013559137,0.06259873,0.2503357,0.0009982563],"about_ca_topic_score_codex":0.0012063016,"about_ca_topic_score_gemma":0.00024417977,"teacher_disagreement_score":0.54971975,"about_ca_system_score_codex":0.00022519511,"about_ca_system_score_gemma":0.0006899504,"threshold_uncertainty_score":0.99980783},"labels":[],"label_agreement":null},{"id":"W4406104356","doi":"10.1111/capa.12600","title":"Delivering Results for Canadians: Improving the Contributions of Enabling Functions","year":2024,"lang":"en","type":"article","venue":"Canadian Public Administration","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa; Carleton University","funders":"","keywords":"Computer science; Business; Sociology; Political science","score_opus":0.1305211542424871,"score_gpt":0.41896440087890874,"score_spread":0.2884432466364216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406104356","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15961906,0.001406688,0.28035432,0.5123606,0.0057352656,0.0029314565,0.0083922,0.00018665129,0.029013805],"genre_scores_gemma":[0.9969611,0.0000052153355,0.00017831067,0.00033245404,0.00020535507,0.00008965683,0.00022066588,0.0000068636455,0.0020003745],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982997,0.00007379054,0.0005942283,0.0002823725,0.0004542332,0.00029565726],"domain_scores_gemma":[0.99737066,0.00095742877,0.00012579784,0.00034693762,0.000889904,0.00030927433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003748803,0.00008619338,0.000105636704,0.00046082996,0.0005989832,0.0007628286,0.0002957715,0.00006985039,0.0002442457],"category_scores_gemma":[0.004284592,0.00006292247,0.000086889806,0.0008923325,0.00006853553,0.0006042739,0.000011000673,0.00011575463,0.00004487447],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050767187,0.000030256373,0.0005824438,0.000052476295,0.00010676672,0.000009937868,0.0014973775,0.0003572949,0.0020446097,0.6328959,0.100750566,0.26162162],"study_design_scores_gemma":[0.00021442487,0.00010958332,0.00082370645,0.000018760937,0.000023001385,0.000010397102,0.0021129404,0.083644144,0.0005093977,0.0017189521,0.9107075,0.00010721275],"about_ca_topic_score_codex":0.017316412,"about_ca_topic_score_gemma":0.7473353,"teacher_disagreement_score":0.837342,"about_ca_system_score_codex":0.00037543944,"about_ca_system_score_gemma":0.009931625,"threshold_uncertainty_score":0.99568117},"labels":[],"label_agreement":null},{"id":"W4406126443","doi":"10.5430/wjel.v15n2p381","title":"Developing an ESP Syllabus to Promote Sustainable Development Goals: A Delphi Study","year":2025,"lang":"en","type":"article","venue":"World Journal of English Language","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Prince Sattam bin Abdulaziz University","keywords":"Syllabus; Delphi; Delphi method; Sustainable development; Computer science; Process management; Development (topology); Engineering management; Business; Mathematics education; Political science; Programming language; Artificial intelligence; Psychology; Engineering; Mathematics","score_opus":0.0734674781528581,"score_gpt":0.45409580950352885,"score_spread":0.38062833135067076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406126443","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98284286,0.00031748746,0.0032179574,0.00068596227,0.00086484256,0.00050042954,7.7707136e-7,0.000027364227,0.011542297],"genre_scores_gemma":[0.9661065,0.0000036545807,0.01615082,0.00080565637,0.0002569016,0.000017163207,0.0000011316738,0.00001067814,0.016647505],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961073,0.0003100689,0.0012771285,0.00029236273,0.0016438866,0.0003692681],"domain_scores_gemma":[0.9952355,0.00028080586,0.000430445,0.00041839338,0.0034358897,0.00019893683],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010592315,0.00017251376,0.0003986661,0.0015608777,0.00025663752,0.000526405,0.0009766044,0.000033733555,0.00051515264],"category_scores_gemma":[0.0053950683,0.00012484293,0.0000746534,0.0025767267,0.000018010387,0.0007881716,0.00022699597,0.0002596455,0.00003799023],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038990015,0.0011575214,0.06294445,0.000058192174,0.00028134589,0.0006385757,0.4969467,0.0022840917,0.00025258624,0.007328495,0.013743891,0.41397426],"study_design_scores_gemma":[0.0015775269,0.00037836435,0.04682372,0.00019351307,0.00003880981,0.000005692566,0.41088197,0.00012646326,0.0015873393,0.00081259425,0.53725994,0.0003140458],"about_ca_topic_score_codex":0.000017190147,"about_ca_topic_score_gemma":0.00091348146,"teacher_disagreement_score":0.52351606,"about_ca_system_score_codex":0.00039730378,"about_ca_system_score_gemma":0.0014977034,"threshold_uncertainty_score":0.64587903},"labels":[],"label_agreement":null},{"id":"W4406150311","doi":"10.1111/tran.12740","title":"No national research assessment here. A Canadian counterfactual?","year":2025,"lang":"en","type":"article","venue":"Transactions of the Institute of British Geographers","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Neoliberalism (international relations); Counterfactual thinking; Subject (documents); Political science; State (computer science); Public administration; Government (linguistics); Law; Psychology","score_opus":0.131840039111143,"score_gpt":0.47383666899614124,"score_spread":0.34199662988499824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406150311","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35657942,0.00032383553,0.015150746,0.006226742,0.0048181005,0.0011084031,0.0007524995,0.000033699274,0.61500657],"genre_scores_gemma":[0.99181205,0.00008350733,0.0013388905,0.00021825037,0.0000150979495,0.000033117918,0.0000033763026,0.000004425968,0.0064913123],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956136,0.00019753132,0.00064468296,0.000262299,0.0030397207,0.00024217326],"domain_scores_gemma":[0.9954466,0.00027947023,0.00013624015,0.0004506672,0.0035937529,0.000093239265],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005177704,0.00008324103,0.00020548412,0.000741059,0.00045258246,0.00012180765,0.0010042299,0.00008133677,0.0014576152],"category_scores_gemma":[0.0003374202,0.00007749,0.00022341684,0.0025218897,0.0007234759,0.00048285653,0.000022246822,0.00030743968,0.000030647578],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016433767,0.0014025323,0.07717916,0.0002355928,0.001156117,0.000009589067,0.0008730102,0.15565689,0.0017084973,0.02626492,0.23633029,0.49901906],"study_design_scores_gemma":[0.0017897567,0.00017952401,0.38455585,0.00064780324,0.0000770525,0.00002099423,0.0030504656,0.008915685,0.00062555936,0.021878203,0.5779346,0.00032448466],"about_ca_topic_score_codex":0.19019468,"about_ca_topic_score_gemma":0.46986046,"teacher_disagreement_score":0.6352326,"about_ca_system_score_codex":0.00024329814,"about_ca_system_score_gemma":0.004159119,"threshold_uncertainty_score":0.9994552},"labels":[],"label_agreement":null},{"id":"W4406181783","doi":"10.1007/978-3-030-74923-1_562","title":"Impact","year":2024,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science","score_opus":0.35060516586083373,"score_gpt":0.5698663820303878,"score_spread":0.21926121616955402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406181783","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000029617191,0.00029979806,0.00014439966,0.00092698244,0.0007756392,0.00010478211,0.000025945075,0.000060145707,0.9976327],"genre_scores_gemma":[0.0060805506,0.0000688286,0.00009864252,0.00032126583,0.00022981751,0.0000022975062,0.000012111892,0.000019204466,0.9931673],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99707377,0.000007564928,0.0004728438,0.0003729963,0.0019585213,0.00011429531],"domain_scores_gemma":[0.99873084,0.00025759355,0.000115733426,0.00056230277,0.00024401718,0.00008949327],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0015429512,0.00017819942,0.00024304647,0.0003529294,0.000038849546,0.00037837488,0.00039384444,0.00014736084,0.288916],"category_scores_gemma":[0.000061356914,0.00009430298,0.00030433323,0.00006021794,0.00003458314,0.00012749775,0.000109726505,0.00023188037,0.117868006],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000024949395,0.0000023060309,0.0000505648,0.0000018521179,0.00003035363,0.000004927903,0.000034011682,0.000016690201,0.0000012560887,0.6621243,0.28577653,0.051954765],"study_design_scores_gemma":[0.000026477252,0.000035951223,0.0001552022,0.000014142258,0.000010473873,0.0000033883398,0.000006861103,0.000646304,0.0000011840796,0.3723895,0.62662095,0.00008954044],"about_ca_topic_score_codex":0.000005041705,"about_ca_topic_score_gemma":0.000030956653,"teacher_disagreement_score":0.34084445,"about_ca_system_score_codex":0.000079326026,"about_ca_system_score_gemma":0.0002925921,"threshold_uncertainty_score":0.8828188},"labels":[],"label_agreement":null},{"id":"W4406258567","doi":"10.3138/cjpe-2023-0055","title":"Reporting Lines of Inquiry: Documenting Evaluations and Making Values Explicit","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Documentation; Set (abstract data type); Dimension (graph theory); Key (lock); Computer science; Value (mathematics); Quality (philosophy); Action (physics); Psychology; Epistemology; Mathematics","score_opus":0.5936105233649892,"score_gpt":0.6283661788620908,"score_spread":0.03475565549710158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406258567","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98439884,0.004273318,0.0045954194,0.0021129567,0.0017188098,0.00080930017,0.0000037837115,0.000019225816,0.002068337],"genre_scores_gemma":[0.9916321,0.000024234017,0.0077498304,0.00005559577,0.0003582699,0.0000390474,0.000005728642,0.000011868346,0.00012330142],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9941642,0.00045155216,0.0026558603,0.0002511565,0.0022430727,0.00023415816],"domain_scores_gemma":[0.9936929,0.00051213265,0.0022832386,0.00023777418,0.0030606794,0.00021329444],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.040812105,0.00012135005,0.00030452682,0.0011090161,0.00022749983,0.0007961701,0.0002454239,0.00006776542,0.0008959249],"category_scores_gemma":[0.013578381,0.00009413398,0.000138138,0.0010404431,0.00009911454,0.0010401335,0.000023204273,0.00019331016,0.000014064643],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004593414,0.000013129312,0.028001122,0.000030422038,0.00004933264,0.000008807215,0.0067251744,0.0022061495,0.00032938772,0.0012600109,0.0010415476,0.9603303],"study_design_scores_gemma":[0.00087458506,0.00073296204,0.14195865,0.0014983455,0.0006006826,0.00033854146,0.015767418,0.7182884,0.0009851777,0.08503619,0.03353383,0.0003851976],"about_ca_topic_score_codex":0.00015745926,"about_ca_topic_score_gemma":0.0018170113,"teacher_disagreement_score":0.95994514,"about_ca_system_score_codex":0.00019785012,"about_ca_system_score_gemma":0.003921776,"threshold_uncertainty_score":0.99473065},"labels":[],"label_agreement":null},{"id":"W4406258628","doi":"10.3138/cjpe-2024-0028","title":"Theory-of-Change Visuals: Using Diagrams, Metaphors, and Symbols to Communicate Complex Ideas and Get Buy-In","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Context (archaeology); Creativity; Field (mathematics); Stakeholder; Dynamism; Sociology; Epistemology; Psychology; Public relations; Social psychology","score_opus":0.7625487198627899,"score_gpt":0.6027241267009266,"score_spread":0.15982459316186337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406258628","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9865531,0.009220324,0.00073662115,0.0019400335,0.00027621802,0.0010583024,0.000015255159,0.0000057910997,0.00019437273],"genre_scores_gemma":[0.9951955,0.000105600986,0.004388324,0.00018541771,0.00005853069,0.000036272308,0.000006055744,0.000009608833,0.000014693316],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99680185,0.0009875986,0.000814714,0.00018318859,0.0010040639,0.00020859574],"domain_scores_gemma":[0.99782026,0.00056078495,0.00026807698,0.00022548936,0.00074450433,0.00038087828],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021275569,0.00011295491,0.00029790407,0.001015876,0.00011541519,0.00037238584,0.0002758356,0.00005524092,0.0003508228],"category_scores_gemma":[0.0012149533,0.000086980814,0.000059164184,0.00084596046,0.00012441793,0.0005545152,0.000036771762,0.00017213506,0.000007535834],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017690752,0.000021164817,0.050326135,0.000020880329,0.00003627016,0.000007879108,0.005503331,0.0002630645,0.0001466035,0.004007802,0.00018841155,0.93946075],"study_design_scores_gemma":[0.0009725943,0.0008421758,0.50719684,0.0006556051,0.0002688285,0.00012381462,0.0064683002,0.3801218,0.000111569716,0.08026316,0.022660244,0.0003150806],"about_ca_topic_score_codex":0.0011806024,"about_ca_topic_score_gemma":0.018701218,"teacher_disagreement_score":0.9391457,"about_ca_system_score_codex":0.00017076611,"about_ca_system_score_gemma":0.0010110842,"threshold_uncertainty_score":0.99920493},"labels":[],"label_agreement":null},{"id":"W4406259049","doi":"10.3138/cjpe-2024-0034","title":"Old Knowledge, New Tools: Applying an Indigenous Approach to Social Network Analysis","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Indigenous; Honour; Traditional knowledge; Social network analysis; Work (physics); Indigenous education; Value (mathematics); Scale (ratio); Process (computing); Sociology; Data science; Computer science; Geography; Social science; Engineering; Cartography; Archaeology; Ecology; Social capital","score_opus":0.42867378272941575,"score_gpt":0.5489013155159965,"score_spread":0.12022753278658077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406259049","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78234386,0.006904803,0.1626492,0.0030559285,0.0052362112,0.006688591,0.000046831334,0.00013358537,0.032940965],"genre_scores_gemma":[0.9843445,0.000005103349,0.012466848,0.00024402769,0.0018629646,0.00013891341,0.000050176597,0.000017819233,0.00086967304],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99546605,0.0006369331,0.0010112056,0.00036321976,0.0020699482,0.00045261052],"domain_scores_gemma":[0.99658996,0.00019548029,0.00031416758,0.00028496498,0.0016355809,0.0009798201],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01873785,0.00016286015,0.00036884996,0.0017901931,0.00046678883,0.0023157685,0.0006529238,0.0001164243,0.000965435],"category_scores_gemma":[0.0005779562,0.00013101142,0.0002952832,0.0056986366,0.000040691477,0.001078311,0.000018298662,0.0002940687,0.00017422305],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000076220617,0.000040356997,0.003577185,0.0000047412072,0.0001967181,0.0000032164944,0.015846886,0.043007474,0.0000035199494,0.0009041082,0.008115009,0.92829317],"study_design_scores_gemma":[0.0006209069,0.0007420038,0.097292565,0.00006337745,0.0017069508,0.00003958484,0.005903044,0.51652044,0.000009858559,0.014607765,0.36201945,0.00047406473],"about_ca_topic_score_codex":0.000909454,"about_ca_topic_score_gemma":0.038442884,"teacher_disagreement_score":0.9278191,"about_ca_system_score_codex":0.00064653717,"about_ca_system_score_gemma":0.009474202,"threshold_uncertainty_score":0.99994785},"labels":[],"label_agreement":null},{"id":"W4406357355","doi":"10.5751/es-15729-300109","title":"Cultural and empowerment priorities amid tensions in knowledge systems and resource allocation: insights from the Great Limpopo Transfrontier Conservation Area","year":2025,"lang":"en","type":"article","venue":"Ecology and Society","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Universität für Bodenkultur Wien","keywords":"Empowerment; Business; Resource (disambiguation); Environmental resource management; Environmental planning; Natural resource economics; Geography; Political science; Economic growth; Economics; Computer science","score_opus":0.105055639842475,"score_gpt":0.39872111777173014,"score_spread":0.2936654779292551,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406357355","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9835153,0.00389126,0.00010823307,0.01024007,0.00028806942,0.00028439375,0.000006576976,0.000010315159,0.001655756],"genre_scores_gemma":[0.99448675,0.0012963065,0.000078086356,0.0016671503,0.000028968167,0.000036437617,0.000012418143,0.0000017976911,0.0023921104],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989222,0.00026438668,0.00031179813,0.0002466791,0.00015682503,0.000098107004],"domain_scores_gemma":[0.9985344,0.0011019126,0.000059605616,0.00013680788,0.00013590395,0.00003139062],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000919771,0.00008728728,0.00018049442,0.000032763255,0.0004548311,0.00013275784,0.0000893098,0.000120597586,0.000025442405],"category_scores_gemma":[0.000114602764,0.000051510553,0.000029362674,0.00018328174,0.00028864117,0.0001858551,0.000055781762,0.0001297069,0.000002367621],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003214041,0.00005443119,0.8515196,0.000018279201,0.00006680879,8.12766e-7,0.055951875,0.000041800024,0.00015867995,0.010945279,0.078332245,0.002878034],"study_design_scores_gemma":[0.0005879729,0.000038629372,0.88886786,0.000030631993,0.000018642842,0.0000018340479,0.033680726,0.014562928,0.00000912899,0.0019580182,0.06018022,0.00006340538],"about_ca_topic_score_codex":0.00008522456,"about_ca_topic_score_gemma":0.0015015175,"teacher_disagreement_score":0.037348248,"about_ca_system_score_codex":0.000039004506,"about_ca_system_score_gemma":0.00010994532,"threshold_uncertainty_score":0.34982392},"labels":[],"label_agreement":null},{"id":"W4406423589","doi":"10.1016/s1541-9800(07)70399-x","title":"10.1016/s1541-9800(07)70399-x","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Quality (philosophy); Business; Computer science; Physics","score_opus":0.07747168506392338,"score_gpt":0.371107160017894,"score_spread":0.29363547495397063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406423589","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020235868,0.000027587452,0.0000083970735,0.0017322198,0.000005709345,0.000187102,0.000010863812,0.00007134936,0.9959332],"genre_scores_gemma":[0.0011864444,3.8696035e-7,0.00028861215,0.00029164026,0.00013762942,0.000021515705,0.000007752449,0.000011423501,0.9980546],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973053,0.00013359361,0.0004609256,0.00036609403,0.0014591715,0.00027494816],"domain_scores_gemma":[0.99861014,0.00028498637,0.00007287735,0.00061940745,0.00021174687,0.00020084923],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0020897132,0.00013375672,0.00020406424,0.00017194984,0.00015471775,0.00023042678,0.00062410434,0.000056364715,0.9998586],"category_scores_gemma":[0.00027567687,0.00010107629,0.00008485147,0.0006246077,0.00003772674,0.00033435842,0.000062806284,0.00010422864,0.9996842],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024780971,0.000023611172,0.0000013596182,4.2276173e-7,0.000003306207,8.762105e-7,0.000031411342,0.00029879765,0.000009914534,0.0000025591212,0.43187392,0.56772906],"study_design_scores_gemma":[0.00024316103,0.00013210968,0.00054924504,0.000006599467,0.0000061484798,0.000004136442,0.000007735442,0.0035685983,0.000063040345,0.00017778999,0.9950913,0.00015010583],"about_ca_topic_score_codex":0.000010208063,"about_ca_topic_score_gemma":7.542086e-7,"teacher_disagreement_score":0.5675789,"about_ca_system_score_codex":0.000042610387,"about_ca_system_score_gemma":0.000115797906,"threshold_uncertainty_score":0.41217718},"labels":[],"label_agreement":null},{"id":"W4406457328","doi":"10.1016/s1544-8800(07)70338-x","title":"10.1016/s1544-8800(07)70338-x","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Quality (philosophy); Computer science; Business; Physics","score_opus":0.07747390489841657,"score_gpt":0.37104719440827316,"score_spread":0.2935732895098566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406457328","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024415303,0.000026190371,0.000009178297,0.0017144901,0.0000057440266,0.00018697805,0.000010430199,0.00007119281,0.99553424],"genre_scores_gemma":[0.0012419146,3.8670265e-7,0.00029222167,0.00025471675,0.00013674886,0.000021244025,0.0000072535213,0.000011393686,0.9980341],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973205,0.00013253109,0.0004586207,0.00036440816,0.0014500673,0.00027391338],"domain_scores_gemma":[0.99861246,0.00028677774,0.00007264005,0.00061557686,0.00021239168,0.00020016277],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0020030972,0.00013342388,0.00020360095,0.00017008226,0.0001556085,0.00023119274,0.00062059966,0.00005622138,0.9998353],"category_scores_gemma":[0.000264701,0.00010084303,0.00008478112,0.0006183037,0.000037599104,0.00033492345,0.00006247888,0.00010379083,0.9996781],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026343043,0.000023507573,0.0000014330183,4.2316702e-7,0.0000032825587,8.73884e-7,0.00003059403,0.00032608208,0.000009924782,0.000002623666,0.4094615,0.5901134],"study_design_scores_gemma":[0.00023782732,0.00013214379,0.0008560532,0.000006508616,0.0000061321502,0.0000041459175,0.000007704289,0.0036825873,0.000058586582,0.00015395695,0.994704,0.00015033872],"about_ca_topic_score_codex":0.000013971661,"about_ca_topic_score_gemma":9.349669e-7,"teacher_disagreement_score":0.5899631,"about_ca_system_score_codex":0.000042565323,"about_ca_system_score_gemma":0.000117638105,"threshold_uncertainty_score":0.41122594},"labels":[],"label_agreement":null},{"id":"W4406530370","doi":"10.3138/cjpe-2023-0026","title":"Foundations for a Utopia: Can Evaluation Contribute to Achieving a Better World, and How?","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"École Nationale d'Administration Publique; Government of Canada; Government of Nova Scotia; University of Victoria","funders":"","keywords":"Utopia; Environmental ethics; Sociology; Aesthetics; Philosophy; History; Art history","score_opus":0.3634329391642527,"score_gpt":0.5449652074120074,"score_spread":0.1815322682477547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406530370","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.717147,0.0023239607,0.04402025,0.22217576,0.0041250554,0.008504917,0.00012884384,0.000041723906,0.0015324806],"genre_scores_gemma":[0.98960626,0.000005663176,0.007821445,0.000729493,0.00046842903,0.00052504597,0.00004641149,0.0000146184575,0.0007826587],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99633235,0.00045582338,0.0006277838,0.0002950932,0.0019840428,0.00030491975],"domain_scores_gemma":[0.99425524,0.00065772736,0.00028064556,0.0002160038,0.004069536,0.00052084395],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.023293313,0.00013597486,0.00022565745,0.0014766917,0.00033211295,0.0020677848,0.00025271214,0.000058584803,0.0007355592],"category_scores_gemma":[0.0054092463,0.00010839052,0.00012512812,0.001144543,0.000054568445,0.00077617017,0.000013934773,0.00017108601,0.0000249409],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009956641,0.000009384688,0.004378081,0.00001078007,0.000046241308,0.0000017996325,0.0011118958,0.0008333951,0.0000633444,0.0019408737,0.009918071,0.98167616],"study_design_scores_gemma":[0.0011651579,0.00056959,0.04421614,0.0002036288,0.00039698562,0.000040546325,0.0005930098,0.37943763,0.000049478327,0.020539109,0.5525705,0.00021817548],"about_ca_topic_score_codex":0.00015014329,"about_ca_topic_score_gemma":0.056852706,"teacher_disagreement_score":0.981458,"about_ca_system_score_codex":0.00070046494,"about_ca_system_score_gemma":0.005546898,"threshold_uncertainty_score":0.9989682},"labels":[],"label_agreement":null},{"id":"W4406632505","doi":"10.7202/1115410ar","title":"La présélection informelle comme stratégie organisationnelle pour contrer la pénurie de directions d’école franco-ontariennes","year":2024,"lang":"fr","type":"article","venue":"Éducation et francophonie","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Humanities; Art; Sociology","score_opus":0.08081954408609363,"score_gpt":0.41975918814101226,"score_spread":0.3389396440549186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406632505","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18530588,0.014745267,0.13583936,0.10156068,0.0443153,0.0016767121,0.00026550354,0.0007730881,0.5155182],"genre_scores_gemma":[0.8902923,0.0015875474,0.0019760637,0.0020426388,0.0009845197,0.00021618318,0.00010128838,0.00006086583,0.10273858],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99523693,0.001271318,0.001085223,0.0006988235,0.001139308,0.0005684031],"domain_scores_gemma":[0.99392235,0.0041663237,0.0002979234,0.00061281584,0.0007067123,0.00029386664],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.005813384,0.00041132924,0.00039685346,0.00059375295,0.000756427,0.0016570061,0.00042651687,0.0004926913,0.0285899],"category_scores_gemma":[0.0011377571,0.00039804223,0.00025229447,0.002207368,0.0002949524,0.0021449109,0.000078618774,0.000890585,0.0063815173],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000085846244,0.001427428,0.010065482,0.0003261945,0.0002864898,0.000025134272,0.116439074,0.008420099,0.0012985375,0.090677515,0.37830082,0.3926474],"study_design_scores_gemma":[0.0008405678,0.00012252951,0.027640168,0.00027553752,0.00008765783,0.00011614214,0.018197542,0.03942972,0.0008485453,0.030562416,0.88144106,0.00043810616],"about_ca_topic_score_codex":0.0030093794,"about_ca_topic_score_gemma":0.008392655,"teacher_disagreement_score":0.70498645,"about_ca_system_score_codex":0.0011126458,"about_ca_system_score_gemma":0.008498744,"threshold_uncertainty_score":0.9998472},"labels":[],"label_agreement":null},{"id":"W4406674398","doi":"10.1016/b978-0-08-024699-4.50011-6","title":"10.1016/b978-0-08-024699-4.50011-6","year":2000,"lang":"en","type":"book-chapter","venue":"Time to knit","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Race (biology); Sociology; Gender studies","score_opus":0.0874056891079193,"score_gpt":0.34463120403579595,"score_spread":0.25722551492787665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406674398","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000001484829,0.00015671477,0.0000043558566,0.00078589394,0.000020123787,0.00046879004,0.00011032818,0.000112196816,0.99834013],"genre_scores_gemma":[0.0000037296547,0.0000017666772,0.0001541459,0.000275469,0.0004342212,0.000026071495,0.000082657025,0.00006455885,0.9989574],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99462193,0.00007757034,0.0010571727,0.00086168427,0.0029842402,0.00039737264],"domain_scores_gemma":[0.99703324,0.0004689866,0.0003664257,0.0013185671,0.00047504395,0.00033773383],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0019402852,0.00046856885,0.0006650655,0.0006771749,0.00019589555,0.0003777664,0.0012490739,0.0003489672,0.99984497],"category_scores_gemma":[0.00019302234,0.00037878146,0.00030468564,0.00019333618,0.00009638841,0.00027606322,0.00021907563,0.0004224603,0.9996869],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003882783,0.000011448171,3.3583177e-8,0.0000019096383,0.000019581857,0.000004582365,0.000016639684,0.00006417171,8.196499e-7,0.00016844082,0.43948388,0.56018966],"study_design_scores_gemma":[0.00025113957,0.00021036713,0.000009300298,0.0000669495,0.000040995015,0.0000101722335,0.0000017231035,0.00039788685,0.000005330813,0.0036726734,0.9948485,0.00048496245],"about_ca_topic_score_codex":0.000005875973,"about_ca_topic_score_gemma":0.0000015070821,"teacher_disagreement_score":0.5597047,"about_ca_system_score_codex":0.00012846147,"about_ca_system_score_gemma":0.00037946992,"threshold_uncertainty_score":0.9998664},"labels":[],"label_agreement":null},{"id":"W4406741889","doi":"10.35542/osf.io/qtcmg","title":"Questionnaire d’anxiété évaluative scolaire (QAES) : Adaptation française d’une échelle courte destinée aux jeunes","year":2025,"lang":"fr","type":"preprint","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Adaptation (eye); Psychology; Humanities; Art","score_opus":0.16593530700342238,"score_gpt":0.4525825444668043,"score_spread":0.28664723746338194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406741889","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16800061,0.010153226,0.41305217,0.11578725,0.018280804,0.006763539,0.00041620302,0.000823888,0.26672232],"genre_scores_gemma":[0.78802615,0.0014098489,0.01770121,0.0018146293,0.0004941374,0.00064876454,0.00019982699,0.000046553756,0.1896589],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9863509,0.002085116,0.0030930415,0.0023387352,0.005182539,0.0009496739],"domain_scores_gemma":[0.9880211,0.002315306,0.0015934407,0.001990061,0.0055582137,0.0005219234],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.010259624,0.0011693129,0.0014706011,0.000978678,0.0016957122,0.0009631986,0.001999097,0.001025501,0.016871009],"category_scores_gemma":[0.0039267167,0.0010118056,0.00068940624,0.0026934543,0.0007708315,0.0014181678,0.0012347096,0.0015126363,0.004950485],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003013586,0.0008014234,0.03185912,0.0003595682,0.00031779113,0.000022462886,0.0260868,0.19042264,0.000052486164,0.0951134,0.027632447,0.6270305],"study_design_scores_gemma":[0.0019754907,0.00034194413,0.08431057,0.00283952,0.00043442665,0.000014479481,0.019059775,0.76789105,0.00031529638,0.04448462,0.07706627,0.0012665786],"about_ca_topic_score_codex":0.006936039,"about_ca_topic_score_gemma":0.013253098,"teacher_disagreement_score":0.62576395,"about_ca_system_score_codex":0.0006443596,"about_ca_system_score_gemma":0.012599066,"threshold_uncertainty_score":0.9996769},"labels":[],"label_agreement":null},{"id":"W4406883428","doi":"10.1007/978-3-031-81068-8_11","title":"Learning from Mistakes","year":2025,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Psychology; Computer science","score_opus":0.2827184533552689,"score_gpt":0.4703562651379598,"score_spread":0.1876378117826909,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406883428","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000036173325,0.00020232952,0.0017488119,0.0010162394,0.00050845416,0.00009634073,0.000013450889,0.000055857996,0.99632233],"genre_scores_gemma":[0.0033166686,0.00006861827,0.0007835502,0.0007981053,0.00014514652,0.0000029232078,0.000054842858,0.0000090736,0.9948211],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971837,0.000040376948,0.0005684213,0.00044858293,0.001648986,0.0001099358],"domain_scores_gemma":[0.9976738,0.0011737142,0.0002561563,0.0004882074,0.00034991998,0.000058193666],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0011943042,0.00017672378,0.00031125237,0.00024330581,0.00012684174,0.0002679172,0.00049326685,0.000185584,0.14216946],"category_scores_gemma":[0.00043113367,0.00012294507,0.00015536317,0.00005092353,0.0000401726,0.00011259572,0.00006823541,0.0003404781,0.0073733963],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013124655,0.000007042956,0.00066084205,0.0000036827428,0.00005837957,0.0000043172786,0.000279423,0.00016962682,0.000009949091,0.38204953,0.25360325,0.36314082],"study_design_scores_gemma":[0.0000963738,0.0000229658,0.0002223389,0.000040125622,0.00001558548,1.6312424e-7,0.00016959115,0.0019640424,0.000013541049,0.104708955,0.89261156,0.00013476326],"about_ca_topic_score_codex":0.000031409836,"about_ca_topic_score_gemma":0.000124154,"teacher_disagreement_score":0.6390083,"about_ca_system_score_codex":0.000044664466,"about_ca_system_score_gemma":0.00031163965,"threshold_uncertainty_score":0.9933995},"labels":[],"label_agreement":null},{"id":"W4406938302","doi":"10.3138/cjpe-2023-0005","title":"Developing a Community of Practice (CoP) on Monitoring, Evaluation, and Learning (MEL) in a Global Network of Women’s Funds","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Business; Psychology; Medical education; Medicine","score_opus":0.38552297080082165,"score_gpt":0.5674184361961859,"score_spread":0.18189546539536428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406938302","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99380505,0.0018477984,0.0004663667,0.0010091962,0.0007050244,0.0006227441,0.0000024427115,0.000005562159,0.001535791],"genre_scores_gemma":[0.9952029,0.000044972297,0.0045040883,0.00004950567,0.000112568756,0.00006055999,0.0000036988042,0.0000066960856,0.000015031281],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99299806,0.0029925075,0.0011605272,0.00015585676,0.0024006213,0.00029242338],"domain_scores_gemma":[0.993818,0.0012186441,0.00078994414,0.00019818827,0.0037390504,0.00023621746],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.073799334,0.00011359618,0.00029080742,0.00045683255,0.00019808782,0.00024044448,0.0002820306,0.0000798697,0.00023876433],"category_scores_gemma":[0.013937587,0.0000965249,0.00005853851,0.0015946944,0.000090994996,0.0006960363,0.00002285661,0.0005281995,0.0000055390983],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049072303,0.000040335228,0.1232374,0.00002984125,0.000050109258,0.0000030098095,0.010353641,0.035653032,0.000007856139,0.001337135,0.00012589534,0.82911265],"study_design_scores_gemma":[0.0016006187,0.0020958008,0.7582463,0.0013374927,0.00017595496,0.00006139445,0.030509073,0.1520023,0.000059142654,0.029682469,0.024004938,0.00022452652],"about_ca_topic_score_codex":0.0018581988,"about_ca_topic_score_gemma":0.008033517,"teacher_disagreement_score":0.8288881,"about_ca_system_score_codex":0.002438691,"about_ca_system_score_gemma":0.008855318,"threshold_uncertainty_score":0.9967635},"labels":[],"label_agreement":null},{"id":"W4407118209","doi":"","title":"Imagining the future of evaluation","year":2025,"lang":"en","type":"other","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Paul's Hospital; University of British Columbia","funders":"","keywords":"Geography; Computer science","score_opus":0.044626768743320853,"score_gpt":0.37536412253151746,"score_spread":0.33073735378819663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407118209","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017481706,0.0035452694,0.027102461,0.022969006,0.000589896,0.00052010105,0.00004811737,0.00007809681,0.9449722],"genre_scores_gemma":[0.045422625,0.00083541597,0.009717605,0.00031692005,0.00010587929,0.00007228609,0.00015782748,0.00008096852,0.9432905],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9876461,0.008447416,0.00074465777,0.00055997167,0.0023926694,0.0002092022],"domain_scores_gemma":[0.9892222,0.0028177432,0.0010720883,0.002428381,0.0043922,0.000067367495],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.031339884,0.00022366835,0.00034745858,0.00044799,0.00022674966,0.000285976,0.0014974368,0.00018819656,0.011697628],"category_scores_gemma":[0.0036482392,0.00015349106,0.00018612397,0.0010745709,0.00022766416,0.00012738846,0.0003544316,0.00031151733,0.00021377539],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000046968753,0.0001296864,0.0010918027,0.000028704882,0.000057360176,3.219402e-7,0.0030628305,0.000026113932,0.000082276405,0.12066981,0.33161265,0.54323375],"study_design_scores_gemma":[0.00044217898,2.6227474e-7,0.0021813528,0.0006924831,0.00006655228,0.0000017253676,0.0008335063,0.016850773,0.001262971,0.008303326,0.9691736,0.00019123286],"about_ca_topic_score_codex":0.00047789543,"about_ca_topic_score_gemma":0.003082766,"teacher_disagreement_score":0.63756096,"about_ca_system_score_codex":0.00006298375,"about_ca_system_score_gemma":0.0009875337,"threshold_uncertainty_score":0.99743944},"labels":[],"label_agreement":null},{"id":"W4407144531","doi":"10.11124/jbies-24-00291","title":"Textual evidence systematic reviews series paper 1: introduction to the revised JBI methodology and overview of recent changes","year":2025,"lang":"en","type":"article","venue":"JBI Evidence Synthesis","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick; Saint John Regional Hospital; Dalhousie University","funders":"","keywords":"Conceptualization; Systematic review; Management science; Evidence-based practice; Engineering ethics; Data science; Computer science; MEDLINE; Political science; Medicine; Engineering; Alternative medicine; Artificial intelligence","score_opus":0.4163216566033499,"score_gpt":0.5277943959252123,"score_spread":0.11147273932186236,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407144531","genre_codex":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008449957,0.17175342,0.009689836,0.7996535,0.0016884643,0.0075684516,0.000010363448,0.000069334776,0.0011167352],"genre_scores_gemma":[0.22561494,0.70597327,0.028255172,0.020869758,0.0013219229,0.0053314776,0.0000017268086,0.000042277028,0.01258949],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9885412,0.007617896,0.0016024775,0.0006954238,0.0012818886,0.0002611429],"domain_scores_gemma":[0.9708207,0.025768843,0.0008771508,0.0015863023,0.00085744023,0.0000895617],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.048521284,0.00023098534,0.0011211873,0.00033167063,0.00023950846,0.00019265903,0.0009191276,0.00008651187,0.002105591],"category_scores_gemma":[0.19638392,0.00012263088,0.00013027755,0.0017996153,0.0001680646,0.000962131,0.00028644153,0.00013875791,0.00024521947],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031498625,0.000065237975,0.0024495486,0.020480603,0.00013246831,0.0000013883617,0.0031689843,0.00011410584,0.012999379,0.01225325,0.09300868,0.85501134],"study_design_scores_gemma":[0.0001912015,0.00053473096,0.02503156,0.07243987,0.0010619836,0.000049060578,0.011182417,0.0007345188,0.01992867,0.004398249,0.86375755,0.0006901828],"about_ca_topic_score_codex":0.00003601007,"about_ca_topic_score_gemma":0.00035776486,"teacher_disagreement_score":0.8543212,"about_ca_system_score_codex":0.00009658689,"about_ca_system_score_gemma":0.00019406178,"threshold_uncertainty_score":0.9988066},"labels":[],"label_agreement":null},{"id":"W4407180276","doi":"10.11124/jbies-24-00293","title":"Textual evidence systematic reviews series paper 3: critical appraisal of evidence from narrative, opinion, and policy","year":2025,"lang":"en","type":"article","venue":"JBI Evidence Synthesis","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick; Saint John Regional Hospital; Dalhousie University","funders":"","keywords":"Critical appraisal; Conceptualization; Narrative; Evidence-based practice; Systematic review; Empirical evidence; Delphi method; Expert opinion; Legitimacy; Sociology; Political science; Epistemology; Computer science; Linguistics; MEDLINE; Medicine; Law","score_opus":0.23698335469203274,"score_gpt":0.5417262355122717,"score_spread":0.304742880820239,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407180276","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19639225,0.32288897,0.037336152,0.41939482,0.005991975,0.010895742,0.00015969643,0.00042715904,0.00651322],"genre_scores_gemma":[0.97361517,0.019238373,0.004238148,0.00088387006,0.00021762941,0.0006160933,6.8744913e-7,0.000013951692,0.0011760637],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9899204,0.0037689009,0.002554676,0.0009845742,0.0023671356,0.00040433294],"domain_scores_gemma":[0.7956083,0.19866398,0.0012329802,0.0023600117,0.0018167208,0.00031803374],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.015202663,0.00038392315,0.0014657418,0.0005393294,0.00037753218,0.00049414317,0.0013696094,0.00017068259,0.0016851919],"category_scores_gemma":[0.5167724,0.00023493415,0.0002563386,0.0017994628,0.00072974496,0.005012737,0.00041856486,0.00023543263,0.000296142],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022386278,0.00090746826,0.22897325,0.08968569,0.00082361867,0.000033514378,0.07316711,0.00032315715,0.062023293,0.1236421,0.14542787,0.2727543],"study_design_scores_gemma":[0.0005743399,0.0009083987,0.2433897,0.60843056,0.001027549,0.00006695189,0.06766699,0.008110561,0.017145736,0.024417074,0.026122952,0.0021391609],"about_ca_topic_score_codex":0.00039489273,"about_ca_topic_score_gemma":0.000160701,"teacher_disagreement_score":0.77722293,"about_ca_system_score_codex":0.00012422855,"about_ca_system_score_gemma":0.0010003399,"threshold_uncertainty_score":0.9992274},"labels":[],"label_agreement":null},{"id":"W4407219767","doi":"10.3138/9781487552718-008","title":"Chapter Six. Managing Uncertainty in New Brunswick","year":2024,"lang":"en","type":"book-chapter","venue":"University of Toronto Press eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Environmental science","score_opus":0.10803159356567357,"score_gpt":0.34745831581005937,"score_spread":0.2394267222443858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407219767","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000065109794,0.0015557364,0.00014405591,0.00020927613,0.00039240113,0.00029119814,0.000018446995,0.00003908977,0.9972847],"genre_scores_gemma":[0.0038319281,0.0004682416,0.00023678319,0.00006983645,0.00007829479,7.9269675e-8,0.000006794581,0.000019028663,0.995289],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975354,0.000030681225,0.00043227663,0.00057671004,0.0012203245,0.00020460886],"domain_scores_gemma":[0.99852616,0.00016889452,0.0003260684,0.0006432393,0.0001931441,0.0001425214],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007950543,0.000257734,0.00045991718,0.00014640916,0.000075292475,0.00007859281,0.0008952365,0.00021697315,0.0068325126],"category_scores_gemma":[0.000016361988,0.0002527973,0.00023565479,0.0000036879442,0.00013165467,0.0002612598,0.00043404015,0.00026465187,0.00021428453],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000091101436,0.0000072328344,0.000039615144,0.000035012206,0.00007015218,0.00004737976,0.004789539,0.0004144303,0.000005496366,0.9016637,0.005528661,0.08730763],"study_design_scores_gemma":[0.0004189054,0.00005587135,0.0001765945,0.00025083992,0.000059124868,0.0000015985058,0.00024795698,0.0026414227,0.000006031269,0.024532432,0.9713555,0.00025373683],"about_ca_topic_score_codex":0.12753265,"about_ca_topic_score_gemma":0.3467571,"teacher_disagreement_score":0.9658268,"about_ca_system_score_codex":0.00034145662,"about_ca_system_score_gemma":0.000554924,"threshold_uncertainty_score":0.99999243},"labels":[],"label_agreement":null},{"id":"W4407221834","doi":"10.3138/9781487550509-014","title":"CHAPTER ELEVEN Translating Social and Planning Interventions to Increase Self-Identification among Canadian Public Servants","year":2024,"lang":"en","type":"book-chapter","venue":"University of Toronto Press eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Identification (biology); Psychological intervention; Political science; Self identification; Psychology; Public administration; Sociology; Gender studies","score_opus":0.19593911568273525,"score_gpt":0.3792757226735953,"score_spread":0.18333660699086002,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407221834","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0060301544,0.00041352672,0.00031503433,0.00034037288,0.0003061681,0.00047294534,0.00025518122,0.0000534038,0.99181324],"genre_scores_gemma":[0.38248307,0.000021558497,0.00030199613,0.000034255216,0.00007028834,0.000001021209,0.000026911164,0.000017907334,0.617043],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99825174,0.000046268124,0.000406819,0.00043345144,0.0006749835,0.00018675106],"domain_scores_gemma":[0.9987124,0.000074867174,0.0002936048,0.00026814392,0.00037731847,0.00027366073],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009965475,0.00017946321,0.00027934124,0.00021418203,0.0003816908,0.0002089906,0.00046796276,0.00017963264,0.0011394562],"category_scores_gemma":[0.000033648426,0.00019834476,0.00018369053,0.000005449149,0.000083120605,0.0004252198,0.00015627693,0.0001674142,0.00003431279],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000120452365,0.000051827697,0.0027444204,0.00063551933,0.00082680036,0.00010221081,0.14432557,0.00005796708,0.00009454908,0.6465467,0.013057805,0.19143616],"study_design_scores_gemma":[0.00042742625,0.00007279241,0.010583395,0.00063713506,0.00030826984,0.0000029249636,0.0019127538,0.0023336003,0.000010039068,0.0043085557,0.9789174,0.00048569046],"about_ca_topic_score_codex":0.22491167,"about_ca_topic_score_gemma":0.78934234,"teacher_disagreement_score":0.9658596,"about_ca_system_score_codex":0.0002839134,"about_ca_system_score_gemma":0.00020330335,"threshold_uncertainty_score":0.9997736},"labels":[],"label_agreement":null},{"id":"W4407250372","doi":"10.24908/encounters.v25i0.17732","title":"Compliance or Culture Shift: Reflecting on the Impact of Education Inspection on Educational Institutions","year":2024,"lang":"en","type":"article","venue":"Encounters in Theory and History of Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Compliance (psychology); Business; Psychology; Social psychology","score_opus":0.2999912841046896,"score_gpt":0.5661220785693444,"score_spread":0.26613079446465476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407250372","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83668655,0.0019449415,0.000286555,0.0022136134,0.0065343017,0.00036837888,0.0000115439825,0.000020912426,0.1519332],"genre_scores_gemma":[0.9908331,0.00006974554,0.00007971728,0.00029547652,0.00016587482,0.000056039,0.000012348133,0.0000052509577,0.008482433],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985185,0.00031882056,0.00041695594,0.00024902358,0.00041576865,0.00008090652],"domain_scores_gemma":[0.99811316,0.0011779036,0.00022481818,0.00026462565,0.00018631818,0.000033174234],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0026920207,0.00010524476,0.00012938448,0.00048579613,0.00013381356,0.000042491898,0.00019680132,0.000050847615,0.0010502695],"category_scores_gemma":[0.0010068526,0.00006224034,0.00006949922,0.00050198525,0.00023374222,0.00035993004,0.000011820475,0.0001988855,0.000035895442],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035347507,0.0008162002,0.0026911611,0.000056362318,0.0000237427,8.835668e-8,0.04558897,0.00090789684,0.00064297835,0.85780454,0.06059941,0.030515188],"study_design_scores_gemma":[0.00041862603,0.0015337478,0.24568425,0.0030203445,0.00005017989,0.000023855533,0.0393731,0.0028120787,0.00038078666,0.6006231,0.10561396,0.00046599505],"about_ca_topic_score_codex":0.00011068679,"about_ca_topic_score_gemma":0.00009995615,"teacher_disagreement_score":0.25718147,"about_ca_system_score_codex":0.0012348302,"about_ca_system_score_gemma":0.0048514092,"threshold_uncertainty_score":0.9998629},"labels":[],"label_agreement":null},{"id":"W4407319717","doi":"10.31224/4360","title":"Leveraging Order-Theoretic Tournament Graphs for Assessing Internal Consistency in Survey-Based Instruments Across Diverse Scenarios","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Alliance de recherche numérique du Canada; Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Tournament; Consistency (knowledge bases); Order (exchange); Internal consistency; Computer science; Econometrics; Data science; Mathematics; Information retrieval; Business; Statistics; Artificial intelligence; Combinatorics","score_opus":0.24539874522722965,"score_gpt":0.5055707140056989,"score_spread":0.2601719687784692,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407319717","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86305195,0.000043883836,0.124763,0.001295072,0.003250051,0.0013592487,0.00023397295,0.00005193575,0.0059508723],"genre_scores_gemma":[0.9810388,0.000025927364,0.014825285,0.0015469755,0.000031063188,0.0001652572,0.00013761099,0.000015282445,0.0022137894],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99325264,0.00095128105,0.0018731449,0.0011779519,0.0021322975,0.00061266654],"domain_scores_gemma":[0.99435335,0.0022053616,0.0008680519,0.0009835865,0.0014388032,0.00015084763],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016073816,0.00044952155,0.00079051446,0.00084924145,0.00040159532,0.0018503148,0.0014927057,0.00027370002,0.0017773005],"category_scores_gemma":[0.0028321142,0.00035903533,0.00032754397,0.0007360463,0.00020194832,0.00039288343,0.001267971,0.00072744663,0.000036009027],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016482333,0.00027940696,0.8626864,0.00013149504,0.00007368328,0.0000056582917,0.002256428,0.017833509,0.000009440755,0.0011896434,0.0013057349,0.114063784],"study_design_scores_gemma":[0.0056305546,0.00012071776,0.31584027,0.0017161987,0.00006389801,0.0000027834926,0.00943639,0.57836115,0.00031460624,0.085344166,0.0021525885,0.0010166562],"about_ca_topic_score_codex":0.0013693227,"about_ca_topic_score_gemma":0.0032210413,"teacher_disagreement_score":0.5605277,"about_ca_system_score_codex":0.0005568457,"about_ca_system_score_gemma":0.0024794978,"threshold_uncertainty_score":0.99988616},"labels":[],"label_agreement":null},{"id":"W4407364769","doi":"10.36227/techrxiv.173933234.41986222/v1","title":"Leveraging Order-Theoretic Tournament Graphs for Assessing Internal Consistency in Survey-Based Instruments Across Diverse Scenarios","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Tournament; Consistency (knowledge bases); Order (exchange); Internal consistency; Computer science; Data science; Econometrics; Mathematics; Business; Statistics; Artificial intelligence; Combinatorics","score_opus":0.24539874522722965,"score_gpt":0.5055707140056989,"score_spread":0.2601719687784692,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407364769","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86305195,0.000043883836,0.124763,0.001295072,0.003250051,0.0013592487,0.00023397295,0.00005193575,0.0059508723],"genre_scores_gemma":[0.9810388,0.000025927364,0.014825285,0.0015469755,0.000031063188,0.0001652572,0.00013761099,0.000015282445,0.0022137894],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99325264,0.00095128105,0.0018731449,0.0011779519,0.0021322975,0.00061266654],"domain_scores_gemma":[0.99435335,0.0022053616,0.0008680519,0.0009835865,0.0014388032,0.00015084763],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016073816,0.00044952155,0.00079051446,0.00084924145,0.00040159532,0.0018503148,0.0014927057,0.00027370002,0.0017773005],"category_scores_gemma":[0.0028321142,0.00035903533,0.00032754397,0.0007360463,0.00020194832,0.00039288343,0.001267971,0.00072744663,0.000036009027],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016482333,0.00027940696,0.8626864,0.00013149504,0.00007368328,0.0000056582917,0.002256428,0.017833509,0.000009440755,0.0011896434,0.0013057349,0.114063784],"study_design_scores_gemma":[0.0056305546,0.00012071776,0.31584027,0.0017161987,0.00006389801,0.0000027834926,0.00943639,0.57836115,0.00031460624,0.085344166,0.0021525885,0.0010166562],"about_ca_topic_score_codex":0.0013693227,"about_ca_topic_score_gemma":0.0032210413,"teacher_disagreement_score":0.5605277,"about_ca_system_score_codex":0.0005568457,"about_ca_system_score_gemma":0.0024794978,"threshold_uncertainty_score":0.99988616},"labels":[],"label_agreement":null},{"id":"W4407549570","doi":"10.61846/cuji-ssh.2024.4.03","title":"ENHANCING TEACHING IN HIGHER EDUCATION – EVALUATION","year":2024,"lang":"en","type":"article","venue":"Cluj University Journal Interdisciplinary Social Sciences and Humanities","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mathematics education; Computer science; Psychology","score_opus":0.3229862630766537,"score_gpt":0.5124865417504545,"score_spread":0.18950027867380081,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407549570","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7646157,0.00062433624,0.00013992522,0.008608844,0.001954901,0.00009665933,0.000002395797,0.00001912637,0.22393812],"genre_scores_gemma":[0.98277897,0.000033368466,0.00010766232,0.00014408697,0.0004550136,6.0033415e-7,0.0000014635166,0.0000027306276,0.01647612],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9979781,0.00037797823,0.00027522678,0.00023909348,0.0009660883,0.00016352767],"domain_scores_gemma":[0.9994289,0.00023727264,0.00010653909,0.000050644172,0.00013822723,0.000038383972],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006673157,0.0000842416,0.00012224936,0.0007036522,0.0024135928,0.0012395293,0.0003309995,0.0000429167,0.0020264876],"category_scores_gemma":[0.00003714088,0.000066776076,0.00006899525,0.00038021797,0.00030251514,0.0020327708,0.00026007174,0.00030518218,0.000022576342],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004378341,0.00013517276,0.0051681586,0.00003216141,0.00002933396,0.000030344008,0.15980113,0.00025576007,0.00030201595,0.55568796,0.018701509,0.25981265],"study_design_scores_gemma":[0.00033388907,0.00029742328,0.082702644,0.0003356661,0.000049253606,0.000059755726,0.47543117,0.012355493,0.000011014034,0.29808846,0.13002045,0.00031476788],"about_ca_topic_score_codex":0.000021680858,"about_ca_topic_score_gemma":0.00072497816,"teacher_disagreement_score":0.31563005,"about_ca_system_score_codex":0.00032659908,"about_ca_system_score_gemma":0.000507723,"threshold_uncertainty_score":0.9997973},"labels":[],"label_agreement":null},{"id":"W4407739843","doi":"10.55016/ojs/tsw.v2i2.78262","title":"Methodological reflections on research with racialized communities and stigmatized topics: Towards a model of transformative engagement","year":2025,"lang":"en","type":"article","venue":"Transformative Social Work","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary; University of Toronto","funders":"Movember Foundation","keywords":"Transformative learning; Sociology; Gender studies; Pedagogy","score_opus":0.850797175823737,"score_gpt":0.6592754659845275,"score_spread":0.19152170983920958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407739843","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24590455,0.00006729102,0.47939146,0.017313689,0.00012391634,0.0013396639,0.00006640733,0.000058602644,0.25573444],"genre_scores_gemma":[0.98857164,0.0001343182,0.009629869,0.00042938473,0.000020526219,0.00019282829,0.000008574687,0.000005799585,0.0010070456],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9931276,0.0040677222,0.0007731202,0.000183354,0.0015579681,0.00029027095],"domain_scores_gemma":[0.99592596,0.002850181,0.00014517376,0.00021509304,0.00080726173,0.000056308043],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.013856019,0.00017623809,0.00055055815,0.00052316004,0.0016618556,0.00013271254,0.0003894727,0.00011962662,0.0003897295],"category_scores_gemma":[0.00033545896,0.00011392271,0.00011737092,0.0019132057,0.00071903795,0.00041173253,0.000044840745,0.00069723406,0.000010644682],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026521,0.0002772552,0.00043468215,0.000094295596,0.00023185572,3.2803177e-7,0.49644226,0.0024462251,0.00017131287,0.36212856,0.00090593466,0.13421522],"study_design_scores_gemma":[0.009074138,0.0017514561,0.031390123,0.0005724447,0.00016196906,9.670293e-7,0.5016936,0.018550718,0.0073032333,0.40328,0.025548233,0.0006731447],"about_ca_topic_score_codex":0.000033816774,"about_ca_topic_score_gemma":0.00016504036,"teacher_disagreement_score":0.7426671,"about_ca_system_score_codex":0.00009386342,"about_ca_system_score_gemma":0.00034928333,"threshold_uncertainty_score":0.99963784},"labels":[],"label_agreement":null},{"id":"W4407740827","doi":"10.14430/arctic80841","title":"Reshaping Research Paradigms: Insights from a Large-Scale Project Based in Nunatsiavut, Labrador, Canada","year":2025,"lang":"en","type":"article","venue":"ARCTIC","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Scale (ratio); Geography; Environmental resource management; Regional science; Oceanography; Geology; Physical geography; Environmental science; Cartography","score_opus":0.20441224442464392,"score_gpt":0.5041129584870293,"score_spread":0.2997007140623854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407740827","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9748343,0.0006743926,0.00024454528,0.006126403,0.00040823896,0.00051911344,0.000028081236,0.000020484373,0.017144416],"genre_scores_gemma":[0.99574846,0.000013112069,0.00045297047,0.002045944,0.000036026704,0.000074671494,0.000020279027,0.000006502305,0.0016020274],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9955345,0.00088061794,0.00054800615,0.0005124141,0.002129709,0.0003947967],"domain_scores_gemma":[0.9961085,0.0026507378,0.00008043063,0.0006616233,0.0004272013,0.0000715346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036569259,0.000116420364,0.00023131078,0.00073512306,0.00026162344,0.00019279272,0.0006351991,0.000062091654,0.0009027068],"category_scores_gemma":[0.0015879701,0.000086565415,0.000052285603,0.002911209,0.00007363339,0.00026058513,0.00013119576,0.0003943361,0.000102120124],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026387337,0.00046971792,0.8344904,0.00004974688,0.000056082674,0.00008494719,0.0059085265,0.0030786055,0.0004102488,0.009500122,0.12462828,0.02105945],"study_design_scores_gemma":[0.0015475771,0.000064971726,0.48673823,0.0002475426,0.0000071392433,5.144873e-7,0.004031057,0.22075377,0.00044118124,0.023758102,0.26220858,0.00020132192],"about_ca_topic_score_codex":0.6995588,"about_ca_topic_score_gemma":0.9588399,"teacher_disagreement_score":0.34775215,"about_ca_system_score_codex":0.00065385946,"about_ca_system_score_gemma":0.00554577,"threshold_uncertainty_score":0.98840064},"labels":[],"label_agreement":null},{"id":"W4407775247","doi":"10.1017/ehs.2025.3","title":"Construct validity in cross-cultural, developmental research: challenges and strategies for improvement","year":2025,"lang":"en","type":"article","venue":"Evolutionary Human Sciences","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Economic and Social Research Council","keywords":"Construct validity; Construct (python library); Psychology; External validity; Computer science; Developmental psychology; Social psychology; Psychometrics","score_opus":0.6656248021872823,"score_gpt":0.6127833348367184,"score_spread":0.05284146735056383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407775247","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9333614,0.0013072469,0.00007898975,0.00216857,0.00026913852,0.00042668526,0.000010797578,0.00001854959,0.062358588],"genre_scores_gemma":[0.9955984,0.0002311383,0.0023850163,0.000097018106,0.000039799823,0.00011574938,0.0000035848375,0.0000019086813,0.0015274205],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99673885,0.00022908075,0.00054868433,0.00061634154,0.0015060992,0.00036091654],"domain_scores_gemma":[0.9979282,0.0010882985,0.00009864555,0.0001584601,0.0006701416,0.000056248187],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.01138155,0.00011428217,0.0001745174,0.0005983365,0.0014863851,0.0007035643,0.0006164002,0.000054583787,0.00024964253],"category_scores_gemma":[0.0007751474,0.00008116222,0.000038761435,0.0007610813,0.0020976437,0.0017162302,0.00024373292,0.00013196797,0.00001948163],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036593803,0.00013113346,0.102983356,0.000041165666,0.000010873155,0.0000012677244,0.0039602485,0.00023157171,0.0022722215,0.8451395,0.011580255,0.033611808],"study_design_scores_gemma":[0.00047687907,0.00023229288,0.48707297,0.000036476285,0.000001413482,0.0000027296185,0.042327512,0.001602402,0.00016887492,0.45433804,0.013622409,0.00011799803],"about_ca_topic_score_codex":0.000040632498,"about_ca_topic_score_gemma":0.0005945861,"teacher_disagreement_score":0.39080146,"about_ca_system_score_codex":0.00017785084,"about_ca_system_score_gemma":0.0011238768,"threshold_uncertainty_score":0.99981356},"labels":[],"label_agreement":null},{"id":"W4407808295","doi":"10.1080/1034912x.2025.2467355","title":"Perceived Training Needs of Municipal Stakeholders in Quebec (Canada) Relating to Universal Design Action Plans","year":2025,"lang":"en","type":"article","venue":"International Journal of Disability Development and Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Centre intégré de santé et de services sociaux de la Montérégie-Centre; Centre intégré de santé et de services sociaux de Chaudière-Appalaches; Centre Intégré de Santé et de Services Sociaux des Laurentides; Cegep de Victoriaville; Université Laval; Université de Montréal; Centre for Interdisciplinary Research in Rehabilitation","funders":"Fonds de recherche du Québec","keywords":"Psychology; Training (meteorology); Action (physics); Applied psychology; Needs assessment; Public relations; Medical education; Sociology; Political science; Social science","score_opus":0.30520082076530247,"score_gpt":0.4550722005048611,"score_spread":0.1498713797395586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407808295","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9893818,0.00000964111,0.0031953692,0.004884786,0.0009876998,0.00009995991,0.0000011739837,0.0000016906863,0.0014378815],"genre_scores_gemma":[0.995575,0.0000057604366,0.0033063428,0.00016406144,0.000034622903,0.0000030917993,0.0000037777731,0.0000018590663,0.00090546964],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99805444,0.00014552202,0.00077798805,0.000094987336,0.0008453663,0.0000816742],"domain_scores_gemma":[0.99845535,0.00054182817,0.00030046713,0.00007785342,0.0005686461,0.000055834465],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002162717,0.00006720861,0.00014645988,0.0004347166,0.00005057559,0.00006612757,0.000275963,0.000030962972,0.000094970645],"category_scores_gemma":[0.0009195047,0.00005802402,0.000026279584,0.00037695764,0.000043285014,0.00042157996,0.000032366053,0.00010728411,7.69901e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021034894,0.00017244497,0.41177636,0.000008107719,0.000047232003,4.0028792e-7,0.04906428,0.006086536,0.0004911651,0.00080353895,0.00089743285,0.5304421],"study_design_scores_gemma":[0.0003463105,0.00002180497,0.82952005,0.00013501047,0.000005771412,0.0000017296319,0.16390206,0.000924578,0.0003273126,0.00094521506,0.003809778,0.00006040314],"about_ca_topic_score_codex":0.022014132,"about_ca_topic_score_gemma":0.3846574,"teacher_disagreement_score":0.53038174,"about_ca_system_score_codex":0.00089408143,"about_ca_system_score_gemma":0.0042358725,"threshold_uncertainty_score":0.9844984},"labels":[],"label_agreement":null},{"id":"W4407872184","doi":"10.2139/ssrn.5121870","title":"FEDERAL IMPACT ASSESSMENT FRAMEWORK: A REVIEW OF THE TRENDS AND LEGISLATIVE CHANGES POST RE REFERENCE IMPACT ASSESSMENT ACT","year":2025,"lang":"en","type":"review","venue":"SSRN Electronic Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Legislature; Impact assessment; Political science; Public administration; Environmental planning; Geography; Law","score_opus":0.1587386150199439,"score_gpt":0.5710385782137053,"score_spread":0.4122999631937614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407872184","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004260057,0.9820786,0.0007127877,0.004030939,0.00041389503,0.0008615128,0.00013005409,0.000014971821,0.011714612],"genre_scores_gemma":[0.002598689,0.9922999,0.00023265295,0.00036625363,0.00026376065,0.00007085315,0.0000588692,0.00003509278,0.0040739295],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98849636,0.0030257297,0.0021740461,0.0008004322,0.003412883,0.0020905617],"domain_scores_gemma":[0.9913665,0.0022516658,0.0037496565,0.0012695836,0.0011340898,0.00022851967],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.020935604,0.0008491859,0.0029428413,0.0009356702,0.00065912184,0.0005694273,0.0020464521,0.00040849333,0.0021616141],"category_scores_gemma":[0.001506978,0.00040112538,0.0016110343,0.0025682144,0.00016204924,0.0005143945,0.00047683163,0.0064073848,0.000012095079],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000011740747,0.000060613136,0.0004738422,0.002701341,0.00064928824,0.0000012742505,0.00009905817,0.0000034527254,2.8133994e-7,0.0064685605,0.001044159,0.9884864],"study_design_scores_gemma":[0.00089615176,0.003139054,0.010542547,0.1918909,0.002276643,0.00075039285,0.0010482265,0.00014320984,4.1218743e-7,0.040991526,0.7470579,0.0012629997],"about_ca_topic_score_codex":0.000095555435,"about_ca_topic_score_gemma":0.0009302365,"teacher_disagreement_score":0.9872234,"about_ca_system_score_codex":0.004104429,"about_ca_system_score_gemma":0.04303132,"threshold_uncertainty_score":0.9998441},"labels":[],"label_agreement":null},{"id":"W4408043693","doi":"10.56240/irafpa.cm.v2n1/job","title":"Définir et surtout décider les rôles des divers gardiensde l’intégrité académique","year":2024,"lang":"fr","type":"article","venue":"Les Cahiers de l’IRAFPA","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École Nationale d'Administration Publique","funders":"","keywords":"Art; Philosophy; Humanities","score_opus":0.1123576873664932,"score_gpt":0.442736907226868,"score_spread":0.3303792198603748,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408043693","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75450236,0.036694854,0.026429148,0.041360095,0.0058869272,0.0007071282,0.0003649895,0.00044968352,0.1336048],"genre_scores_gemma":[0.8383235,0.011503336,0.009128911,0.004057736,0.00072795356,0.000065992695,0.000056335415,0.000091521644,0.13604471],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99332356,0.0014432425,0.0010761928,0.0011295668,0.0018637364,0.0011636723],"domain_scores_gemma":[0.9948762,0.0031790491,0.00022620313,0.0007511065,0.00044603483,0.0005214226],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.007599812,0.00059805927,0.00062901067,0.00064101146,0.0010022224,0.0015645709,0.0010387723,0.0009239061,0.009166645],"category_scores_gemma":[0.0014668505,0.0005191139,0.0005694372,0.0013347336,0.002291412,0.0014716755,0.00028776514,0.001832558,0.0026000629],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008888015,0.0001598053,0.03271594,0.000385914,0.0003381422,0.00034669982,0.022018827,0.0035972106,0.0010803535,0.14372365,0.083258234,0.71228635],"study_design_scores_gemma":[0.00068646134,0.000274649,0.028796962,0.0008984565,0.00022786434,0.00017653577,0.013920161,0.020253861,0.002335745,0.04319275,0.8883551,0.0008814955],"about_ca_topic_score_codex":0.000684923,"about_ca_topic_score_gemma":0.0017225154,"teacher_disagreement_score":0.8050968,"about_ca_system_score_codex":0.0010128261,"about_ca_system_score_gemma":0.0011806898,"threshold_uncertainty_score":0.99972606},"labels":[],"label_agreement":null},{"id":"W4408060850","doi":"10.1145/3717075","title":"THINKING ISSUES: A Path Backward and Forward: A New Chapter for <i>Inroads</i>","year":2025,"lang":"en","type":"article","venue":"ACM Inroads","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Royal University","funders":"","keywords":"Path (computing); Computational thinking; Computer science; Engineering ethics; Management science; Artificial intelligence; Programming language; Economics; Engineering","score_opus":0.12842560138784692,"score_gpt":0.483553675463802,"score_spread":0.3551280740759551,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408060850","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4581503,0.004792113,0.13912426,0.22850326,0.0048339213,0.0037043395,0.000076924625,0.00043669893,0.1603782],"genre_scores_gemma":[0.86430997,0.00037977172,0.0464954,0.022066493,0.00032295226,0.00013383056,0.000016807837,0.000028028455,0.066246726],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99760467,0.000055702567,0.0005497052,0.0004908192,0.0010158449,0.00028328566],"domain_scores_gemma":[0.99769056,0.0008820149,0.00015484246,0.0008751814,0.0002769561,0.00012044466],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029470695,0.00018034292,0.0003241883,0.00024946564,0.0002747174,0.00043862857,0.0009290471,0.00010092672,0.0007493144],"category_scores_gemma":[0.0019510973,0.00012840216,0.00012376385,0.00038563117,0.00005900026,0.00045643098,0.000399209,0.00012126325,0.00016735937],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010770259,0.00006439896,0.069724254,0.000027508537,0.00008543295,0.0000019102363,0.004872784,0.000054477787,0.0003329717,0.13763085,0.2543967,0.532701],"study_design_scores_gemma":[0.0010648544,0.00011723767,0.014502147,0.000050315928,0.00002746435,0.0000018253398,0.0006518776,0.0028387255,0.00038945663,0.2905507,0.6896369,0.00016848477],"about_ca_topic_score_codex":0.000053970507,"about_ca_topic_score_gemma":0.00007349855,"teacher_disagreement_score":0.5325325,"about_ca_system_score_codex":0.000029574909,"about_ca_system_score_gemma":0.00022132447,"threshold_uncertainty_score":0.82044667},"labels":[],"label_agreement":null},{"id":"W4408118815","doi":"10.30834/kjp.37.2.2024.494","title":"Reporting of ‘Ethical Considerations’ in Research Papers: The Essentials","year":2024,"lang":"en","type":"article","venue":"Kerala Journal of Psychiatry","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Thomas Hospital","funders":"","keywords":"Engineering ethics; Management science; Psychology; Computer science; Engineering","score_opus":0.501245057885095,"score_gpt":0.6311568746478656,"score_spread":0.12991181676277064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408118815","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7201177,0.0035945384,0.0002940991,0.25734347,0.0039945035,0.00016549084,0.0000020246384,0.000006611116,0.014481582],"genre_scores_gemma":[0.99567884,0.00007978171,0.0028904,0.0006153895,0.00038401884,0.0000022998481,2.2031664e-7,0.0000051732573,0.00034386336],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9925797,0.0010292968,0.0035123285,0.00015974557,0.0025550313,0.0001639054],"domain_scores_gemma":[0.99419326,0.0031596746,0.0013228668,0.0002835345,0.0009842437,0.00005642786],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.059063043,0.00006373786,0.00026890766,0.00051016,0.00013921606,0.00032587652,0.0003005759,0.00009311141,0.002251015],"category_scores_gemma":[0.010031152,0.00003341863,0.00016612824,0.00092446525,0.0001489027,0.00026087346,0.00004618454,0.001115482,0.00003582053],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009268974,0.0002713656,0.32693666,0.00010854169,0.00014325725,0.0001293967,0.008021685,0.0029754979,0.00807165,0.35006952,0.27955702,0.023622721],"study_design_scores_gemma":[0.0005974768,0.00027811053,0.1663301,0.00082454435,0.000029345954,0.0005690854,0.010251373,0.0032625874,0.000856796,0.7942081,0.02266267,0.00012982909],"about_ca_topic_score_codex":0.000011477851,"about_ca_topic_score_gemma":0.00017399083,"teacher_disagreement_score":0.44413856,"about_ca_system_score_codex":0.000030420342,"about_ca_system_score_gemma":0.0018708352,"threshold_uncertainty_score":0.99866104},"labels":[],"label_agreement":null},{"id":"W4408128150","doi":"10.7202/1116750ar","title":"Le rôle et l’expansion des instruments d’action publique dans la transformation des systèmes éducatifs pour atteindre l’excellence et l’équité : une analyse historique en Ontario de 1993-2017","year":2025,"lang":"fr","type":"article","venue":"Canadian Journal of Educational Administration and Policy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.07095049806914625,"score_gpt":0.42802333384105884,"score_spread":0.3570728357719126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408128150","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6874519,0.0005049219,0.0015490683,0.2734497,0.00077095465,0.00017341957,0.000047044112,0.0000034523534,0.036049582],"genre_scores_gemma":[0.97086245,0.00051852374,0.0014352335,0.0017448439,0.0003228836,0.000019645944,0.000067492634,0.000010929115,0.025017986],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.996923,0.0009205029,0.0010491065,0.00025645446,0.000497379,0.00035351186],"domain_scores_gemma":[0.9969049,0.0005847981,0.0006097155,0.00021319778,0.0009884905,0.00069888186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003226866,0.0002405453,0.00029336615,0.0012511521,0.00077133585,0.00067766104,0.00036036735,0.00022830266,0.00047772875],"category_scores_gemma":[0.001129139,0.00024506808,0.00014249119,0.00092479883,0.00035869828,0.0023419398,0.000013236367,0.00048044935,0.00001637332],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00007813589,0.00036446445,0.13382716,0.00018043094,0.00012098822,0.000007554172,0.12136887,0.0006853576,0.000679931,0.69843507,0.011475889,0.032776173],"study_design_scores_gemma":[0.00080753333,0.0002966679,0.6438626,0.00069094985,0.000102890066,0.0007715175,0.03315683,0.00040218176,0.00065310596,0.14328738,0.17567039,0.00029796592],"about_ca_topic_score_codex":0.32189253,"about_ca_topic_score_gemma":0.9186336,"teacher_disagreement_score":0.596741,"about_ca_system_score_codex":0.004041733,"about_ca_system_score_gemma":0.16924672,"threshold_uncertainty_score":0.99978155},"labels":[],"label_agreement":null},{"id":"W4408158826","doi":"10.3389/feduc.2025.1423832","title":"Navigating barriers and pathways in capacity development for knowledge mobilization: perspectives from McGill University’s Faculty of Education","year":2025,"lang":"en","type":"article","venue":"Frontiers in Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University","funders":"","keywords":"Mobilization; Knowledge management; Engineering ethics; Sociology; Political science; Engineering management; Medical education; Engineering; Pedagogy; Computer science; Medicine","score_opus":0.08589789874954618,"score_gpt":0.42242424906425274,"score_spread":0.33652635031470657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408158826","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9851575,0.0005377466,0.009741582,0.00046108253,0.0012958451,0.00047727785,0.00005393465,0.000008044108,0.0022669984],"genre_scores_gemma":[0.9475511,0.000047180314,0.05148682,0.000053473632,0.000020856562,0.00004262745,0.000065588196,0.0000035376945,0.0007288357],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9988186,0.00014422688,0.00038977718,0.00032507896,0.0002211482,0.00010120043],"domain_scores_gemma":[0.99890137,0.00020366552,0.00017665765,0.00016095104,0.00050927355,0.000048063885],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011119223,0.000086849665,0.00017373892,0.00032176657,0.00013885372,0.000021542151,0.0001833196,0.00006694917,0.000036266072],"category_scores_gemma":[0.0009666042,0.00008815957,0.000025520416,0.0008493463,0.000054719076,0.0003550366,0.000033778797,0.000094513984,0.0000012900431],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045685378,0.00037843455,0.39949968,0.000041675095,0.000015254192,2.4565855e-8,0.06516237,0.00028716415,0.0001959573,0.006216761,0.0069373017,0.5212197],"study_design_scores_gemma":[0.00077035575,0.00002721597,0.3319369,0.00032153164,0.000013454391,1.3754664e-7,0.57098085,0.007397215,0.0018898485,0.03013999,0.056340687,0.00018178485],"about_ca_topic_score_codex":0.00016919505,"about_ca_topic_score_gemma":0.00043678482,"teacher_disagreement_score":0.52103794,"about_ca_system_score_codex":0.00080639607,"about_ca_system_score_gemma":0.0020805248,"threshold_uncertainty_score":0.36907616},"labels":[],"label_agreement":null},{"id":"W4408301688","doi":"10.1016/j.jneb.2025.01.007","title":"Thinking Through How Best to Evaluate What We Do","year":2025,"lang":"en","type":"editorial","venue":"Journal of Nutrition Education and Behavior","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology","score_opus":0.1268587701587347,"score_gpt":0.5157613236038529,"score_spread":0.38890255344511815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408301688","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010940459,0.007181817,0.0003617847,0.03601507,0.9442867,0.00068958994,0.000045876644,0.000010961074,0.0004677356],"genre_scores_gemma":[0.006472696,0.05130213,0.015544444,0.0019410857,0.89727664,0.0004990257,0.00016117659,0.00004615533,0.026756642],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9931319,0.00037942707,0.0012120631,0.00040664812,0.004665583,0.00020442814],"domain_scores_gemma":[0.99126834,0.0011483599,0.0014134884,0.00040307926,0.005556647,0.00021010164],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0047909645,0.00027257128,0.00059407885,0.0010049408,0.00029228334,0.00346815,0.00077242276,0.0004217029,0.0007739685],"category_scores_gemma":[0.0021302681,0.00020798823,0.00024238645,0.0007666047,0.000050117957,0.0025674095,0.00009865197,0.0007612876,0.00007284664],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024047446,0.0020191057,0.00010792668,0.000053219712,0.000013045557,0.0000018506104,0.0013071136,0.0000021346107,0.000035590107,0.00006362423,0.8453277,0.1510447],"study_design_scores_gemma":[0.00081177376,0.00038256406,0.00054323516,0.0022377858,0.00034143776,0.000021530837,0.020338796,0.00000451968,0.000065565066,0.004197775,0.970842,0.00021300855],"about_ca_topic_score_codex":0.000006420808,"about_ca_topic_score_gemma":0.000015563757,"teacher_disagreement_score":0.15083168,"about_ca_system_score_codex":0.00029688963,"about_ca_system_score_gemma":0.0027743024,"threshold_uncertainty_score":0.99756634},"labels":[],"label_agreement":null},{"id":"W4408366806","doi":"10.1007/978-3-031-82775-4_8","title":"Connecting to Decision-Making","year":2025,"lang":"en","type":"book-chapter","venue":"Natural resource management and policy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Computer science","score_opus":0.06967104212010684,"score_gpt":0.4596391552660249,"score_spread":0.38996811314591806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408366806","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004539036,0.0009757035,0.0006262593,0.0051659285,0.00037406123,0.0005264938,0.000014733032,0.00005974126,0.99180317],"genre_scores_gemma":[0.07566542,0.00015405193,0.0027180875,0.007177564,0.0004692464,0.000009172377,0.000011082671,0.000023959663,0.9137714],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964032,0.000043020624,0.0007046298,0.0007202968,0.0018034072,0.00032541668],"domain_scores_gemma":[0.9971434,0.0015392322,0.00028935343,0.00067493616,0.0002195828,0.00013351334],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017771923,0.00033868602,0.00042673643,0.0019036033,0.00037336722,0.00058411114,0.00077049853,0.00017565885,0.001370977],"category_scores_gemma":[0.0012413012,0.00025886262,0.00016344771,0.00040443908,0.00003274066,0.00011573825,0.0010760308,0.00040669163,0.00060424185],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035873763,0.000002233531,0.000016048258,0.000016172005,0.000034837292,0.000006067604,0.0001755035,0.00006776153,2.466529e-7,0.27178684,0.058932252,0.6689262],"study_design_scores_gemma":[0.00020400835,0.00003201645,0.00045218348,0.00051574776,0.000037082107,0.0000026706327,0.0002447162,0.00078201835,6.667868e-7,0.085587084,0.9118846,0.00025721084],"about_ca_topic_score_codex":0.00000970668,"about_ca_topic_score_gemma":0.000057842477,"teacher_disagreement_score":0.85295236,"about_ca_system_score_codex":0.00015317604,"about_ca_system_score_gemma":0.0000813622,"threshold_uncertainty_score":0.99998635},"labels":[],"label_agreement":null},{"id":"W4408427063","doi":"10.5194/egusphere-egu25-11024","title":"Skill assessment of a multi-system ensemble of initialized 20-year predictions","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Environment and Climate Change Canada","funders":"","keywords":"Computer science; Statistics; Artificial intelligence; Econometrics; Mathematics","score_opus":0.2566147092626727,"score_gpt":0.5422345913921873,"score_spread":0.2856198821295146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408427063","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028938012,0.00009372741,0.4291942,0.00057554746,0.003032149,0.0016701253,0.0010645138,0.00013552888,0.5352962],"genre_scores_gemma":[0.9329362,0.00006453693,0.04929769,0.00006397603,0.000058829766,0.00014687235,0.00007150936,0.000009135988,0.01735128],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9937866,0.0005942148,0.0021820813,0.000623906,0.0026091398,0.00020406778],"domain_scores_gemma":[0.994151,0.00096707116,0.0012903883,0.0014223179,0.00207296,0.00009627207],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0053046835,0.0002526984,0.00093785353,0.00081060507,0.00009112685,0.00009210982,0.0009996406,0.00029669737,0.0026823413],"category_scores_gemma":[0.0005457422,0.00018837606,0.00039410676,0.00068157964,0.00010392144,0.00014440363,0.0009232975,0.00037974495,0.000044901924],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035738343,0.0048217652,0.23242152,0.003987926,0.0020519271,0.00001010975,0.008910429,0.35176483,0.0024691182,0.2702535,0.084892966,0.03805853],"study_design_scores_gemma":[0.0031495201,0.00022942494,0.057246394,0.0011103277,0.00024105317,0.000002710276,0.008469484,0.9140358,0.002367227,0.003238059,0.00947348,0.00043653644],"about_ca_topic_score_codex":0.00024286174,"about_ca_topic_score_gemma":0.00026444322,"teacher_disagreement_score":0.90399814,"about_ca_system_score_codex":0.00017017352,"about_ca_system_score_gemma":0.002411313,"threshold_uncertainty_score":0.9982293},"labels":[],"label_agreement":null},{"id":"W4408470784","doi":"10.21083/ruralreview.v7i1.7393","title":"Climate Change and Education in Canada: A Critical Discourse Analysis of 3 Provinces","year":2023,"lang":"en","type":"article","venue":"Rural Review Ontario Rural Planning Development and Policy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Climate change; Critical discourse analysis; Political science; Geography; Ecology; Politics; Biology","score_opus":0.16094470767117353,"score_gpt":0.49440022925378846,"score_spread":0.33345552158261493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408470784","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9879251,0.005237355,0.000001428321,0.005661086,0.00009762771,0.00026748673,0.000009735616,0.0000073591273,0.0007928337],"genre_scores_gemma":[0.9931944,0.0046903216,0.00016839821,0.0012031369,0.000034623612,0.00006244851,0.000083879444,0.000003704831,0.00055909815],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99815845,0.00008249612,0.0006670146,0.00017775528,0.0006521829,0.00026208654],"domain_scores_gemma":[0.9992071,0.0002869545,0.00017030783,0.00012984028,0.0000942773,0.00011156524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015301725,0.00012804403,0.00044909472,0.00058017037,0.00010675229,0.00005833964,0.00014351784,0.000023920944,0.00013032352],"category_scores_gemma":[0.00034241166,0.00008803845,0.000036402147,0.001501878,0.000043774395,0.00031338396,0.00007422709,0.00009165678,0.000010885839],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000065146924,0.000008719255,0.7203004,0.000120867175,0.00002140199,0.0000015124638,0.0039539137,0.000005773776,0.000002045565,0.00096521416,0.00093384297,0.27367985],"study_design_scores_gemma":[0.000080577374,0.00001327875,0.9882333,0.0011287973,0.000068241236,0.0000019655668,0.0029393134,0.0003976687,0.000003842613,0.000198325,0.006815573,0.000119078824],"about_ca_topic_score_codex":0.70442533,"about_ca_topic_score_gemma":0.954619,"teacher_disagreement_score":0.27356076,"about_ca_system_score_codex":0.0003315668,"about_ca_system_score_gemma":0.0049099573,"threshold_uncertainty_score":0.87100536},"labels":[],"label_agreement":null},{"id":"W4408483538","doi":"10.1177/20597991251325470","title":"The implications of a mixed methods way of thinking to practice","year":2025,"lang":"en","type":"article","venue":"Methodological Innovations","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Psychology; Computer science; Epistemology; Philosophy","score_opus":0.7025745338988933,"score_gpt":0.6943509281734068,"score_spread":0.008223605725486527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408483538","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009944738,0.000057119167,0.88260734,0.077740274,0.0004486005,0.0002884812,0.0000072743014,0.00001807198,0.028888106],"genre_scores_gemma":[0.1116526,0.000015275282,0.88442564,0.0023567632,0.000015877135,0.00009285752,0.0000026356545,0.0000025484119,0.0014357727],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99322885,0.0041598976,0.0014288843,0.00028668393,0.0007290234,0.00016663238],"domain_scores_gemma":[0.93120825,0.06397935,0.00063914794,0.00082640897,0.003313085,0.000033737884],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05782112,0.00008389513,0.00029196744,0.00036383615,0.0004080656,0.00008029971,0.00091020274,0.00007572819,0.00019876852],"category_scores_gemma":[0.14056675,0.00004543781,0.00008616179,0.0060682474,0.00017055606,0.00017653378,0.0002802954,0.00018188661,0.000015797232],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019028696,0.000052087405,0.0013638035,0.0000019075255,0.00002214679,2.3866027e-8,0.00021665425,0.0003054312,0.011778423,0.7018637,0.005075487,0.27930132],"study_design_scores_gemma":[0.000110786634,0.00007106868,0.17896464,0.000010695412,0.000024631145,0.0000010020387,0.0018795175,0.00043358837,0.011826314,0.56087625,0.24574366,0.00005784804],"about_ca_topic_score_codex":0.000012943371,"about_ca_topic_score_gemma":0.00001535665,"teacher_disagreement_score":0.27924347,"about_ca_system_score_codex":0.000030626947,"about_ca_system_score_gemma":0.0002080475,"threshold_uncertainty_score":0.97017145},"labels":[],"label_agreement":null},{"id":"W4408733561","doi":"10.63485/d04st-hp96","title":"Call to strengthen Canadian commitment to OA","year":2008,"lang":"en","type":"preprint","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Business","score_opus":0.33863219605790695,"score_gpt":0.49101659875967535,"score_spread":0.1523844027017684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408733561","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1833245,0.000031128355,0.003871496,0.07570273,0.0030843543,0.0020809437,0.00026075979,0.000090986956,0.7315531],"genre_scores_gemma":[0.8924005,0.000038301478,0.0130706355,0.02521961,0.0002690116,0.00022538546,0.000057357036,0.000021201076,0.06869797],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9955283,0.00016990455,0.0007682835,0.00079284504,0.0022974706,0.00044321435],"domain_scores_gemma":[0.9961927,0.00026510592,0.00012093991,0.0015139283,0.00060731586,0.001300018],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0023888433,0.00026074875,0.00039671754,0.0008752188,0.0002085517,0.0003868947,0.0015961393,0.00017238186,0.010460432],"category_scores_gemma":[0.0005686974,0.00019141796,0.00013125154,0.00048652038,0.000021700434,0.00007397995,0.0008243167,0.00031994018,0.013138662],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008496994,0.000037973336,0.0060104434,0.0000029126325,0.000022804797,0.000010156982,0.0029971225,0.042141046,0.0000028699133,0.00077972416,0.8409694,0.10701705],"study_design_scores_gemma":[0.00012651533,0.00008629271,0.027506758,0.000021989648,0.0000064240808,0.0000023113319,0.00055770535,0.0080487905,0.000045807137,0.0007351641,0.96252555,0.00033670064],"about_ca_topic_score_codex":0.12377203,"about_ca_topic_score_gemma":0.65476054,"teacher_disagreement_score":0.70907605,"about_ca_system_score_codex":0.0006396537,"about_ca_system_score_gemma":0.0021182995,"threshold_uncertainty_score":0.9904441},"labels":[],"label_agreement":null},{"id":"W4408742992","doi":"10.63485/5afcq-ye86","title":"OA projects and advocacy in Canada","year":2008,"lang":"en","type":"preprint","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Business","score_opus":0.2601634568168895,"score_gpt":0.4720895328203993,"score_spread":0.21192607600350977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408742992","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90248984,0.00010668226,0.00010470068,0.0022497347,0.0005672209,0.0003586163,0.0000051214224,0.000010063721,0.094108045],"genre_scores_gemma":[0.99371576,0.00035663514,0.0007929229,0.00091749494,0.00003689061,0.000032335884,0.000006317539,0.0000046338478,0.004137],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9971615,0.00012254089,0.00053397473,0.0004589737,0.00155528,0.00016774827],"domain_scores_gemma":[0.9987945,0.0003234395,0.00016225397,0.0004657349,0.00017372107,0.00008034934],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013704194,0.00013211249,0.00026444756,0.0002142982,0.000046310153,0.000103237464,0.0003945945,0.00006998707,0.0011800169],"category_scores_gemma":[0.0003880272,0.000090676105,0.000025722218,0.00024547582,0.000026305193,0.000097280266,0.00046925052,0.00028928943,0.000047780984],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018278623,0.000040365117,0.74103904,0.000029308943,0.000012008685,0.00004387923,0.002714296,0.0053055617,0.000005448054,0.00037350674,0.09253294,0.15788536],"study_design_scores_gemma":[0.0005798119,0.000028056442,0.8366668,0.000057678433,0.000004419734,0.000016078337,0.0050485376,0.09344654,0.00010250158,0.00462944,0.059009448,0.0004106685],"about_ca_topic_score_codex":0.91632175,"about_ca_topic_score_gemma":0.98750937,"teacher_disagreement_score":0.1574747,"about_ca_system_score_codex":0.00031376787,"about_ca_system_score_gemma":0.012486024,"threshold_uncertainty_score":0.99973303},"labels":[],"label_agreement":null},{"id":"W4408751627","doi":"10.63485/7rmyw-6ez31","title":"OA theses and dissertations at U of British Columbia","year":2008,"lang":"en","type":"preprint","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Library science; History; Computer science","score_opus":0.2091466727039885,"score_gpt":0.47836953584032305,"score_spread":0.26922286313633453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408751627","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9309948,0.00015742073,0.0002783055,0.00027478006,0.00022651283,0.00021129854,0.00008768026,0.000018960014,0.06775025],"genre_scores_gemma":[0.9121103,0.0007703693,0.0014918824,0.00011346288,0.000020527696,0.000026105416,0.000024068271,0.0000057677516,0.08543749],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9976871,0.00009615079,0.00059714896,0.00037446406,0.0011418582,0.00010324851],"domain_scores_gemma":[0.9980803,0.0006195829,0.0003025023,0.00044254816,0.0004833937,0.000071630115],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00094876904,0.00007301324,0.0002825979,0.000065548535,0.00014142807,0.0003713561,0.00035884898,0.00010158294,0.007580292],"category_scores_gemma":[0.00047972865,0.00008516032,0.000084574654,0.00016616113,0.00013152718,0.00012248741,0.0004640969,0.000118605334,0.00007431599],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009833797,0.00013492086,0.7124554,0.000044666504,0.00004986766,0.0000055756104,0.0019059869,0.00069549424,0.0001049065,0.00024714455,0.16520642,0.119139805],"study_design_scores_gemma":[0.0001749961,0.000031849984,0.9713299,0.000052054533,0.000013582579,0.000018083847,0.0011153443,0.0050809407,0.000053675674,0.010928908,0.011041723,0.00015888936],"about_ca_topic_score_codex":0.011784598,"about_ca_topic_score_gemma":0.18833983,"teacher_disagreement_score":0.25887457,"about_ca_system_score_codex":0.00002405858,"about_ca_system_score_gemma":0.00019157032,"threshold_uncertainty_score":0.99479604},"labels":[],"label_agreement":null},{"id":"W4408757760","doi":"10.63485/1wqsq-kjf34","title":"NCIC adopts an OA mandate","year":2008,"lang":"en","type":"preprint","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mandate; Business; Political science; Law","score_opus":0.44115905705508024,"score_gpt":0.5602487086078295,"score_spread":0.11908965155274925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408757760","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55447394,0.00011312122,0.015525965,0.0026343113,0.0029039679,0.00054657576,0.000038228805,0.0001978556,0.42356604],"genre_scores_gemma":[0.94723856,0.0005141966,0.007932714,0.001973068,0.00033628364,0.000044670775,0.000104042425,0.000017860179,0.04183859],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99509543,0.00026885903,0.00080445904,0.00079320563,0.0027900685,0.0002479897],"domain_scores_gemma":[0.9970849,0.00019534632,0.0003438166,0.0015784673,0.00060174736,0.00019571424],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0036179228,0.00023187812,0.00037008207,0.00032735147,0.00017220869,0.00046545855,0.0013866812,0.0002209303,0.017334096],"category_scores_gemma":[0.00026408266,0.00015503763,0.00015544258,0.00027528958,0.00007082353,0.00039086843,0.0007587769,0.00042511948,0.005004741],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008508243,0.00044830484,0.03894941,0.000035385954,0.00007488314,0.000044786648,0.00341908,0.027286433,0.000075123564,0.0055081095,0.25102744,0.673046],"study_design_scores_gemma":[0.00077400246,0.00021197488,0.13746811,0.000049710703,0.000030727737,0.000034621324,0.00090439536,0.23936504,0.0005246307,0.05390348,0.5657617,0.0009716325],"about_ca_topic_score_codex":0.00007095345,"about_ca_topic_score_gemma":0.00017959256,"teacher_disagreement_score":0.6720743,"about_ca_system_score_codex":0.00006419021,"about_ca_system_score_gemma":0.00058701035,"threshold_uncertainty_score":0.99577},"labels":[],"label_agreement":null},{"id":"W4408762332","doi":"10.1111/1467-8551.12910","title":"Establishing a Contribution: Calibration, Contextualization, Construction and Creation","year":2025,"lang":"en","type":"article","venue":"British Journal of Management","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Contextualization; Calibration; Computer science; Epistemology; Philosophy; Mathematics; Statistics","score_opus":0.03722468718209723,"score_gpt":0.3918786275416493,"score_spread":0.3546539403595521,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408762332","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06829962,0.0014138974,0.9054665,0.0047550467,0.0010728564,0.00031583922,0.0000069232283,0.000017362292,0.01865197],"genre_scores_gemma":[0.9909492,0.001115881,0.004441873,0.00087180565,0.000094807394,0.0000063375533,0.000009467706,0.0000035010314,0.002507118],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978748,0.00019735935,0.0008496434,0.00014664124,0.0008382693,0.00009330525],"domain_scores_gemma":[0.99793917,0.00021313103,0.00048640766,0.000106771215,0.0012042533,0.000050247538],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038389268,0.00006219914,0.00017631061,0.00032917596,0.00023953732,0.001010862,0.00018292664,0.000035299257,0.00033688772],"category_scores_gemma":[0.001148789,0.000061258936,0.000045647816,0.00057793624,0.00006904265,0.0011521365,0.000057731664,0.000086455344,0.0000036066353],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048866816,0.00007400916,0.020078467,0.00001913889,0.0000876831,0.000027259153,0.00016102182,0.0013671557,0.000016289607,0.15813263,0.045116827,0.77487063],"study_design_scores_gemma":[0.005893294,0.0002109211,0.2313697,0.0009146589,0.00022133008,0.00076660997,0.008405045,0.023979656,0.00034883502,0.13116832,0.59641767,0.00030394213],"about_ca_topic_score_codex":0.000012002699,"about_ca_topic_score_gemma":0.00004499962,"teacher_disagreement_score":0.92264956,"about_ca_system_score_codex":0.000064370215,"about_ca_system_score_gemma":0.000085943495,"threshold_uncertainty_score":0.97477645},"labels":[],"label_agreement":null},{"id":"W4408772945","doi":"10.63485/71rcr-xqt96","title":"Create Change Canada","year":2008,"lang":"en","type":"preprint","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Business; Political science","score_opus":0.5816603506462094,"score_gpt":0.529955662023022,"score_spread":0.051704688623187334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408772945","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17092855,0.00031962426,0.0009385257,0.019324632,0.0054061604,0.00077907,0.00009969749,0.00008394084,0.8021198],"genre_scores_gemma":[0.9282391,0.00061078207,0.0008102584,0.0061811237,0.00046013668,0.0001158993,0.000042091597,0.000011238748,0.06352934],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99588895,0.0001189308,0.00053337455,0.0004745268,0.0027848443,0.00019939213],"domain_scores_gemma":[0.99802524,0.00025552517,0.00024877343,0.00088542455,0.00045464016,0.00013040453],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013367531,0.00016643808,0.0002906229,0.00014097661,0.0001139158,0.00014696541,0.00082795665,0.00011013622,0.011314501],"category_scores_gemma":[0.00026830492,0.00011016991,0.0000834868,0.00020692585,0.000028894641,0.000115727074,0.00057477487,0.00027701067,0.00056299055],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008426843,0.000030204694,0.031048907,0.000010710799,0.00002663988,0.000028504748,0.0007381281,0.001115272,0.0000020696714,0.00088410045,0.8627941,0.10331293],"study_design_scores_gemma":[0.00015693875,0.000015960852,0.105901495,0.000020543659,0.000007409602,0.0000068915565,0.00026959096,0.021213904,0.00008633627,0.0034867271,0.86853695,0.0002972696],"about_ca_topic_score_codex":0.70861185,"about_ca_topic_score_gemma":0.888197,"teacher_disagreement_score":0.75731057,"about_ca_system_score_codex":0.00019183614,"about_ca_system_score_gemma":0.0030142288,"threshold_uncertainty_score":0.9895893},"labels":[],"label_agreement":null},{"id":"W4408811937","doi":"10.1007/s10459-025-10427-6","title":"How can research supervision relationships affect dissemination?","year":2025,"lang":"en","type":"editorial","venue":"Advances in Health Sciences Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Wilson Centre; University of Toronto; Health Sciences Centre; University Health Network; Sunnybrook Health Science Centre","funders":"","keywords":"Affect (linguistics); Psychology; Medical education; Computer science; Medicine; Communication","score_opus":0.20659623853651052,"score_gpt":0.6297228789586193,"score_spread":0.4231266404221088,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408811937","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00054442795,0.019338585,0.0007051315,0.05193877,0.8991618,0.0019102726,0.00009483014,0.000051191437,0.02625499],"genre_scores_gemma":[0.19557536,0.07024451,0.012009279,0.0012014342,0.45519578,0.0028804669,0.0019213166,0.00006157696,0.2609103],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9838753,0.0040819305,0.001588296,0.001643382,0.007973945,0.00083715667],"domain_scores_gemma":[0.957465,0.036574747,0.00100089,0.00119426,0.0035248892,0.00024020068],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.060317058,0.00032684708,0.0006072932,0.0042770756,0.0022090515,0.0013869188,0.0023029163,0.00047500024,0.00011843191],"category_scores_gemma":[0.068287365,0.00026368746,0.000101978265,0.009978404,0.0005686715,0.0024784212,0.0002492946,0.0018774549,0.0000402605],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000097909615,0.000118903736,0.0064256024,0.00023682204,0.0000014169007,1.4623446e-7,0.0008675756,0.00033483582,5.797405e-7,0.0069217947,0.81447625,0.17060629],"study_design_scores_gemma":[0.00014036469,0.00019042908,0.0032688892,0.0017839731,0.0000035108387,3.5929364e-7,0.00739035,0.001513435,0.000007838123,0.044872623,0.94060427,0.00022395248],"about_ca_topic_score_codex":0.00058434816,"about_ca_topic_score_gemma":0.008264033,"teacher_disagreement_score":0.44396603,"about_ca_system_score_codex":0.0016091998,"about_ca_system_score_gemma":0.026913673,"threshold_uncertainty_score":0.9999815},"labels":[],"label_agreement":null},{"id":"W4408816518","doi":"10.5194/oos2025-1140","title":"Strategies and best practices for fostering diverse engagement in international collaborations","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Best practice; Public relations; Political science; Knowledge management; Business; Computer science","score_opus":0.6665369740258519,"score_gpt":0.6086780789269668,"score_spread":0.05785889509888509,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408816518","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16283083,0.00024043198,0.06694081,0.025992384,0.0058300463,0.003177584,0.0004924171,0.000067496796,0.734428],"genre_scores_gemma":[0.9479001,0.0006341584,0.028163478,0.0004204422,0.00014400022,0.00053541246,0.00009680987,0.0000054117754,0.02210015],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980438,0.00014674252,0.0005436631,0.00043225344,0.0007270064,0.0001065605],"domain_scores_gemma":[0.9971898,0.0013016098,0.00052105996,0.00027573036,0.0006801377,0.000031619493],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0035525134,0.00012394998,0.00018458352,0.00050268887,0.0001275331,0.0017406521,0.00045558627,0.00008824863,0.00079562416],"category_scores_gemma":[0.0015730821,0.000100509555,0.00003838225,0.00024716769,0.000031257783,0.0009499483,0.001271825,0.00019883635,0.000017142429],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031460365,0.00084328826,0.03881232,0.0003507203,0.00032890504,0.0000070395213,0.021383246,0.09712322,0.0002287691,0.26779985,0.023495235,0.54931283],"study_design_scores_gemma":[0.0014564489,0.00014254576,0.007692018,0.00023422074,0.000062221494,8.9417284e-7,0.22018825,0.24961893,0.0001121767,0.053955745,0.46612075,0.00041579324],"about_ca_topic_score_codex":0.00031727122,"about_ca_topic_score_gemma":0.006879793,"teacher_disagreement_score":0.7850693,"about_ca_system_score_codex":0.00008461771,"about_ca_system_score_gemma":0.000966772,"threshold_uncertainty_score":0.99929565},"labels":[],"label_agreement":null},{"id":"W4408818139","doi":"10.31219/osf.io/y79u5_v1","title":"Megastudy testing 25 treatments to reduce antidemocratic attitudes and partisan animosity","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Political science; Law and economics; Social psychology; Psychology; Positive economics; Economics","score_opus":0.5426614289220236,"score_gpt":0.56098410045556,"score_spread":0.018322671533536394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408818139","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9863241,0.00004202737,0.0010494703,0.0032439195,0.00069956295,0.0009816841,0.000023599383,0.0001820906,0.007453593],"genre_scores_gemma":[0.970101,0.000028624296,0.013226861,0.0003898024,0.00010503831,0.00012823503,0.0000118195585,0.000019231908,0.015989397],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99568737,0.00029058807,0.00087770086,0.0010798434,0.0017406279,0.0003238493],"domain_scores_gemma":[0.99684006,0.0012734308,0.00030314625,0.0008899987,0.0004381839,0.00025517226],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0041311537,0.00030211287,0.0005323642,0.00031813173,0.0003294577,0.00081009004,0.00060643174,0.00011364491,0.00050517725],"category_scores_gemma":[0.0028192122,0.00021249524,0.00007628129,0.0007351098,0.00005214204,0.00021387055,0.0014956663,0.00024241417,0.0011509488],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011848298,0.00014813761,0.95434254,0.000029361725,0.00008223741,0.000009472893,0.00070124003,0.0016389152,0.0003909241,0.00018879195,0.010520107,0.0319364],"study_design_scores_gemma":[0.00027490128,0.00018845077,0.9816269,0.00012556376,0.0000466939,0.0000035359662,0.00043220617,0.01013264,0.00028236548,0.0062567242,0.00037074662,0.00025924516],"about_ca_topic_score_codex":0.0003023263,"about_ca_topic_score_gemma":0.00058084616,"teacher_disagreement_score":0.031677153,"about_ca_system_score_codex":0.000093620656,"about_ca_system_score_gemma":0.00029606043,"threshold_uncertainty_score":0.99962676},"labels":[],"label_agreement":null},{"id":"W4408842455","doi":"10.63485/dzbft-1cq88","title":"An OA repository on governance","year":2007,"lang":"en","type":"preprint","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Corporate governance; Business; Computer science; Process management; Finance","score_opus":0.2559746585203667,"score_gpt":0.5498229676815097,"score_spread":0.293848309161143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408842455","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15950072,0.00007995878,0.009236574,0.0012155087,0.0037271625,0.00028035208,0.000011513653,0.00010361102,0.8258446],"genre_scores_gemma":[0.9458931,0.00003739738,0.0026925274,0.00221705,0.0004762827,0.00001638167,0.0000110791525,0.000011383518,0.048644785],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9946013,0.00019504207,0.0007794603,0.000793209,0.0034241143,0.00020687941],"domain_scores_gemma":[0.9966554,0.00042484308,0.00052522507,0.0018170689,0.0004308204,0.00014664166],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0054182275,0.00019652676,0.0002726108,0.00014474682,0.00013136907,0.00051278656,0.0013044721,0.00023251031,0.004446528],"category_scores_gemma":[0.00029715346,0.00013335483,0.00013176582,0.00021101568,0.00004984711,0.00022327893,0.0002778139,0.00049609825,0.0016447497],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023966597,0.00084173493,0.052679613,0.00003198992,0.00004634542,0.00006496031,0.0014905256,0.045350086,0.0007828235,0.08988238,0.20647281,0.60211706],"study_design_scores_gemma":[0.00058239425,0.00052993174,0.48500744,0.00012675418,0.00002244636,0.000011753273,0.0006956904,0.09940097,0.009672995,0.03665317,0.36633545,0.0009609992],"about_ca_topic_score_codex":0.00009009348,"about_ca_topic_score_gemma":0.00009511469,"teacher_disagreement_score":0.7863924,"about_ca_system_score_codex":0.00015400776,"about_ca_system_score_gemma":0.00035331486,"threshold_uncertainty_score":0.9991326},"labels":[],"label_agreement":null},{"id":"W4409045203","doi":"10.33524/cjar.v25i1.764","title":"van den Hoonaard, D. K., &amp; van den Scott, L.-J. (2022). Qualitative research in action: A Canadian primer. (4th ed.). Oxford University Press.","year":2025,"lang":"en","type":"article","venue":"The Canadian Journal of Action Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Primer (cosmetics); Action research; Sociology; Library science; Pedagogy; Chemistry; Computer science","score_opus":0.5526590670886591,"score_gpt":0.607015650160806,"score_spread":0.05435658307214697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409045203","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6532454,0.0014538888,0.00062375073,0.11516042,0.0019478031,0.0016163522,0.00010345232,0.00001583655,0.22583309],"genre_scores_gemma":[0.93447363,0.0005085136,0.00018235043,0.0002418918,0.0002095213,0.000007900495,0.000006091215,0.000013028677,0.06435704],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9864823,0.0075100013,0.0007497287,0.00039595738,0.0038078614,0.0010541156],"domain_scores_gemma":[0.98951113,0.0033093768,0.0002630253,0.00075912225,0.004957201,0.0012001456],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.052828826,0.00015684718,0.00031841005,0.0053445483,0.0023714383,0.00075953687,0.0019517216,0.00018707545,0.0034614208],"category_scores_gemma":[0.0038864184,0.00012201911,0.00013170655,0.00468071,0.0006937587,0.0010082664,0.00011849185,0.002573451,0.00023521572],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.0008795486,0.00011658002,0.03607235,0.000053038173,0.00030700886,0.00025559473,0.023671716,0.0033483726,0.00027777985,0.029666323,0.7966952,0.10865651],"study_design_scores_gemma":[0.0006186157,0.00015380823,0.026943414,0.00010404002,0.000014099853,0.00002885315,0.037397705,0.00038510954,0.00015828568,0.011537276,0.9225336,0.00012524516],"about_ca_topic_score_codex":0.5755093,"about_ca_topic_score_gemma":0.9807383,"teacher_disagreement_score":0.40522894,"about_ca_system_score_codex":0.005213365,"about_ca_system_score_gemma":0.032314524,"threshold_uncertainty_score":0.99972767},"labels":[],"label_agreement":null},{"id":"W4409079237","doi":"10.33524/cjar.v25i1.763","title":"A Powerful Relationship: The Interdependence of Action Research and Social Justice Work","year":2025,"lang":"en","type":"article","venue":"The Canadian Journal of Action Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Thompson Rivers University","funders":"","keywords":"Action research; Social justice; Sociology; Work (physics); Action (physics); Social psychology; Pedagogy; Psychology; Criminology; Engineering","score_opus":0.7425039567243484,"score_gpt":0.6616048255883804,"score_spread":0.08089913113596803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409079237","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84041023,0.00029329627,0.00057357916,0.13749045,0.0010342065,0.00031589117,0.0000043257514,0.0000025587856,0.019875461],"genre_scores_gemma":[0.9886733,0.000048681348,0.000035271372,0.0001329052,0.00017997828,0.000004124224,3.840611e-7,0.0000036910515,0.010921609],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99390984,0.002407671,0.00054961466,0.00014191354,0.0026808097,0.00031018304],"domain_scores_gemma":[0.9889879,0.0060687056,0.00023669426,0.00030564176,0.004258465,0.00014257296],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.04321711,0.000058639867,0.00013213172,0.0013569326,0.0022407258,0.00053607323,0.0008826799,0.000086822874,0.00071380625],"category_scores_gemma":[0.0061446335,0.000032498978,0.000055671953,0.002763151,0.00085754594,0.00041478584,0.000077701516,0.0016349006,0.00006581537],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012862579,0.00012717645,0.09363516,0.00009252542,0.00017299398,0.000020013922,0.025771314,0.00091616606,0.0011976304,0.10107229,0.60086334,0.17484511],"study_design_scores_gemma":[0.0006916545,0.000498145,0.5669895,0.00019716857,0.000047291847,0.0000622405,0.09542043,0.0011807957,0.000985741,0.112226374,0.2215881,0.00011258856],"about_ca_topic_score_codex":0.0023571025,"about_ca_topic_score_gemma":0.0562207,"teacher_disagreement_score":0.4733543,"about_ca_system_score_codex":0.00042461633,"about_ca_system_score_gemma":0.0041148406,"threshold_uncertainty_score":0.99905825},"labels":[],"label_agreement":null},{"id":"W4409153149","doi":"10.1177/0193841x251331723","title":"A Critical Reflection of Generalization in Mixed Methods Research","year":2025,"lang":"en","type":"article","venue":"Evaluation Review","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Centre for Interdisciplinary Research in Rehabilitation","funders":"","keywords":"Generalization; Constructive; Multimethodology; Relevance (law); Management science; Computer science; Reflection (computer programming); Psychology; Epistemology; Mathematics education; Process (computing); Political science","score_opus":0.7561451234814716,"score_gpt":0.7902642498582428,"score_spread":0.03411912637677128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409153149","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026428724,0.21613093,0.3893906,0.07450326,0.004043583,0.006459859,0.0000072512757,0.000067734465,0.28296807],"genre_scores_gemma":[0.8900823,0.034898482,0.06545601,0.004164876,0.00011424271,0.0011226669,0.00005305173,0.000016846914,0.0040915124],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9825403,0.012153848,0.001455338,0.00039832492,0.003265872,0.00018629609],"domain_scores_gemma":[0.99180037,0.0029146376,0.00018206134,0.0005307549,0.0045365277,0.000035674573],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1237473,0.00007601793,0.00032607545,0.0008254117,0.000101129444,0.000061049366,0.00029476857,0.00006238579,0.0039748973],"category_scores_gemma":[0.05347765,0.000058857175,0.00007578693,0.004820862,0.00007870713,0.00032815008,0.00007010957,0.00016433741,0.000119396296],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009694826,0.000078893645,0.0017583248,0.00033733924,0.000005509396,9.647043e-8,0.000118122145,0.0004529586,0.0012317554,0.04759291,0.018398045,0.93001634],"study_design_scores_gemma":[0.0009645883,0.00014862852,0.09582551,0.0044455063,0.00011555706,0.0000019497822,0.00044821654,0.2964904,0.0042091673,0.3791482,0.21799298,0.00020931433],"about_ca_topic_score_codex":0.000019546564,"about_ca_topic_score_gemma":0.000080947175,"teacher_disagreement_score":0.92980707,"about_ca_system_score_codex":0.00019420388,"about_ca_system_score_gemma":0.00078321475,"threshold_uncertainty_score":0.9969356},"labels":[],"label_agreement":null},{"id":"W4409249547","doi":"10.64000/9yk4w3ivc","title":"The programs approach: our experiences during the first quarter of 2025","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Political science; Psychology; Geography; Archaeology","score_opus":0.2091367945894002,"score_gpt":0.47512580794216097,"score_spread":0.26598901335276076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409249547","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38808843,0.0010458792,0.0056811417,0.042513136,0.005703152,0.0038108167,0.000019144445,0.00014760003,0.5529907],"genre_scores_gemma":[0.9624687,0.00008772033,0.00063782296,0.00018085273,0.00012006588,0.0008436956,0.0000038994503,0.0000038205735,0.03565344],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99578065,0.00025818034,0.0009741262,0.0005323284,0.0021982065,0.00025648557],"domain_scores_gemma":[0.9969532,0.0005084518,0.0005290589,0.0015137896,0.00045384938,0.000041688163],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0050962963,0.00021081777,0.00031272095,0.000120656776,0.00067121774,0.0008193784,0.0026575336,0.0001302904,0.00038406247],"category_scores_gemma":[0.0002891667,0.00008135623,0.00025649337,0.00052906125,0.00016891047,0.00013006314,0.001062439,0.00038227643,0.000057918955],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028329686,0.0010230024,0.15221685,0.00059679046,0.00055850466,0.0000021432795,0.2263451,0.010671901,0.000012647646,0.02812118,0.16836825,0.41180032],"study_design_scores_gemma":[0.00057751196,0.00012166851,0.056904025,0.00022458348,0.000051973537,0.000003326736,0.7010424,0.0592234,0.0005017288,0.010583076,0.170225,0.0005412762],"about_ca_topic_score_codex":0.000077588484,"about_ca_topic_score_gemma":0.0003076502,"teacher_disagreement_score":0.5743803,"about_ca_system_score_codex":0.000037982114,"about_ca_system_score_gemma":0.00040499048,"threshold_uncertainty_score":0.7901285},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"},{"model":"grok","categories":["insufficient_payload"],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W4409249912","doi":"10.5465/amj.2025.4002","title":"Making a Theoretical Contribution with Qualitative Research","year":2025,"lang":"en","type":"article","venue":"Academy of Management Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"","keywords":"Qualitative research; Organizational behavior; Psychology; Management science; Sociology; Process management; Social psychology; Business; Economics; Social science","score_opus":0.4468758608439882,"score_gpt":0.6726011909847328,"score_spread":0.22572533014074458,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409249912","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22126833,0.00048659064,0.1867487,0.14653148,0.00030824027,0.0009769492,0.000005451757,0.000028807388,0.44364545],"genre_scores_gemma":[0.99456793,0.00010658385,0.002508206,0.00071215775,0.000052468924,0.0000108790255,4.1385738e-7,0.0000029391852,0.0020384023],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99437785,0.0015140143,0.0006602646,0.00021057774,0.002963415,0.00027387706],"domain_scores_gemma":[0.99737895,0.0016011136,0.00025682975,0.00012628906,0.00058520486,0.00005159245],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03693648,0.00007729789,0.00018838179,0.0008073169,0.00034149134,0.00018845942,0.0006282911,0.000054994493,0.0012488181],"category_scores_gemma":[0.0008539146,0.00004720202,0.000058124493,0.0012461265,0.00039716353,0.000298086,0.00017337459,0.0005739237,0.000069968504],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001780282,0.000029920711,0.0013042617,0.000008077842,0.00007689245,0.000002465079,0.0010100432,0.000091575435,0.000018250454,0.95251733,0.0077514206,0.037011757],"study_design_scores_gemma":[0.0010393865,0.00012258925,0.019338606,0.00022514877,0.000031062915,0.0000070197666,0.016632475,0.0017446441,0.00030837368,0.9125624,0.047917537,0.00007081273],"about_ca_topic_score_codex":3.4100563e-7,"about_ca_topic_score_gemma":5.18605e-7,"teacher_disagreement_score":0.77329963,"about_ca_system_score_codex":0.00009195064,"about_ca_system_score_gemma":0.00007737797,"threshold_uncertainty_score":0.9996642},"labels":[],"label_agreement":null},{"id":"W4409261837","doi":"10.64000/4s2ee-wkr84","title":"The programs approach: our experiences during the first quarter of 2025","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Psychology; Political science; History; Archaeology","score_opus":0.2091367945894002,"score_gpt":0.47512580794216097,"score_spread":0.26598901335276076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409261837","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38808843,0.0010458792,0.0056811417,0.042513136,0.005703152,0.0038108167,0.000019144445,0.00014760003,0.5529907],"genre_scores_gemma":[0.9624687,0.00008772033,0.00063782296,0.00018085273,0.00012006588,0.0008436956,0.0000038994503,0.0000038205735,0.03565344],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99578065,0.00025818034,0.0009741262,0.0005323284,0.0021982065,0.00025648557],"domain_scores_gemma":[0.9969532,0.0005084518,0.0005290589,0.0015137896,0.00045384938,0.000041688163],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0050962963,0.00021081777,0.00031272095,0.000120656776,0.00067121774,0.0008193784,0.0026575336,0.0001302904,0.00038406247],"category_scores_gemma":[0.0002891667,0.00008135623,0.00025649337,0.00052906125,0.00016891047,0.00013006314,0.001062439,0.00038227643,0.000057918955],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028329686,0.0010230024,0.15221685,0.00059679046,0.00055850466,0.0000021432795,0.2263451,0.010671901,0.000012647646,0.02812118,0.16836825,0.41180032],"study_design_scores_gemma":[0.00057751196,0.00012166851,0.056904025,0.00022458348,0.000051973537,0.000003326736,0.7010424,0.0592234,0.0005017288,0.010583076,0.170225,0.0005412762],"about_ca_topic_score_codex":0.000077588484,"about_ca_topic_score_gemma":0.0003076502,"teacher_disagreement_score":0.5743803,"about_ca_system_score_codex":0.000037982114,"about_ca_system_score_gemma":0.00040499048,"threshold_uncertainty_score":0.7901285},"labels":[],"label_agreement":null},{"id":"W4409336988","doi":"10.5334/ijic.icic24190","title":"Evaluating the impact of engagement: An introduction to the Engage with Impact Toolkit","year":2025,"lang":"en","type":"article","venue":"International Journal of Integrated Care","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Process management; Computer science; Psychology; Data science; Business","score_opus":0.15278746414079047,"score_gpt":0.5602994632867854,"score_spread":0.4075119991459949,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409336988","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9839508,0.00012189075,0.0059496504,0.007369282,0.0010362827,0.00022956381,0.00004277136,0.000005862206,0.0012939308],"genre_scores_gemma":[0.9983106,0.0000121502335,0.0006024999,0.00028980285,0.0004618104,0.0000076317065,0.000015578853,0.000006073478,0.00029384738],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.99569505,0.0009104567,0.0008364521,0.00018008184,0.0022472274,0.00013070746],"domain_scores_gemma":[0.9902871,0.000686761,0.000700046,0.0004011371,0.007863917,0.000061007366],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0083416095,0.00014156493,0.00021283573,0.0005117427,0.00018364684,0.00039125694,0.0015375757,0.00003564179,0.0014526545],"category_scores_gemma":[0.003475688,0.000051955256,0.00023974622,0.00091886154,0.00006218704,0.0005521506,0.00007781598,0.0005134814,0.000014054423],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020143273,0.00015487606,0.0977158,0.0000033457577,0.00096697756,0.000006773951,0.012732468,0.48357773,0.0070419926,0.0014435144,0.021671796,0.3726704],"study_design_scores_gemma":[0.0043931627,0.012697474,0.61472654,0.0005461557,0.00031078488,0.0002879537,0.24014786,0.07724152,0.014229886,0.0033382191,0.031576525,0.0005039566],"about_ca_topic_score_codex":0.00034481025,"about_ca_topic_score_gemma":0.00016997822,"teacher_disagreement_score":0.5170107,"about_ca_system_score_codex":0.0007403403,"about_ca_system_score_gemma":0.0017446596,"threshold_uncertainty_score":0.99946016},"labels":[],"label_agreement":null},{"id":"W4409337016","doi":"10.5334/ijic.icic24200","title":"Measuring integration in “Integrated Youth Services” in Canada: Experiences with research and evaluation","year":2025,"lang":"en","type":"article","venue":"International Journal of Integrated Care","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Integrated care; Integrated services; Psychology; Knowledge management; Process management; Health care; Business; Computer science; Political science","score_opus":0.22220384926252493,"score_gpt":0.483455196234873,"score_spread":0.2612513469723481,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409337016","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9942028,0.0005959099,0.000352023,0.0009520813,0.00075088587,0.00022038606,0.000014487978,0.0000032870005,0.0029081346],"genre_scores_gemma":[0.9994296,0.00004926507,0.00020065215,0.00015285186,0.0000329031,0.000027216136,0.000030148021,0.00000527629,0.000072092924],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99375665,0.0005892439,0.0010866331,0.00028323763,0.004084023,0.00020020938],"domain_scores_gemma":[0.98803765,0.00040821108,0.00036090615,0.00016474663,0.010962783,0.00006569706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005976794,0.00014470365,0.00027352755,0.0019406882,0.00006500746,0.00033835036,0.00082136365,0.00006468605,0.00023714287],"category_scores_gemma":[0.0010004519,0.00009142714,0.00003191449,0.0018075521,0.00007621173,0.0007222433,0.0000613727,0.00060359034,0.0000023355574],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.0009780723,0.000097752694,0.7005899,0.000011412561,0.00006175031,0.00006985904,0.06532057,0.0061147492,0.0004158524,0.00042477337,0.0002099678,0.22570536],"study_design_scores_gemma":[0.0014815752,0.0001378917,0.07443326,0.0011584443,0.000008514292,0.000016558435,0.8972758,0.02155827,0.0028655208,0.00070339197,0.0002620091,0.00009873429],"about_ca_topic_score_codex":0.35211563,"about_ca_topic_score_gemma":0.9259171,"teacher_disagreement_score":0.83195525,"about_ca_system_score_codex":0.0045735487,"about_ca_system_score_gemma":0.010663839,"threshold_uncertainty_score":0.9992477},"labels":[],"label_agreement":null},{"id":"W4409337597","doi":"10.5334/ijic.icic24174","title":"What should we consider when implementing digital assessments in integrated health and social care? Ten action areas for implementation planning&amp;nbsp;","year":2025,"lang":"en","type":"article","venue":"International Journal of Integrated Care","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Integrated care; Social care; Action (physics); Process management; Health care; Digital health; Computer science; Knowledge management; Medicine; Engineering management; Business; Nursing; Engineering; Political science","score_opus":0.2844690586249479,"score_gpt":0.595476211794915,"score_spread":0.311007153169967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409337597","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94430596,0.002050476,0.023521917,0.023672322,0.00440943,0.0007741011,0.00047083333,0.000028968441,0.0007659929],"genre_scores_gemma":[0.9955506,0.00018722424,0.0013816006,0.0017013081,0.00014156042,0.000028070594,0.0006790998,0.000012711794,0.0003178523],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9963217,0.0001985458,0.0014945611,0.00030232954,0.0014093728,0.0002734889],"domain_scores_gemma":[0.9940852,0.0004436162,0.0010541596,0.00011046219,0.0042222403,0.00008431177],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0015803446,0.00020684952,0.00038294288,0.0011127547,0.00019648306,0.0016511224,0.0004641568,0.00009562869,0.00029312243],"category_scores_gemma":[0.00039701062,0.00015722212,0.00015663002,0.00036072446,0.000050519688,0.0021783873,0.000095810065,0.000361252,0.0000036402175],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004743672,0.000054176347,0.22859076,0.00003673719,0.00024345532,0.000006789077,0.022846293,0.00012533192,0.00016966707,0.0007142477,0.017986156,0.728752],"study_design_scores_gemma":[0.0035212915,0.00028460284,0.0150398165,0.0006186369,0.000030520034,0.000027486956,0.7642059,0.00070372113,0.00051289174,0.0049514375,0.20990494,0.00019878267],"about_ca_topic_score_codex":0.00018434126,"about_ca_topic_score_gemma":0.0017983714,"teacher_disagreement_score":0.7413596,"about_ca_system_score_codex":0.0015531343,"about_ca_system_score_gemma":0.0024255759,"threshold_uncertainty_score":0.99938524},"labels":[],"label_agreement":null},{"id":"W4409460274","doi":"10.31234/osf.io/ngsb6_v1","title":"Affective and interactional polarization align across countries","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Polarization (electrochemistry); Psychology; Social psychology; Business","score_opus":0.2614500989003316,"score_gpt":0.562161763963666,"score_spread":0.3007116650633344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409460274","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.869603,0.00013250484,0.08671664,0.015383257,0.007537539,0.0010987434,0.00044883625,0.0003572929,0.018722199],"genre_scores_gemma":[0.9691786,0.00010097302,0.0006944177,0.0006751194,0.00019446398,0.000057291974,0.00011605403,0.000014108347,0.028968967],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99701583,0.00019008848,0.00048435052,0.0005640335,0.0015774071,0.00016828242],"domain_scores_gemma":[0.99717844,0.0013690514,0.00030524502,0.00036274787,0.0007178113,0.0000666917],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003956679,0.00016397312,0.0002458775,0.0001973385,0.0002331114,0.0010312021,0.00030028768,0.00017268775,0.0019345793],"category_scores_gemma":[0.0010017243,0.000119797325,0.00006927621,0.00024456796,0.000095374,0.000417664,0.0007986509,0.00028324462,0.0011693877],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018393608,0.00012489333,0.771196,0.000106898886,0.00028931192,0.000008173786,0.014034341,0.013807004,0.00023350731,0.05098007,0.08985009,0.05918578],"study_design_scores_gemma":[0.00043363072,0.00007260589,0.7557689,0.00009130697,0.00002250705,0.0000085637685,0.0040020924,0.08120492,0.00043297792,0.1088814,0.048659857,0.00042122602],"about_ca_topic_score_codex":0.00017000086,"about_ca_topic_score_gemma":0.00060893653,"teacher_disagreement_score":0.09957561,"about_ca_system_score_codex":0.000090156165,"about_ca_system_score_gemma":0.0002720954,"threshold_uncertainty_score":0.99960834},"labels":[],"label_agreement":null},{"id":"W4409476791","doi":"10.5751/es-15757-300208","title":"Using monitoring and evaluation to build equity and resilience: lessons from practice","year":2025,"lang":"en","type":"article","venue":"Ecology and Society","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Resilience (materials science); Equity (law); Environmental resource management; Business; Environmental planning; Geography; Political science; Environmental science","score_opus":0.3038168986840555,"score_gpt":0.6087335776084707,"score_spread":0.3049166789244152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409476791","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98370653,0.00043766297,0.0019034902,0.010853093,0.0004069241,0.0001831492,0.000003435395,0.000007988244,0.0024977273],"genre_scores_gemma":[0.9877054,0.00026313812,0.0102635715,0.0014632699,0.00005265273,0.000012520188,8.404476e-7,0.0000015825672,0.00023700467],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99861085,0.00027281346,0.00021400709,0.00032052214,0.00044217048,0.00013962574],"domain_scores_gemma":[0.99778855,0.0016610683,0.00008632127,0.00014252277,0.00026226445,0.00005928099],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0072147013,0.00006466689,0.00012932917,0.00004141219,0.0005583796,0.00016446147,0.00010005146,0.00010097144,0.000076277334],"category_scores_gemma":[0.0017523373,0.00005423317,0.00001980248,0.00022989167,0.00010292861,0.0004528913,0.00039472186,0.00012042663,0.0000046389555],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051420313,0.00006140921,0.7713766,0.000009973523,0.00006946631,7.7487084e-7,0.011085284,0.001120153,0.0038961915,0.005291114,0.0040457295,0.20299189],"study_design_scores_gemma":[0.00039570927,0.00003643734,0.930601,0.0000131158195,0.000051740477,0.0000016165139,0.00923101,0.038004097,0.00019728288,0.018208044,0.0031930313,0.00006694315],"about_ca_topic_score_codex":0.000072764204,"about_ca_topic_score_gemma":0.000064460975,"teacher_disagreement_score":0.20292494,"about_ca_system_score_codex":0.000062346924,"about_ca_system_score_gemma":0.00021888984,"threshold_uncertainty_score":0.4294661},"labels":[],"label_agreement":null},{"id":"W4409536097","doi":"10.63485/fja4a-g5244","title":"The case for OA, focusing on Canada","year":2006,"lang":"en","type":"preprint","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.29206693214794627,"score_gpt":0.5156730270523473,"score_spread":0.22360609490440103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409536097","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39467466,0.00031342922,0.056235775,0.08164768,0.013888937,0.003230735,0.00033911256,0.000089286084,0.4495804],"genre_scores_gemma":[0.95959026,0.000005642751,0.001825102,0.0017076186,0.000372602,0.00011086671,0.000018325612,0.000010785172,0.036358792],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99747145,0.000108950895,0.00055655965,0.00038405502,0.0012701012,0.00020889589],"domain_scores_gemma":[0.9955784,0.0028249198,0.00027659338,0.0007853666,0.0004782478,0.0000564452],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003891218,0.00014098137,0.00017486824,0.00006620092,0.0005872748,0.00062887743,0.00056316797,0.00007678188,0.00036569053],"category_scores_gemma":[0.00064577366,0.00007075235,0.00010005645,0.00011089408,0.000028606195,0.000044690318,0.00021759626,0.00020473168,0.00003372454],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001743766,0.000014475433,0.0003803186,0.0000061245514,0.000013290648,0.000040245763,0.000041951407,0.015106378,0.0000012260962,0.0074173305,0.67645407,0.30050716],"study_design_scores_gemma":[0.00026330637,0.000039234088,0.0012483652,0.000017277633,0.000015027972,0.00003422313,0.00064093916,0.12127952,0.00019484239,0.0434915,0.83253616,0.00023961299],"about_ca_topic_score_codex":0.51798064,"about_ca_topic_score_gemma":0.97789973,"teacher_disagreement_score":0.5649156,"about_ca_system_score_codex":0.0002501883,"about_ca_system_score_gemma":0.002133914,"threshold_uncertainty_score":0.6064279},"labels":[],"label_agreement":null},{"id":"W4409589284","doi":"10.63485/e2sag-xq886","title":"OA to civic information in Canada","year":2006,"lang":"en","type":"preprint","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Public administration","score_opus":0.13698220748912326,"score_gpt":0.45348733175749867,"score_spread":0.3165051242683754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409589284","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6588766,0.00001277511,0.01134077,0.008627167,0.0018936772,0.00067270355,0.000046261146,0.000024232359,0.31850585],"genre_scores_gemma":[0.9914428,0.0000025594047,0.0014811489,0.004035452,0.000041610725,0.00005135406,0.000062408566,0.0000029191037,0.0028797197],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99634427,0.00008029932,0.0009414204,0.00023079231,0.002219366,0.00018385838],"domain_scores_gemma":[0.99862444,0.00019315904,0.00021953185,0.0005413934,0.00033587465,0.000085604624],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0021648323,0.0001273805,0.00022476798,0.00046712946,0.00003353062,0.0002932625,0.0006396746,0.00007141221,0.0037674713],"category_scores_gemma":[0.00032655464,0.000095019896,0.00003701698,0.00048395936,0.0000054906786,0.00036518148,0.00042680517,0.00023058418,0.0010118579],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000077796085,0.000012257685,0.13906783,0.000012760454,0.000003404391,0.0000013605276,0.0004776656,0.3242241,0.0000011366672,0.0005366226,0.35091203,0.18474303],"study_design_scores_gemma":[0.00019126864,0.000011332527,0.6442288,0.0000267267,0.0000021632852,5.4074263e-7,0.00078288966,0.11175839,0.000039424373,0.004512285,0.2382022,0.0002439493],"about_ca_topic_score_codex":0.96030104,"about_ca_topic_score_gemma":0.99740136,"teacher_disagreement_score":0.505161,"about_ca_system_score_codex":0.0009259843,"about_ca_system_score_gemma":0.005276323,"threshold_uncertainty_score":0.999766},"labels":[],"label_agreement":null},{"id":"W4409767570","doi":"10.1037/pspa0000445","title":"Inference from social evaluation.","year":2025,"lang":"en","type":"article","venue":"Journal of Personality and Social Psychology","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Psychology; Inference; Social psychology; Cognitive psychology; Epistemology","score_opus":0.4122296720824712,"score_gpt":0.6253446062998984,"score_spread":0.21311493421742722,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409767570","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9263811,0.0002744584,0.0029762029,0.050234463,0.0010055262,0.000065183645,0.0000137557945,0.0000035016863,0.019045768],"genre_scores_gemma":[0.9934995,0.00003036999,0.00024010826,0.0054299957,0.000468708,0.0000020281157,0.0000024488988,0.0000017323965,0.00032510675],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9971385,0.0007734247,0.0006600287,0.00017292687,0.0011394804,0.00011562198],"domain_scores_gemma":[0.9977791,0.00061792525,0.0004623162,0.000084078165,0.0010209061,0.000035696055],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0073925257,0.00007544926,0.00029172344,0.00017093186,0.00033699127,0.000110416164,0.00029310104,0.00013328846,0.0031105198],"category_scores_gemma":[0.0007988326,0.000057840374,0.00013074526,0.00029623028,0.0001949405,0.00024245933,0.00003601284,0.00026087856,0.000022793216],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046708898,0.00033975518,0.1596849,0.000008946207,0.0002560062,0.0000037222162,0.027411144,0.00001401562,0.0007874523,0.044135075,0.10892135,0.65797055],"study_design_scores_gemma":[0.0010342663,0.000045243676,0.7940753,0.0000048458755,0.00004432432,0.0000018938915,0.0026953216,0.000249919,0.000005424155,0.16718648,0.03460401,0.00005294061],"about_ca_topic_score_codex":0.000021693482,"about_ca_topic_score_gemma":0.00006116826,"teacher_disagreement_score":0.6579176,"about_ca_system_score_codex":0.000050708764,"about_ca_system_score_gemma":0.0004005963,"threshold_uncertainty_score":0.99780077},"labels":[],"label_agreement":null},{"id":"W4409871507","doi":"10.1007/978-3-031-91137-8_4","title":"Sustainability in International Research Collaborations","year":2025,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Sustainability; Business; Biology; Ecology","score_opus":0.448295494904078,"score_gpt":0.6237964114619085,"score_spread":0.17550091655783046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409871507","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000030380415,0.000039133138,0.00035749612,0.035087537,0.0005525389,0.00049371255,0.000034014487,0.000016410671,0.9633888],"genre_scores_gemma":[0.020714695,0.00007290737,0.000305504,0.000280359,0.00008635597,0.000041035808,0.00003747334,0.0000056703616,0.978456],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99487257,0.00017685011,0.0008390275,0.00053257676,0.0033876342,0.00019131177],"domain_scores_gemma":[0.99027634,0.002033701,0.00012307371,0.00070286146,0.006807945,0.000056068166],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.012169882,0.00012642534,0.00023557269,0.0017379848,0.00013516234,0.00036870549,0.0009207135,0.00020461758,0.03563237],"category_scores_gemma":[0.00494963,0.00009882261,0.00007140373,0.00055365975,0.00015001999,0.000266657,0.0003395652,0.0005332863,0.0008680433],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012086638,0.00001986134,0.0007370941,0.0000037220595,0.00000673939,0.0000027278186,0.00013437736,0.00008294102,3.4738815e-7,0.77439064,0.19954786,0.025061583],"study_design_scores_gemma":[0.0001102096,0.0000145711,0.00091793464,0.000016404421,0.0000011878138,1.6885072e-7,0.0006220584,0.0014959715,0.0000018274409,0.37888047,0.61787826,0.000060896982],"about_ca_topic_score_codex":0.000059751193,"about_ca_topic_score_gemma":0.0028665839,"teacher_disagreement_score":0.41833043,"about_ca_system_score_codex":0.0009355258,"about_ca_system_score_gemma":0.004068135,"threshold_uncertainty_score":0.9999099},"labels":[],"label_agreement":null},{"id":"W4409990764","doi":"10.1522/rhe.v9i2.1779","title":"Analyse de l’appropriation de pratiques évaluatives spécifiquement développées pour les élèves vivant avec un trouble du spectre de l’autisme par des enseignants du secondaire au Québec","year":2025,"lang":"fr","type":"article","venue":"Revue hybride de l éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Humanities; Art; Political science","score_opus":0.1509188346347095,"score_gpt":0.4050868676049429,"score_spread":0.2541680329702334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409990764","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8540921,0.0016861894,0.09510651,0.044927094,0.0006623128,0.0007053308,0.000033079392,0.0000849469,0.0027024075],"genre_scores_gemma":[0.96296567,0.003205632,0.02399795,0.0008051618,0.0006290607,0.00024780422,0.00007431145,0.000037626818,0.008036796],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9933947,0.0026288996,0.0014241716,0.0008583456,0.0007676677,0.0009262307],"domain_scores_gemma":[0.99572843,0.0013494563,0.0009250134,0.00067847996,0.0010069435,0.000311665],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010890134,0.00047824671,0.0006079177,0.0006308074,0.0011604785,0.0005948496,0.0006216027,0.00025291968,0.0018110923],"category_scores_gemma":[0.0041167317,0.00047284385,0.0002853479,0.0010366588,0.00027935623,0.0011058063,0.00012545056,0.00038253318,0.00011959037],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000095360636,0.00063097524,0.553998,0.00033599476,0.00022872236,0.000021118833,0.22057116,0.0045773415,0.0034210035,0.006402239,0.0046270676,0.20509104],"study_design_scores_gemma":[0.0007167311,0.00012577906,0.75947,0.00071371085,0.00029447637,0.000113613896,0.043168716,0.11928042,0.035594027,0.035462875,0.004641419,0.00041825065],"about_ca_topic_score_codex":0.017165883,"about_ca_topic_score_gemma":0.061158802,"teacher_disagreement_score":0.205472,"about_ca_system_score_codex":0.008348565,"about_ca_system_score_gemma":0.024660962,"threshold_uncertainty_score":0.9997723},"labels":[],"label_agreement":null},{"id":"W4410005733","doi":"10.1080/13573322.2025.2495818","title":"Understanding the development of physical education professionals’ policy capacity","year":2025,"lang":"en","type":"article","venue":"Sport Education and Society","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Physical education; Pedagogy; Sociology; Psychology","score_opus":0.25938541579999863,"score_gpt":0.5254562486879737,"score_spread":0.26607083288797506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410005733","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9525223,0.000042727755,0.00322673,0.007792321,0.00060027867,0.0002452544,0.0000011403088,0.000009832375,0.03555944],"genre_scores_gemma":[0.9889062,0.00000857175,0.0015701234,0.0016176401,0.00010721324,0.000038800175,0.000008635725,0.0000021623543,0.007740639],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9987974,0.000038447688,0.0003469998,0.00017040528,0.00055757794,0.000089125395],"domain_scores_gemma":[0.9991599,0.0001447148,0.00018180709,0.00020715916,0.0002655318,0.000040935905],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017350358,0.00006933186,0.00011648592,0.00008594409,0.00041725856,0.00005373555,0.00016781743,0.000038351816,0.00008621901],"category_scores_gemma":[0.00012081871,0.00004188465,0.00006913768,0.0006512682,0.00010423019,0.00014891678,0.000043820328,0.000093895615,0.0000080243135],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006049374,0.0009447476,0.100716725,0.000046272195,0.00003629762,3.1392706e-9,0.14012693,0.0000149744465,0.00023844447,0.63333875,0.03697114,0.08755964],"study_design_scores_gemma":[0.00015337032,0.000010353904,0.5858017,0.00008069976,0.000014092876,4.6463634e-7,0.27440402,0.0011725575,0.0005678179,0.08720707,0.050483156,0.00010470788],"about_ca_topic_score_codex":0.000018425026,"about_ca_topic_score_gemma":0.000017422422,"teacher_disagreement_score":0.54613173,"about_ca_system_score_codex":0.00019083689,"about_ca_system_score_gemma":0.006312804,"threshold_uncertainty_score":0.9993205},"labels":[],"label_agreement":null},{"id":"W4410087790","doi":"10.18294/ci.9789878926896","title":"Evaluación en salud: De los modelos teóricos a la práctica en la evaluación de programas y sistemas de salud","year":2025,"lang":"es","type":"book","venue":"De la UNLa - Universidad Nacional de Lanús eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Philosophy","score_opus":0.03545083820254344,"score_gpt":0.42271851531725835,"score_spread":0.3872676771147149,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410087790","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06527744,0.0005900045,0.015040962,0.002552293,0.00046651266,0.003420746,0.0005716817,0.0007384202,0.91134197],"genre_scores_gemma":[0.44672444,0.0008116309,0.03170191,0.0034481995,0.001218302,0.0006065946,0.00038572022,0.000478309,0.5146249],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.97759616,0.0119101005,0.0017108638,0.001935349,0.004694157,0.0021533703],"domain_scores_gemma":[0.97941357,0.015425633,0.0010968087,0.0016067515,0.0012638126,0.0011934486],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","research_integrity"],"category_scores_codex":[0.022620335,0.0014500918,0.0016527271,0.0020759003,0.00084070064,0.0013436548,0.0030963535,0.0027634331,0.0019135249],"category_scores_gemma":[0.0024862716,0.0014188738,0.0011719031,0.00076939084,0.0010951995,0.0005078563,0.00092808006,0.0030394585,0.0006877195],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.0024154005,0.0014081764,0.022363365,0.0018131449,0.0022867227,0.0019314566,0.013626756,0.016660212,0.0020541174,0.8155451,0.061302144,0.058593396],"study_design_scores_gemma":[0.004839174,0.0006091544,0.011592266,0.0024918942,0.001981114,0.0010463642,0.0025979653,0.1257721,0.00046236662,0.049400322,0.7973463,0.0018609818],"about_ca_topic_score_codex":0.00015993179,"about_ca_topic_score_gemma":0.00010793704,"teacher_disagreement_score":0.7661448,"about_ca_system_score_codex":0.006330205,"about_ca_system_score_gemma":0.02864289,"threshold_uncertainty_score":0.9998249},"labels":[],"label_agreement":null},{"id":"W4410103324","doi":"10.1177/21582440251335171","title":"Prevalence and Quality of Mixed Methods Research in Educational Subdisciplines: A Systematic Review","year":2025,"lang":"en","type":"review","venue":"SAGE Open","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Quality (philosophy); Multimethodology; Systematic review; Psychology; MEDLINE; Mathematics education; Political science; Epistemology","score_opus":0.7921660796059052,"score_gpt":0.7663058905935556,"score_spread":0.025860189012349655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410103324","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000023033442,0.9861444,0.00008948388,0.00047515513,0.00021899598,0.0064422046,0.00005124983,0.0000022833567,0.006573928],"genre_scores_gemma":[0.0000038907915,0.97859675,0.003356344,0.000050418195,0.00002211162,0.001693993,0.000019915884,0.000007158627,0.016249416],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9701115,0.02275768,0.0038222119,0.0007894484,0.002277533,0.00024163499],"domain_scores_gemma":[0.9719127,0.024594495,0.0012745635,0.0014183822,0.0007217871,0.000078078505],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1473842,0.00021135875,0.003124717,0.0006703304,0.000107075255,0.00029220863,0.0027238433,0.00012141466,0.0010013182],"category_scores_gemma":[0.025356123,0.00012881515,0.00020346353,0.003001638,0.00012945307,0.0003492328,0.0015533074,0.00037036627,0.000094307376],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015238679,0.000038743878,0.00008988383,0.7618661,0.00001590022,1.382259e-7,0.000061375926,6.020918e-8,4.2873264e-8,0.0011164158,0.0005155637,0.23629424],"study_design_scores_gemma":[0.00010430696,0.000019165105,0.00064048247,0.9537758,0.00020208201,0.0000020714592,0.0001519602,0.0000069705625,2.0065136e-7,0.004717413,0.040226586,0.0001529459],"about_ca_topic_score_codex":0.00005996557,"about_ca_topic_score_gemma":0.0001550362,"teacher_disagreement_score":0.2361413,"about_ca_system_score_codex":0.00013214712,"about_ca_system_score_gemma":0.0035241977,"threshold_uncertainty_score":0.9999119},"labels":[],"label_agreement":null},{"id":"W4410202591","doi":"10.7202/1117870ar","title":"Utiliser une banque de cas pour comprendre les politiques pour la santé publique et leurs enjeux éthiques","year":2025,"lang":"fr","type":"article","venue":"Canadian Journal of Bioethics","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"McGill University; Université TÉLUQ; The Quebec Population Health Research Network; Université du Québec à Montréal","funders":"","keywords":"Political science","score_opus":0.40546543600179497,"score_gpt":0.545016638663841,"score_spread":0.13955120266204601,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410202591","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14048767,0.018602282,0.012949529,0.76696014,0.0025415663,0.00022513863,0.0002700257,0.00002189267,0.057941783],"genre_scores_gemma":[0.9514971,0.005053491,0.0062410715,0.021479072,0.00048995635,0.000003854018,0.000009706823,0.00002820339,0.015197594],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99314183,0.0033990964,0.0013742001,0.00033933594,0.00097372377,0.0007717921],"domain_scores_gemma":[0.9888922,0.003409334,0.0007213999,0.00045121682,0.0052877595,0.0012380916],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01440144,0.00034432544,0.00060220115,0.0013794599,0.00045162142,0.001136253,0.0011808105,0.0008530262,0.002414483],"category_scores_gemma":[0.0073826625,0.0003121724,0.00033848622,0.001058319,0.0012147577,0.0009797837,0.00007044315,0.0024743224,0.000057844496],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003805529,0.00008432898,0.06199189,0.000121076446,0.0001669308,0.0003758045,0.015029323,0.00049641845,0.000092983246,0.6915643,0.14136085,0.08867801],"study_design_scores_gemma":[0.00089581346,0.00021430264,0.07902962,0.0017191524,0.00013214539,0.00064658996,0.029303582,0.0029168096,0.0020276704,0.30633453,0.57633454,0.0004452686],"about_ca_topic_score_codex":0.11496955,"about_ca_topic_score_gemma":0.6023741,"teacher_disagreement_score":0.8110094,"about_ca_system_score_codex":0.001051762,"about_ca_system_score_gemma":0.06778129,"threshold_uncertainty_score":0.99993306},"labels":[],"label_agreement":null},{"id":"W4410203269","doi":"10.1080/15265161.2025.2488264","title":"Critically Evaluating MAID in Canada Through an Inequities Lens","year":2025,"lang":"en","type":"letter","venue":"The American Journal of Bioethics","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Brock University","funders":"","keywords":"Lens (geology); Optometry; Political science; Sociology; Optics; Medicine; Physics","score_opus":0.4336791379518888,"score_gpt":0.5528043784759129,"score_spread":0.11912524052402412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410203269","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048649695,0.00016216746,0.0005246501,0.9466639,0.001153104,0.00013026113,0.000041619278,0.0000046844393,0.0026698906],"genre_scores_gemma":[0.09717457,0.00050143444,0.0030198602,0.8973789,0.0013301788,0.0000046168825,0.000007391596,0.000018569453,0.0005644301],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9888163,0.0030093582,0.001994873,0.00029903286,0.005428415,0.00045200897],"domain_scores_gemma":[0.9860227,0.00824587,0.002159743,0.0007928232,0.0027167078,0.00006215273],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.016021004,0.000268842,0.0009626041,0.00035202876,0.0002006473,0.0002759683,0.0021592642,0.00014822713,0.00041441794],"category_scores_gemma":[0.005737248,0.00015772265,0.000169814,0.0011015873,0.001037303,0.00057861826,0.00017026585,0.0045035305,0.000011994535],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016126792,0.000039458522,0.0031311805,0.00004817122,0.00011740664,0.00026706106,0.0046617608,0.0022432834,0.000037684706,0.0018139425,0.92976385,0.057714943],"study_design_scores_gemma":[0.0010413106,0.0032330044,0.008015649,0.0011030518,0.00029864715,0.00031613515,0.0770561,0.0062561906,0.00012953588,0.05917146,0.84239703,0.0009818964],"about_ca_topic_score_codex":0.3450369,"about_ca_topic_score_gemma":0.48317733,"teacher_disagreement_score":0.13814044,"about_ca_system_score_codex":0.0007088128,"about_ca_system_score_gemma":0.021456782,"threshold_uncertainty_score":0.99779314},"labels":[],"label_agreement":null},{"id":"W4410343200","doi":"10.36367/ntqr.21.2.2025.e1261","title":"UNLOCKING THE POTENTIAL OF QUALITATIVELY ORIENTED MIXED METHODS RESEARCH","year":2025,"lang":"en","type":"article","venue":"New Trends in Qualitative Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science","score_opus":0.8085162221333939,"score_gpt":0.8054898790584072,"score_spread":0.003026343074986726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410343200","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45594934,0.0024117727,0.18185723,0.096300386,0.0017025807,0.0015721158,0.00008219322,0.000062974534,0.2600614],"genre_scores_gemma":[0.9249287,0.000056964145,0.023317443,0.00009083383,0.000076374665,0.00011324203,0.00001212406,0.000014028738,0.051390268],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.87130016,0.112207875,0.0024771069,0.0012212864,0.011460782,0.0013327956],"domain_scores_gemma":[0.91542953,0.077164166,0.0003052657,0.001264601,0.005659728,0.00017669029],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.27491868,0.00018279399,0.0005260055,0.005389791,0.0006633657,0.0002402533,0.0018424623,0.00014758673,0.0029976054],"category_scores_gemma":[0.03982884,0.00011377951,0.00017898051,0.020263063,0.0015299544,0.00036300565,0.0007753124,0.0015742274,0.00015300595],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031114044,0.00017500036,0.0005862714,0.000016503116,0.000054780972,0.000002435031,0.10445011,0.00022867907,0.002828417,0.27931917,0.047295302,0.5647322],"study_design_scores_gemma":[0.0015184307,0.00039937635,0.03760456,0.00013706963,0.0000066698526,6.11748e-7,0.49183083,0.0063477955,0.0050991033,0.40450072,0.052397367,0.00015747597],"about_ca_topic_score_codex":0.0013867932,"about_ca_topic_score_gemma":0.00087004073,"teacher_disagreement_score":0.5645747,"about_ca_system_score_codex":0.00035002254,"about_ca_system_score_gemma":0.0016801252,"threshold_uncertainty_score":0.9979138},"labels":[],"label_agreement":null},{"id":"W4410439814","doi":"10.3390/educsci15050613","title":"The Consolidated Framework for Implementation Research: Application to Education","year":2025,"lang":"en","type":"article","venue":"Education Sciences","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Ontario Tech University; St. Francis Xavier University","funders":"","keywords":"Computer science; Process management; Higher education; Mathematics education; Knowledge management; Political science; Business; Psychology","score_opus":0.5133591673148261,"score_gpt":0.7409893788099423,"score_spread":0.2276302114951162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410439814","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22524638,0.0010972269,0.3252634,0.32064763,0.012260701,0.007769983,0.000024419285,0.00011728111,0.107572965],"genre_scores_gemma":[0.97154063,0.000036735477,0.0144671565,0.0031114134,0.00021577408,0.0024874453,0.000016729406,0.000004327813,0.008119806],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99666226,0.00037670563,0.0005880736,0.0005200628,0.0015477104,0.00030521123],"domain_scores_gemma":[0.99290717,0.003698303,0.00021004428,0.00058396964,0.0025027168,0.000097811266],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.01281103,0.00008743827,0.00009938257,0.00069473096,0.0024338977,0.001228872,0.0011512397,0.000048240287,0.00018171324],"category_scores_gemma":[0.0039772596,0.00005683432,0.000044289733,0.0045425487,0.0002798912,0.0004522883,0.00008467029,0.000112762784,0.00034226765],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006173713,0.00003931005,0.0023823997,0.0000017230552,0.0000019155282,6.724484e-10,0.0007768347,0.000015508784,0.00013140494,0.4426086,0.0948348,0.45920134],"study_design_scores_gemma":[0.000051026098,0.000048750426,0.0147846555,0.000022537613,0.0000033221468,1.8156754e-7,0.0387017,0.00048129944,0.0010667047,0.4327105,0.5120718,0.000057555753],"about_ca_topic_score_codex":0.00009366518,"about_ca_topic_score_gemma":0.0002481425,"teacher_disagreement_score":0.7462942,"about_ca_system_score_codex":0.00016781162,"about_ca_system_score_gemma":0.006749944,"threshold_uncertainty_score":0.99980795},"labels":[],"label_agreement":null},{"id":"W4410490974","doi":"10.4000/13yaq","title":"Les pratiques évaluatives sommatives déclarées d’enseignant·e·s québécois·es d’ÉPS en termes de planification et de prise d’informations","year":2025,"lang":"fr","type":"article","venue":"Ejournal de la recherche sur l intervention en éducation physique et sport -eJRIEPS","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Humanities; Political science; Mathematics; Art","score_opus":0.28835258688971105,"score_gpt":0.5612544978347789,"score_spread":0.2729019109450678,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410490974","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73250747,0.0022002675,0.18073666,0.052814137,0.00091883907,0.00096151873,0.00005114257,0.00016550244,0.029644432],"genre_scores_gemma":[0.9256263,0.0064209374,0.0226891,0.0014438711,0.00026378126,0.00036739607,0.00023605178,0.000049400503,0.042903155],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9758052,0.019497635,0.002352843,0.0006089881,0.001115615,0.0006196866],"domain_scores_gemma":[0.9858985,0.009624715,0.0019205011,0.0006641398,0.0016251063,0.000267035],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06065154,0.0005491356,0.0006491802,0.0009281534,0.000529668,0.0013502894,0.000934557,0.00091288576,0.0017630672],"category_scores_gemma":[0.011556264,0.00052057195,0.0006352573,0.0011170995,0.00033288467,0.004494666,0.00015481567,0.0024846673,0.00012335299],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.0002320379,0.002231798,0.032351483,0.00058110553,0.00050129596,0.000008171698,0.44642717,0.005116612,0.0027585465,0.31502187,0.015182304,0.17958759],"study_design_scores_gemma":[0.0011093221,0.0002102065,0.6935228,0.0024526222,0.0002149797,0.000098105316,0.10460246,0.010810646,0.009130078,0.10137837,0.07591328,0.0005571294],"about_ca_topic_score_codex":0.004433562,"about_ca_topic_score_gemma":0.00868951,"teacher_disagreement_score":0.6611713,"about_ca_system_score_codex":0.0039924653,"about_ca_system_score_gemma":0.01358224,"threshold_uncertainty_score":0.999831},"labels":[],"label_agreement":null},{"id":"W4410523880","doi":"10.1136/bmjoq-2025-qshu.187","title":"187 Improving departmental quality improvement plans through standardization, structured peer-to-peer feedback, and building improvement capacity and culture","year":2025,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kingston Health Sciences Centre; McMaster University Medical Centre","funders":"","keywords":"Standardization; Quality management; Computer science; Capacity planning; Quality (philosophy); Performance improvement; Peer-to-peer; Process management; Engineering management; Knowledge management; Operations management; Business; Engineering; Operating system; World Wide Web; Management system","score_opus":0.07708762795380153,"score_gpt":0.44966369726492444,"score_spread":0.3725760693111229,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410523880","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85906667,0.000057193858,0.12867129,0.0063916543,0.0005668929,0.00096505834,0.00028344285,0.00006571414,0.0039321138],"genre_scores_gemma":[0.9674195,0.000020806196,0.0208518,0.0030036767,0.00006431376,0.000056694473,0.000035498066,0.000010105116,0.008537627],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9951182,0.00013422567,0.00098576,0.00086218375,0.002514731,0.00038491318],"domain_scores_gemma":[0.9976531,0.00020286247,0.00027116237,0.00050349586,0.0011873421,0.00018203628],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041248826,0.00030104662,0.00040053212,0.00017692648,0.00061568874,0.0008788781,0.00032795192,0.00012401765,0.0003246171],"category_scores_gemma":[0.0009426784,0.00020997548,0.00006832619,0.00057535915,0.000112311194,0.00073426066,0.00039715366,0.00019829327,0.0000070650467],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029807494,0.00019473901,0.09779686,0.00016055447,0.00025508302,0.0000019354834,0.013906914,0.0007171517,0.2089143,0.05040676,0.050632708,0.57671493],"study_design_scores_gemma":[0.007981972,0.0015562718,0.2019512,0.00011367055,0.0001911342,0.000010958926,0.0515852,0.010546144,0.28763378,0.08048638,0.35630354,0.0016397495],"about_ca_topic_score_codex":0.00040517419,"about_ca_topic_score_gemma":0.0015137341,"teacher_disagreement_score":0.5750752,"about_ca_system_score_codex":0.00026007948,"about_ca_system_score_gemma":0.00020542502,"threshold_uncertainty_score":0.8562551},"labels":[],"label_agreement":null},{"id":"W4410524996","doi":"10.1080/25741292.2025.2506262","title":"Educating for uncertainty: Integrating abductive reasoning into the public policy curriculum","year":2025,"lang":"en","type":"article","venue":"Policy Design and Practice","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Research Foundation of Korea; National Research Foundation","keywords":"Abductive reasoning; Curriculum; Psychology; Mathematics education; Management science; Sociology; Computer science; Pedagogy; Artificial intelligence; Engineering","score_opus":0.17503930331929254,"score_gpt":0.5538830924219238,"score_spread":0.3788437891026313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410524996","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0045697098,0.0007961083,0.4704832,0.46327943,0.0005493717,0.001122893,0.0000033302201,0.00005835222,0.059137587],"genre_scores_gemma":[0.8640987,0.0002689073,0.11085297,0.019081369,0.0010152635,0.00037909643,0.0000052896185,0.000016117665,0.004282275],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964424,0.001616553,0.0005365175,0.00041753936,0.0006280141,0.0003589847],"domain_scores_gemma":[0.97195214,0.025522638,0.00055569917,0.0005135105,0.0013255196,0.00013046629],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.015941974,0.00017194501,0.00021204462,0.00054203253,0.0011896588,0.0012009054,0.0005119822,0.00006713365,0.000059769798],"category_scores_gemma":[0.1593184,0.00010353724,0.0000717365,0.0021400314,0.00014012742,0.0013108685,0.00014187252,0.00027574378,0.0000303162],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058361158,0.00005531337,0.00043679043,0.000008670782,0.000043682736,2.2998329e-7,0.009346857,0.0001946925,0.00021061639,0.63922113,0.009193877,0.3412298],"study_design_scores_gemma":[0.0006064581,0.00016053063,0.0004837512,0.00007963251,0.00006751355,0.000045527642,0.0809653,0.12639311,0.0001489241,0.248764,0.5420239,0.00026134733],"about_ca_topic_score_codex":0.0029158122,"about_ca_topic_score_gemma":0.00020526351,"teacher_disagreement_score":0.859529,"about_ca_system_score_codex":0.00021640578,"about_ca_system_score_gemma":0.0031927568,"threshold_uncertainty_score":0.99983597},"labels":[],"label_agreement":null},{"id":"W4410632682","doi":"10.22215/etd/2024-16380","title":"“Long, Long Time Ago”: Collaborative Engagement with Indigenous Descendant Communities in Ontario through Object Elicitation","year":2024,"lang":"en","type":"dissertation","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Carleton University","funders":"","keywords":"Descendant; Indigenous; Geography; Object (grammar); Computer science; Ecology; Artificial intelligence; Biology","score_opus":0.13523621123454752,"score_gpt":0.44834666908051063,"score_spread":0.31311045784596314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410632682","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8643332,0.00044146224,0.00036597744,0.00012095576,0.0006928978,0.0014781398,0.00002440916,0.00007910046,0.13246386],"genre_scores_gemma":[0.8083195,0.00020686904,0.002096864,0.00037521866,0.00005202796,0.00036475717,0.0031661752,0.000060093542,0.1853585],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99407285,0.00084508036,0.001218461,0.00058386504,0.0028604823,0.00041925436],"domain_scores_gemma":[0.9964577,0.0009817577,0.0005604548,0.0006916558,0.0012351074,0.000073346484],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0043342193,0.0004820656,0.00066088577,0.0008614346,0.00045345243,0.0010198564,0.00070801075,0.00024163625,0.009257368],"category_scores_gemma":[0.00012674561,0.0003312103,0.0001051779,0.0015951548,0.000079064936,0.00088444847,0.00007370676,0.0011096119,0.0017204882],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005195088,0.00033782693,0.046582844,0.00011995427,0.00027527622,0.00007862106,0.92603695,0.002230011,0.000045754437,0.0011591899,0.004410595,0.018203445],"study_design_scores_gemma":[0.0017033234,0.0013526025,0.4566907,0.0014891734,0.00023716677,0.000011088996,0.5032662,0.0023720479,0.0014596712,0.005320038,0.024729148,0.0013688238],"about_ca_topic_score_codex":0.055853616,"about_ca_topic_score_gemma":0.9666986,"teacher_disagreement_score":0.910845,"about_ca_system_score_codex":0.0011107238,"about_ca_system_score_gemma":0.004736409,"threshold_uncertainty_score":0.999914},"labels":[],"label_agreement":null},{"id":"W4410799851","doi":"10.56645/jmde.v21i50.1173","title":"Ray Rist: An Evaluator at the Government Accountability Office (GAO)","year":2025,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Carleton University","funders":"","keywords":"Accountability; Government (linguistics); Political science; Linguistics; Philosophy; Law","score_opus":0.16430975445695797,"score_gpt":0.5301316705100111,"score_spread":0.36582191605305314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410799851","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9805992,0.0004298054,0.003010206,0.008600093,0.0019596857,0.0007954471,0.00001765293,0.000010270503,0.0045776125],"genre_scores_gemma":[0.99590176,0.000043773194,0.0009545726,0.0002985007,0.00025524435,0.00003699676,0.000008522961,0.000009408245,0.002491231],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98528624,0.002657589,0.001963623,0.00043786276,0.009398041,0.0002566641],"domain_scores_gemma":[0.9919024,0.002160104,0.0016168959,0.0010513888,0.0031343673,0.0001348178],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.06662107,0.0002136739,0.00037771475,0.00019273146,0.0007771644,0.00026952507,0.0010909438,0.00010865917,0.0044642603],"category_scores_gemma":[0.0045581535,0.000119666794,0.00027426,0.0007931192,0.00015897791,0.0013320894,0.00036184068,0.00034654542,0.00021617002],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0041069323,0.001992282,0.26310265,0.00003827945,0.00026649548,0.0000075886132,0.010247321,0.18083957,0.011053025,0.00044067053,0.04728979,0.4806154],"study_design_scores_gemma":[0.0018426218,0.00030928655,0.7232678,0.00004317644,0.0001977452,0.000012514128,0.00509185,0.2562713,0.0006819403,0.0044345134,0.0077168527,0.00013041876],"about_ca_topic_score_codex":0.000009952273,"about_ca_topic_score_gemma":0.00032062054,"teacher_disagreement_score":0.48048496,"about_ca_system_score_codex":0.0016858544,"about_ca_system_score_gemma":0.0013602324,"threshold_uncertainty_score":0.9964458},"labels":[],"label_agreement":null},{"id":"W4410799871","doi":"10.56645/jmde.v21i50.1175","title":"From Studies to Systems: Ray Rist’s Influence on Evaluation Systems: Insights from International Research Group for Policy and Program Evaluation (INTEVAL)","year":2025,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Group (periodic table); Psychology; Management science; Political science; Engineering; Chemistry","score_opus":0.42995390967908126,"score_gpt":0.6383168529536529,"score_spread":0.20836294327457167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410799871","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9689114,0.0054623396,0.0029322014,0.008068181,0.0049676117,0.008732039,0.00007973056,0.000026939799,0.00081953424],"genre_scores_gemma":[0.99249446,0.00022929533,0.0027022914,0.00010387926,0.0015341974,0.0024969634,0.00013843294,0.000021205105,0.00027926054],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97699106,0.0057209698,0.0027920902,0.0009479204,0.013166466,0.00038150733],"domain_scores_gemma":[0.9627817,0.007645054,0.0015845032,0.0007311038,0.027041718,0.00021588734],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06507224,0.00033652753,0.0007191424,0.002806047,0.0006954283,0.00094967184,0.00095024967,0.00021071236,0.000067625406],"category_scores_gemma":[0.04000937,0.00024761935,0.00017958341,0.0016498887,0.00017835465,0.0015831422,0.00034061685,0.00044427297,0.000061822946],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00204978,0.00079019484,0.0033248037,0.00006589515,0.0007190056,0.0000022446336,0.013780809,0.5444557,0.0037258682,0.0018674593,0.010700385,0.41851786],"study_design_scores_gemma":[0.0046072593,0.0012690255,0.084568866,0.0014142067,0.00038809518,0.0000034673922,0.019850466,0.84711754,0.00015309625,0.035223555,0.005176064,0.0002283418],"about_ca_topic_score_codex":0.00028147356,"about_ca_topic_score_gemma":0.00022160322,"teacher_disagreement_score":0.4182895,"about_ca_system_score_codex":0.0035284439,"about_ca_system_score_gemma":0.0025868695,"threshold_uncertainty_score":0.9999976},"labels":[],"label_agreement":null},{"id":"W4410833463","doi":"10.26034/vd.fpeq.2021.304","title":"Transition vers une notation succès/échec pour l’évaluation de stages en enseignement au Québec : regards croisés de divers acteurs impliqués","year":2021,"lang":"fr","type":"article","venue":"Formation et pratiques d’enseignement en question","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Notation; Mathematics; Arithmetic","score_opus":0.04905474240041743,"score_gpt":0.4069169876478099,"score_spread":0.3578622452473925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410833463","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5611238,0.00045742444,0.36729905,0.064459614,0.001020371,0.0010684272,0.00013518191,0.00018311678,0.0042530308],"genre_scores_gemma":[0.95968443,0.0020960027,0.026384419,0.0035300625,0.0004012386,0.00031078063,0.0018652347,0.000060068094,0.005667754],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.986306,0.0069275596,0.0020657333,0.00085935416,0.0029279522,0.00091337616],"domain_scores_gemma":[0.9945322,0.0010945582,0.0012099632,0.0006941081,0.0021087895,0.00036033586],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.015154977,0.0006366381,0.0005609865,0.00060513814,0.0009844633,0.0009074449,0.0004247756,0.00060319336,0.0028867382],"category_scores_gemma":[0.0018650377,0.0006835139,0.00032058562,0.0010767609,0.000160768,0.0054716207,0.0001195631,0.00068828405,0.000447624],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.0004999934,0.0011860498,0.0030335758,0.0005898328,0.0002781432,0.00006128075,0.4995258,0.08954516,0.030920373,0.03017112,0.01854996,0.3256387],"study_design_scores_gemma":[0.0072281826,0.0024072623,0.22066574,0.0017027104,0.0010773521,0.00033003115,0.15682147,0.41034204,0.10073787,0.023413677,0.073059455,0.0022142238],"about_ca_topic_score_codex":0.027186118,"about_ca_topic_score_gemma":0.0976051,"teacher_disagreement_score":0.39856064,"about_ca_system_score_codex":0.011719823,"about_ca_system_score_gemma":0.015536737,"threshold_uncertainty_score":0.9995616},"labels":[],"label_agreement":null},{"id":"W4411017294","doi":"10.3917/e.resg.093.0073","title":"Ranking Research: Toward an Ethnostatistical Perspective on Performance Metrics in Higher Education","year":2012,"lang":"en","type":"article","venue":"Recherches en Sciences de Gestion","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Ranking (information retrieval); Perspective (graphical); Computer science; Psychology; Data science; Mathematics education; Information retrieval; Artificial intelligence","score_opus":0.9097330040120792,"score_gpt":0.6923624310607263,"score_spread":0.21737057295135298,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411017294","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9392681,0.00023498561,0.0019263108,0.009937996,0.0007799103,0.0002726323,0.0000017429077,0.000034553414,0.04754378],"genre_scores_gemma":[0.98054934,0.00010977372,0.01715349,0.00036647535,0.00029826668,0.000049127717,0.000003055277,0.000007443752,0.0014630312],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9914463,0.004363684,0.0004113803,0.0004840293,0.0027135182,0.00058104994],"domain_scores_gemma":[0.99138963,0.0073101297,0.000116558374,0.0003180373,0.0006534092,0.00021225408],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08010309,0.00012592258,0.00016571746,0.0013266446,0.00033738813,0.000308774,0.000676713,0.00021051777,0.00063325214],"category_scores_gemma":[0.015108041,0.00009542135,0.00003422812,0.0042355424,0.0003285947,0.0017281343,0.00007532246,0.00078941457,0.000349453],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008650027,0.00063643215,0.23004137,0.000011290726,0.0000036882368,6.1916205e-7,0.030933851,0.0028803546,0.00064571254,0.31753698,0.0006311515,0.41659203],"study_design_scores_gemma":[0.00018659134,0.00042776144,0.88531786,0.00006002463,0.0000045243482,0.000005411722,0.013435113,0.038799822,0.000565682,0.059093934,0.0019302345,0.00017306748],"about_ca_topic_score_codex":0.00033690772,"about_ca_topic_score_gemma":0.000045596244,"teacher_disagreement_score":0.6552765,"about_ca_system_score_codex":0.0023519027,"about_ca_system_score_gemma":0.001160816,"threshold_uncertainty_score":0.99318814},"labels":[],"label_agreement":null},{"id":"W4411023204","doi":"10.4324/9781003510284-17","title":"Beyond implementation","year":2025,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.21832442708437227,"score_gpt":0.5478224649344168,"score_spread":0.3294980378500445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411023204","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000008060296,0.000060908787,0.0014675912,0.0020292448,0.00063995406,0.0002267231,0.00003307429,0.000029582596,0.99550486],"genre_scores_gemma":[0.00090551196,0.00006567798,0.000747299,0.0021803572,0.00010065517,0.000008072244,0.00007911638,0.0000068818017,0.9959064],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971625,0.000021686516,0.0006590033,0.00035343945,0.0016950571,0.000108290966],"domain_scores_gemma":[0.99846315,0.00032619643,0.000255984,0.0004870638,0.00042006664,0.000047535967],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0017067937,0.00014972423,0.00022222473,0.00038261563,0.00009348967,0.00018555197,0.00037855643,0.0001146841,0.19787368],"category_scores_gemma":[0.00005522472,0.00010590972,0.00012410125,0.00006672086,0.000026444084,0.0001702162,0.000110160916,0.00012745935,0.0045420006],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013779799,0.0000013187052,0.00006241905,0.0000012067616,0.000008635676,3.0808374e-7,0.000023040908,0.000001572848,0.0000011515586,0.5027538,0.27237844,0.22476675],"study_design_scores_gemma":[0.000115916315,0.000019839845,0.0001830399,0.0000065167865,0.00001261168,3.64183e-7,0.00008582348,0.00011954129,0.000024335535,0.31008527,0.6892585,0.00008823434],"about_ca_topic_score_codex":0.000008648611,"about_ca_topic_score_gemma":0.00029198904,"teacher_disagreement_score":0.41688004,"about_ca_system_score_codex":0.00006584538,"about_ca_system_score_gemma":0.0004216776,"threshold_uncertainty_score":0.9962331},"labels":[],"label_agreement":null},{"id":"W4411134512","doi":"10.7202/1118271ar","title":"L’entrevue cognitive : les apports et les limites dans la validation d’un questionnaire","year":2024,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université du Québec en Abitibi-Témiscamingue; University of Ottawa","funders":"","keywords":"Political science; Psychology; Humanities; Philosophy","score_opus":0.15362133875675418,"score_gpt":0.48029423292388873,"score_spread":0.3266728941671345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411134512","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5320831,0.009965341,0.28478163,0.12721786,0.00843766,0.0016060234,0.00015509731,0.0003801517,0.03537314],"genre_scores_gemma":[0.9754023,0.0022585287,0.0013015444,0.00043378072,0.0005307316,0.00023895955,0.0011188583,0.00005774082,0.018657587],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9798023,0.014957091,0.0013187781,0.0010233289,0.002522561,0.00037594466],"domain_scores_gemma":[0.9914975,0.0058425907,0.0005185005,0.00041650268,0.0015683793,0.00015653516],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.053337324,0.0004425901,0.00036438883,0.0006858173,0.0005063493,0.0014524808,0.00030608973,0.0004997392,0.007089402],"category_scores_gemma":[0.0065913983,0.0004194246,0.00023783249,0.0014055703,0.0002268369,0.0026285786,0.000084689425,0.00068664993,0.0018898026],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002615019,0.00043591217,0.027467465,0.0001998689,0.0001387785,0.000009440796,0.15545739,0.0042845043,0.00042959812,0.057206735,0.0065946295,0.7477495],"study_design_scores_gemma":[0.0006977516,0.00021693765,0.7738185,0.0023901858,0.0006363092,0.00010890562,0.02274082,0.11464293,0.0025900374,0.030314779,0.051102325,0.0007405433],"about_ca_topic_score_codex":0.00035634587,"about_ca_topic_score_gemma":0.0006294809,"teacher_disagreement_score":0.747009,"about_ca_system_score_codex":0.0005406677,"about_ca_system_score_gemma":0.0037543578,"threshold_uncertainty_score":0.9998258},"labels":[],"label_agreement":null},{"id":"W4411134913","doi":"10.1016/j.jmir.2025.101957","title":"Ready for the Big Time: Provincial Formalization of an APRT(T) Class of Practice","year":2025,"lang":"en","type":"article","venue":"Journal of medical imaging and radiation sciences","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; Southlake Regional Health Center; BC Cancer Agency; University of Alberta; Health Sciences Centre; Sunnybrook Health Science Centre; Nova Scotia Health Authority","funders":"","keywords":"Class (philosophy); Computer science; Artificial intelligence","score_opus":0.09908406302182318,"score_gpt":0.5160014253647472,"score_spread":0.4169173623429241,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411134913","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39811108,0.005053941,0.3500347,0.23384967,0.0046609472,0.00072539743,0.000019634237,0.00001410006,0.007530497],"genre_scores_gemma":[0.9960773,0.0004748676,0.0019126106,0.0011811288,0.00020671591,0.0000024550204,9.900782e-7,0.0000016111111,0.00014230865],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961748,0.00023230708,0.0008398713,0.0001060764,0.002558629,0.00008832748],"domain_scores_gemma":[0.9940462,0.0035925892,0.0011035535,0.00010170064,0.0010888386,0.00006709371],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.023566673,0.000048432074,0.00017101596,0.00031335253,0.0002228552,0.00012679587,0.0005028021,0.000035100828,0.000045891593],"category_scores_gemma":[0.014311399,0.000024285227,0.000046375942,0.0006659126,0.00039194123,0.0010192872,0.000032308075,0.0000935901,7.1065045e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006426941,0.00008048576,0.004975143,0.00001202072,0.000014997942,3.8503092e-7,0.0010978462,0.00090659177,0.0002500602,0.006133514,0.0074441824,0.9790205],"study_design_scores_gemma":[0.001099472,0.00031312043,0.020239959,0.00008632247,0.000072543844,0.000035535515,0.009453018,0.86515325,0.00087090436,0.0046342495,0.09798161,0.00006004059],"about_ca_topic_score_codex":0.00002468285,"about_ca_topic_score_gemma":0.000010396602,"teacher_disagreement_score":0.97896045,"about_ca_system_score_codex":0.000016748045,"about_ca_system_score_gemma":0.001364158,"threshold_uncertainty_score":0.9939915},"labels":[],"label_agreement":null},{"id":"W4411157354","doi":"10.1080/10645578.2025.2480500","title":"Conceptualizing the Dimensions of Organizational Evaluation Capacity in Art Museums: A Framework for Visitor Studies","year":2025,"lang":"en","type":"article","venue":"Visitor Studies","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Visitor pattern; Museology; Public relations; Sociology; Political science; Visual arts; Art; Computer science","score_opus":0.45420861115937466,"score_gpt":0.5455654716352704,"score_spread":0.0913568604758957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411157354","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9475874,0.011935315,0.01305156,0.017923564,0.0061576418,0.0023648574,0.000050410978,0.000056522298,0.00087275176],"genre_scores_gemma":[0.99494517,0.0004305037,0.0030582044,0.00062503683,0.00021820972,0.00024727246,0.000005302288,0.0000073472934,0.00046297433],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9966832,0.00044852824,0.0008857004,0.0003869992,0.001398685,0.00019689398],"domain_scores_gemma":[0.98776644,0.0080745015,0.0003538732,0.00043286028,0.0033477857,0.0000245161],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006024048,0.00016216202,0.00046457897,0.00027994777,0.0005060134,0.000063426436,0.00035254055,0.00006740575,0.00007222147],"category_scores_gemma":[0.021829767,0.00008827729,0.00009753921,0.0014776419,0.00030873224,0.00021425381,0.00021282458,0.00012946113,0.000035512243],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002377338,0.0005290775,0.25209492,0.00022670046,0.0019312628,9.175245e-7,0.11108547,0.01016319,0.002397662,0.42682734,0.17920238,0.015303352],"study_design_scores_gemma":[0.002591939,0.00032232815,0.15793855,0.0009539736,0.0003696004,0.0000010163078,0.23748665,0.02730689,0.0033509042,0.5308175,0.038388412,0.00047221463],"about_ca_topic_score_codex":0.0000046164723,"about_ca_topic_score_gemma":0.00012477957,"teacher_disagreement_score":0.14081396,"about_ca_system_score_codex":0.00019145083,"about_ca_system_score_gemma":0.0002738914,"threshold_uncertainty_score":0.9864098},"labels":[],"label_agreement":null},{"id":"W4411157553","doi":"10.1080/10645578.2025.2494485","title":"Implementing Culturally Responsive Evaluation Methods: Reflections on Challenges to Traditional Understandings of Power, Validity, and Rigor","year":2025,"lang":"en","type":"article","venue":"Visitor Studies","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Learning Partnership","funders":"National Aeronautics and Space Administration","keywords":"Power (physics); Rigour; Sociology; Psychology; Engineering ethics; Political science; Epistemology; Engineering","score_opus":0.728286921715105,"score_gpt":0.6583180992551956,"score_spread":0.06996882245990943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411157553","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78719956,0.0052863825,0.012756143,0.084440924,0.0040152557,0.0019620298,0.000084072424,0.00009498088,0.10416065],"genre_scores_gemma":[0.9890832,0.00056239153,0.009052254,0.00044029337,0.00008113309,0.00007971653,0.0000026050373,0.00000424879,0.00069416536],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9969105,0.00073496025,0.0005269422,0.0003824191,0.0012675801,0.0001775623],"domain_scores_gemma":[0.99503213,0.0032001256,0.00020581858,0.00021745403,0.001301365,0.000043104304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010451761,0.00012354336,0.0002798758,0.0005003039,0.00056016416,0.00008122113,0.00016201292,0.00003572888,0.00013707842],"category_scores_gemma":[0.004361462,0.000087885295,0.000067096786,0.0006242067,0.00008905727,0.00020521291,0.00015232612,0.000078914585,0.000011903825],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006843905,0.0003681496,0.0034769126,0.000109578876,0.0009583873,0.0000015617105,0.08169604,0.0004987387,0.019088993,0.53196305,0.06565853,0.2954957],"study_design_scores_gemma":[0.0019760076,0.0020041387,0.27905497,0.00038523573,0.00026362803,0.0000038664825,0.27401933,0.001211464,0.010121173,0.33125722,0.09924677,0.00045618752],"about_ca_topic_score_codex":0.000004290814,"about_ca_topic_score_gemma":0.00010941061,"teacher_disagreement_score":0.2950395,"about_ca_system_score_codex":0.00018836708,"about_ca_system_score_gemma":0.00013440235,"threshold_uncertainty_score":0.5221392},"labels":[],"label_agreement":null},{"id":"W4411338512","doi":"10.3390/educsci15060752","title":"RETRACTED: The Possibilities and Impossibilities of Transformative Leadership: An Autoethnographic Study of Demographic Data Policy Enactment in Ontario","year":2025,"lang":"en","type":"article","venue":"Education Sciences","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":true,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Western University","funders":"","keywords":"Transformative learning; Autoethnography; Sociology; Educational leadership; Transformational leadership; Instructional leadership; Pedagogy; Public relations; Political science; Social science","score_opus":0.519866322832364,"score_gpt":0.56007901721874,"score_spread":0.04021269438637598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411338512","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9921055,0.00034615787,0.000025883539,0.0031656465,0.0002699723,0.00061496167,0.000011328205,0.000007037385,0.0034535397],"genre_scores_gemma":[0.9988587,0.00003183011,0.00022040308,0.00018021525,0.0000118972785,0.00003332286,0.0000061994,0.0000016773192,0.0006557453],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99640584,0.00062074594,0.000989989,0.00046154635,0.0013359459,0.0001859167],"domain_scores_gemma":[0.9972424,0.0011111152,0.00035708505,0.0008978954,0.00034554716,0.000045976416],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010073197,0.00011675483,0.00025014233,0.0014861913,0.00028702195,0.00019128261,0.0013712278,0.000049898237,0.00012965666],"category_scores_gemma":[0.0007608559,0.00006844449,0.000033919812,0.0034383133,0.001126357,0.0017411163,0.00010258869,0.00020179567,8.2593226e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018009392,0.00070719013,0.80967236,0.000015375063,0.000012197937,1.9455214e-8,0.16115989,0.000057709574,0.000053603653,0.0069028516,0.00007357607,0.02132725],"study_design_scores_gemma":[0.0001683718,0.00025627916,0.5821353,0.000041051968,0.0000074858094,2.872622e-7,0.40644297,0.0005510906,0.00007029337,0.01014714,0.00013503087,0.000044688182],"about_ca_topic_score_codex":0.0547337,"about_ca_topic_score_gemma":0.31420958,"teacher_disagreement_score":0.2594759,"about_ca_system_score_codex":0.00006388386,"about_ca_system_score_gemma":0.0046945554,"threshold_uncertainty_score":0.9515609},"labels":[],"label_agreement":null},{"id":"W4411404682","doi":"10.1017/9781009403092.011","title":"Mixed Effects Modelling","year":2025,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science","score_opus":0.1543693640417782,"score_gpt":0.3362003386612167,"score_spread":0.18183097461943848,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411404682","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009305221,0.00011560587,0.037442334,0.00004006634,0.0008438362,0.00043894502,0.00008278452,0.00008740612,0.96085596],"genre_scores_gemma":[0.0019915304,0.000084896536,0.0007142873,0.00016506041,0.00009252129,9.79027e-7,0.000026886812,0.000017850392,0.996906],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971549,0.00012346773,0.00039060242,0.0007108215,0.0013659684,0.00025422024],"domain_scores_gemma":[0.99711007,0.00083863485,0.00035950015,0.00095825375,0.0005740678,0.0001594609],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008915424,0.00033575183,0.00051734294,0.000526442,0.00028923852,0.000164363,0.00107854,0.00034250907,0.000041116404],"category_scores_gemma":[0.00007164413,0.00032674216,0.00031384378,0.000028389777,0.00013390287,0.00016894893,0.00048632768,0.0004499553,0.0001604054],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040915296,0.0000057308757,0.0000030306803,0.000038536586,0.00006165137,0.000046467485,0.000029043822,0.0005688559,0.0000048622014,0.86989826,0.117440194,0.011862435],"study_design_scores_gemma":[0.0004990549,0.000037066846,0.0000120639925,0.00018489217,0.00013383286,0.000001916107,0.00003183594,0.026341759,0.00019176348,0.00028546216,0.971955,0.00032534183],"about_ca_topic_score_codex":0.000039933384,"about_ca_topic_score_gemma":0.0000024315764,"teacher_disagreement_score":0.8696128,"about_ca_system_score_codex":0.0002038137,"about_ca_system_score_gemma":0.00035851594,"threshold_uncertainty_score":0.99991846},"labels":[],"label_agreement":null},{"id":"W4411419444","doi":"10.21825/deuilvanminerva.94064","title":"Max Liboiron en Josh Lepawsky, &lt;em&gt;Discard Studies: Wasting, Systems, and Power&lt;/em&gt; Parels in de modder","year":2024,"lang":"en","type":"article","venue":"De Uil van Minerva","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine","score_opus":0.10778400499997426,"score_gpt":0.425690720970276,"score_spread":0.31790671597030173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411419444","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9717223,0.015402531,0.0011800694,0.0017165696,0.0010670137,0.0004215032,0.000036808102,0.00010967648,0.008343543],"genre_scores_gemma":[0.9865182,0.0008575054,0.001103239,0.00040685697,0.00026375768,0.00009648465,0.000009694926,0.000036609803,0.010707649],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99559194,0.00055026193,0.00097551616,0.00074876397,0.0015356858,0.0005978156],"domain_scores_gemma":[0.99728715,0.0014415006,0.00018703435,0.0005921578,0.00027112488,0.00022100953],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0069878534,0.00031707724,0.00055279635,0.00049097685,0.00015113821,0.0007242869,0.00054204545,0.00017047122,0.00037019796],"category_scores_gemma":[0.0015112837,0.00023743519,0.0001219814,0.0008145761,0.000079392,0.00060639466,0.00029028853,0.0002975885,0.0004557443],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014957052,0.000823539,0.19652419,0.0011573955,0.0005895325,0.00068440224,0.117630854,0.020504592,0.010869956,0.012834347,0.51198053,0.1262511],"study_design_scores_gemma":[0.0033860414,0.0005219675,0.09808048,0.0019225109,0.00016916651,0.00025741148,0.048296407,0.40376088,0.00031940214,0.008771015,0.43323997,0.0012747571],"about_ca_topic_score_codex":0.00003908218,"about_ca_topic_score_gemma":0.0005455533,"teacher_disagreement_score":0.3832563,"about_ca_system_score_codex":0.00031976876,"about_ca_system_score_gemma":0.00036864588,"threshold_uncertainty_score":0.9682326},"labels":[{"model":"gemma","categories":["sts"],"domain":null,"study_design":"theoretical_or_conceptual","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4411674357","doi":"10.55752/amwa.2025.425","title":"Breaking Into Regulatory Writing: Tried and Tested Tips","year":2025,"lang":"en","type":"article","venue":"AMWA Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Medical Council of Canada","funders":"","keywords":"Business","score_opus":0.1167326236647184,"score_gpt":0.5028992897294127,"score_spread":0.3861666660646943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411674357","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95541126,0.0005761492,0.00637349,0.012645132,0.000625404,0.00008723789,6.3605717e-7,0.000022788568,0.024257919],"genre_scores_gemma":[0.9932797,0.000048462764,0.0013796677,0.0017132566,0.00016443894,0.0000018947079,4.569828e-7,0.0000037606326,0.0034083792],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99797076,0.00023353467,0.0005788317,0.000177835,0.0008855459,0.0001534656],"domain_scores_gemma":[0.99845564,0.000627777,0.00022993392,0.00021299926,0.00037599396,0.000097680815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0065350076,0.00008048454,0.0001607542,0.0003331369,0.00044945118,0.00054073636,0.0002725013,0.00004846637,0.000671711],"category_scores_gemma":[0.00095979794,0.000057682,0.000051730283,0.00050952105,0.00006752828,0.00041675064,0.00007909131,0.00023791166,0.000053132313],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026452635,0.00002293683,0.10093227,0.0000050297995,0.000025034085,0.000008764979,0.00081448985,0.00005008484,0.0014692863,0.004933902,0.03378804,0.8579237],"study_design_scores_gemma":[0.0017008727,0.000094480405,0.6537045,0.00015320945,0.00002941923,0.00027822275,0.0034213618,0.009743137,0.000764391,0.07225877,0.25765905,0.00019254329],"about_ca_topic_score_codex":0.0000044149024,"about_ca_topic_score_gemma":0.000017806278,"teacher_disagreement_score":0.85773116,"about_ca_system_score_codex":0.000055896082,"about_ca_system_score_gemma":0.00032068905,"threshold_uncertainty_score":0.73547643},"labels":[],"label_agreement":null},{"id":"W4411699134","doi":"10.1353/obs.2025.a963648","title":"The interventionist approach can address questions related to causes of effects if causes are considered as states instead of interventions","year":2025,"lang":"en","type":"article","venue":"Observational Studies","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"","keywords":"Psychological intervention; Psychology; Political science; Epistemology; Philosophy; Psychiatry","score_opus":0.4067792709568964,"score_gpt":0.5462981473238175,"score_spread":0.13951887636692112,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411699134","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9723033,0.004106501,0.0008203952,0.01825758,0.00083936955,0.0008839875,0.00013590594,0.000039231254,0.00261375],"genre_scores_gemma":[0.99156016,0.00028849725,0.00057030993,0.00028339896,0.000010263683,0.00023513641,0.000033570373,0.0000059163444,0.0070127537],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99691576,0.00041676447,0.0012931367,0.00028436116,0.00093298923,0.0001570096],"domain_scores_gemma":[0.99231833,0.004093432,0.0006616792,0.00038304288,0.0025003946,0.00004310298],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002195414,0.00014838667,0.00041640952,0.00025418118,0.0006338102,0.00010300273,0.00040934177,0.000044664877,0.00006453523],"category_scores_gemma":[0.00841086,0.00009766251,0.00022837328,0.0010688956,0.00039698125,0.00018965133,0.00027745118,0.00011124773,0.00001957746],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011428369,0.0007904886,0.4896705,0.00083469966,0.0018154598,0.000001970895,0.0053372886,0.012675301,0.00029948534,0.4425588,0.040176667,0.005725082],"study_design_scores_gemma":[0.0005583495,0.00021486552,0.90159947,0.0012298158,0.0001115893,0.0000012139506,0.016996706,0.00054168195,0.0011779822,0.07283629,0.00459644,0.00013560509],"about_ca_topic_score_codex":0.00020000979,"about_ca_topic_score_gemma":0.0029395053,"teacher_disagreement_score":0.41192898,"about_ca_system_score_codex":0.000095463285,"about_ca_system_score_gemma":0.00025107843,"threshold_uncertainty_score":0.9999417},"labels":[],"label_agreement":null},{"id":"W4411776676","doi":"10.54254/2753-7048/2025.cb24291","title":"Educational Evaluation in China and the U.S.: A Literature-Based Inquiry into Its Impact on High School Students","year":2025,"lang":"en","type":"article","venue":"Lecture Notes in Education Psychology and Public Media","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Summative assessment; Formative assessment; Neglect; Educational equity; Psychology; China; Sociology of Education; Pedagogy; Academic achievement; Context (archaeology); Sociology; Political science","score_opus":0.061683287907399076,"score_gpt":0.5345476808189168,"score_spread":0.4728643929115177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411776676","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8769884,0.0032024093,0.000792942,0.11500271,0.002686486,0.00061643723,0.0000026552123,0.000006456889,0.00070146983],"genre_scores_gemma":[0.9858616,0.00021031045,0.00027298802,0.012816142,0.00023068156,0.00046659377,0.00009461773,0.000004781509,0.000042272695],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99640703,0.0014338188,0.0005468012,0.0005125112,0.00089899445,0.0002008237],"domain_scores_gemma":[0.99538344,0.0034865662,0.00018063924,0.00043346066,0.00041372344,0.000102161364],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0077448324,0.00017334132,0.000239321,0.0012755196,0.00015126626,0.0003707816,0.00042672837,0.00020295086,0.0015115286],"category_scores_gemma":[0.01344216,0.000101864935,0.000037350103,0.0019239505,0.00020761351,0.00032259806,0.000040152838,0.0004907227,0.000028710361],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036672005,0.0005959669,0.6639777,0.000012265021,0.000019180323,1.7274824e-7,0.0097459955,0.0005561145,0.0000145328195,0.009769168,0.00314238,0.3117998],"study_design_scores_gemma":[0.0020905295,0.00003861041,0.7745729,0.00006621533,0.0000076119504,0.0000020242276,0.00015539405,0.0017240444,0.000007798349,0.22079155,0.00046886213,0.00007447288],"about_ca_topic_score_codex":0.000045084016,"about_ca_topic_score_gemma":0.00035210635,"teacher_disagreement_score":0.31172532,"about_ca_system_score_codex":0.0001429553,"about_ca_system_score_gemma":0.0017793232,"threshold_uncertainty_score":0.9994012},"labels":[],"label_agreement":null},{"id":"W4411865010","doi":"10.17269/s41997-025-01076-8","title":"Capitalisation as a boundary object in intervention research, serving knowledge production and mobilisation","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Public Health","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Production (economics); Boundary (topology); Object (grammar); Boundary object; Knowledge management; Intervention (counseling); Business; Knowledge production; Operations management; Computer science; Medicine; Mathematics; Geography; Artificial intelligence; Engineering; Nursing; Cartography; Economics; Microeconomics","score_opus":0.3971654836995795,"score_gpt":0.5633982261325508,"score_spread":0.16623274243297126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411865010","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9506603,0.0020528333,0.0007625538,0.042249303,0.0010659851,0.00026923808,0.0000018512927,0.0000033279084,0.0029346012],"genre_scores_gemma":[0.998125,0.000099422345,0.00012748428,0.00033233312,0.00010625009,0.000007650664,0.0000037085947,0.0000037534403,0.0011943708],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99580735,0.0019992327,0.0009569667,0.00020486698,0.0006874337,0.00034413615],"domain_scores_gemma":[0.9969763,0.00036049902,0.000327561,0.00019934708,0.0016557398,0.00048055252],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05540786,0.00006475297,0.00018090552,0.0030494577,0.00037705316,0.0005195801,0.00024413352,0.00005326583,0.0002609021],"category_scores_gemma":[0.013728735,0.00005587294,0.000041362884,0.001818108,0.00012369959,0.001270367,0.000022847742,0.0003426748,0.0000192739],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010869608,0.00006815469,0.28052896,0.00007513157,0.000013248116,0.0000034139293,0.029277466,0.00009730169,0.000022669223,0.008324726,0.014761431,0.6668166],"study_design_scores_gemma":[0.0006047022,0.00038858125,0.821492,0.00047163604,0.0000023919874,0.00004397344,0.04662181,0.0024171085,0.00002636017,0.03965408,0.088184,0.00009334827],"about_ca_topic_score_codex":0.013271455,"about_ca_topic_score_gemma":0.46105492,"teacher_disagreement_score":0.66672325,"about_ca_system_score_codex":0.0015774913,"about_ca_system_score_gemma":0.017377669,"threshold_uncertainty_score":0.994579},"labels":[],"label_agreement":null},{"id":"W4411928219","doi":"10.1016/j.jclinepi.2025.111892","title":"Response to the letter ‘Balancing methodological rigor and simplicity in ROBUST-RCT: is optional assessment of bias domains the ideal path forward’","year":2025,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"","keywords":"Rigour; Simplicity; Ideal (ethics); Path (computing); Computer science; Medicine; Mathematics; Epistemology; Philosophy","score_opus":0.754285470495182,"score_gpt":0.6616606810892643,"score_spread":0.09262478940591767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411928219","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07479794,0.00012061882,0.06810854,0.85461706,0.0016733407,0.00038635315,0.00005347792,0.000003528021,0.00023915421],"genre_scores_gemma":[0.019661603,0.00037819578,0.063761234,0.91288424,0.0027811443,0.000023423689,0.0000052935216,0.000010744429,0.00049411826],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.8678252,0.10875847,0.017107613,0.0012343957,0.0041240854,0.00095021335],"domain_scores_gemma":[0.5697914,0.42202523,0.006253677,0.000872527,0.0008894927,0.00016767377],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4310589,0.0003516454,0.0037677197,0.00051486306,0.00018766084,0.00006739809,0.0018630021,0.001117771,0.0005876401],"category_scores_gemma":[0.29997972,0.00014804206,0.0011684863,0.0006245838,0.00057965075,0.00014654617,0.0005822176,0.005433095,0.00001569729],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006774408,0.0000528387,0.11191714,0.000013198952,0.00011124728,0.000035367477,0.000110207424,0.0047702603,0.000005961733,0.00063015637,0.87448055,0.007195616],"study_design_scores_gemma":[0.0005985591,0.0004771777,0.44461542,0.00009217593,0.000054823366,0.0000459159,0.000074097195,0.005508314,6.7381103e-7,0.015911397,0.5325189,0.00010252213],"about_ca_topic_score_codex":0.000047017034,"about_ca_topic_score_gemma":0.00006391003,"teacher_disagreement_score":0.34196165,"about_ca_system_score_codex":0.00013704716,"about_ca_system_score_gemma":0.0014667168,"threshold_uncertainty_score":0.9968614},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"evaluation","study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W4412006250","doi":"10.1037/cbs0000460","title":"Expanding statistical horizons: Supplementary training trends in a sample of North American psychology researchers.","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Behavioural Science/Revue canadienne des sciences du comportement","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Sample (material); Training (meteorology); Psychology; New horizons; Applied psychology; Geography; Engineering","score_opus":0.4821058939281206,"score_gpt":0.5051328296864216,"score_spread":0.023026935758301004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412006250","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9932832,0.000054617445,0.0011037164,0.003432848,0.0008198837,0.00015946996,0.00018732809,0.0000025200197,0.00095637643],"genre_scores_gemma":[0.9922905,0.000015690912,0.007276716,0.0003008622,0.0000387223,0.000009010196,0.000011927418,0.0000050373883,0.000051550964],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99492186,0.00029968077,0.0017524556,0.00057568104,0.0011955143,0.00125478],"domain_scores_gemma":[0.9960495,0.00056612847,0.000799831,0.00036524862,0.00090080133,0.0013184777],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01685674,0.00019620327,0.0005780281,0.0055941595,0.000951903,0.00031395568,0.0023084588,0.000028449522,0.0015248432],"category_scores_gemma":[0.0015803754,0.00016127502,0.00011921039,0.009701478,0.0068544215,0.0007534149,0.00009184248,0.000327373,0.0000017961526],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013641138,0.000036211088,0.85426366,0.0000028952732,0.0000074392096,0.00007278927,0.0037739906,0.00041075115,0.000067767556,0.0018698368,0.0005602766,0.13892072],"study_design_scores_gemma":[0.0005296468,0.0010037617,0.97912115,0.00006877373,0.000019274774,0.000060383238,0.012374257,0.0016912845,0.000041173287,0.002887844,0.0020364036,0.00016602702],"about_ca_topic_score_codex":0.14238022,"about_ca_topic_score_gemma":0.9287088,"teacher_disagreement_score":0.78632855,"about_ca_system_score_codex":0.0018428502,"about_ca_system_score_gemma":0.006590391,"threshold_uncertainty_score":0.9993879},"labels":[],"label_agreement":null},{"id":"W4412031376","doi":"10.1016/j.evalprogplan.2025.102648","title":"Approaches to incorporating equity into program evaluation: A scoping review","year":2025,"lang":"en","type":"review","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Wilfrid Laurier University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Participatory evaluation; Equity (law); Program evaluation; Oppression; Social justice; Engineering ethics; Sociology; Psychology; Public relations; Political science; Engineering; Politics; Social science; Public administration","score_opus":0.8271630226958828,"score_gpt":0.689856398152968,"score_spread":0.13730662454291487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412031376","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000003930209,0.94518155,0.00071458815,0.0007698837,0.00054451457,0.03670886,0.000009111358,0.00023594887,0.015831595],"genre_scores_gemma":[0.0000453522,0.9404581,0.023880618,0.00058931037,0.00027030916,0.033692017,0.0007332078,0.00003790718,0.00029315462],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9832255,0.0043268157,0.003184059,0.0017013911,0.006996226,0.0005659889],"domain_scores_gemma":[0.99301684,0.0019750076,0.0018564914,0.0011122248,0.0016894911,0.00034997394],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06818065,0.00072151475,0.00233834,0.0010359357,0.0007315546,0.0015598756,0.001008028,0.0003522494,0.00090918405],"category_scores_gemma":[0.011727642,0.00054222613,0.0004225978,0.003936895,0.000106868334,0.00062825775,0.0008329042,0.0006053926,0.00021412809],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004559404,0.000094034025,0.00003893163,0.035892762,0.00005705032,9.1682625e-7,0.0002873447,0.00013155484,1.6720088e-8,0.0001970703,0.0013258205,0.9619699],"study_design_scores_gemma":[0.00039865728,0.00033645236,0.000030709005,0.45079282,0.001642578,0.00001392638,0.00018002429,0.036351398,2.4123827e-7,0.0019319367,0.50765765,0.00066361093],"about_ca_topic_score_codex":0.000006545602,"about_ca_topic_score_gemma":0.000032414293,"teacher_disagreement_score":0.96130633,"about_ca_system_score_codex":0.00042861473,"about_ca_system_score_gemma":0.0063597546,"threshold_uncertainty_score":0.99970293},"labels":[],"label_agreement":null},{"id":"W4412072961","doi":"10.36510/learnland.vi29.1151","title":"You Cannot Find the Calm Without the Storm: Creating Spaces for Embracing Change","year":2025,"lang":"en","type":"article","venue":"LEARNing Landscapes","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Institute for Christian Studies; McGill University","funders":"","keywords":"Storm; History; Meteorology; Geography","score_opus":0.12658405509061496,"score_gpt":0.444414174885886,"score_spread":0.3178301197952711,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412072961","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9432572,0.0006809839,0.002856929,0.027873734,0.000592213,0.00062896905,0.000005426263,0.00006632877,0.024038196],"genre_scores_gemma":[0.9728289,0.000019076811,0.00024426513,0.0012973496,0.0002930105,0.00015912832,0.000005804548,0.000008136116,0.025144331],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980693,0.0003352635,0.00034331717,0.00027651404,0.00072196685,0.00025367306],"domain_scores_gemma":[0.99646336,0.0026947923,0.00025241284,0.0003322204,0.00022589741,0.000031340227],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0054786764,0.00012447625,0.00019090583,0.0001145447,0.0013863343,0.0005809899,0.00052049407,0.000050940624,0.00029054823],"category_scores_gemma":[0.0027438786,0.000055839162,0.000087430446,0.00048661162,0.000045380926,0.00022417867,0.00010318599,0.00027521828,0.00005355485],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000089287154,0.00002683735,0.77950454,0.000028712506,0.00007040058,6.450756e-7,0.034119356,0.011863684,0.00028209496,0.005343942,0.009960723,0.15870976],"study_design_scores_gemma":[0.000655366,0.00010904275,0.18808566,0.00010771255,0.000054223256,0.0000026779567,0.027118843,0.20040797,0.00026735791,0.0014981208,0.5815089,0.00018415131],"about_ca_topic_score_codex":0.00021875245,"about_ca_topic_score_gemma":0.0013860188,"teacher_disagreement_score":0.5914189,"about_ca_system_score_codex":0.000027910462,"about_ca_system_score_gemma":0.0001279471,"threshold_uncertainty_score":0.99991375},"labels":[],"label_agreement":null},{"id":"W4412095627","doi":"10.20944/preprints202507.0447.v1","title":"Appraising the Decision-Making Process Concerning COVID-19 Policy in Postsecondary Education in Canada: A Critical Scoping Review","year":2025,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"University of Alberta","keywords":"Coronavirus disease 2019 (COVID-19); Process (computing); Decision-making; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); 2019-20 coronavirus outbreak; Political science; Management science; Computer science; Economics; Medicine; Operations management; Virology","score_opus":0.37415181384060353,"score_gpt":0.6196409928549538,"score_spread":0.24548917901435025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412095627","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8705318,0.024743946,0.0031999138,0.052802645,0.0033194867,0.006251405,0.00006594323,0.00008340958,0.03900145],"genre_scores_gemma":[0.97931236,0.0021128608,0.0002834076,0.017429927,0.00014398954,0.0005350855,0.000014913538,0.000015240998,0.00015222831],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99228483,0.0012320145,0.0023336539,0.0013991616,0.0022392587,0.00051110605],"domain_scores_gemma":[0.98710567,0.009268783,0.00085618853,0.0017986243,0.00073284894,0.00023785891],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.012920657,0.00036673673,0.0008515835,0.00083842064,0.00029447107,0.00017617477,0.0021060843,0.00018502913,0.0029043953],"category_scores_gemma":[0.08007984,0.00029117096,0.00013829677,0.0017017875,0.00013374053,0.00037833495,0.0018977602,0.0014655566,0.00011226092],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047476657,0.00009140123,0.8906422,0.0055041146,0.00001439153,0.000012913692,0.0029924498,0.019495444,0.000005754213,0.00097303686,0.0003974174,0.07982335],"study_design_scores_gemma":[0.0007051054,0.0000133734275,0.6763671,0.2335878,0.00006162495,0.000038982675,0.007453643,0.012482785,0.000092956034,0.06239936,0.005724493,0.001072746],"about_ca_topic_score_codex":0.25307533,"about_ca_topic_score_gemma":0.6619311,"teacher_disagreement_score":0.40885574,"about_ca_system_score_codex":0.003278195,"about_ca_system_score_gemma":0.16084136,"threshold_uncertainty_score":0.99995404},"labels":[],"label_agreement":null},{"id":"W4412156054","doi":"10.1177/01466216251358492","title":"Including Empirical Prior Information in the Reliable Change Index","year":2025,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Index (typography); Statistics; Econometrics; Mathematics; Psychology; Computer science","score_opus":0.6224068475520583,"score_gpt":0.5555954167953175,"score_spread":0.06681143075674079,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412156054","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49109244,0.0001355187,0.012866363,0.037420686,0.0010029643,0.0025252737,0.000002062985,0.00009019939,0.4548645],"genre_scores_gemma":[0.9773301,0.000014405102,0.0003074054,0.021681678,0.00004790667,0.0005560362,0.0000027578192,0.0000020913237,0.00005760402],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9956038,0.00021569747,0.0008099866,0.00032886103,0.002757973,0.0002836688],"domain_scores_gemma":[0.99865806,0.00029479718,0.00017224859,0.00057450694,0.000254824,0.000045538276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0139393965,0.00014004909,0.0002092759,0.00030452915,0.0002103252,0.00024035959,0.0008223165,0.00012301817,0.00046977258],"category_scores_gemma":[0.0006021005,0.00007441773,0.00005838443,0.0018059126,0.00005652565,0.0003046732,0.00010958889,0.00031902903,0.0005792576],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040827086,0.0007193444,0.2332389,0.00001348435,0.000019112676,0.0000017336862,0.00493418,0.0003517708,0.0001483829,0.020121394,0.07163732,0.6684061],"study_design_scores_gemma":[0.0008862074,0.000058156093,0.80418533,0.000020145628,0.000004982458,4.8870567e-7,0.0011143291,0.00039999658,0.000035538025,0.016834343,0.1763555,0.00010499211],"about_ca_topic_score_codex":0.000008292787,"about_ca_topic_score_gemma":0.000018694827,"teacher_disagreement_score":0.6683011,"about_ca_system_score_codex":0.00016047743,"about_ca_system_score_gemma":0.00005416128,"threshold_uncertainty_score":0.74453783},"labels":[],"label_agreement":null},{"id":"W4412273418","doi":"","title":"Forsker- og rådgiverkonferanse i Nova Scotia 2013","year":2014,"lang":"no","type":"article","venue":"Research at the University of Copenhagen (University of Copenhagen)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nova scotia; Nova (rocket); Geography; Archaeology; Engineering; Aeronautics","score_opus":0.19389160805811592,"score_gpt":0.42002014659522835,"score_spread":0.22612853853711243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412273418","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49584252,0.004436865,0.009384804,0.009422996,0.00054724433,0.0020065885,0.00028180066,0.000048392136,0.47802877],"genre_scores_gemma":[0.5285716,0.00048347167,0.0005103242,0.00006995887,0.0000396661,5.672736e-8,0.00002963264,0.000019232231,0.47027606],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9871409,0.0044843447,0.00068526616,0.0011926582,0.0052610612,0.0012357502],"domain_scores_gemma":[0.9889753,0.0033494625,0.0011700684,0.0023036099,0.0034924413,0.0007091441],"candidate_categories":["metaepi_narrow","sts","open_science","insufficient_payload"],"consensus_categories":["sts","insufficient_payload"],"category_scores_codex":[0.016229244,0.00047901343,0.0011389839,0.00080745463,0.0028610427,0.00018165886,0.0055212458,0.00041931565,0.8672429],"category_scores_gemma":[0.0007317771,0.0004796588,0.00069053937,0.0029222297,0.003179933,0.0017425333,0.0026235287,0.0010077527,0.48548964],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015460742,0.00031860493,0.000109325425,0.00014704575,0.00027845547,0.000060942188,0.007391,0.00065070495,0.0019169401,0.0009493791,0.974859,0.011772503],"study_design_scores_gemma":[0.003252626,0.00084241136,0.026654454,0.00023317234,0.00021475062,0.000009470591,0.026779536,0.008840901,0.0012318409,0.000068388115,0.9313989,0.0004735218],"about_ca_topic_score_codex":0.008132173,"about_ca_topic_score_gemma":0.018145699,"teacher_disagreement_score":0.38175324,"about_ca_system_score_codex":0.00060837506,"about_ca_system_score_gemma":0.0015992994,"threshold_uncertainty_score":0.99985933},"labels":[],"label_agreement":null},{"id":"W4412279787","doi":"","title":"Designing Transformative Multi-stakeholder Policy Learning Dialogues:an 11-Step Protocol","year":2019,"lang":"en","type":"article","venue":"Research at the University of Copenhagen (University of Copenhagen)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Transformative learning; Protocol (science); Stakeholder; Policy learning; Computer science; Political science; Sociology; Pedagogy; Public relations; Medicine; Machine learning","score_opus":0.4157658494434059,"score_gpt":0.4758664573218556,"score_spread":0.06010060787844973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412279787","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49451903,0.00016696204,0.06872003,0.002560905,0.00011495135,0.047619417,0.000116695664,0.0001095999,0.38607243],"genre_scores_gemma":[0.58880377,0.000018034094,0.0021125532,0.000028147402,0.000016591881,0.00000984073,0.000023382347,0.000014196691,0.4089735],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99191046,0.0033405446,0.00042105856,0.0006317985,0.0030317772,0.0006643667],"domain_scores_gemma":[0.9951358,0.0013841675,0.0005222075,0.0009588576,0.0016673786,0.00033159048],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.010437412,0.00024009387,0.0005730136,0.0006616211,0.0018281608,0.00011254343,0.00268557,0.00017060048,0.40707055],"category_scores_gemma":[0.00040353695,0.0002183957,0.00026185616,0.0020510855,0.00083208305,0.0021403858,0.0007646535,0.0006032539,0.08998589],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003741734,0.0008619646,0.0011225435,0.00030124412,0.00034477026,0.00009284573,0.098636344,0.011139123,0.030381078,0.0017739749,0.8105585,0.04104588],"study_design_scores_gemma":[0.004097297,0.000844157,0.019538207,0.000089136236,0.000033694618,0.0000049043715,0.096315354,0.015886726,0.0036959206,0.000028249933,0.8591598,0.00030652995],"about_ca_topic_score_codex":0.0016660349,"about_ca_topic_score_gemma":0.0027521173,"teacher_disagreement_score":0.31708464,"about_ca_system_score_codex":0.0004236657,"about_ca_system_score_gemma":0.0013438418,"threshold_uncertainty_score":0.9994713},"labels":[],"label_agreement":null},{"id":"W4412298309","doi":"","title":"Hvor skal vi hente det rene vand om 10 år?:Pesticider som eksempel","year":2011,"lang":"da","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Semtech (Canada)","funders":"","keywords":"Traditional medicine; Medicine","score_opus":0.38399615778539076,"score_gpt":0.47563790638027725,"score_spread":0.0916417485948865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412298309","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38428345,0.0009581961,0.020682493,0.004516527,0.007768348,0.0010866394,0.00008457396,0.00020172852,0.58041805],"genre_scores_gemma":[0.8218523,0.0001569098,0.008351111,0.0026944054,0.0004574016,0.000026422189,0.000022380511,0.00003147317,0.16640756],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9935708,0.0003908501,0.00147299,0.0009970939,0.0027766365,0.0007916015],"domain_scores_gemma":[0.996201,0.00063362333,0.00049220247,0.0012640823,0.0008976618,0.0005114689],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.004171174,0.00045771978,0.0005773544,0.00037819194,0.0004797816,0.00052466587,0.001117662,0.0002583169,0.23152462],"category_scores_gemma":[0.0009115789,0.00032870934,0.000260667,0.0008522664,0.0002817445,0.0011352702,0.00037540196,0.00034213127,0.029614106],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011179793,0.002374292,0.1589006,0.00009338519,0.00036981644,0.00011119369,0.016098237,0.00027570172,0.0022988985,0.017101021,0.5024121,0.29884678],"study_design_scores_gemma":[0.0052154018,0.0018548466,0.33526966,0.00019322489,0.00037835288,0.000058275196,0.0076006027,0.059280764,0.009176218,0.026395746,0.5527099,0.0018670482],"about_ca_topic_score_codex":0.00039860807,"about_ca_topic_score_gemma":0.0007909961,"teacher_disagreement_score":0.4375689,"about_ca_system_score_codex":0.000109947534,"about_ca_system_score_gemma":0.00087322417,"threshold_uncertainty_score":0.9999165},"labels":[],"label_agreement":null},{"id":"W4412442873","doi":"10.1016/j.jval.2025.04.1388","title":"PCR67 Assessing the Feasibility of Using an Electronic Platform for Personalized Outcome Assessment: GoalNav for Goal Attainment Scaling","year":2025,"lang":"en","type":"article","venue":"Value in Health","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Goal Attainment Scaling; Outcome (game theory); Scaling; Computer science; Medicine; Physical therapy; Mathematics","score_opus":0.5023063607248556,"score_gpt":0.610520864269291,"score_spread":0.1082145035444354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412442873","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78743833,0.00028111247,0.20494272,0.004247203,0.00045111438,0.002385481,0.000033882916,0.000018656268,0.00020148902],"genre_scores_gemma":[0.98028964,0.00002165722,0.01832826,0.0009835372,0.00006336263,0.00013031883,0.000017043612,0.000013187019,0.00015299958],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9951053,0.0006369037,0.001851238,0.00056963967,0.0011844318,0.0006524438],"domain_scores_gemma":[0.9948155,0.0033401165,0.00072580116,0.00063492736,0.00038905884,0.00009457831],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.030923927,0.0001878123,0.00057412876,0.00031112123,0.0006036054,0.00022459465,0.00059906405,0.00008768862,0.00005383812],"category_scores_gemma":[0.0011446766,0.00012807093,0.000215235,0.0007803905,0.00010833675,0.0005606821,0.00007524153,0.00025251554,9.3928185e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002841621,0.0007023512,0.6728553,0.00062499713,0.00005358967,2.1336304e-7,0.0026520204,0.11889099,0.0006359453,0.16305722,0.00014657932,0.04009662],"study_design_scores_gemma":[0.0022627746,0.00030154563,0.061256643,0.00014335952,0.000021619675,0.0000011727853,0.00444767,0.8822128,0.000108505745,0.046764255,0.002337246,0.0001424066],"about_ca_topic_score_codex":0.00047888476,"about_ca_topic_score_gemma":0.00011472738,"teacher_disagreement_score":0.7633218,"about_ca_system_score_codex":0.0015387553,"about_ca_system_score_gemma":0.003721489,"threshold_uncertainty_score":0.99786776},"labels":[],"label_agreement":null},{"id":"W4412443002","doi":"10.1016/j.jval.2025.04.1015","title":"HTA4 The Use of QALYs in Decision-Making in Europe, Canada, and the US: A Qualitative Review of Methodological Guidance","year":2025,"lang":"en","type":"review","venue":"Value in Health","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.7805227888960862,"score_gpt":0.6676755933455265,"score_spread":0.11284719555055966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412443002","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011732493,0.99506366,0.0005520925,0.002086042,0.00017258506,0.0017471485,0.00004983477,0.0000016230176,0.00020970301],"genre_scores_gemma":[0.00009688163,0.9911184,0.0061457334,0.0024586245,0.000010106921,0.00009553043,0.0000026704943,0.0000063146526,0.000065787106],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9428338,0.048132095,0.0058589904,0.00064944837,0.0021799966,0.00034571168],"domain_scores_gemma":[0.8567747,0.13947342,0.0023258196,0.0008934972,0.00048540186,0.00004715602],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09945641,0.00022396534,0.0026900347,0.0004361561,0.0000584404,0.000031735406,0.000942742,0.00008552775,0.00006755526],"category_scores_gemma":[0.10361816,0.00009741698,0.00014422307,0.0050231996,0.00021183277,0.00010197716,0.00026778926,0.0005639596,0.0000015015886],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029962248,0.000026814732,0.00042659987,0.020635812,0.000010313217,0.000002971971,0.0018116134,0.0013759453,2.4894613e-9,0.004285357,0.0019130628,0.9694815],"study_design_scores_gemma":[0.00035091012,0.00004908941,0.0021336745,0.3062806,0.00003186554,0.0000043676323,0.00047504416,0.0022568775,1.9749729e-8,0.0036536693,0.68463045,0.00013340604],"about_ca_topic_score_codex":0.20572124,"about_ca_topic_score_gemma":0.25346228,"teacher_disagreement_score":0.96934813,"about_ca_system_score_codex":0.00027382883,"about_ca_system_score_gemma":0.0082020955,"threshold_uncertainty_score":0.9974205},"labels":[],"label_agreement":null},{"id":"W4412451219","doi":"10.1016/j.pec.2025.108903","title":"Reporting guidelines for research using systematic coding of observed human behaviour (SCOBe)","year":2025,"lang":"en","type":"article","venue":"Patient Education and Counseling","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Coding (social sciences); Psychology; MEDLINE; Medicine; Statistics; Biology; Mathematics","score_opus":0.7812308222816406,"score_gpt":0.6602277087088448,"score_spread":0.1210031135727958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412451219","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98627335,0.0008415539,0.01023989,0.0004895361,0.0007297775,0.000853258,0.0000026425682,0.000012669622,0.0005573251],"genre_scores_gemma":[0.99301887,0.00003270441,0.0057389634,0.00023246519,0.000050560328,0.000116515184,0.000008678136,0.000006165941,0.0007950687],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9953163,0.00026890158,0.0028253857,0.0003126839,0.0010959454,0.00018074969],"domain_scores_gemma":[0.9902749,0.00093172374,0.001684271,0.00036038022,0.00669535,0.0000533644],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017517434,0.000091581416,0.00032849816,0.0004828609,0.00056239875,0.00020574378,0.00019108245,0.00004844556,0.000037800204],"category_scores_gemma":[0.012965609,0.000072451854,0.00007133184,0.00066854706,0.00004383862,0.00019759731,0.00004383308,0.000087810826,0.0000019931992],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013241959,0.0018001833,0.6138156,0.02185139,0.00019761077,0.0000011410036,0.06386343,0.0071321614,0.056689057,0.054458186,0.02427261,0.15578623],"study_design_scores_gemma":[0.00120287,0.0004466875,0.018308705,0.029211337,0.00032477835,0.000016530936,0.34723705,0.5377948,0.014674399,0.04687943,0.0031532142,0.0007501508],"about_ca_topic_score_codex":0.00010989791,"about_ca_topic_score_gemma":0.00003326811,"teacher_disagreement_score":0.5955069,"about_ca_system_score_codex":0.00008524323,"about_ca_system_score_gemma":0.0007938745,"threshold_uncertainty_score":0.9953486},"labels":[],"label_agreement":null},{"id":"W4412485043","doi":"10.32920/29586188.v1","title":"Expanding Statistical Horizons: Supplementary Training Trends in a Sample of North American Psychology Researchers","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"New horizons; Sample (material); Psychology; Engineering; Chemistry; Chromatography","score_opus":0.5269974662460883,"score_gpt":0.627420234661393,"score_spread":0.10042276841530462,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412485043","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8569379,0.000033582237,0.100606725,0.0076756887,0.00082741695,0.000575681,0.0047142333,0.000035988538,0.028592795],"genre_scores_gemma":[0.9446513,0.00009926092,0.0530587,0.0005243012,0.000044498647,0.00010021266,0.0007387884,0.000007837082,0.00077512447],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9946873,0.00084265927,0.0013747769,0.0008032999,0.0018522358,0.0004397155],"domain_scores_gemma":[0.9947857,0.0037192507,0.00038644133,0.00075815455,0.00021945528,0.00013096396],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006237515,0.00020451775,0.0007017921,0.0020936693,0.00006109892,0.00008742404,0.0009584579,0.000070887676,0.012848354],"category_scores_gemma":[0.0015782019,0.00016439239,0.000115665265,0.0019836626,0.00032125218,0.000078567675,0.0006542734,0.0006784561,0.000011195938],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008507942,0.00008041906,0.32385188,0.000010943167,0.000030794214,0.0000030576637,0.0021789188,0.0005524113,0.0000034250968,0.0008490767,0.009058882,0.6632951],"study_design_scores_gemma":[0.00088067615,0.00042967615,0.9561583,0.000052279076,0.000019703573,8.54289e-7,0.010597411,0.0102673555,0.000019388199,0.011479197,0.0098161865,0.00027902133],"about_ca_topic_score_codex":0.0035834871,"about_ca_topic_score_gemma":0.036588497,"teacher_disagreement_score":0.6630161,"about_ca_system_score_codex":0.00015380238,"about_ca_system_score_gemma":0.00071353005,"threshold_uncertainty_score":0.98805404},"labels":[],"label_agreement":null},{"id":"W4412485044","doi":"10.32920/29586188","title":"Expanding Statistical Horizons: Supplementary Training Trends in a Sample of North American Psychology Researchers","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Sample (material); Training (meteorology); Psychology; Applied psychology; Geography; Meteorology","score_opus":0.5269974662460883,"score_gpt":0.627420234661393,"score_spread":0.10042276841530462,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412485044","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8569379,0.000033582237,0.100606725,0.0076756887,0.00082741695,0.000575681,0.0047142333,0.000035988538,0.028592795],"genre_scores_gemma":[0.9446513,0.00009926092,0.0530587,0.0005243012,0.000044498647,0.00010021266,0.0007387884,0.000007837082,0.00077512447],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9946873,0.00084265927,0.0013747769,0.0008032999,0.0018522358,0.0004397155],"domain_scores_gemma":[0.9947857,0.0037192507,0.00038644133,0.00075815455,0.00021945528,0.00013096396],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006237515,0.00020451775,0.0007017921,0.0020936693,0.00006109892,0.00008742404,0.0009584579,0.000070887676,0.012848354],"category_scores_gemma":[0.0015782019,0.00016439239,0.000115665265,0.0019836626,0.00032125218,0.000078567675,0.0006542734,0.0006784561,0.000011195938],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008507942,0.00008041906,0.32385188,0.000010943167,0.000030794214,0.0000030576637,0.0021789188,0.0005524113,0.0000034250968,0.0008490767,0.009058882,0.6632951],"study_design_scores_gemma":[0.00088067615,0.00042967615,0.9561583,0.000052279076,0.000019703573,8.54289e-7,0.010597411,0.0102673555,0.000019388199,0.011479197,0.0098161865,0.00027902133],"about_ca_topic_score_codex":0.0035834871,"about_ca_topic_score_gemma":0.036588497,"teacher_disagreement_score":0.6630161,"about_ca_system_score_codex":0.00015380238,"about_ca_system_score_gemma":0.00071353005,"threshold_uncertainty_score":0.98805404},"labels":[],"label_agreement":null},{"id":"W4412697111","doi":"10.1007/978-3-031-87869-5_28","title":"Culturally Responsive Evaluation: The Added Value of Cultural Humility","year":2025,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Montreal Clinical Research Institute; Université de Montréal","funders":"","keywords":"Humility; Cultural humility; Value (mathematics); Psychology; Cultural competence; Political science; Computer science; Pedagogy","score_opus":0.2586496759206979,"score_gpt":0.5153600668140844,"score_spread":0.25671039089338654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412697111","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006725399,0.00056008465,0.00013379226,0.0062708743,0.00096457644,0.0010868305,0.00005572674,0.000027746595,0.9902278],"genre_scores_gemma":[0.026486773,0.00014340148,0.00056923804,0.001319721,0.00014460583,0.00003836017,0.0000744612,0.000008304414,0.9712151],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.991815,0.0005555427,0.0014349257,0.00062596134,0.0053840433,0.00018456488],"domain_scores_gemma":[0.98949623,0.002356677,0.0008277811,0.0013606251,0.0058913897,0.00006729324],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011566263,0.00032173962,0.0005579415,0.00022564751,0.00028986132,0.00018436857,0.0012760462,0.0002637996,0.035877503],"category_scores_gemma":[0.003504167,0.00014971575,0.00042039138,0.00023935328,0.0003231533,0.00031122135,0.00028396153,0.00038810473,0.0006525593],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012652467,0.000018909323,0.00005644399,0.000013409252,0.00013190805,7.5595216e-7,0.0015133938,0.0004706564,0.000037625276,0.5907494,0.34500426,0.061876744],"study_design_scores_gemma":[0.00061821693,0.00011977702,0.0033752767,0.0001309896,0.00023927433,0.00000404111,0.002188595,0.008418968,0.0002157449,0.1876062,0.7967501,0.0003328002],"about_ca_topic_score_codex":0.000028676002,"about_ca_topic_score_gemma":0.00017985817,"teacher_disagreement_score":0.45174584,"about_ca_system_score_codex":0.00016976472,"about_ca_system_score_gemma":0.0015882776,"threshold_uncertainty_score":0.96500385},"labels":[],"label_agreement":null},{"id":"W4412697139","doi":"10.1007/978-3-031-87869-5_2","title":"Evaluation Models and their Implementation","year":2025,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto East General Hospital; Trillium Health Centre; University of Toronto","funders":"","keywords":"Computer science; Management science; Engineering","score_opus":0.4519174322867391,"score_gpt":0.5626042380772623,"score_spread":0.11068680579052326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412697139","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007585374,0.00037602612,0.013971874,0.0009128092,0.00029056834,0.0005418855,0.00003469949,0.000023635768,0.98377264],"genre_scores_gemma":[0.05437874,0.00036828514,0.00051689777,0.0007353154,0.00008645983,0.000042798685,0.00011788807,0.000011870077,0.94374174],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9965034,0.00009240779,0.00062718627,0.0004373681,0.0022351278,0.00010451211],"domain_scores_gemma":[0.9974587,0.0005315347,0.00027727793,0.00041466934,0.0012686371,0.000049187973],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007774003,0.00018863393,0.00024622842,0.00038322638,0.00011859912,0.00022689952,0.00021778265,0.00012550212,0.02561104],"category_scores_gemma":[0.00011975108,0.000121416524,0.00007759151,0.000060641298,0.00003421745,0.00039138718,0.000110450375,0.00011373487,0.0001436823],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023997025,0.0000021114415,0.000008554172,0.0000020689454,0.00002225219,4.4563382e-8,0.00022415031,0.00014118622,0.0000027667886,0.2874226,0.020070098,0.6921018],"study_design_scores_gemma":[0.00028023316,0.000024922687,0.00006613611,0.000017618442,0.00004839816,6.746156e-7,0.000499326,0.15892658,0.000027171785,0.725434,0.11454972,0.0001252107],"about_ca_topic_score_codex":0.000007658709,"about_ca_topic_score_gemma":0.0004205117,"teacher_disagreement_score":0.69197655,"about_ca_system_score_codex":0.00010714898,"about_ca_system_score_gemma":0.0006208103,"threshold_uncertainty_score":0.9752797},"labels":[],"label_agreement":null},{"id":"W4412712541","doi":"10.12968/eyed.2025.24.17.9","title":"Developing an assessment toolbox","year":2025,"lang":"en","type":"article","venue":"Early Years Educator","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Education and Early Childhood Development","funders":"","keywords":"Toolbox; Computer science; Medicine; Programming language","score_opus":0.18746055795117755,"score_gpt":0.577382544379839,"score_spread":0.3899219864286615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412712541","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95664424,0.00004123128,0.0047343182,0.003919442,0.0021882856,0.00017075494,0.00000298279,0.00004600878,0.03225275],"genre_scores_gemma":[0.9674389,0.000005146651,0.016020037,0.002049529,0.00014159456,0.00003444699,0.0000047642634,0.000007196616,0.014298398],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9977554,0.00018327103,0.0004393456,0.00037990554,0.0010096546,0.00023243122],"domain_scores_gemma":[0.9986837,0.00025429993,0.00010810604,0.0005965417,0.00025050886,0.00010685874],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0025470823,0.000104178136,0.00017310907,0.00034408667,0.00015429927,0.00052076747,0.0006218278,0.000056831646,0.0022557406],"category_scores_gemma":[0.0002894516,0.00008753682,0.000058625395,0.00087033527,0.00004268126,0.0005577337,0.0000710212,0.00014778157,0.0009344069],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013467078,0.0001812372,0.47807524,0.000005944785,0.000034605913,0.0000031361883,0.0027363969,0.000039590857,0.00030270606,0.1468636,0.04157313,0.33017096],"study_design_scores_gemma":[0.00017849958,0.000039961258,0.83780134,0.000014277878,0.0000052030996,6.298305e-7,0.0015224013,0.00021941135,0.00014002093,0.012178359,0.14778575,0.00011415862],"about_ca_topic_score_codex":0.000054840995,"about_ca_topic_score_gemma":0.00004089223,"teacher_disagreement_score":0.3597261,"about_ca_system_score_codex":0.00016918345,"about_ca_system_score_gemma":0.002526377,"threshold_uncertainty_score":0.9998435},"labels":[],"label_agreement":null},{"id":"W4412825792","doi":"10.1080/15548732.2025.2538016","title":"Strategies for utilizing research findings for policy, program design and practice in child and family social services: a synthesis of the literature","year":2025,"lang":"en","type":"article","venue":"Journal of Public Child Welfare","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Child, Adolescent and Family Mental Health; Casey House","funders":"William T. Grant Foundation; Annie E. Casey Foundation; Casey Family Programs","keywords":"Social work; Psychology; Social Welfare; Process management; Medical education; Business; Medicine; Political science","score_opus":0.19874844236714978,"score_gpt":0.5216137589545232,"score_spread":0.32286531658737344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412825792","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27001107,0.004648935,0.00250888,0.7038783,0.0003429293,0.0033643206,0.000087289,0.000015510963,0.01514281],"genre_scores_gemma":[0.9958207,0.00019480451,0.0032893098,0.00048440695,0.00011391428,0.000059947808,0.0000011291621,0.000005991785,0.00002980778],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972539,0.0007086926,0.0006531402,0.00018903376,0.0009561482,0.00023911837],"domain_scores_gemma":[0.99407643,0.0034779294,0.00043696232,0.00015146732,0.0018034484,0.000053751774],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.016550709,0.00009952706,0.00027193123,0.000802725,0.00073019677,0.0012032135,0.0004969078,0.00010554754,0.0000048446896],"category_scores_gemma":[0.005725185,0.00005876182,0.000102699334,0.0015500321,0.00012680964,0.0012985985,0.00011762585,0.00034768332,7.912361e-8],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012701518,0.0007518816,0.007139819,0.0010416289,0.0002717853,0.0000032548223,0.03535039,0.00014159117,0.0001558039,0.3279565,0.0043769637,0.62154025],"study_design_scores_gemma":[0.0037405423,0.0008375127,0.2945042,0.0024919994,0.00010471136,0.00018518949,0.25523275,0.0059235487,0.00020439849,0.060338277,0.37616932,0.0002675442],"about_ca_topic_score_codex":0.000018155693,"about_ca_topic_score_gemma":0.00006875018,"teacher_disagreement_score":0.72580963,"about_ca_system_score_codex":0.000059848004,"about_ca_system_score_gemma":0.0005828862,"threshold_uncertainty_score":0.99983364},"labels":[],"label_agreement":null},{"id":"W4413076837","doi":"10.2139/ssrn.5355694","title":"From Transactional to Transformative: Evolving Research Practices Through Mutual Aid Collaboration","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Transformative learning; Transactional leadership; Mutual aid; Transactional analysis; Knowledge management; Business; Political science; Sociology; Computer science; Public relations; Psychology; Pedagogy; Social psychology","score_opus":0.26537486772209956,"score_gpt":0.5853415652176701,"score_spread":0.31996669749557055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413076837","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23022851,0.006073578,0.58703476,0.108385585,0.006314856,0.0025466152,0.0005689859,0.00011750054,0.058729593],"genre_scores_gemma":[0.9725744,0.004838661,0.004151784,0.00046671554,0.0020674642,0.00013964878,0.00009261358,0.000025052892,0.015643626],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98702216,0.0023711787,0.001532503,0.0008592728,0.006170338,0.0020445222],"domain_scores_gemma":[0.9913666,0.0026883539,0.0011586053,0.00064799824,0.0039634984,0.00017494222],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03515707,0.00034320354,0.000538653,0.0009788286,0.0010889029,0.0018766116,0.0017837655,0.00037591867,0.0022812034],"category_scores_gemma":[0.0035876024,0.00027901065,0.0002551423,0.0019347938,0.000095228424,0.002418506,0.0001923228,0.008272042,0.0004951314],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0040833214,0.0010668708,0.0039131264,0.00013275999,0.0028976777,0.000017712793,0.16844097,0.08328271,0.0016307917,0.20181209,0.070552826,0.46216917],"study_design_scores_gemma":[0.00095714186,0.0004327402,0.00070920365,0.00019958276,0.00007922121,0.00002543295,0.06994866,0.010602424,0.00037148214,0.81624156,0.1000528,0.00037973234],"about_ca_topic_score_codex":0.0005932524,"about_ca_topic_score_gemma":0.00873531,"teacher_disagreement_score":0.7423459,"about_ca_system_score_codex":0.0034702308,"about_ca_system_score_gemma":0.037520308,"threshold_uncertainty_score":0.9999662},"labels":[],"label_agreement":null},{"id":"W4413086010","doi":"10.53761/xsdd8366","title":"The multiple affordances, complexities and limitations of micro-credentials - practitioner voices","year":2025,"lang":"en","type":"article","venue":"Journal of University Teaching and Learning Practice","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Affordance; Reflexivity; Credential; Credentialing; Context (archaeology); Thematic analysis; Sociology; Qualitative research; Public relations; Psychology; Political science; Medical education; Social science; Medicine","score_opus":0.13536566408185483,"score_gpt":0.42438954420083935,"score_spread":0.2890238801189845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413086010","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8352827,0.0021826352,0.041771483,0.04755418,0.00058337284,0.00013518204,0.0000035746684,0.000014697324,0.07247217],"genre_scores_gemma":[0.97613347,0.00154722,0.01447055,0.00013880972,0.000027363456,6.1513674e-8,5.401144e-7,0.0000016015416,0.0076803807],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969988,0.0021120936,0.00030110404,0.00008334213,0.0004366976,0.00006795543],"domain_scores_gemma":[0.9688382,0.029534819,0.000994098,0.00007782636,0.00052217284,0.000032847205],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.012034261,0.00005014073,0.00013273649,0.00020299159,0.0014174554,0.00023493625,0.0001722078,0.000025295007,0.000009714186],"category_scores_gemma":[0.030082438,0.000034658075,0.00004117793,0.00015447062,0.00013584598,0.0013390059,0.00006394447,0.0005813097,0.0000011053953],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028103765,0.00051000016,0.07007791,0.00007355112,0.0008924405,0.000028201011,0.05732919,0.018907169,0.0043815444,0.11336739,0.025412291,0.70620996],"study_design_scores_gemma":[0.00045709207,0.00010742574,0.019718781,0.00004836828,0.00008352874,0.00003362732,0.12274147,0.002198431,0.0000272664,0.0006758359,0.8538692,0.000038959937],"about_ca_topic_score_codex":0.000101566155,"about_ca_topic_score_gemma":0.00008354072,"teacher_disagreement_score":0.82845694,"about_ca_system_score_codex":0.000023902727,"about_ca_system_score_gemma":0.00013998509,"threshold_uncertainty_score":0.9998826},"labels":[],"label_agreement":null},{"id":"W4413098616","doi":"10.61647/aa74786","title":"Evidence ecosystem and development policies: Francophone West Africa Regional Profile","year":2024,"lang":"en","type":"report","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Robert Bosch Stiftung; International Development Research Centre","keywords":"Political science; Center of excellence; Excellence; Context (archaeology); Economic growth; French; Public policy; Development economics; Public economics; Business; Geography; Economics","score_opus":0.4776168703502846,"score_gpt":0.5028932229328953,"score_spread":0.025276352582610684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413098616","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013536678,0.026433017,0.0010314808,0.006645084,0.0072036027,0.0014291215,0.00009636256,0.0002571477,0.9433675],"genre_scores_gemma":[0.43896344,0.007868897,0.0069419583,0.00068345515,0.0014893912,0.0006155441,0.000074481446,0.000087988796,0.5432748],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9898985,0.00015492173,0.0015470294,0.000982047,0.0070509175,0.00036655643],"domain_scores_gemma":[0.9959093,0.0012209746,0.00037237073,0.00070539315,0.001572292,0.0002197253],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0099120615,0.00036989307,0.00064877764,0.0006611698,0.0002057424,0.000692426,0.000661855,0.0002802216,0.014637727],"category_scores_gemma":[0.0011792637,0.00023447054,0.000117204385,0.0009854198,0.00006844712,0.0003605204,0.0003973039,0.00038561886,0.009681874],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009706852,0.000030205156,0.0016244369,0.0003499518,0.000068951646,0.000017172848,0.002404401,0.000013184089,0.000033674245,0.00025886248,0.9209616,0.074227825],"study_design_scores_gemma":[0.0000836083,0.000049215974,0.007548481,0.0012307945,0.000014698591,0.000085021165,0.0014914087,0.0003960505,0.00009476922,0.00024403207,0.9884259,0.0003359975],"about_ca_topic_score_codex":0.00011072941,"about_ca_topic_score_gemma":0.00074290653,"teacher_disagreement_score":0.42542678,"about_ca_system_score_codex":0.00048363832,"about_ca_system_score_gemma":0.010525369,"threshold_uncertainty_score":0.99508405},"labels":[],"label_agreement":null},{"id":"W4413128915","doi":"10.1002/ev.70009","title":"Community‐Based Research on Evaluation: Beyond Academic and Evaluator Perspectives","year":2025,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; University of Waterloo","funders":"Canadian Mental Health Association","keywords":"Evaluation methods; Program evaluation; Computer science; Sociology; Engineering ethics; Management science; Psychology; Political science; Public administration; Engineering","score_opus":0.6424948000151569,"score_gpt":0.6631852882198059,"score_spread":0.020690488204649027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413128915","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67417395,0.004150063,0.016882418,0.060728762,0.0032735248,0.010576932,0.0000677313,0.00025296627,0.22989365],"genre_scores_gemma":[0.987997,0.00007788343,0.0012152693,0.00083466514,0.00026241018,0.001514025,0.00008553801,0.000017914548,0.007995293],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98656046,0.0056574047,0.00082757405,0.00072891155,0.0058525335,0.0003730962],"domain_scores_gemma":[0.9860942,0.0069090463,0.00024212805,0.0009942732,0.005604618,0.00015575415],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.076589204,0.00021573737,0.0002927718,0.0020287598,0.0023818885,0.00038024122,0.0005549098,0.00022109007,0.0018778932],"category_scores_gemma":[0.019417228,0.0001873534,0.00013415588,0.0029899478,0.0002292463,0.000567909,0.00009967574,0.00088153867,0.000114452756],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003698355,0.00035710147,0.0024832613,0.000020644815,0.000079673315,5.2871634e-8,0.004655154,0.011670796,0.0011284911,0.026913749,0.11467541,0.8376458],"study_design_scores_gemma":[0.005863603,0.00064648106,0.050362073,0.00012224975,0.00028527484,0.0000013978984,0.015753767,0.58153534,0.0025586,0.2541974,0.0883907,0.0002831476],"about_ca_topic_score_codex":0.00010566431,"about_ca_topic_score_gemma":0.00029324915,"teacher_disagreement_score":0.8373627,"about_ca_system_score_codex":0.00080321427,"about_ca_system_score_gemma":0.0036505095,"threshold_uncertainty_score":0.9990345},"labels":[],"label_agreement":null},{"id":"W4413187217","doi":"10.3138/cjpe-2023-0049","title":"Intersections between Participatory Evaluation and Social Pedagogy When Assessing Socio-Educational Projects","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Citizen journalism; Sociology; Pedagogy; Political science","score_opus":0.6169192173815058,"score_gpt":0.6321641301355303,"score_spread":0.015244912754024509,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413187217","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9706464,0.00047179312,0.001970258,0.020331942,0.0012467687,0.001279122,0.000007505727,0.000010018838,0.0040361867],"genre_scores_gemma":[0.9975872,0.0000026646392,0.0012540207,0.00026505225,0.00041930852,0.00018584295,0.000033209264,0.000008069058,0.0002446204],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9949975,0.0013848365,0.0010271409,0.00023920552,0.0020622169,0.00028907164],"domain_scores_gemma":[0.9936443,0.0005380952,0.00071454607,0.0001774415,0.0046935263,0.00023207262],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.021630757,0.00013890454,0.00026982953,0.0011603484,0.0007430469,0.00080244994,0.00028872068,0.00012741127,0.0017661565],"category_scores_gemma":[0.003484142,0.00012230249,0.00011553731,0.0006359327,0.00019391128,0.0010936111,0.000022007694,0.0002833565,0.000022822556],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000061403593,0.000037010275,0.2397014,0.000009685707,0.00006575686,3.207793e-7,0.008351111,0.00014864156,0.000026068257,0.0010606787,0.0050905156,0.74550265],"study_design_scores_gemma":[0.0012483108,0.00018033128,0.8688912,0.00007902546,0.00050087506,0.000010640826,0.01894887,0.02736717,0.000039107406,0.06317215,0.019385623,0.00017671978],"about_ca_topic_score_codex":0.00042610307,"about_ca_topic_score_gemma":0.008804557,"teacher_disagreement_score":0.7453259,"about_ca_system_score_codex":0.000976082,"about_ca_system_score_gemma":0.019733518,"threshold_uncertainty_score":0.99914634},"labels":[],"label_agreement":null},{"id":"W4413187250","doi":"10.3138/cjpe-2024-0045","title":"L’utilisation des évaluations par l’analyse thématique : le cas d’Anciens Combattants Canada (ACC)","year":2025,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"École Nationale d'Administration Publique","funders":"","keywords":"Political science","score_opus":0.2822294590102694,"score_gpt":0.49894638162417587,"score_spread":0.21671692261390646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413187250","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87621385,0.015172091,0.011255077,0.059695482,0.010451124,0.0035899943,0.00015848574,0.00002379537,0.02344013],"genre_scores_gemma":[0.9902142,0.0001890461,0.005489838,0.00086343935,0.00023125585,0.00012334913,0.00006173429,0.000020364047,0.0028067597],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9908357,0.0023334078,0.0023424379,0.0004462927,0.003159671,0.0008824595],"domain_scores_gemma":[0.9862507,0.00083712325,0.0014119504,0.0006131818,0.009826603,0.0010604673],"candidate_categories":["metaresearch","metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.024183003,0.00035026885,0.00060063455,0.0013946505,0.0013398494,0.00089348725,0.0008603703,0.0002549122,0.0041201264],"category_scores_gemma":[0.008693611,0.00033579394,0.00027403864,0.0031848683,0.0005386932,0.0015844054,0.000035139914,0.0005838741,0.000054302032],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00002213324,0.00014599465,0.072323866,0.00005158739,0.00022016658,0.00002350318,0.0029658098,0.021886934,0.00004084082,0.0038767636,0.029534345,0.86890805],"study_design_scores_gemma":[0.0023636557,0.00039260503,0.46575478,0.0006933845,0.0010211713,0.00009838182,0.01036627,0.30743465,0.00067815796,0.037834156,0.17289995,0.0004628461],"about_ca_topic_score_codex":0.6397611,"about_ca_topic_score_gemma":0.99472404,"teacher_disagreement_score":0.8684452,"about_ca_system_score_codex":0.0057840315,"about_ca_system_score_gemma":0.17567328,"threshold_uncertainty_score":0.99996024},"labels":[],"label_agreement":null},{"id":"W4413187340","doi":"10.3138/cjpe-2024-0033","title":"How Do Municipal Policy- and Decision-Makers Evaluate the Impact of Their Policies? Insights from the City of Regina in Saskatchewan, Canada","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Saskatchewan; Public Health Ontario; Saskatchewan Health; University of Toronto; Saskatchewan Science Centre; Saskatchewan Health Authority; University of Regina","funders":"","keywords":"Political science; Public administration; Environmental planning; Geography","score_opus":0.14757668733566243,"score_gpt":0.46834605433322624,"score_spread":0.3207693669975638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413187340","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98309153,0.0018196774,0.00009874452,0.013414725,0.0002552608,0.00082250475,0.000044040633,0.0000013565394,0.00045216366],"genre_scores_gemma":[0.99934196,0.000037894955,0.00022398388,0.00023319048,0.00007338077,0.000020124022,0.000004670258,0.00000559609,0.000059172315],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99584854,0.0009910073,0.00081249117,0.00018944961,0.0018948518,0.0002636565],"domain_scores_gemma":[0.9934709,0.002653825,0.0008148784,0.0005984735,0.002239528,0.00022237159],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009110388,0.00016492316,0.00039174382,0.0006222581,0.00021061847,0.0002973393,0.0008814285,0.00007889596,0.00009873582],"category_scores_gemma":[0.0055570803,0.00007902788,0.00015992133,0.001846644,0.00030715144,0.00033328633,0.000046332985,0.00028903692,3.2995882e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009694368,0.000035081186,0.15224439,0.0000038184858,0.00014883284,0.0000022784736,0.011405907,0.0056861723,0.00009139842,0.00056507403,0.005140622,0.8245795],"study_design_scores_gemma":[0.0013111164,0.00027243025,0.8774469,0.00021054602,0.00008282829,0.0000074408863,0.036929622,0.027703106,0.00013434408,0.049050435,0.006742307,0.000108923196],"about_ca_topic_score_codex":0.7857941,"about_ca_topic_score_gemma":0.9923807,"teacher_disagreement_score":0.8244706,"about_ca_system_score_codex":0.00095374015,"about_ca_system_score_gemma":0.032310564,"threshold_uncertainty_score":0.97317535},"labels":[],"label_agreement":null},{"id":"W4413206445","doi":"10.1016/j.cjca.2025.06.065","title":"Planning with Purpose — and People","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Cardiology","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine","score_opus":0.08745367271469266,"score_gpt":0.4244035487318725,"score_spread":0.33694987601717985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413206445","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8663185,0.0011238881,0.022152193,0.006137639,0.00082075247,0.00007458694,0.000004091809,0.000002202506,0.1033661],"genre_scores_gemma":[0.9986184,0.00000906909,0.0002445798,0.0004424194,0.00010558377,8.5271535e-7,3.0754612e-7,0.0000016485251,0.0005771344],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9992175,0.00012253124,0.00025794664,0.00008243539,0.0001902956,0.00012926203],"domain_scores_gemma":[0.9989931,0.0002553772,0.00011203939,0.000114025854,0.00033616018,0.00018932277],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016600698,0.000046614306,0.00023003158,0.00042975598,0.0000993251,0.00007160328,0.00018344664,0.00003768995,0.000061141196],"category_scores_gemma":[0.00039673524,0.000029650448,0.000035052046,0.00027398372,0.000074009,0.0001181594,0.0000063630123,0.00011712386,0.000006647427],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022056485,2.834969e-7,0.9400385,0.0000016031747,0.000039227663,0.00003710834,0.00052726315,0.005426033,0.00001292955,0.0024429054,0.025171094,0.026280977],"study_design_scores_gemma":[0.00033379075,0.000115005234,0.5764185,0.000018801615,0.000016401866,0.00020439005,0.0014668462,0.0001266342,0.000009804151,0.0032137784,0.41803512,0.00004091597],"about_ca_topic_score_codex":0.00012315786,"about_ca_topic_score_gemma":0.003723709,"teacher_disagreement_score":0.39286402,"about_ca_system_score_codex":0.000037964357,"about_ca_system_score_gemma":0.0017181716,"threshold_uncertainty_score":0.30479628},"labels":[],"label_agreement":null},{"id":"W4413304054","doi":"10.1080/0969594x.2025.2549158","title":"Diversity: a necessary imperative for assessment research","year":2025,"lang":"en","type":"article","venue":"Assessment in Education Principles Policy and Practice","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Diversity (politics); Data science; Engineering ethics; Management science; Computer science; Sociology; Engineering; Anthropology","score_opus":0.4676913733950703,"score_gpt":0.6664621529759441,"score_spread":0.19877077958087386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413304054","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22293155,0.00035804967,0.010533431,0.25223917,0.0013472149,0.0024241463,0.000029609524,0.000042551437,0.5100943],"genre_scores_gemma":[0.96007776,0.0006724112,0.018744979,0.006185903,0.00021965067,0.00057324505,0.000027530237,0.0000088703055,0.0134896645],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9943515,0.0021908216,0.00080408744,0.00067029253,0.0015592295,0.00042406557],"domain_scores_gemma":[0.9763798,0.020397281,0.00035617818,0.0006250004,0.0021038302,0.00013787788],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.025257729,0.00017682526,0.0002804151,0.0015561784,0.0018257675,0.0006116584,0.00061385497,0.00011731227,0.0001691306],"category_scores_gemma":[0.015674029,0.00015354408,0.000061033326,0.002260363,0.00015798748,0.0020829486,0.0011247696,0.0005452217,0.000016696893],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010793987,0.0007498134,0.057627738,0.000034524117,0.000040956114,6.2101964e-7,0.004673721,0.0001712208,0.00007685571,0.8599273,0.0065100286,0.070079304],"study_design_scores_gemma":[0.00083220814,0.00016202047,0.2861777,0.000059230195,0.000028008799,0.0000057910656,0.045070346,0.005298485,0.000046074983,0.11255848,0.5495876,0.0001740563],"about_ca_topic_score_codex":0.0009658303,"about_ca_topic_score_gemma":0.00037814552,"teacher_disagreement_score":0.7473688,"about_ca_system_score_codex":0.00083319243,"about_ca_system_score_gemma":0.010208866,"threshold_uncertainty_score":0.9994737},"labels":[],"label_agreement":null},{"id":"W4413358167","doi":"10.5334/ijic.nacic24168","title":"Development and Implementation of a System Accountability Framework for Nova Scotia","year":2025,"lang":"en","type":"article","venue":"International Journal of Integrated Care","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Nova Scotia Health Authority","funders":"","keywords":"Nova scotia; Accountability; Nova (rocket); Process management; Political science; Business; Public administration; Geography; Engineering","score_opus":0.09827246598025277,"score_gpt":0.5193029106686489,"score_spread":0.4210304446883961,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413358167","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.900075,0.00019352572,0.09672883,0.0005053278,0.0017069464,0.00017223907,0.000056007062,0.000004400604,0.00055771845],"genre_scores_gemma":[0.9708477,0.000005973834,0.028915249,0.00013463364,0.000046587895,0.0000040647683,0.000016051685,0.000002838068,0.000026888063],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9976403,0.000057533296,0.00107355,0.00012802139,0.0010264426,0.00007412046],"domain_scores_gemma":[0.99253863,0.00044431456,0.0006698,0.00010421786,0.006210378,0.000032641365],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001878341,0.000081389066,0.00020425944,0.00041807766,0.00003660644,0.00013175208,0.0004424672,0.000052874064,0.00022807882],"category_scores_gemma":[0.00051473215,0.00005549787,0.000086167165,0.0002652594,0.000032556436,0.0002563198,0.00004466117,0.000112976246,0.000003956183],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044339424,0.00006704111,0.35083398,0.00011377272,0.00040049764,0.0000027491044,0.008975243,0.00020471822,0.0010938265,0.058495615,0.0012414312,0.57812774],"study_design_scores_gemma":[0.0035570078,0.00031883272,0.20263277,0.0019995593,0.000102248916,0.000045217526,0.64545256,0.0015282927,0.08806053,0.010449354,0.0455894,0.0002642487],"about_ca_topic_score_codex":0.00010841446,"about_ca_topic_score_gemma":0.00057660183,"teacher_disagreement_score":0.6364773,"about_ca_system_score_codex":0.00053846854,"about_ca_system_score_gemma":0.001419132,"threshold_uncertainty_score":0.2517479},"labels":[],"label_agreement":null},{"id":"W4413358462","doi":"10.5334/ijic.nacic24212","title":"Building of a Learning Health System surrounding Hospital Discharge: A toolbox for Sustainable Metrics from Implementation to Evaluation and Emulation","year":2025,"lang":"en","type":"article","venue":"International Journal of Integrated Care","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Toolbox; Emulation; Engineering management; Computer science; Health care; Process management; Software engineering; Engineering; Psychology; Programming language","score_opus":0.07609850032532006,"score_gpt":0.5107499146078738,"score_spread":0.4346514142825537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413358462","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70895404,0.00042855408,0.2877124,0.0013803496,0.0008730734,0.00046339817,0.000039542534,0.0000064882347,0.00014215746],"genre_scores_gemma":[0.993105,0.000014522294,0.0065206843,0.00008190884,0.00008849942,0.000022654162,0.0000702804,0.000005992187,0.00009046817],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99651957,0.00027640554,0.0011392246,0.00019149506,0.0017348273,0.00013850561],"domain_scores_gemma":[0.9867377,0.00070051925,0.0010948323,0.000089420755,0.011312964,0.000064560874],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0054556285,0.00010167539,0.00027160527,0.0012928639,0.0001369012,0.00035441024,0.0003278447,0.000042790314,0.000066754226],"category_scores_gemma":[0.003854135,0.00007946415,0.00010104134,0.0008027397,0.000013400894,0.00072756264,0.000048778707,0.00013493288,9.225282e-7],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042635264,0.00006833257,0.25623572,0.00009644771,0.00035684585,0.0000029923665,0.012350054,0.022419091,0.0018974604,0.044364415,0.0017563192,0.66002595],"study_design_scores_gemma":[0.0044626645,0.001184622,0.06631109,0.0010019979,0.00014451989,0.00000765421,0.77570134,0.12446537,0.0062637436,0.0054430026,0.014768231,0.00024573144],"about_ca_topic_score_codex":0.0005021132,"about_ca_topic_score_gemma":0.000084680025,"teacher_disagreement_score":0.7633513,"about_ca_system_score_codex":0.0018331631,"about_ca_system_score_gemma":0.0013802758,"threshold_uncertainty_score":0.47936577},"labels":[],"label_agreement":null},{"id":"W4413360974","doi":"10.1177/10982140251355140","title":"Theory-Practice Connections in Collaborative Approaches to Evaluation: A Systematic Review of Practice","year":2025,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Systematic review; Management science; Psychology; Evaluation methods; Program evaluation; Peer evaluation; Computer science; Engineering ethics; MEDLINE; Political science; Higher education; Engineering","score_opus":0.31953432024649814,"score_gpt":0.545800497569362,"score_spread":0.22626617732286386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413360974","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0806444,0.1044661,0.14920712,0.3967833,0.0038976045,0.025021022,0.000044010336,0.00003942833,0.23989704],"genre_scores_gemma":[0.97854435,0.0015357384,0.012710321,0.0066717463,0.000053798987,0.00031402492,0.00000451559,0.000008658731,0.00015685736],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.97634304,0.014846642,0.0028717134,0.00029137635,0.005487799,0.00015945702],"domain_scores_gemma":[0.965926,0.01338631,0.004552295,0.00056731293,0.015479848,0.00008822717],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13738212,0.00014470372,0.00088759314,0.0010114486,0.00009388689,0.00010160088,0.00041884193,0.000032444863,0.00052454544],"category_scores_gemma":[0.21781065,0.00010444481,0.00013212927,0.006078054,0.00011413006,0.0013545203,0.000048775306,0.00021844589,0.000042805776],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0039892998,0.0038562182,0.001801657,0.028361477,0.0027845749,0.000016966682,0.058190223,0.118970685,0.0004553052,0.20682012,0.019400695,0.55535275],"study_design_scores_gemma":[0.0075313547,0.006215972,0.011332629,0.19292821,0.014364318,0.00039571963,0.56356835,0.120796084,0.00070350646,0.06838824,0.012769241,0.0010063997],"about_ca_topic_score_codex":0.000015595484,"about_ca_topic_score_gemma":0.000026999356,"teacher_disagreement_score":0.8978999,"about_ca_system_score_codex":0.0005038938,"about_ca_system_score_gemma":0.0034736386,"threshold_uncertainty_score":0.88824666},"labels":[],"label_agreement":null},{"id":"W4413366189","doi":"10.5334/ijic.nacic24057","title":"Development and Implementation of a System Accountability Framework for Nova Scotia","year":2025,"lang":"en","type":"article","venue":"International Journal of Integrated Care","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nova scotia; Accountability; Process management; Political science; Business; Public administration; Sociology","score_opus":0.09827246598025277,"score_gpt":0.5193029106686489,"score_spread":0.4210304446883961,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413366189","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.900075,0.00019352572,0.09672883,0.0005053278,0.0017069464,0.00017223907,0.000056007062,0.000004400604,0.00055771845],"genre_scores_gemma":[0.9708477,0.000005973834,0.028915249,0.00013463364,0.000046587895,0.0000040647683,0.000016051685,0.000002838068,0.000026888063],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9976403,0.000057533296,0.00107355,0.00012802139,0.0010264426,0.00007412046],"domain_scores_gemma":[0.99253863,0.00044431456,0.0006698,0.00010421786,0.006210378,0.000032641365],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001878341,0.000081389066,0.00020425944,0.00041807766,0.00003660644,0.00013175208,0.0004424672,0.000052874064,0.00022807882],"category_scores_gemma":[0.00051473215,0.00005549787,0.000086167165,0.0002652594,0.000032556436,0.0002563198,0.00004466117,0.000112976246,0.000003956183],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044339424,0.00006704111,0.35083398,0.00011377272,0.00040049764,0.0000027491044,0.008975243,0.00020471822,0.0010938265,0.058495615,0.0012414312,0.57812774],"study_design_scores_gemma":[0.0035570078,0.00031883272,0.20263277,0.0019995593,0.000102248916,0.000045217526,0.64545256,0.0015282927,0.08806053,0.010449354,0.0455894,0.0002642487],"about_ca_topic_score_codex":0.00010841446,"about_ca_topic_score_gemma":0.00057660183,"teacher_disagreement_score":0.6364773,"about_ca_system_score_codex":0.00053846854,"about_ca_system_score_gemma":0.001419132,"threshold_uncertainty_score":0.2517479},"labels":[],"label_agreement":null},{"id":"W4413366213","doi":"10.5334/ijic.nacic24113","title":"Meeting in the middle: Meso-level organizations working together for macro-level change","year":2025,"lang":"en","type":"article","venue":"International Journal of Integrated Care","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Middle level; Macro level; Micro level; Macro; Process management; Business; Work (physics); Computer science; Engineering; Economic impact analysis","score_opus":0.32021081537629975,"score_gpt":0.47417155019673807,"score_spread":0.15396073482043832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413366213","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6804727,0.0034818344,0.16506392,0.0852393,0.014983048,0.0017857143,0.0006124774,0.00004922524,0.04831182],"genre_scores_gemma":[0.99258786,0.000052762192,0.0030185487,0.0030870705,0.00028367224,0.000027109078,0.000031453485,0.000008575377,0.00090296275],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9972028,0.00020909146,0.00089745846,0.0001618308,0.0013824101,0.00014638751],"domain_scores_gemma":[0.99251884,0.00089257833,0.00048635958,0.00017018047,0.005901199,0.00003083851],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029798644,0.00012024371,0.0001915435,0.0006990235,0.00011648487,0.00038304616,0.0014273246,0.00007309386,0.00040546956],"category_scores_gemma":[0.0034236081,0.00007024047,0.00012637407,0.0012278081,0.000043337543,0.00032376373,0.000060385424,0.00027846923,0.000014881187],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004179661,0.00036239505,0.32876018,0.000023796403,0.00043681773,0.000052424133,0.06978608,0.0032513735,0.0013523764,0.03627179,0.025617814,0.53366697],"study_design_scores_gemma":[0.0053189634,0.000294416,0.16222055,0.0026490607,0.00013374665,0.00013985962,0.40151092,0.015913999,0.0057282974,0.026319465,0.37920627,0.00056445383],"about_ca_topic_score_codex":0.0000928031,"about_ca_topic_score_gemma":0.0009772427,"teacher_disagreement_score":0.5331025,"about_ca_system_score_codex":0.00039573398,"about_ca_system_score_gemma":0.0007551726,"threshold_uncertainty_score":0.44396073},"labels":[],"label_agreement":null},{"id":"W4413513083","doi":"10.47611/jsr.v13i4.2655","title":"Pearls on Positionality and Reflexivity: From a Humbled PhD Student","year":2024,"lang":"en","type":"article","venue":"Journal of Student Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Reflexivity; Sociology; Geography; Psychology; Social science","score_opus":0.8020674653622637,"score_gpt":0.7328987768626081,"score_spread":0.06916868849965563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413513083","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97793484,0.0012560716,0.00010502002,0.0109622665,0.0005055924,0.00017677467,0.000011029788,0.0000079219535,0.009040494],"genre_scores_gemma":[0.9966256,0.0004805515,0.00018844384,0.0002332341,0.00050522457,0.0000066887233,0.0000013575122,0.0000071414415,0.0019517451],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9882248,0.0009668586,0.0008018773,0.00031484113,0.009444751,0.00024684795],"domain_scores_gemma":[0.9951003,0.002944704,0.00015039793,0.0002876393,0.0013117946,0.00020515002],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.023676943,0.000101739206,0.00027356492,0.0006836272,0.00025244648,0.0014791563,0.000693379,0.00005165303,0.0019348267],"category_scores_gemma":[0.00046799966,0.000062473046,0.00011808298,0.00068994355,0.00011287713,0.0004863226,0.00030107808,0.0007822498,0.00040531417],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011601023,0.0033724387,0.55715644,0.000069385256,0.0011227202,0.0012216057,0.0275753,0.0004937952,0.014860135,0.04381067,0.14468496,0.20447245],"study_design_scores_gemma":[0.0006557257,0.0009652045,0.9454232,0.0002076211,0.000018657893,0.000022877122,0.0042153066,0.00034846066,0.00029991716,0.022040682,0.025712134,0.000090221765],"about_ca_topic_score_codex":0.000028400109,"about_ca_topic_score_gemma":0.00003343031,"teacher_disagreement_score":0.38826674,"about_ca_system_score_codex":0.00024720986,"about_ca_system_score_gemma":0.00043846143,"threshold_uncertainty_score":0.9995574},"labels":[],"label_agreement":null},{"id":"W4413672324","doi":"10.1002/pad.70020","title":"Killing Two Birds With One Stone? A New Pragmatist Perspective on the Rigor‐Relevance Gap in the Literature on Capacity Building Projects","year":2025,"lang":"en","type":"article","venue":"Public Administration and Development","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Global Affairs Canada","funders":"","keywords":"Pragmatism; Relevance (law); Perspective (graphical); Capacity building; Sociology; Epistemology; Positive economics; Political science; Economics; Philosophy; Mathematics; Law; Geometry","score_opus":0.1755079573731874,"score_gpt":0.43728322351456816,"score_spread":0.2617752661413808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413672324","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7707743,0.00013053733,0.017432047,0.16349235,0.00025305655,0.0015723242,0.000006724552,0.000054629534,0.046284005],"genre_scores_gemma":[0.98899066,0.000021392956,0.0060058725,0.0036664363,0.000044757286,0.00012894705,0.000006779759,0.000004894052,0.001130276],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99723995,0.00031496838,0.00043527107,0.00044414733,0.0013469761,0.00021868122],"domain_scores_gemma":[0.9979318,0.0010924365,0.00020203137,0.00033202954,0.00037190024,0.000069834576],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0037417684,0.00017613344,0.00016619741,0.00030198492,0.00051376043,0.0011756287,0.00034536616,0.00005075375,0.00010229108],"category_scores_gemma":[0.0010769685,0.000086277694,0.000021572185,0.0013013405,0.00007744611,0.00036196734,0.000034175126,0.00033744908,0.00002529496],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017660522,0.00031798618,0.004683773,0.000015253398,0.00003742401,0.0000054773523,0.026542095,0.0000873987,0.00004440127,0.9295518,0.0024755495,0.036062274],"study_design_scores_gemma":[0.0077742036,0.0022491908,0.36417195,0.0022843282,0.000046829664,0.00011123873,0.11336969,0.012906101,0.008490176,0.11062132,0.37622803,0.0017469408],"about_ca_topic_score_codex":0.000014008843,"about_ca_topic_score_gemma":0.00083615613,"teacher_disagreement_score":0.81893045,"about_ca_system_score_codex":0.0002100681,"about_ca_system_score_gemma":0.0018403635,"threshold_uncertainty_score":0.99986124},"labels":[],"label_agreement":null},{"id":"W4413834867","doi":"10.24908/cpp-apc.v2025i1.19135","title":"The Implementation of Compact Development in Moncton, New Brunswick: Perspectives from Developers","year":2025,"lang":"en","type":"article","venue":"Canadian Planning and Policy / Aménagement et politique au Canada","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Software engineering","score_opus":0.05737050102517771,"score_gpt":0.4373366808463941,"score_spread":0.3799661798212164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413834867","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9046684,0.00036220232,0.00009206696,0.047611598,0.00020905297,0.00031137047,0.000058675665,0.0000074371064,0.04667922],"genre_scores_gemma":[0.993504,0.000045076154,0.00011759377,0.0041357432,0.000052004547,0.000006515763,0.00003183862,0.000006148236,0.0021010647],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9979101,0.00019935261,0.00059855235,0.0002826078,0.00054236525,0.00046703208],"domain_scores_gemma":[0.9985049,0.00060829305,0.00016242136,0.0002570936,0.00014839241,0.00031892527],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013492891,0.0001559906,0.0002090111,0.000587927,0.0003176608,0.00016751229,0.0003653058,0.00003896452,0.00011491293],"category_scores_gemma":[0.00032919433,0.00012252375,0.00002338261,0.0006611169,0.00006177258,0.0001543592,0.000045976343,0.00013183366,0.0000022589409],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014802613,0.0000063486827,0.6787264,0.00000907651,0.00008654494,0.000009793704,0.031150084,0.0006388697,0.000009482411,0.21014518,0.05847543,0.020728031],"study_design_scores_gemma":[0.00030263048,0.000008464078,0.6872784,0.000043265252,0.00000428369,5.174536e-7,0.033315156,0.000074764546,0.00014921381,0.0012233852,0.27750355,0.00009637621],"about_ca_topic_score_codex":0.99927664,"about_ca_topic_score_gemma":0.9999002,"teacher_disagreement_score":0.21902813,"about_ca_system_score_codex":0.0019734397,"about_ca_system_score_gemma":0.078701906,"threshold_uncertainty_score":0.926521},"labels":[],"label_agreement":null},{"id":"W4413887482","doi":"10.1016/j.sapharm.2025.06.043","title":"Alexander First Nation members’ views of their relationships with community pharmacists using Community-Based Participatory Research","year":2025,"lang":"en","type":"article","venue":"Research in Social and Administrative Pharmacy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Alexandra Hospital; University of Alberta","funders":"","keywords":"Community-based participatory research; Citizen journalism; Participatory action research; Sociology; Community practice; Medicine; Library science; Political science; Anthropology; Family medicine; Pharmacy; Computer science; Law","score_opus":0.968457681426645,"score_gpt":0.7205271153811582,"score_spread":0.2479305660454868,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413887482","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97588426,0.00012591251,0.0002968892,0.0034544624,0.00004464624,0.00063603837,0.000050220013,0.000010586139,0.019496975],"genre_scores_gemma":[0.99926317,0.000040399562,0.00015432342,0.00012686232,0.000038206155,0.00010419003,0.00002111361,0.0000062537056,0.0002454887],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9742161,0.022443868,0.00067514414,0.0002351979,0.002015631,0.00041405417],"domain_scores_gemma":[0.9865114,0.010989039,0.00017017145,0.00032573417,0.0018735529,0.00013009414],"candidate_categories":["metaresearch","sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.05495655,0.00013845562,0.00030481792,0.0006220775,0.0040067155,0.00019755808,0.000587664,0.00006355868,0.0002533616],"category_scores_gemma":[0.0010713249,0.00010283309,0.000052181163,0.0034141254,0.0014897865,0.00043240975,0.000217181,0.0024454044,0.000006792648],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017398365,0.0025356757,0.9014106,0.0005537682,0.0001238779,0.0000103246975,0.05548215,0.00062009104,0.0023781345,0.014201528,0.004002093,0.016941926],"study_design_scores_gemma":[0.01561245,0.0012697058,0.3756628,0.0013102659,0.0000709774,0.000008295296,0.24146591,0.124471195,0.033244465,0.13663991,0.06935422,0.0008897994],"about_ca_topic_score_codex":0.00076826115,"about_ca_topic_score_gemma":0.004169634,"teacher_disagreement_score":0.5257478,"about_ca_system_score_codex":0.0002846233,"about_ca_system_score_gemma":0.0019159858,"threshold_uncertainty_score":0.999856},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"low"}],"label_agreement":"agree"},{"id":"W4413960996","doi":"10.1017/gmh.2025.10034.pr10","title":"Review: Development and preliminary inter-rater reliability of the new PROOF tool to measure fidelity of problem-solving therapy for depression delivered by non-specialists in a low-resource African setting — R1/PR10","year":2025,"lang":"en","type":"peer-review","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario","funders":"","keywords":"Fidelity; Measure (data warehouse); Reliability (semiconductor); Depression (economics); Inter-rater reliability; Resource (disambiguation); Psychology; Proof of concept; Computer science; Medicine; Data mining; Rating scale; Developmental psychology; Telecommunications; Computer network","score_opus":0.07120928461470935,"score_gpt":0.4063434795554308,"score_spread":0.3351341949407215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413960996","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034834925,0.5023036,0.04285444,0.30178618,0.0026812905,0.090015255,0.0015553226,0.00012085554,0.023848116],"genre_scores_gemma":[0.1569069,0.1091137,0.20213132,0.11317054,0.000897304,0.012217297,0.0018323326,0.00037472593,0.4033559],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99268764,0.00073833915,0.0031625514,0.0010437318,0.0020192985,0.00034845024],"domain_scores_gemma":[0.99376404,0.001202244,0.0015661279,0.001310023,0.0020395576,0.000118009135],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.015820058,0.00044279368,0.0013644904,0.00021016247,0.00014536417,0.000076073346,0.0013319603,0.00018942582,0.00044559498],"category_scores_gemma":[0.0046782703,0.0002468266,0.00027837467,0.0010369066,0.00007710314,0.00020837897,0.00074585254,0.00036855254,0.000002330505],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015031005,0.00009802259,0.00095553725,0.0051108235,0.000017159582,8.130039e-8,0.0007609523,0.000037675807,0.00005093394,0.0000013698441,0.6304357,0.36238143],"study_design_scores_gemma":[0.0007788597,0.00017040544,0.004296785,0.06006337,0.000052936022,9.1021406e-7,0.0001654311,0.0004952218,0.0024714917,0.00018549284,0.93097615,0.0003429623],"about_ca_topic_score_codex":0.00018096341,"about_ca_topic_score_gemma":0.00053571473,"teacher_disagreement_score":0.3931899,"about_ca_system_score_codex":0.00023802178,"about_ca_system_score_gemma":0.0020343268,"threshold_uncertainty_score":0.9999984},"labels":[],"label_agreement":null},{"id":"W4413961005","doi":"10.1017/gmh.2025.10034.pr11","title":"Recommendation: Development and preliminary inter-rater reliability of the new PROOF tool to measure fidelity of problem-solving therapy for depression delivered by non-specialists in a low-resource African setting — R1/PR11","year":2025,"lang":"en","type":"peer-review","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario","funders":"","keywords":"Fidelity; Inter-rater reliability; Measure (data warehouse); Depression (economics); Reliability (semiconductor); Resource (disambiguation); Proof of concept; Computer science; Psychology; Medicine; Data mining; Developmental psychology; Rating scale; Computer network; Telecommunications; Operating system","score_opus":0.08165580773228148,"score_gpt":0.4071247314732017,"score_spread":0.32546892374092024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413961005","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13034798,0.016913353,0.16892608,0.5458896,0.004118203,0.07395251,0.0022184986,0.00015338289,0.057480387],"genre_scores_gemma":[0.5476352,0.002469979,0.17179558,0.027467925,0.0006746826,0.0055755693,0.0021657161,0.00020217143,0.24201319],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9940996,0.00060733996,0.0025738308,0.0009373537,0.0014888516,0.00029299952],"domain_scores_gemma":[0.9947946,0.0012504761,0.0012942614,0.000914278,0.0016501559,0.00009624834],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.012015808,0.00036650916,0.00091600546,0.00023624998,0.0001655545,0.00009896536,0.0009832522,0.00021161599,0.0011369396],"category_scores_gemma":[0.0027048367,0.00021598577,0.00016760573,0.0008680739,0.000060561255,0.00024021012,0.0006293597,0.00031078313,0.0000017637724],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023311989,0.000106347485,0.0017763644,0.0008517364,0.000017416483,4.164487e-8,0.001535375,0.00008124271,0.00005864362,0.0000017788777,0.45427123,0.5410667],"study_design_scores_gemma":[0.0013125322,0.00026053068,0.011869745,0.008298364,0.000038826092,7.861466e-7,0.0006055754,0.0018063091,0.0053317077,0.00032412395,0.96975046,0.0004010456],"about_ca_topic_score_codex":0.00023743148,"about_ca_topic_score_gemma":0.00083766395,"teacher_disagreement_score":0.5406656,"about_ca_system_score_codex":0.0002568261,"about_ca_system_score_gemma":0.0016891265,"threshold_uncertainty_score":0.9997762},"labels":[],"label_agreement":null},{"id":"W4413961006","doi":"10.1017/gmh.2025.10034.pr9","title":"Review: Development and preliminary inter-rater reliability of the new PROOF tool to measure fidelity of problem-solving therapy for depression delivered by non-specialists in a low-resource African setting — R1/PR9","year":2025,"lang":"en","type":"peer-review","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario","funders":"","keywords":"Fidelity; Inter-rater reliability; Measure (data warehouse); Depression (economics); Reliability (semiconductor); Resource (disambiguation); Proof of concept; Psychology; Computer science; Medicine; Data mining; Rating scale; Developmental psychology","score_opus":0.07201903900394914,"score_gpt":0.4065296812950697,"score_spread":0.3345106422911206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413961006","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032923285,0.5094166,0.04245235,0.29758087,0.0026134958,0.08923333,0.001497941,0.00011885828,0.024163295],"genre_scores_gemma":[0.16079816,0.11074792,0.19647755,0.1140044,0.00089355075,0.012333546,0.0018112548,0.000370926,0.40256268],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9927157,0.0007406523,0.0031480866,0.0010371339,0.0020121254,0.00034627266],"domain_scores_gemma":[0.99381375,0.001195331,0.0015567031,0.0012991467,0.0020181283,0.00011691906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015770894,0.00043976613,0.0013568541,0.00020842919,0.00014490423,0.000075452466,0.0013201667,0.00018573715,0.0004415296],"category_scores_gemma":[0.004707241,0.00024486808,0.00027649835,0.0010310569,0.000076049895,0.00020775807,0.00074218976,0.0003587657,0.0000023153489],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014785962,0.00009681048,0.0008978409,0.005120965,0.000017078091,8.017613e-8,0.00076060457,0.000037564398,0.000048598067,0.00000136687,0.62964183,0.3632294],"study_design_scores_gemma":[0.0007772921,0.00016982769,0.0043862737,0.061152592,0.00005284767,8.989346e-7,0.00015711047,0.00048630824,0.0024280306,0.00018635216,0.92986083,0.00034160822],"about_ca_topic_score_codex":0.00018202998,"about_ca_topic_score_gemma":0.0005033535,"teacher_disagreement_score":0.39866865,"about_ca_system_score_codex":0.00024244182,"about_ca_system_score_gemma":0.0020210147,"threshold_uncertainty_score":0.998543},"labels":[],"label_agreement":null},{"id":"W4413961208","doi":"10.1017/gmh.2025.10034.pr6","title":"Recommendation: Development and preliminary inter-rater reliability of the new PROOF tool to measure fidelity of problem-solving therapy for depression delivered by non-specialists in a low-resource African setting — R0/PR6","year":2025,"lang":"en","type":"peer-review","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario","funders":"","keywords":"Fidelity; Measure (data warehouse); Reliability (semiconductor); Depression (economics); Proof of concept; Resource (disambiguation); Inter-rater reliability; Computer science; Psychology; Clinical psychology; Data mining; Developmental psychology; Rating scale","score_opus":0.08079934618591844,"score_gpt":0.4076446152055804,"score_spread":0.32684526901966193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413961208","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10314776,0.012788989,0.1651434,0.56967485,0.004451667,0.07331666,0.0021532443,0.00015108348,0.06917234],"genre_scores_gemma":[0.524265,0.0031998754,0.21564852,0.032331873,0.00075004535,0.006044091,0.0024012174,0.00021869452,0.21514066],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9940672,0.00063993066,0.0025670049,0.0009308052,0.001502132,0.00029295596],"domain_scores_gemma":[0.99475545,0.0013107825,0.0012730325,0.0009141813,0.0016497644,0.00009678725],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.012241243,0.0003651239,0.00091903965,0.00023617473,0.00016643165,0.00010282329,0.0009806595,0.00021089826,0.0014046159],"category_scores_gemma":[0.0027271158,0.000214729,0.00018656459,0.0008698272,0.000060827504,0.00023955709,0.0006392805,0.00031102746,0.0000017554285],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024998057,0.00011396974,0.001663678,0.0008418005,0.000018573946,4.617936e-8,0.0016777957,0.000074587966,0.0000524086,0.0000023802788,0.4466244,0.54868037],"study_design_scores_gemma":[0.0012144812,0.00021773062,0.009334606,0.0071584354,0.000033627242,7.334545e-7,0.00049112056,0.0015657877,0.0050382554,0.0003547685,0.9742296,0.0003608722],"about_ca_topic_score_codex":0.00017118247,"about_ca_topic_score_gemma":0.0006536693,"teacher_disagreement_score":0.5483195,"about_ca_system_score_codex":0.00025634558,"about_ca_system_score_gemma":0.0016895691,"threshold_uncertainty_score":0.99950826},"labels":[],"label_agreement":null},{"id":"W4413961328","doi":"10.1017/gmh.2025.10034.pr5","title":"Review: Development and preliminary inter-rater reliability of the new PROOF tool to measure fidelity of problem-solving therapy for depression delivered by non-specialists in a low-resource African setting — R0/PR5","year":2025,"lang":"en","type":"peer-review","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario","funders":"","keywords":"Fidelity; Measure (data warehouse); Inter-rater reliability; Reliability (semiconductor); Depression (economics); Proof of concept; Resource (disambiguation); Computer science; Psychology; Clinical psychology; Data mining; Developmental psychology; Rating scale","score_opus":0.07201903900394914,"score_gpt":0.4065296812950697,"score_spread":0.3345106422911206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413961328","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041831575,0.31710002,0.062068548,0.40274408,0.0034595048,0.1179903,0.0018618377,0.0001579939,0.052786127],"genre_scores_gemma":[0.17638828,0.11965916,0.23778504,0.13631742,0.0010311133,0.01402909,0.0021081846,0.0004232472,0.31225845],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.992689,0.00077306764,0.0031304387,0.0010475378,0.0020132936,0.00034667578],"domain_scores_gemma":[0.9937828,0.0012347725,0.0015316883,0.0013207007,0.0020131555,0.000116860836],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.015931103,0.00043981895,0.0013602687,0.00020809591,0.00014495534,0.00007746518,0.0013202495,0.0001858539,0.0010640218],"category_scores_gemma":[0.0047670165,0.0002448642,0.00027564695,0.0010244378,0.00007698891,0.00020714597,0.0007475565,0.00035888128,0.0000022702236],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001602407,0.00010424594,0.00093955925,0.005094287,0.000018589088,9.063007e-8,0.0008294823,0.000040083614,0.00004985745,0.0000014838952,0.5942809,0.39848116],"study_design_scores_gemma":[0.000792639,0.00017323667,0.004194194,0.03967739,0.00005353349,9.3816425e-7,0.00015894904,0.00051297486,0.0024000064,0.00018055452,0.9515099,0.0003456778],"about_ca_topic_score_codex":0.00017820325,"about_ca_topic_score_gemma":0.0004971913,"teacher_disagreement_score":0.39813548,"about_ca_system_score_codex":0.00024334555,"about_ca_system_score_gemma":0.002002372,"threshold_uncertainty_score":0.99984914},"labels":[],"label_agreement":null},{"id":"W4413961329","doi":"10.1017/gmh.2025.10034.pr3","title":"Review: Development and preliminary inter-rater reliability of the new PROOF tool to measure fidelity of problem-solving therapy for depression delivered by non-specialists in a low-resource African setting — R0/PR3","year":2025,"lang":"en","type":"peer-review","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario","funders":"","keywords":"Fidelity; Measure (data warehouse); Inter-rater reliability; Reliability (semiconductor); Depression (economics); Proof of concept; Resource (disambiguation); Computer science; Psychology; Clinical psychology; Data mining; Developmental psychology; Rating scale","score_opus":0.07201903900394914,"score_gpt":0.4065296812950697,"score_spread":0.3345106422911206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413961329","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035660606,0.42310795,0.05138835,0.35066527,0.002948989,0.101296835,0.0016615201,0.00013515599,0.033135314],"genre_scores_gemma":[0.16721594,0.11154827,0.21751972,0.12902491,0.00095122977,0.013040632,0.0019620047,0.0003928683,0.35834444],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9926601,0.0007743641,0.0031353685,0.0010665025,0.0020167148,0.00034696312],"domain_scores_gemma":[0.99375325,0.0012340384,0.0015342614,0.0013448428,0.0020155914,0.00011798358],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016240947,0.00044007503,0.0013588697,0.00020826842,0.0001450772,0.000077472396,0.0013215702,0.00018593899,0.0006183612],"category_scores_gemma":[0.0048390185,0.00024497544,0.0002759979,0.0010271451,0.000077036624,0.00020722463,0.00076865515,0.00035933623,0.000002327179],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001528209,0.00009919458,0.0008817313,0.005035692,0.000017625545,8.617617e-8,0.0007919159,0.00003743043,0.00005239755,0.0000014247371,0.6154486,0.37748107],"study_design_scores_gemma":[0.00078116945,0.00017068378,0.0040398026,0.051667605,0.000052706207,9.2572424e-7,0.00015915422,0.0004923956,0.0026233362,0.00018217457,0.93948936,0.00034070807],"about_ca_topic_score_codex":0.0001779324,"about_ca_topic_score_gemma":0.00049773714,"teacher_disagreement_score":0.37714037,"about_ca_system_score_codex":0.00024025579,"about_ca_system_score_gemma":0.0020035398,"threshold_uncertainty_score":0.9989809},"labels":[],"label_agreement":null},{"id":"W4413961330","doi":"10.1017/gmh.2025.10034.pr4","title":"Review: Development and preliminary inter-rater reliability of the new PROOF tool to measure fidelity of problem-solving therapy for depression delivered by non-specialists in a low-resource African setting — R0/PR4","year":2025,"lang":"en","type":"peer-review","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario","funders":"","keywords":"Fidelity; Measure (data warehouse); Inter-rater reliability; Reliability (semiconductor); Depression (economics); Proof of concept; Resource (disambiguation); Psychology; Computer science; Medicine; Clinical psychology; Data mining; Rating scale; Developmental psychology","score_opus":0.07201903900394914,"score_gpt":0.4065296812950697,"score_spread":0.3345106422911206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413961330","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036067035,0.42779455,0.051572487,0.34480458,0.002965276,0.10172735,0.0016688899,0.00013583795,0.033264],"genre_scores_gemma":[0.16637449,0.11201788,0.21880959,0.12682739,0.0009538267,0.013059329,0.0019649495,0.0003936561,0.3595989],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9926795,0.00077397836,0.0031351647,0.0010488586,0.0020156323,0.00034686772],"domain_scores_gemma":[0.9937803,0.0012325591,0.0015332925,0.001322281,0.0020136773,0.00011788598],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01591419,0.0004401009,0.0013590498,0.00020832631,0.00014508124,0.00007748097,0.0013216522,0.00018594755,0.00061906123],"category_scores_gemma":[0.0047505517,0.0002449895,0.00027600664,0.0010263514,0.00007700813,0.00020721991,0.00075606693,0.0003599557,0.0000023252896],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015226651,0.00009883863,0.000857987,0.005027184,0.000017564105,8.5900815e-8,0.0007902847,0.00003740916,0.000047109734,0.0000014165038,0.6134988,0.37947103],"study_design_scores_gemma":[0.00078269554,0.00017097055,0.0040962533,0.05174038,0.0000528059,9.2759154e-7,0.00015811223,0.00049552723,0.0023946862,0.00018251575,0.9395838,0.00034134614],"about_ca_topic_score_codex":0.00017573558,"about_ca_topic_score_gemma":0.00049829565,"teacher_disagreement_score":0.37912968,"about_ca_system_score_codex":0.00024021839,"about_ca_system_score_gemma":0.0019996217,"threshold_uncertainty_score":0.99903816},"labels":[],"label_agreement":null},{"id":"W4413961331","doi":"10.1017/gmh.2025.10034.pr2","title":"Review: Development and preliminary inter-rater reliability of the new PROOF tool to measure fidelity of problem-solving therapy for depression delivered by non-specialists in a low-resource African setting — R0/PR2","year":2025,"lang":"en","type":"peer-review","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario","funders":"","keywords":"Fidelity; Measure (data warehouse); Proof of concept; Inter-rater reliability; Reliability (semiconductor); Depression (economics); Resource (disambiguation); Computer science; Psychology; Medicine; Data mining; Rating scale; Developmental psychology","score_opus":0.07201903900394914,"score_gpt":0.4065296812950697,"score_spread":0.3345106422911206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413961331","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035392646,0.4265115,0.05169168,0.34698153,0.002958632,0.10146739,0.0016646435,0.0001354071,0.03319656],"genre_scores_gemma":[0.16701485,0.11170388,0.2190063,0.12712704,0.00095333357,0.013068601,0.0019663747,0.0003937175,0.3587659],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9926772,0.0007743463,0.0031359373,0.0010489627,0.0020165637,0.00034696358],"domain_scores_gemma":[0.9937776,0.0012336016,0.0015336921,0.001322597,0.0020145834,0.000117931806],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015986925,0.00044011333,0.0013591887,0.0002083884,0.00014509556,0.000077487144,0.0013216748,0.00018595369,0.0006192407],"category_scores_gemma":[0.0047618384,0.0002449943,0.00027601197,0.0010274821,0.00007704194,0.00020724416,0.00075613277,0.00035937078,0.0000023272598],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015306131,0.00009934924,0.0008934988,0.005052772,0.000017653581,8.6340336e-8,0.0007932889,0.000037764137,0.000046973706,0.0000014270126,0.61646324,0.37644088],"study_design_scores_gemma":[0.0007834043,0.00017113925,0.004125761,0.05179796,0.00005284763,9.283487e-7,0.00015970015,0.0004982032,0.0023714984,0.0001827506,0.93951416,0.0003416203],"about_ca_topic_score_codex":0.0001783697,"about_ca_topic_score_gemma":0.00049873744,"teacher_disagreement_score":0.37609926,"about_ca_system_score_codex":0.00024027868,"about_ca_system_score_gemma":0.002003575,"threshold_uncertainty_score":0.99905777},"labels":[],"label_agreement":null},{"id":"W4413961343","doi":"10.1017/gmh.2025.10034.pr12","title":"Decision: Development and preliminary inter-rater reliability of the new PROOF tool to measure fidelity of problem-solving therapy for depression delivered by non-specialists in a low-resource African setting — R1/PR12","year":2025,"lang":"en","type":"peer-review","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario","funders":"","keywords":"Fidelity; Measure (data warehouse); Depression (economics); Reliability (semiconductor); Inter-rater reliability; Proof of concept; Resource (disambiguation); Computer science; Psychology; Data mining; Developmental psychology; Rating scale","score_opus":0.06682207619746232,"score_gpt":0.4018516209327718,"score_spread":0.3350295447353095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413961343","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3565616,0.06375454,0.2705252,0.18434665,0.0056027183,0.08510238,0.0020223518,0.00017109881,0.031913478],"genre_scores_gemma":[0.5712379,0.0026852833,0.23455067,0.015515093,0.0005129386,0.0036724817,0.0005567563,0.00018133255,0.1710875],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9921639,0.00054589135,0.003114568,0.0011460448,0.002652039,0.00037757272],"domain_scores_gemma":[0.99275947,0.0023374073,0.0013418234,0.0013622866,0.002058805,0.00014021518],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.013629996,0.00046503852,0.001215723,0.00030674567,0.0001862985,0.00012244719,0.0014917857,0.00028291854,0.0005114139],"category_scores_gemma":[0.0047799433,0.00025993033,0.00027280618,0.001124303,0.000088044595,0.00024279699,0.0009386805,0.00037286076,0.0000024945177],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047556835,0.00013190848,0.0018675745,0.0007802185,0.000019092737,1.4489748e-7,0.0016238589,0.00018111161,0.00007010862,0.0000028195034,0.4543814,0.5404662],"study_design_scores_gemma":[0.0019397569,0.0003223429,0.019793345,0.020725468,0.000051313065,0.0000015393819,0.00051231356,0.001908731,0.006199328,0.0009848581,0.9470173,0.00054370373],"about_ca_topic_score_codex":0.00017858512,"about_ca_topic_score_gemma":0.0008423184,"teacher_disagreement_score":0.5399225,"about_ca_system_score_codex":0.0002687212,"about_ca_system_score_gemma":0.002227251,"threshold_uncertainty_score":0.9999853},"labels":[],"label_agreement":null},{"id":"W4413972820","doi":"10.3138/cjpe-2024-0044","title":"Taking Stock of Contribution Analysis: Reflecting on the Past to Inform the Future","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Stock (firearms); Geography; Data science; Computer science; Archaeology","score_opus":0.3492271650557068,"score_gpt":0.5756301893170004,"score_spread":0.2264030242612936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413972820","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9126993,0.000391384,0.0062774774,0.069487266,0.0012884745,0.001942702,0.000008454934,0.0000067617852,0.007898168],"genre_scores_gemma":[0.9983015,0.0000027059789,0.00028022396,0.0010641196,0.00018457179,0.000052719588,0.000004502814,0.000002483946,0.00010718631],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9964629,0.00055464264,0.00088353216,0.000120385695,0.0017851924,0.00019335838],"domain_scores_gemma":[0.9938703,0.0006107359,0.0010677687,0.00034056837,0.0039775944,0.00013301596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022468805,0.00008774139,0.00021009531,0.0009797168,0.000529152,0.00033689785,0.0005611293,0.000054125285,0.00084192696],"category_scores_gemma":[0.0047879107,0.00004384513,0.00018164012,0.0043530115,0.000050216287,0.00022450503,0.000014659737,0.00024331042,0.000013492657],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034028333,0.000016421807,0.045759566,0.0000019918202,0.00019499905,4.2516754e-7,0.0015382663,0.017768698,0.00002720332,0.007050478,0.0030586538,0.9245493],"study_design_scores_gemma":[0.0006649877,0.00061380805,0.7900304,0.00011679416,0.000778223,0.0000047028893,0.0093473885,0.07934085,0.00026586477,0.006740878,0.111971036,0.0001250397],"about_ca_topic_score_codex":0.00020439536,"about_ca_topic_score_gemma":0.027797602,"teacher_disagreement_score":0.92442423,"about_ca_system_score_codex":0.00037181677,"about_ca_system_score_gemma":0.0022807717,"threshold_uncertainty_score":0.98994255},"labels":[],"label_agreement":null},{"id":"W4413989991","doi":"10.33524/cjar.v25i2.769","title":"Radical Incrementalism in Action Through Institutional Work: Case Studies of Embedded Research in South Africa","year":2025,"lang":"en","type":"article","venue":"The Canadian Journal of Action Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Universiteit Stellenbosch","keywords":"Incrementalism; Action research; Work (physics); Action (physics); Political science; Sociology; Engineering ethics; Pedagogy; Engineering; Law","score_opus":0.8485844561438768,"score_gpt":0.6751957561293249,"score_spread":0.17338870001455187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413989991","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98097914,0.0006586624,0.00006662655,0.011179606,0.0005775114,0.00028993926,0.000005020686,0.0000014151842,0.006242081],"genre_scores_gemma":[0.9984714,0.00011513147,0.00014062028,0.000065432476,0.000087770444,0.000014725187,6.6701153e-7,0.0000034311038,0.0011008345],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99249995,0.0029444315,0.0009375861,0.00018859528,0.0029798744,0.00044955747],"domain_scores_gemma":[0.9948969,0.0021660735,0.0001945666,0.0003001667,0.0022769726,0.00016532776],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.045150217,0.00007724282,0.00024883766,0.003355049,0.00082894124,0.00018395923,0.00060840836,0.000093858696,0.00048630548],"category_scores_gemma":[0.0048124045,0.000050811766,0.00006602467,0.005457491,0.0010877107,0.00056585413,0.000084983,0.0014867528,0.000030911484],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0038517474,0.00082927855,0.2328151,0.00024779927,0.000577653,0.005508632,0.3016261,0.031529587,0.0024239882,0.09494429,0.14742254,0.17822328],"study_design_scores_gemma":[0.005830939,0.00081250776,0.13101491,0.0014251318,0.00003006796,0.0009340588,0.565959,0.0041933525,0.0040502986,0.14991169,0.13548444,0.0003535889],"about_ca_topic_score_codex":0.007952716,"about_ca_topic_score_gemma":0.1821202,"teacher_disagreement_score":0.2643329,"about_ca_system_score_codex":0.0017903174,"about_ca_system_score_gemma":0.0072820084,"threshold_uncertainty_score":0.9986534},"labels":[],"label_agreement":null},{"id":"W4414076920","doi":"10.5430/ijhe.v14n5p1","title":"Towards an Inclusive Approach to Evaluation of Teaching","year":2025,"lang":"en","type":"article","venue":"International Journal of Higher Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Curriculum; Perception; Likert scale; Higher education; Course evaluation; Teaching method; Faculty development","score_opus":0.1747654185085843,"score_gpt":0.582711521443415,"score_spread":0.4079461029348307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414076920","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6089058,0.00021890065,0.011756452,0.0132222455,0.007929503,0.000259843,0.000005049389,0.000006076295,0.35769615],"genre_scores_gemma":[0.9877993,0.0000040379864,0.0081155235,0.0012422596,0.0004820098,0.000012551724,0.000010183507,0.0000039339125,0.0023302245],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99478364,0.00048010497,0.00091277534,0.00016431816,0.0035849707,0.00007418258],"domain_scores_gemma":[0.99164474,0.00015701282,0.00070332945,0.00022359917,0.0071979514,0.000073354044],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008895348,0.00007981705,0.00016846621,0.0010227636,0.0000617503,0.0001484287,0.0009297566,0.000043516586,0.0006781134],"category_scores_gemma":[0.001251869,0.000060826766,0.00008605829,0.00036487123,0.000022676897,0.0008167566,0.00008303968,0.00015086896,0.000017224114],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014731675,0.0014310385,0.013870795,0.0000054557063,0.00014006179,2.1127433e-7,0.004741334,0.013707894,0.0021758927,0.23523973,0.023773866,0.7047664],"study_design_scores_gemma":[0.0013359055,0.0002355254,0.5627608,0.00016227453,0.00013072081,0.000019247533,0.00505571,0.010500623,0.0024262501,0.30640128,0.11079418,0.00017748986],"about_ca_topic_score_codex":0.000039324354,"about_ca_topic_score_gemma":0.0000049928685,"teacher_disagreement_score":0.7045889,"about_ca_system_score_codex":0.00041751974,"about_ca_system_score_gemma":0.002382631,"threshold_uncertainty_score":0.74248666},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W4414416969","doi":"10.1016/j.clnesp.2025.07.1105","title":"Cooking together pilot study: Preliminary efficacy findings","year":2025,"lang":"en","type":"article","venue":"Clinical Nutrition ESPEN","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sheridan College; University of Waterloo","funders":"","keywords":"MEDLINE; Pilot trial; Clinical trial","score_opus":0.4001447365152482,"score_gpt":0.5876408913424614,"score_spread":0.18749615482721327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414416969","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9674575,0.00009006524,0.0012282756,0.0075368234,0.0011903056,0.0012094068,0.0000049401724,0.00008269623,0.021199988],"genre_scores_gemma":[0.9899208,0.000051548654,0.00046749116,0.0024983967,0.00021117879,0.000081087885,0.000008179772,0.000008627955,0.00675269],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9957954,0.00077265844,0.0014866457,0.0006157382,0.0011043921,0.00022513904],"domain_scores_gemma":[0.9934923,0.005115805,0.00020436173,0.0006709204,0.00040449173,0.0001120962],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008644891,0.00014420049,0.0004005434,0.0002853179,0.0002604539,0.00028894792,0.00074429077,0.00008172313,0.002886887],"category_scores_gemma":[0.0042048353,0.000113390124,0.00014937946,0.000877478,0.00012790498,0.0003379281,0.00022858368,0.0003315392,0.0011374959],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0035942146,0.025555106,0.49763748,0.000035729227,0.00015625419,0.00002406622,0.000750711,0.00011497884,0.00047064212,0.006361749,0.28267837,0.18262073],"study_design_scores_gemma":[0.008691368,0.006101693,0.7338863,0.00017791694,0.00006826062,0.0000019146194,0.001781741,0.0018598784,0.00026144087,0.019509964,0.22739254,0.00026699665],"about_ca_topic_score_codex":0.0000057351162,"about_ca_topic_score_gemma":0.000018670831,"teacher_disagreement_score":0.23624882,"about_ca_system_score_codex":0.00005012012,"about_ca_system_score_gemma":0.0001524446,"threshold_uncertainty_score":0.9996402},"labels":[],"label_agreement":null},{"id":"W4414585184","doi":"10.1101/2025.09.24.25336521","title":"Common Barriers to Implementation Across Contexts: Evidence to inform the selection of implementation strategies","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital","funders":"National Health and Medical Research Council; Medical Research Council","keywords":"Context (archaeology); Psychological intervention; Data collection; Sample (material); Likert scale; Selection (genetic algorithm); Intervention (counseling); Sample size determination","score_opus":0.22428346262457427,"score_gpt":0.5875247041065834,"score_spread":0.36324124148200915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414585184","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97708744,0.000050450217,0.010733307,0.00800779,0.0010271429,0.0020092602,0.00020693867,0.0000373051,0.00084034697],"genre_scores_gemma":[0.9967442,0.00003681829,0.00049635494,0.0017415523,0.00007166758,0.00045427695,0.00004195769,0.000007740494,0.00040541345],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9949704,0.00044161401,0.0015544331,0.00054004195,0.00215628,0.00033724244],"domain_scores_gemma":[0.99617904,0.00088451785,0.0007489841,0.0007695477,0.0012291252,0.00018878838],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00918281,0.00025116044,0.00040613362,0.00036106101,0.0004894211,0.0007164402,0.0012037992,0.000105821055,0.0029404883],"category_scores_gemma":[0.0009746509,0.00017411185,0.00014326983,0.0013585468,0.000058677993,0.0007109146,0.0007692828,0.00029719595,0.00009336592],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017796062,0.000021088554,0.6556146,0.000102248036,0.00011062852,3.6284925e-7,0.038627606,0.02387856,0.0015535111,0.003328501,0.012600346,0.26398456],"study_design_scores_gemma":[0.0005264485,0.00042556628,0.8251052,0.00026718588,0.00007230602,0.0000011568073,0.116388045,0.0022078063,0.018683262,0.0050134268,0.030920882,0.00038872962],"about_ca_topic_score_codex":0.0011560163,"about_ca_topic_score_gemma":0.021162365,"teacher_disagreement_score":0.26359582,"about_ca_system_score_codex":0.0002448721,"about_ca_system_score_gemma":0.001600603,"threshold_uncertainty_score":0.99797094},"labels":[],"label_agreement":null},{"id":"W4414820788","doi":"10.36368/jcsh.v2i1.1261","title":"Barriers and opportunities to disseminate and translate evidence from implementation research and quality improvement in the context of resource limited settings","year":2025,"lang":"en","type":"article","venue":"Journal of community systems for health /","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Dissemination; Context (archaeology); Best practice; Quality management; Quality (philosophy); Health care; Sierra leone; Implementation research; Health policy","score_opus":0.568816029526823,"score_gpt":0.6303024682658783,"score_spread":0.06148643873905535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414820788","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9510113,0.0025251997,0.0002927,0.045321397,0.00006126366,0.000705637,0.00005093481,0.0000015788956,0.000029983734],"genre_scores_gemma":[0.9969401,0.0011870078,0.00007161578,0.0017107411,0.000011591012,0.000021796113,0.0000026483208,0.0000024264561,0.000052084837],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99328727,0.0041254596,0.0014316969,0.00008569898,0.0009059816,0.00016389208],"domain_scores_gemma":[0.9888104,0.009485288,0.00061736954,0.00026809424,0.0006878909,0.00013095891],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.069067925,0.00006929141,0.00034404144,0.0003860878,0.00048761233,0.00018258565,0.00034771865,0.00003149298,0.0000043946548],"category_scores_gemma":[0.00107361,0.000044644334,0.000024879491,0.0002414984,0.00012127899,0.0002804137,0.000062397376,0.0003470457,5.91884e-8],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014274722,0.000096719894,0.11961658,0.0013729153,0.00007402373,8.0740045e-7,0.44533235,0.000024353554,0.0012457016,0.0031990053,0.012824798,0.41478527],"study_design_scores_gemma":[0.0011613485,0.0016088001,0.19428532,0.0011499772,0.000009755442,0.0000032257337,0.77967256,0.0005579906,0.00015149757,0.0019275643,0.019414773,0.000057183657],"about_ca_topic_score_codex":0.0035804552,"about_ca_topic_score_gemma":0.0024309931,"teacher_disagreement_score":0.41472808,"about_ca_system_score_codex":0.0000783043,"about_ca_system_score_gemma":0.0003669644,"threshold_uncertainty_score":0.95859045},"labels":[],"label_agreement":null},{"id":"W4414922933","doi":"10.1080/02722011.2025.2516357","title":"Is There a “Hollowing Consensus” in Ontario Education Governance? School Board Erosion and the Bill 98 Debate","year":2025,"lang":"en","type":"article","venue":"The American Review of Canadian Studies","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"Queen's University","keywords":"Erosion; Work (physics); Government (linguistics); Legislation","score_opus":0.11088717571278732,"score_gpt":0.4467273290918376,"score_spread":0.33584015337905027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414922933","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4832484,0.27180433,0.000001922125,0.22411002,0.0002662729,0.0008425272,0.0000074845243,0.00000428048,0.019714741],"genre_scores_gemma":[0.74933887,0.21178162,0.00011259726,0.034126867,0.000013310113,0.000080544654,4.8128777e-7,0.0000036908243,0.004542024],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99818003,0.00041901812,0.0005559215,0.00020487745,0.00047550164,0.00016462339],"domain_scores_gemma":[0.9978278,0.00089921517,0.00041461762,0.00047131086,0.00032264122,0.000064405074],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003620203,0.00011411431,0.00054239715,0.00018420827,0.00021517457,0.00004313756,0.0003563253,0.000010562852,0.00018079452],"category_scores_gemma":[0.0017129547,0.000047626145,0.00008689501,0.0014469267,0.0006032127,0.00006448139,0.00007702407,0.00014854608,0.0000267042],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006541187,0.000022439142,0.27692723,0.0002750042,0.00018312334,0.0000015720182,0.006179658,0.000008430748,0.000010876747,0.005293981,0.29823437,0.4127979],"study_design_scores_gemma":[0.00030666697,0.000026342534,0.6373858,0.002899582,0.00006782467,0.0000015324475,0.0068948483,0.00003434709,0.000007049059,0.005627231,0.3466626,0.00008619459],"about_ca_topic_score_codex":0.7548242,"about_ca_topic_score_gemma":0.95057255,"teacher_disagreement_score":0.4127117,"about_ca_system_score_codex":0.00029429566,"about_ca_system_score_gemma":0.002511403,"threshold_uncertainty_score":0.44551212},"labels":[],"label_agreement":null},{"id":"W4414976767","doi":"10.3917/rfap.187.0199","title":"L’utilisation paradoxale des rapports d’évaluation de politiques publiques : évidences empiriques dans le contexte canadien","year":2025,"lang":"fr","type":"article","venue":"Revue française d administration publique","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Work (physics); Politics","score_opus":0.10900300780034897,"score_gpt":0.42408535274064324,"score_spread":0.3150823449402943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414976767","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6420814,0.005671852,0.06339682,0.21915154,0.0022041786,0.0016517161,0.00017235838,0.00028800755,0.065382145],"genre_scores_gemma":[0.92439204,0.0015479719,0.004300139,0.0029405144,0.00046508983,0.00038325926,0.00028442615,0.000034918143,0.065651625],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99104935,0.0033460709,0.002242449,0.0011405041,0.0012418967,0.0009797403],"domain_scores_gemma":[0.9925196,0.00144401,0.0009527998,0.0009678388,0.0035386435,0.0005770932],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.015225036,0.00057041715,0.00072325143,0.0009884541,0.0013987338,0.0021684282,0.0009578564,0.0006583562,0.001710088],"category_scores_gemma":[0.006421891,0.00060363655,0.00034582484,0.0019321253,0.0011515395,0.0057455264,0.00011400546,0.0005642978,0.0000784715],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016564228,0.0005802369,0.13351345,0.00042839817,0.000132504,0.000047104928,0.022649167,0.00049577694,0.00047652086,0.67493665,0.02166437,0.14491017],"study_design_scores_gemma":[0.0010918761,0.0007795809,0.17040595,0.0013130566,0.00014983493,0.00016865907,0.014139404,0.02770371,0.012732824,0.22459593,0.5460076,0.0009115742],"about_ca_topic_score_codex":0.044700447,"about_ca_topic_score_gemma":0.18311027,"teacher_disagreement_score":0.5243432,"about_ca_system_score_codex":0.0010939004,"about_ca_system_score_gemma":0.0497345,"threshold_uncertainty_score":0.9999013},"labels":[],"label_agreement":null},{"id":"W4414980125","doi":"10.1016/j.plas.2025.100195","title":"Call for papers: Leading projects through time","year":2025,"lang":"en","type":"article","venue":"Project Leadership and Society","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"","score_opus":0.39595081764932105,"score_gpt":0.5026396017998451,"score_spread":0.10668878415052407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414980125","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12420653,0.0040175016,0.046215396,0.10765749,0.0024040474,0.009573029,0.00010020335,0.0007838876,0.7050419],"genre_scores_gemma":[0.8216138,0.00020344458,0.013384847,0.016624233,0.00024725506,0.0003434354,0.00002290924,0.000021644704,0.14753845],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980898,0.000116473726,0.000373101,0.0004794011,0.0005884267,0.0003528042],"domain_scores_gemma":[0.99833924,0.0010335508,0.00010891548,0.0002639341,0.0002194494,0.00003491421],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029410373,0.0001537936,0.00026501087,0.00007094631,0.000401676,0.00029451735,0.00027708418,0.00013353919,0.00010983303],"category_scores_gemma":[0.00060336775,0.000111223,0.00021590345,0.00063264475,0.00014670833,0.0004018191,0.000060476843,0.00015972526,0.000058450267],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012988056,0.00019899,0.013012301,0.0004904536,0.00026403286,8.062365e-7,0.1357732,0.00003934863,0.0033295716,0.020779116,0.71210814,0.113874145],"study_design_scores_gemma":[0.0029605462,0.00035235318,0.003930957,0.00020570394,0.00011530832,0.000003723225,0.14598875,0.03638213,0.0024459292,0.012296627,0.7946651,0.0006528502],"about_ca_topic_score_codex":0.000019106188,"about_ca_topic_score_gemma":0.000016307937,"teacher_disagreement_score":0.69740725,"about_ca_system_score_codex":0.00006409662,"about_ca_system_score_gemma":0.00044227552,"threshold_uncertainty_score":0.45355424},"labels":[],"label_agreement":null},{"id":"W4415006373","doi":"10.54656/jces.v18i1.628","title":"Case Study for a Research Capacity Building Initiative for Community-Based Organizations","year":2025,"lang":"en","type":"article","venue":"Journal of Community Engagement and Scholarship","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Community Based Research Centre","funders":"National Institute on Minority Health and Health Disparities","keywords":"Capacity building; Process (computing); Research center; Research program; Community engagement; Value (mathematics)","score_opus":0.827609940724928,"score_gpt":0.6170005795498112,"score_spread":0.21060936117511675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415006373","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.951179,0.000030194413,0.045331348,0.001870347,0.00018207035,0.00095359713,0.000020284553,0.000008360442,0.0004247793],"genre_scores_gemma":[0.9919961,0.0000052687215,0.006983116,0.00082869775,0.00003882407,0.000051162595,0.000005739205,0.000008194224,0.00008288692],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.98049486,0.017326336,0.0008871338,0.000085626576,0.0009886492,0.00021737497],"domain_scores_gemma":[0.96419156,0.028481774,0.00038637518,0.00056587986,0.006273722,0.0001007139],"candidate_categories":["metaresearch","sts","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14618164,0.000117840944,0.00031547158,0.0010273495,0.006390036,0.00070184463,0.0009348608,0.00006257489,0.000041668027],"category_scores_gemma":[0.028145121,0.00009252423,0.000090073976,0.0013863111,0.00012986983,0.0007512928,0.00027799956,0.0028246304,0.0000010604476],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015570468,0.011621427,0.61829895,0.0005689184,0.0010649496,0.00006422351,0.25171596,0.0030769936,0.0023656576,0.030276893,0.01831623,0.061072752],"study_design_scores_gemma":[0.012491348,0.0060176295,0.09979544,0.00030211432,0.00032423218,0.000101491205,0.6629729,0.0043023373,0.0023431007,0.18711898,0.0238495,0.0003808974],"about_ca_topic_score_codex":0.00006119277,"about_ca_topic_score_gemma":0.0005896565,"teacher_disagreement_score":0.51850355,"about_ca_system_score_codex":0.00014392596,"about_ca_system_score_gemma":0.00055233884,"threshold_uncertainty_score":0.9994759},"labels":[],"label_agreement":null},{"id":"W4415045219","doi":"10.1016/j.hrmr.2025.101117","title":"Delivering high-quality feedback is a choice: A self-regulatory framework for understanding feedback provision in organizations","year":2025,"lang":"en","type":"article","venue":"Human Resource Management Review","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Hierarchy; Order (exchange); Neglect; Work (physics); Variance (accounting); Through-the-lens metering; Performance management; Core (optical fiber)","score_opus":0.1845177416748472,"score_gpt":0.4936274746788597,"score_spread":0.3091097330040125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415045219","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13522452,0.03925618,0.6160687,0.037915852,0.0010452105,0.020720191,0.00004988232,0.0008632252,0.1488562],"genre_scores_gemma":[0.906569,0.012091081,0.03190613,0.028017605,0.00023723241,0.0009420065,0.00012776595,0.00010316828,0.020006012],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9958204,0.00037206398,0.0013973875,0.00076625246,0.0012779711,0.00036593323],"domain_scores_gemma":[0.99735075,0.0007338031,0.0004776943,0.0010845481,0.00027112907,0.00008207663],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0058600004,0.0002588919,0.000572326,0.00054864935,0.00055454514,0.00035269736,0.0008372442,0.00009575037,0.001705536],"category_scores_gemma":[0.00063966075,0.0002190221,0.000156088,0.0027709173,0.000052573538,0.00025782431,0.0004170856,0.00020563736,0.00015735059],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015793923,0.00023325026,0.013835221,0.005305989,0.00012947668,0.0000018320147,0.00083706365,0.0003587567,0.0000100676925,0.89783335,0.04258838,0.038850825],"study_design_scores_gemma":[0.0019203946,0.00008563319,0.1651466,0.012230409,0.00029797194,5.162857e-7,0.0027891395,0.0013641763,0.000020381623,0.15722549,0.6582944,0.0006249269],"about_ca_topic_score_codex":0.000025666377,"about_ca_topic_score_gemma":0.0000822793,"teacher_disagreement_score":0.7713445,"about_ca_system_score_codex":0.0005905364,"about_ca_system_score_gemma":0.00008050537,"threshold_uncertainty_score":0.999207},"labels":[],"label_agreement":null},{"id":"W4415053959","doi":"10.1101/2025.10.09.25337684","title":"‘On Your Mark’: Operationalizing a Readiness for Change Module in the SHIFT Intervention","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; Winnipeg Regional Health Authority; University of Manitoba; University of Toronto; York University","funders":"","keywords":"Operationalization; Intervention (counseling); Behaviour change; Quality (philosophy); Process (computing); Antecedent (behavioral psychology)","score_opus":0.42147406133526505,"score_gpt":0.5405403855333508,"score_spread":0.11906632419808577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415053959","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9234486,0.0002733287,0.035043098,0.025279364,0.0033214167,0.002973819,0.00018340259,0.000037759375,0.00943919],"genre_scores_gemma":[0.9927184,0.000024697541,0.00049989333,0.0017544447,0.00025606403,0.0018934223,0.00011737574,0.0000073223855,0.002728384],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9966884,0.0006497839,0.0007329364,0.00054550613,0.0012029582,0.00018037332],"domain_scores_gemma":[0.9974235,0.001261711,0.0002708284,0.00073155656,0.00028447344,0.000027920873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014030065,0.00018023264,0.0002771527,0.00045118266,0.00013868554,0.0004036803,0.0011104267,0.00013743543,0.00046922165],"category_scores_gemma":[0.0018047284,0.000111682384,0.00021059452,0.00042297822,0.000026195428,0.00020218873,0.00027845736,0.0003173667,0.00007592839],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000624663,0.0015223629,0.30196387,0.0008299347,0.00015066909,0.000013339984,0.032313496,0.01980674,0.000052341078,0.22015136,0.028816959,0.39375427],"study_design_scores_gemma":[0.0011171411,0.00013276894,0.5810509,0.0007934864,0.00003434533,0.0000011285518,0.0010952394,0.19867273,0.00012335622,0.18739577,0.029223455,0.00035972163],"about_ca_topic_score_codex":0.00007813066,"about_ca_topic_score_gemma":0.0005332165,"teacher_disagreement_score":0.39339456,"about_ca_system_score_codex":0.00008051141,"about_ca_system_score_gemma":0.00013476139,"threshold_uncertainty_score":0.5137648},"labels":[],"label_agreement":null},{"id":"W4415221463","doi":"10.1111/1468-5973.70083","title":"Early Warnings, No Actions: A Practice Perspective on Barriers to Anticipatory Action Approaches","year":2025,"lang":"en","type":"article","venue":"Journal of Contingencies and Crisis Management","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"International Development Research Centre; Government of the United Kingdom","keywords":"Credibility; Perspective (graphical); Action (physics); Agency (philosophy); Corporate governance; Resilience (materials science); Adaptation (eye); Psychological resilience","score_opus":0.22076292589969237,"score_gpt":0.4917897816651028,"score_spread":0.2710268557654104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415221463","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8044845,0.00051957305,0.009644448,0.04704821,0.0016396401,0.00048545343,0.0000017935783,0.000020605774,0.1361558],"genre_scores_gemma":[0.98971665,0.0003698182,0.002102218,0.0034534517,0.000100948535,0.000014263076,1.07275575e-7,0.0000049040264,0.004237617],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976316,0.00020499295,0.0006004053,0.00024297033,0.0011536017,0.00016639818],"domain_scores_gemma":[0.99757737,0.0003420235,0.0005779889,0.00021715036,0.0011350446,0.00015039893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046195863,0.000119561555,0.0002395513,0.00066147617,0.00033249822,0.00040975327,0.00026823502,0.00003624345,0.00018242998],"category_scores_gemma":[0.0025083113,0.00008707846,0.00010722469,0.00056280714,0.000031097625,0.0007153619,0.00009761428,0.00019612971,0.000045886016],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021543996,0.00066433806,0.020900825,0.00011790608,0.0019687663,0.000050510345,0.065153144,0.0031869467,0.00038391247,0.13113932,0.40206382,0.3722161],"study_design_scores_gemma":[0.0006292384,0.0005516873,0.066011146,0.00009753609,0.00022052653,0.0000050790577,0.38449216,0.0009621986,0.00015920901,0.0022208544,0.5445028,0.00014753593],"about_ca_topic_score_codex":0.000030122397,"about_ca_topic_score_gemma":0.000008584695,"teacher_disagreement_score":0.37206858,"about_ca_system_score_codex":0.00018340001,"about_ca_system_score_gemma":0.00011315571,"threshold_uncertainty_score":0.39512601},"labels":[],"label_agreement":null},{"id":"W4415240354","doi":"10.12927/hcpap.2025.27696","title":"How to Achieve Meaningful Change","year":2025,"lang":"en","type":"article","venue":"A Nudge Too Far? A Nudge at All? On Paying People to Be Healthy","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Public Health Ontario","funders":"","keywords":"Remuneration; Accountability; Payment; Health policy; Health care; Health management system; Public health","score_opus":0.3129481228548567,"score_gpt":0.4942154762005411,"score_spread":0.18126735334568445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415240354","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29996055,0.0001047406,0.002487448,0.6869879,0.0013796593,0.001445953,0.000053519278,0.00018268773,0.007397583],"genre_scores_gemma":[0.17373322,0.00008248996,0.0016513447,0.80576724,0.00006861576,0.00073458574,0.000032477637,0.00004483133,0.017885173],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9925959,0.0006426098,0.0012179234,0.0015606562,0.0026922657,0.0012906346],"domain_scores_gemma":[0.9945027,0.0017631482,0.00040043824,0.0016991964,0.0006665823,0.00096792117],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0057772193,0.000561811,0.00089809945,0.0011756865,0.00092317857,0.0007854977,0.0014698792,0.00023681748,0.0009417806],"category_scores_gemma":[0.0023118928,0.00045602486,0.00028055723,0.0034446185,0.000039608793,0.0006458008,0.00076855783,0.00047477707,0.0035243474],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00078743964,0.00021024646,0.0061210687,0.00002633499,0.000039506158,0.000008475108,0.012129585,0.000049572063,0.00029035774,0.0059084343,0.8993626,0.075066335],"study_design_scores_gemma":[0.0011921505,0.0015573497,0.03309814,0.0000024172384,0.000027625996,0.00000747921,0.0021458818,0.0024237419,0.00020486,0.0007544666,0.9580592,0.0005267172],"about_ca_topic_score_codex":0.0003549443,"about_ca_topic_score_gemma":0.0042150225,"teacher_disagreement_score":0.12622733,"about_ca_system_score_codex":0.0009925724,"about_ca_system_score_gemma":0.00065855205,"threshold_uncertainty_score":0.9999715},"labels":[],"label_agreement":null},{"id":"W4415288052","doi":"10.2196/86055","title":"Developing a shared understanding of humanism: Protocol for critical review, empirical exploration and modified e-Delphi study. (Preprint)","year":2025,"lang":"en","type":"article","venue":"JMIR Research Protocols","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Transparency (behavior); Experiential learning; Thematic analysis; Protocol (science); Humanism; Construct (python library); Compassion; Experiential knowledge; Conceptual framework","score_opus":0.9315585526728535,"score_gpt":0.7682788434844006,"score_spread":0.16327970918845292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415288052","genre_codex":"protocol","genre_gemma":"protocol","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"protocol","genre_consensus":"protocol","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000060866972,0.0000016932293,0.10814856,0.00747664,0.0000060092466,0.88163686,0.0000038096398,0.000026436805,0.002639158],"genre_scores_gemma":[0.0080948565,0.000001098132,0.0028165497,0.00021379451,0.000026347945,0.98845613,0.0000019374759,0.0000097889215,0.00037949093],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9939659,0.0013132443,0.0012099195,0.00065891567,0.0024695937,0.00038242605],"domain_scores_gemma":[0.99416214,0.0029583757,0.00017862931,0.0006390445,0.0019601223,0.00010170115],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020347087,0.00014544849,0.00040417098,0.00054431014,0.0005378719,0.00046602427,0.00063615025,0.00008200434,0.00036313027],"category_scores_gemma":[0.007918192,0.00010756056,0.000072440795,0.0012685204,0.00022312516,0.0007531201,0.0004781617,0.00030336692,0.000018653982],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004355747,0.0047226483,0.028154297,0.021847373,0.000119197866,0.0000106484895,0.016373457,0.000146671,0.0012223389,0.6859068,0.17251602,0.064624764],"study_design_scores_gemma":[0.008906011,0.0038335593,0.010119199,0.020900564,0.000008375028,0.0000020419811,0.015429375,0.018050442,0.0014623179,0.7777702,0.14306425,0.00045367365],"about_ca_topic_score_codex":0.000003053109,"about_ca_topic_score_gemma":0.000023858365,"teacher_disagreement_score":0.10681931,"about_ca_system_score_codex":0.00029056103,"about_ca_system_score_gemma":0.0010945861,"threshold_uncertainty_score":0.94793874},"labels":[],"label_agreement":null},{"id":"W4415333245","doi":"10.1080/09593985.2025.2571798","title":"A Foucauldian reading of the multiple mini-interview tool used in Canadian physiotherapy admissions","year":2025,"lang":"en","type":"article","venue":"Physiotherapy Theory and Practice","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Disadvantage; Reading (process); Categorization; Discipline; Underpinning; Neutrality; White paper; Power (physics); Psychological intervention","score_opus":0.10821843968155706,"score_gpt":0.5159527369201973,"score_spread":0.4077342972386402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415333245","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8855121,0.0023965412,0.00248584,0.06287469,0.0012725738,0.0017110968,0.00005361925,0.000038763774,0.04365476],"genre_scores_gemma":[0.9860607,0.0004548701,0.00035210486,0.00977332,0.000034949753,0.000031313994,0.0000013333369,0.000010236947,0.0032811726],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.995609,0.0028319482,0.0005050815,0.00032010084,0.00047741146,0.0002564962],"domain_scores_gemma":[0.9894834,0.009285368,0.00028341555,0.0006429298,0.00017881591,0.00012605403],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00954555,0.00014952666,0.00027869918,0.0002709314,0.0002693505,0.00012767914,0.00052087224,0.00006660351,0.0012088632],"category_scores_gemma":[0.0057631475,0.00009304685,0.00010700391,0.0010675873,0.00009187647,0.00062402274,0.00004655058,0.00018962506,0.000016086606],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024623366,0.00081853394,0.07685366,0.00013249546,0.0003018947,0.000005209756,0.023373865,0.0006141245,0.085975975,0.24199249,0.00693177,0.56053764],"study_design_scores_gemma":[0.002668534,0.00015623763,0.15833746,0.0005594973,0.00003840678,0.0000068343843,0.007954067,0.0045733475,0.0065784627,0.11946881,0.69928396,0.00037441571],"about_ca_topic_score_codex":0.011803498,"about_ca_topic_score_gemma":0.03885774,"teacher_disagreement_score":0.6923522,"about_ca_system_score_codex":0.000077572826,"about_ca_system_score_gemma":0.0009440797,"threshold_uncertainty_score":0.9997042},"labels":[],"label_agreement":null},{"id":"W4415525600","doi":"10.1177/27536386251390504","title":"Towards sociological praxis in paramedic education – A response to Hill and Campbell","year":2025,"lang":"en","type":"article","venue":"Paramedicine","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Northern Lakes College; University of the Fraser Valley","funders":"","keywords":"Praxis; Key (lock); Field (mathematics); Ethnography","score_opus":0.11412149236753337,"score_gpt":0.5455408662831231,"score_spread":0.43141937391558977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415525600","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8995619,0.00046335717,0.0017414829,0.08804174,0.0005137778,0.00043650853,0.0000020743962,0.00001902427,0.009220132],"genre_scores_gemma":[0.9830869,0.000073674666,0.0008864983,0.011777128,0.000067175955,0.0001039239,0.0000042888614,0.0000028118309,0.0039975857],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9974661,0.0006280273,0.0005696146,0.0003842913,0.0007507911,0.00020120223],"domain_scores_gemma":[0.9972778,0.0019607327,0.000090923386,0.00032956546,0.00018927279,0.00015168055],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010152999,0.00010845955,0.0002755286,0.0004901612,0.00006837722,0.000047088568,0.00024763765,0.000094608,0.0006162205],"category_scores_gemma":[0.012899241,0.00006973067,0.000026696067,0.000964868,0.00014072919,0.000094170406,0.000089844754,0.00019622562,0.00017889384],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009964886,0.00026578465,0.21546678,0.000015352896,0.000012048813,0.000008534859,0.005153544,0.0001264158,0.00081102515,0.0044087823,0.068432294,0.70430297],"study_design_scores_gemma":[0.0007831624,0.00029791726,0.82716495,0.00009210344,0.000008199188,0.0000051217485,0.0031602415,0.0032773993,0.00003728333,0.021033693,0.14404015,0.00009977526],"about_ca_topic_score_codex":0.00011861515,"about_ca_topic_score_gemma":0.00007765097,"teacher_disagreement_score":0.7042032,"about_ca_system_score_codex":0.00010809696,"about_ca_system_score_gemma":0.0008748642,"threshold_uncertainty_score":0.9954155},"labels":[],"label_agreement":null},{"id":"W4415587005","doi":"10.21083/crrf.v33i1.7901","title":"Steel River’s Integrated Consultation and Engagement Approach Complimented by the One-Team Approach and Collective Impact Model | Consultation Intégrée et Approche D’engagement de Steel River Complimenté Par le Modèle des Retombées Collectives et Par la Démarche D’équipe Unifiée","year":2025,"lang":"","type":"article","venue":"Proceedings of the Canadian Rural Revitalization Foundation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Congress of Aboriginal Peoples","funders":"","keywords":"Government (linguistics); Stakeholder engagement; Context (archaeology); Process (computing); Work (physics)","score_opus":0.10659865891893686,"score_gpt":0.3774140992930693,"score_spread":0.2708154403741324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415587005","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83543694,0.00084244495,0.10101089,0.005374858,0.00014770824,0.0097119715,0.00045931147,0.00007744943,0.046938457],"genre_scores_gemma":[0.9873172,0.0007832098,0.008089206,0.0007352849,0.000011200084,0.0004630923,0.0004863682,0.000036957474,0.0020774626],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.994223,0.0017680671,0.0013107469,0.0008539887,0.001282022,0.00056219375],"domain_scores_gemma":[0.99344856,0.0013210649,0.0013373491,0.0003039954,0.0032887468,0.00030027924],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.010119351,0.0005803786,0.00065884925,0.00074623595,0.0034637132,0.0017477501,0.00068618974,0.0002672289,0.000025338515],"category_scores_gemma":[0.0034462376,0.0004336695,0.00013765227,0.003110267,0.0020562804,0.0018712109,0.00030285883,0.0007330256,0.0000023624964],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018373652,0.0022101174,0.06118061,0.0021210366,0.0029234446,2.3024965e-7,0.3307432,0.08019848,0.029867632,0.4208632,0.047974426,0.020080227],"study_design_scores_gemma":[0.0035366644,0.00024387888,0.06856374,0.0005745555,0.00048358866,0.000008418998,0.050209697,0.84538054,0.0017490871,0.027180407,0.0015482156,0.0005212331],"about_ca_topic_score_codex":0.0062041916,"about_ca_topic_score_gemma":0.001776015,"teacher_disagreement_score":0.765182,"about_ca_system_score_codex":0.0025792604,"about_ca_system_score_gemma":0.0055739335,"threshold_uncertainty_score":0.99981153},"labels":[],"label_agreement":null},{"id":"W4415749087","doi":"10.1007/978-3-032-03833-3_1","title":"A New Blueprint for Brain Health: How Community-Led Evaluations Can Construct a Healthier Future","year":2025,"lang":"en","type":"book-chapter","venue":"Integrated science","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Health Canada; Ontario Brain Institute","funders":"","keywords":"Blueprint; Construct (python library); Thriving; General partnership; Psychological intervention; Health care; Mental health; Set (abstract data type); Indigenous","score_opus":0.21978310035108697,"score_gpt":0.5176816807826938,"score_spread":0.2978985804316069,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415749087","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00048604584,0.0009080592,0.08604315,0.54277253,0.008141774,0.005832011,0.0015124056,0.0002973982,0.35400665],"genre_scores_gemma":[0.015962884,0.0001703515,0.026813375,0.02025675,0.000457643,0.0001552988,0.0002652087,0.000043588192,0.9358749],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99233437,0.00062777475,0.001354063,0.00108265,0.003880349,0.0007208033],"domain_scores_gemma":[0.9891703,0.0029341173,0.0011688654,0.0019585309,0.004113779,0.0006544092],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02426398,0.00051997683,0.00090381806,0.0016779626,0.002466724,0.0012452926,0.00314828,0.00034148563,0.0022032305],"category_scores_gemma":[0.0057729017,0.00038623382,0.00029687228,0.0015752874,0.000994812,0.0004666023,0.00034923133,0.0017707163,0.00013432566],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035300494,0.000022987706,0.000035851714,0.000029834424,0.000027603557,6.681948e-7,0.003258232,0.00004293474,0.00006607436,0.27557144,0.237152,0.48375708],"study_design_scores_gemma":[0.0008265891,0.0003851597,0.00022844996,0.00044729546,0.000027034905,0.000014329073,0.003775595,0.01021199,0.000072906325,0.14808404,0.83549976,0.0004268151],"about_ca_topic_score_codex":0.0007461176,"about_ca_topic_score_gemma":0.010035331,"teacher_disagreement_score":0.5983478,"about_ca_system_score_codex":0.0012261645,"about_ca_system_score_gemma":0.039777577,"threshold_uncertainty_score":0.999859},"labels":[],"label_agreement":null},{"id":"W4415749092","doi":"10.1007/978-3-032-03833-3_4","title":"Elevating Community Care: Building Evaluation Capacity for Brain Health","year":2025,"lang":"en","type":"book-chapter","venue":"Integrated science","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Health Canada","funders":"","keywords":"Work (physics); Capacity building; Health care; Value (mathematics); Community organization; Community health","score_opus":0.4968666406506092,"score_gpt":0.5477491233362635,"score_spread":0.05088248268565426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415749092","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007919409,0.0006750659,0.1263942,0.008985085,0.0039556343,0.0044831093,0.00056398415,0.00021229075,0.84681123],"genre_scores_gemma":[0.5371182,0.0000727199,0.08721252,0.012533708,0.0003962079,0.000424067,0.00048010002,0.00008223656,0.36168024],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99171984,0.0006119709,0.0013691947,0.00087164773,0.0049049915,0.0005223506],"domain_scores_gemma":[0.98642874,0.0034005858,0.0011277316,0.0012825318,0.007562122,0.00019829578],"candidate_categories":["metaresearch","metaepi_narrow","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0552213,0.00036122472,0.0005836779,0.0011852515,0.0024553388,0.00079001655,0.0023254962,0.00021053907,0.00066024787],"category_scores_gemma":[0.016693715,0.00028034774,0.0001922421,0.0010837805,0.000705705,0.00067976274,0.00026431572,0.0011247998,0.00006713756],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001805439,0.00002123145,0.000058475172,0.000053123356,0.000015109948,1.4867052e-7,0.0032453942,0.000623907,0.000666956,0.16462441,0.020317959,0.81035525],"study_design_scores_gemma":[0.000920452,0.0005604278,0.00040329824,0.0012652993,0.00005143,0.0000049078,0.00496064,0.16117823,0.0012353671,0.22197084,0.60669535,0.00075372],"about_ca_topic_score_codex":0.0005083533,"about_ca_topic_score_gemma":0.0013971545,"teacher_disagreement_score":0.80960155,"about_ca_system_score_codex":0.002071634,"about_ca_system_score_gemma":0.010547895,"threshold_uncertainty_score":0.9999649},"labels":[],"label_agreement":null},{"id":"W4416003053","doi":"10.5465/amproc.2025.19428symposium","title":"New Pathways to Research in Social Evaluations – A Roadmap for Junior and Emerging Scholars","year":2025,"lang":"en","type":"article","venue":"Academy of Management Proceedings","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Field (mathematics); Work (physics); Context (archaeology); Government (linguistics); Agency (philosophy)","score_opus":0.39377440233772515,"score_gpt":0.5889397050959606,"score_spread":0.19516530275823546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416003053","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7421125,0.00016907882,0.00562175,0.1656661,0.0001730676,0.003597922,0.000008130365,0.000044321096,0.082607105],"genre_scores_gemma":[0.97691464,0.00007959262,0.011563778,0.0017844817,0.00008451364,0.00030624747,0.0000011788367,0.0000084664125,0.00925707],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9968726,0.000046103894,0.0006320051,0.0004674729,0.0016647949,0.00031699476],"domain_scores_gemma":[0.99899226,0.0002748624,0.00012781247,0.00006983771,0.0004570519,0.000078152785],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013565773,0.00010066214,0.00020147431,0.0017847519,0.00034763038,0.00023049692,0.00059924956,0.000081263905,0.00009730601],"category_scores_gemma":[0.0008177537,0.00009165462,0.000046372505,0.0025674447,0.000045588753,0.0006609449,0.00040583237,0.00023666224,0.0000250307],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060434868,0.00003142112,0.006183691,0.00008573495,0.000022017353,6.826397e-8,0.001916479,0.000023810922,0.0007013788,0.49616465,0.09678945,0.39802086],"study_design_scores_gemma":[0.0019642885,0.000106655236,0.29268017,0.0002340934,0.000038906703,2.1792766e-7,0.013104343,0.0045272307,0.0011761097,0.42975506,0.2562206,0.00019231715],"about_ca_topic_score_codex":0.000007976717,"about_ca_topic_score_gemma":0.000004885008,"teacher_disagreement_score":0.39782855,"about_ca_system_score_codex":0.000088557834,"about_ca_system_score_gemma":0.00009275535,"threshold_uncertainty_score":0.47016534},"labels":[],"label_agreement":null},{"id":"W4416438724","doi":"10.12927/cjnl.2025.27717","title":"Enhancing Evaluation Capacity to Advance Program Evaluation in Nursing Mentorship","year":2025,"lang":"en","type":"article","venue":"Nursing leadership","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Sunnybrook Health Science Centre; University of Waterloo","funders":"","keywords":"Mentorship; Intervention (counseling); Program evaluation; Capacity building; Bridge (graph theory); Nurse education; Nursing practice; Impact evaluation","score_opus":0.5966030751884697,"score_gpt":0.552900754571408,"score_spread":0.043702320617061696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416438724","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84399843,0.0007850152,0.025445353,0.036918405,0.0036906502,0.006116791,0.0000026153348,0.00018708118,0.08285567],"genre_scores_gemma":[0.99036556,0.000001555921,0.0072581507,0.0010005743,0.000108730725,0.0005967313,0.000012343296,0.000013542819,0.0006428183],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9914893,0.001709358,0.0010211477,0.00085430295,0.0042799218,0.00064599636],"domain_scores_gemma":[0.99700296,0.00071850244,0.0002478632,0.00067574455,0.0012126083,0.0001423227],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024645083,0.00023553503,0.00032568316,0.0011518332,0.00027111993,0.00038393732,0.0005045411,0.00015148972,0.0005228039],"category_scores_gemma":[0.005835617,0.00022346113,0.0000915727,0.0029999132,0.00013803062,0.00078473444,0.000016795579,0.0003335934,0.00021045124],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007843132,0.00034012328,0.0048106625,0.00001421436,0.0000057700754,2.1601318e-7,0.014623412,0.0069479705,0.0019427248,0.002561719,0.00092720625,0.96774757],"study_design_scores_gemma":[0.003384616,0.00042414299,0.34825906,0.00577895,0.00019035436,0.0000042795514,0.046787325,0.41257924,0.017431831,0.16025028,0.004133412,0.0007765003],"about_ca_topic_score_codex":0.000016360766,"about_ca_topic_score_gemma":0.00037428198,"teacher_disagreement_score":0.96697104,"about_ca_system_score_codex":0.0025034065,"about_ca_system_score_gemma":0.0007388877,"threshold_uncertainty_score":0.9112481},"labels":[],"label_agreement":null},{"id":"W4416643754","doi":"10.1108/979-8-88730-088-720251012","title":"Intellectual Courage","year":2022,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Reflection (computer programming); Courage; Practical wisdom; The Thing","score_opus":0.3523304675909333,"score_gpt":0.4881659621937948,"score_spread":0.13583549460286154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416643754","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000023013523,0.00010610316,0.00072551024,0.0012748777,0.00081263075,0.00015918241,0.00002270048,0.000046640074,0.99682933],"genre_scores_gemma":[0.002949127,0.00017546842,0.00016960606,0.0014759948,0.00013925755,0.000009168528,0.000032455624,0.000019293193,0.9950296],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956661,0.000045735305,0.0006138041,0.00042494357,0.0031142768,0.0001351707],"domain_scores_gemma":[0.9973323,0.0014733758,0.00023555571,0.0006440458,0.00023868654,0.000076073076],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0027374323,0.0001809541,0.00028855633,0.00036037283,0.00018555646,0.00015965053,0.00074381276,0.00010066442,0.8592399],"category_scores_gemma":[0.00050122483,0.00012684338,0.0001787708,0.000078824254,0.000058062436,0.00015309076,0.00031911235,0.00039983544,0.019290263],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008348371,0.000006204219,0.000008027173,9.439558e-7,0.000015109447,0.000004796727,0.0002867274,0.000044604618,0.0000011580751,0.46142983,0.47961453,0.058579717],"study_design_scores_gemma":[0.00008777358,0.000078324694,0.000012287454,0.0000035824196,0.000008383212,0.0000061960136,0.00015630257,0.00090949686,0.0000042720285,0.06115697,0.9374128,0.00016360155],"about_ca_topic_score_codex":0.0000049939626,"about_ca_topic_score_gemma":0.000038196606,"teacher_disagreement_score":0.8399496,"about_ca_system_score_codex":0.00010338345,"about_ca_system_score_gemma":0.00034656157,"threshold_uncertainty_score":0.9814733},"labels":[],"label_agreement":null},{"id":"W4416643759","doi":"10.1108/979-8-88730-088-7-20251017","title":"Conclusion","year":2022,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Reflection (computer programming); Natural (archaeology); Subjectivity; The Thing","score_opus":0.3321952993037506,"score_gpt":0.5115215601805031,"score_spread":0.17932626087675252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416643759","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000011968361,0.00010417388,0.00020252759,0.0019908517,0.0008338313,0.00015335403,0.000017420174,0.00003822921,0.99664766],"genre_scores_gemma":[0.0015981216,0.00012571742,0.00020717242,0.0020257926,0.00010977751,0.0000067120322,0.00003364769,0.000014232785,0.9958788],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99570954,0.00003628441,0.000531546,0.0003738206,0.0032481183,0.00010066441],"domain_scores_gemma":[0.99840826,0.00042806426,0.00027188144,0.0006079999,0.00021788348,0.00006588685],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0026563695,0.00014150303,0.0002398648,0.00024932594,0.00023472498,0.000101723665,0.0005913936,0.00009222138,0.7602126],"category_scores_gemma":[0.00011123633,0.000096581854,0.00014614448,0.000051203624,0.00003817374,0.00014818698,0.0005097243,0.0002574705,0.0101688085],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004430761,0.0000034619036,0.000021293561,7.049715e-7,0.0000059797935,0.0000031392847,0.00005613793,0.000027927239,0.000002671327,0.75758564,0.1723946,0.06989404],"study_design_scores_gemma":[0.00009398179,0.000047572925,0.000038637358,0.0000033806552,0.000005861813,0.000002939101,0.000037843347,0.00045125972,0.0000034034847,0.13199836,0.8671978,0.0001189337],"about_ca_topic_score_codex":0.000005887229,"about_ca_topic_score_gemma":0.000027829883,"teacher_disagreement_score":0.7500438,"about_ca_system_score_codex":0.00009368709,"about_ca_system_score_gemma":0.0002715489,"threshold_uncertainty_score":0.9906019},"labels":[],"label_agreement":null},{"id":"W4416643913","doi":"10.1108/979-8-88730-088-7-20251010","title":"Thinking Outside the Box","year":2022,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Reflection (computer programming); Natural (archaeology); Key (lock); The Thing","score_opus":0.2972251036252251,"score_gpt":0.47782895105251666,"score_spread":0.18060384742729158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416643913","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000004664121,0.00016933399,0.0006511961,0.011839412,0.0010295138,0.0002185769,0.000009996997,0.000045423134,0.9860319],"genre_scores_gemma":[0.0017348096,0.00011222283,0.0003856538,0.00755476,0.00019819122,0.000014970801,0.00001294512,0.00001782084,0.9899686],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99406916,0.000076829994,0.00060409924,0.00038601406,0.0047168504,0.00014706986],"domain_scores_gemma":[0.997346,0.0010873858,0.00035896167,0.00096543203,0.00019569205,0.000046567286],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.006982803,0.00017624524,0.00023638303,0.00017325378,0.0005647069,0.00041376497,0.0015796861,0.000084967774,0.35116154],"category_scores_gemma":[0.0001811909,0.00008742716,0.00020666934,0.00007277666,0.000065794025,0.00018616588,0.00054132985,0.00049261533,0.0052201],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027448593,0.0000025742336,0.000056632685,6.474234e-7,0.000014196091,0.0000022757977,0.00035526362,0.00009398316,4.4305946e-7,0.82927036,0.14048287,0.029718012],"study_design_scores_gemma":[0.00004861165,0.000019919782,0.000097339405,0.000004209668,0.000010037885,0.0000035247033,0.0002139198,0.0002686953,0.000001945667,0.29406223,0.7051737,0.000095890624],"about_ca_topic_score_codex":0.000016088701,"about_ca_topic_score_gemma":0.0001241712,"teacher_disagreement_score":0.56469077,"about_ca_system_score_codex":0.000080227226,"about_ca_system_score_gemma":0.00028993312,"threshold_uncertainty_score":0.99555445},"labels":[],"label_agreement":null},{"id":"W4416643928","doi":"10.1108/979-8-88730-088-7-20251009","title":"Mindfulness and Practical Wisdom For Evaluators","year":2022,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Practical wisdom; Mindfulness; Reflection (computer programming); Practical reason; Evaluation methods","score_opus":0.3508700649018345,"score_gpt":0.5387531955033553,"score_spread":0.18788313060152084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416643928","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017483557,0.00008768883,0.0070853606,0.0063704117,0.00090067746,0.00082569214,0.000070842776,0.000028551976,0.98445594],"genre_scores_gemma":[0.0039891624,0.00000825025,0.0027389715,0.0013108207,0.00018335892,0.00018329508,0.000041140553,0.000029979374,0.99151504],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957119,0.00007666858,0.0006737528,0.00062411395,0.0027340343,0.00017947984],"domain_scores_gemma":[0.9956268,0.0029015723,0.00037344324,0.00051855325,0.0004479762,0.00013165383],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0065690493,0.00022155621,0.00038944164,0.00027759673,0.00028643044,0.00021850425,0.00024209461,0.00016033613,0.1386845],"category_scores_gemma":[0.0010672575,0.00015821545,0.0001512939,0.000058155347,0.00011644128,0.0003235863,0.0002354373,0.00027557102,0.00042012948],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055095774,0.000013723671,0.000016681599,0.0000069987204,0.000030009773,0.0000030437689,0.00007279002,0.00000937561,3.4905906e-7,0.7381867,0.11088427,0.15072097],"study_design_scores_gemma":[0.00032827837,0.00014816324,0.00001822465,0.0000057346847,0.00004771986,0.000017682869,0.00016470911,0.0024342996,0.000038130824,0.22840136,0.7682137,0.00018202544],"about_ca_topic_score_codex":0.0000033540562,"about_ca_topic_score_gemma":0.000030726605,"teacher_disagreement_score":0.6573294,"about_ca_system_score_codex":0.00007813456,"about_ca_system_score_gemma":0.000648465,"threshold_uncertainty_score":0.86210287},"labels":[],"label_agreement":null},{"id":"W4416644031","doi":"10.1108/979-8-88730-088-720251008","title":"Practical Wisdom in Action","year":2022,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Practical wisdom; Action (physics); Reflection (computer programming); Practical reason","score_opus":0.6119425549653196,"score_gpt":0.6006222281890242,"score_spread":0.011320326776295353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416644031","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007470934,0.000014076841,0.00055335154,0.0062406035,0.0007253576,0.000184611,0.0000051763973,0.000023014569,0.9921791],"genre_scores_gemma":[0.0045061684,0.00014004718,0.00091706234,0.0009133689,0.000104191444,0.000016795046,0.000019608668,0.000012876738,0.9933699],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99621814,0.00008342548,0.0006096125,0.00039969216,0.00256704,0.00012206471],"domain_scores_gemma":[0.9982408,0.00085379137,0.0002739064,0.00044434663,0.00013076879,0.00005635531],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0035916723,0.00013479462,0.00023954714,0.00043512243,0.000081172075,0.000108477936,0.0002530353,0.00012973923,0.38102043],"category_scores_gemma":[0.00038601801,0.00010109479,0.00009460899,0.00010013645,0.000038531296,0.00043057397,0.00014899249,0.00053528295,0.0043282905],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027499447,0.000023514931,0.00019001684,0.0000017628786,0.000007319842,0.000013710594,0.000074462994,0.000073203395,0.000003070451,0.8614924,0.091002084,0.047090944],"study_design_scores_gemma":[0.00015927757,0.000054370306,0.00044351086,0.0000048763545,0.0000055598134,0.00000956989,0.0001621091,0.0013413264,0.0000037123382,0.064564615,0.93312883,0.00012223673],"about_ca_topic_score_codex":0.000021099395,"about_ca_topic_score_gemma":0.0004423632,"teacher_disagreement_score":0.8421267,"about_ca_system_score_codex":0.0001993466,"about_ca_system_score_gemma":0.00046472254,"threshold_uncertainty_score":0.99644697},"labels":[],"label_agreement":null},{"id":"W4416644039","doi":"10.1108/979-8-88730-088-7-20251006","title":"Competencies, Practical Wisdom, and the Professionalization of Ethical Practice","year":2022,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Reflection (computer programming); Professionalization; Ethical issues; Practical reason; Practical wisdom","score_opus":0.28082258181436776,"score_gpt":0.538725533613994,"score_spread":0.25790295179962625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416644039","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000013833121,0.00020915187,0.0015562573,0.1077093,0.00037793576,0.00049812905,0.000011649664,0.000014021378,0.8896097],"genre_scores_gemma":[0.010042753,0.00097528676,0.007747838,0.016886234,0.00014528855,0.00005211517,0.000056250323,0.000026964668,0.9640673],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9933672,0.00085151126,0.00094948296,0.00037066502,0.0043532206,0.00010792528],"domain_scores_gemma":[0.9823326,0.015037644,0.0010208986,0.0005108046,0.0010370471,0.00006103863],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01579916,0.00015933505,0.00039640834,0.0001376848,0.0003073808,0.000095339834,0.00034352805,0.00027774,0.040872015],"category_scores_gemma":[0.008485447,0.00008041806,0.00010028834,0.000112460184,0.00065492507,0.00034929079,0.00043936138,0.0012061922,0.0001190351],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021320426,0.00001933171,0.000017864853,0.000007696053,0.000028587032,0.0000018585657,0.0005456609,0.000016465421,0.0000018123628,0.97560334,0.021444935,0.0020992393],"study_design_scores_gemma":[0.0006229667,0.00007226894,0.000058942525,0.000019756066,0.000065759996,0.00003894782,0.000992067,0.0028885556,0.000002313339,0.107731834,0.8874068,0.00009975285],"about_ca_topic_score_codex":0.000023586192,"about_ca_topic_score_gemma":0.000031535,"teacher_disagreement_score":0.8678715,"about_ca_system_score_codex":0.000044196855,"about_ca_system_score_gemma":0.0010006363,"threshold_uncertainty_score":0.9998665},"labels":[],"label_agreement":null},{"id":"W4416644074","doi":"10.1108/979-8-88730-088-7-20251004","title":"Practical Wisdom Forevaluators","year":2022,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Evaluation Society","funders":"","keywords":"Practical wisdom; Reflection (computer programming); Practical reason; The Thing","score_opus":0.4776094358206994,"score_gpt":0.5661818427882132,"score_spread":0.08857240696751373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416644074","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000014844534,0.000055809196,0.0012834686,0.007318171,0.0010596432,0.00034432637,0.000024159881,0.000056497847,0.9898431],"genre_scores_gemma":[0.0012891676,0.000112682785,0.0030242098,0.0021018975,0.00020955391,0.000029028652,0.000039757106,0.000032369837,0.9931613],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99205333,0.00012418552,0.0009456742,0.0006554725,0.0060056346,0.00021567542],"domain_scores_gemma":[0.99636894,0.0015348815,0.0005228635,0.0009888875,0.0004270633,0.00015735097],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.007130741,0.00026094783,0.00042497367,0.0003811942,0.0002534374,0.00021237294,0.00061843963,0.00017604919,0.683305],"category_scores_gemma":[0.0009385601,0.0001824096,0.00028432172,0.000106181964,0.000106212545,0.0004162994,0.00039932705,0.0005941106,0.012480266],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010865524,0.000010395197,0.00004715815,0.0000014138446,0.000019445493,0.0000074284208,0.000040737414,0.0000160731,3.5846506e-7,0.67920125,0.30207524,0.018569665],"study_design_scores_gemma":[0.00016490006,0.00010654456,0.00005195937,0.0000047511708,0.00003224073,0.000017004688,0.00010325509,0.0013156482,0.0000024017077,0.17596944,0.82202756,0.00020431087],"about_ca_topic_score_codex":0.0000057536745,"about_ca_topic_score_gemma":0.000040097428,"teacher_disagreement_score":0.67082477,"about_ca_system_score_codex":0.00017737427,"about_ca_system_score_gemma":0.0010409007,"threshold_uncertainty_score":0.98828864},"labels":[],"label_agreement":null},{"id":"W4416997770","doi":"10.1108/978-1-64802-604-120251008","title":"Methods and Biases in Measuring Change with Self-Reports","year":2021,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Measure (data warehouse); Noise (video); Set (abstract data type); Identification (biology); Work (physics)","score_opus":0.5942247094761783,"score_gpt":0.5405715551568674,"score_spread":0.05365315431931095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416997770","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027446612,0.0016531928,0.0007553987,0.00063338404,0.00030292454,0.00040290962,0.0000024914357,0.000051120882,0.9934539],"genre_scores_gemma":[0.020085344,0.001180656,0.09356044,0.0013772441,0.00025145686,0.0000805893,0.00001887619,0.000052149295,0.8833932],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969395,0.0001248293,0.0006412928,0.00061357813,0.0015086995,0.00017212298],"domain_scores_gemma":[0.9978429,0.0008418409,0.00033037804,0.0005252715,0.00035734367,0.00010224296],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006566002,0.00021720005,0.00045058786,0.00043966642,0.00006127305,0.00021490689,0.00013630961,0.00013684515,0.0063806847],"category_scores_gemma":[0.0003488621,0.00013722472,0.000055427,0.00013582027,0.000040375882,0.00029287432,0.00013791023,0.00020589879,0.000036597125],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035579927,0.00008452967,0.02994371,0.000070197275,0.00018406866,0.0008153838,0.0027430318,0.00008730932,0.000045761568,0.038581256,0.0018736598,0.9255355],"study_design_scores_gemma":[0.00070057146,0.00022800759,0.022139302,0.00092787016,0.00011548811,0.00046067097,0.00082993857,0.0035592576,0.0005188589,0.021375818,0.94811445,0.0010297861],"about_ca_topic_score_codex":0.00004257199,"about_ca_topic_score_gemma":0.001267053,"teacher_disagreement_score":0.9462408,"about_ca_system_score_codex":0.000060696475,"about_ca_system_score_gemma":0.00028070025,"threshold_uncertainty_score":0.99452764},"labels":[],"label_agreement":null},{"id":"W4417184697","doi":"10.1111/capa.70043","title":"Escaping the Tunnel: How Formative Evaluation Complements Performance Audit to Improve Decision Navigation","year":2025,"lang":"en","type":"article","venue":"Canadian Public Administration","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Formative assessment; Audit; Performance audit; Evaluation methods; Reliability (semiconductor)","score_opus":0.1439210505811699,"score_gpt":0.4574227160440045,"score_spread":0.31350166546283453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417184697","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7846454,0.00003836612,0.049238257,0.14785023,0.002078749,0.0022939474,0.00008404378,0.00004575333,0.013725288],"genre_scores_gemma":[0.99474806,0.0000047095664,0.0006399104,0.00267127,0.00012210288,0.000309251,0.00023048697,0.0000085722095,0.0012656277],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.995833,0.00035303543,0.0007467805,0.00049564755,0.0021171016,0.0004544615],"domain_scores_gemma":[0.99607617,0.0005150246,0.00033843244,0.0007359841,0.0019712134,0.00036317267],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008643717,0.00019769213,0.00019148855,0.00074564427,0.0011992672,0.001609866,0.0007954799,0.00009938499,0.0009146927],"category_scores_gemma":[0.0025862593,0.00014537307,0.00007344354,0.0018746256,0.00006733002,0.0019401101,0.0000716949,0.00019840943,0.00032561301],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003687746,0.00003099678,0.0074664718,0.000011456732,0.000030435896,6.9869867e-7,0.0008574316,0.00027616438,0.00017126602,0.023956433,0.049989734,0.917172],"study_design_scores_gemma":[0.0011269912,0.00037876057,0.141793,0.000115574236,0.000045297114,0.000006554229,0.005562194,0.3546844,0.0010420467,0.010598909,0.48426124,0.00038502214],"about_ca_topic_score_codex":0.00019775829,"about_ca_topic_score_gemma":0.0746985,"teacher_disagreement_score":0.916787,"about_ca_system_score_codex":0.0010615103,"about_ca_system_score_gemma":0.0054781428,"threshold_uncertainty_score":0.9999986},"labels":[],"label_agreement":null},{"id":"W4417434618","doi":"10.1177/13563890251395056","title":"Unraveling the complexities of learning in community development evaluation","year":2025,"lang":"en","type":"article","venue":"Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; University of Victoria","funders":"","keywords":"Neoliberalism (international relations); Community development; Focus (optics); Learning community; Key (lock)","score_opus":0.42157615803294757,"score_gpt":0.5579690605544919,"score_spread":0.13639290252154435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417434618","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95451057,0.00019094293,0.005377234,0.0015573854,0.00029190467,0.0007068303,5.7461085e-7,0.000013354647,0.03735122],"genre_scores_gemma":[0.9985002,0.000004754017,0.00061782345,0.00015479901,0.000016140611,0.000111831985,0.000030444955,0.00000300246,0.000560992],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9904492,0.0048194914,0.0009976852,0.0001783032,0.003415149,0.0001401655],"domain_scores_gemma":[0.9955357,0.0019774619,0.0003388283,0.00039182996,0.0017412308,0.000014971858],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.07685577,0.00008753845,0.00017055348,0.0004170769,0.0004758031,0.00009192168,0.0004231305,0.00004472172,0.0012217795],"category_scores_gemma":[0.006692639,0.000059756727,0.00003903186,0.0010754216,0.00007520949,0.00023545219,0.0001068656,0.00029811624,0.00005459689],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000318763,0.000097460674,0.075849764,0.000014891731,0.000020006373,2.6345841e-8,0.01805038,0.19258171,0.0005148027,0.006109304,0.00045888353,0.7062709],"study_design_scores_gemma":[0.0005510733,0.000020486954,0.47523436,0.000055435175,0.000017694823,1.3705703e-7,0.012632826,0.47916502,0.0010437927,0.029435996,0.0017940751,0.00004908723],"about_ca_topic_score_codex":0.00010298693,"about_ca_topic_score_gemma":0.001097403,"teacher_disagreement_score":0.7062218,"about_ca_system_score_codex":0.00029723707,"about_ca_system_score_gemma":0.0013660745,"threshold_uncertainty_score":0.99969125},"labels":[],"label_agreement":null},{"id":"W4502007","doi":"","title":"Alcoholism, Native and non-Native treatment technologies and the discourse of difference.","year":2002,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Linguistics; Political science; Communication; Psychology; Sociology; Philosophy","score_opus":0.20294567075729558,"score_gpt":0.4705454207811644,"score_spread":0.2675997500238688,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4502007","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95945925,0.00050465326,0.00065696647,0.010779316,0.000049390088,0.00033571658,0.000008995848,0.000022073991,0.028183615],"genre_scores_gemma":[0.9916756,0.0009290551,0.0003125553,0.000075749726,0.000006572062,0.000037022135,3.7622672e-7,0.0000020337936,0.006961021],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9988273,0.000085829095,0.0002574143,0.00020452302,0.0005281823,0.000096758646],"domain_scores_gemma":[0.9983971,0.0010617322,0.00014245746,0.00023900894,0.00013738348,0.000022293083],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007161305,0.00009739459,0.00022105509,0.00011739172,0.00012159394,0.000075077885,0.00018136261,0.000034850298,0.0004465591],"category_scores_gemma":[0.0003199103,0.00003808669,0.000033150158,0.00024527675,0.000805595,0.0001529895,0.00009495388,0.000050602644,0.000012794579],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057243436,0.00016824514,0.037165307,0.0000029471557,0.00007461127,9.635637e-7,0.021858618,0.000018495028,0.00012561248,0.057744768,0.0011999337,0.8815833],"study_design_scores_gemma":[0.010373592,0.0013137372,0.38991493,0.000048029364,0.00011062333,0.000012931603,0.2275522,0.20494457,0.0142519185,0.14747967,0.003542429,0.00045536377],"about_ca_topic_score_codex":0.000041775966,"about_ca_topic_score_gemma":0.00009822876,"teacher_disagreement_score":0.8811279,"about_ca_system_score_codex":0.000016663249,"about_ca_system_score_gemma":0.000016577069,"threshold_uncertainty_score":0.4889509},"labels":[],"label_agreement":null},{"id":"W53722850","doi":"","title":"Issues in evaluating the community benefits of social interventions","year":2014,"lang":"en","type":"article","venue":"USC Research Bank (University of the Sunshine Coast)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Audit; Public relations; Value (mathematics); Business; Psychological intervention; Duty; Perspective (graphical); Political science; Accounting; Computer science; Psychology","score_opus":0.5949273046907162,"score_gpt":0.5776323626205211,"score_spread":0.017294942070195107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W53722850","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98361284,0.000079588426,0.000298929,0.011843301,0.000057366145,0.00024821237,0.000020653737,0.0000052662053,0.0038338387],"genre_scores_gemma":[0.99503237,0.00001772261,0.00020002207,0.000021338708,0.00002261212,0.0000010138755,0.0000035426115,0.0000034231573,0.004697932],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98954314,0.0073075234,0.00034637973,0.00015083184,0.0024376218,0.00021448669],"domain_scores_gemma":[0.9940183,0.0036410557,0.00030096606,0.00077828014,0.001223479,0.000037887225],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.04238587,0.000074225216,0.00029048105,0.00030920227,0.0011572014,0.000052872692,0.0023940173,0.000050139795,0.002683593],"category_scores_gemma":[0.0043724976,0.000044144832,0.000386608,0.0014337833,0.0005648409,0.00028477408,0.0013624871,0.0006671408,0.00003557258],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008568135,0.0015600014,0.2691485,0.00033251735,0.0007151628,0.0000010377775,0.14782408,0.050705392,0.002345731,0.080925025,0.07964609,0.36593965],"study_design_scores_gemma":[0.00064578035,0.00035425168,0.93188095,0.00007529192,0.00004345516,4.6339613e-7,0.021498917,0.02451321,0.000089390065,0.019056607,0.001776687,0.00006502505],"about_ca_topic_score_codex":0.007440652,"about_ca_topic_score_gemma":0.036272418,"teacher_disagreement_score":0.6627324,"about_ca_system_score_codex":0.00007231442,"about_ca_system_score_gemma":0.00016258511,"threshold_uncertainty_score":0.9991689},"labels":[],"label_agreement":null},{"id":"W56576167","doi":"10.3138/cjpe.017.003","title":"Evaluation and Municipal Urban Planning: Practice and Prospects","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Government (linguistics); Urban planning; Local government; Scale (ratio); Environmental planning; Evaluation methods; Comprehensive planning; Public administration; Process management; Management science; Business; Environmental resource management; Political science; Geography; Engineering; Economics; Civil engineering","score_opus":0.4565580453517729,"score_gpt":0.5429851099364679,"score_spread":0.08642706458469496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W56576167","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95949346,0.013549857,0.0001663078,0.0069856863,0.0007053656,0.0020354562,0.0000036610213,0.000012100489,0.01704811],"genre_scores_gemma":[0.99652284,0.00005484248,0.0027629249,0.00026002334,0.00018140346,0.00005704878,0.0000033977994,0.000008620876,0.00014886764],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99441063,0.0010439958,0.00072903815,0.00023795824,0.0033353372,0.00024304788],"domain_scores_gemma":[0.99364436,0.00044657133,0.00073610846,0.00022902609,0.0044462495,0.00049768965],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.030606369,0.00012313134,0.00019981015,0.0005718962,0.0002937187,0.0006621281,0.00020980531,0.00008070521,0.0015034799],"category_scores_gemma":[0.013263645,0.00009852379,0.000042449217,0.00052864425,0.00012347968,0.0013532476,0.000015403974,0.00022532212,0.00002842157],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001473712,0.000048612215,0.03453352,0.0000039248,0.000041045223,0.000008731161,0.009659731,0.0009590867,0.000016304624,0.00044429774,0.005266649,0.94900334],"study_design_scores_gemma":[0.0021628817,0.0010761272,0.10549274,0.00007714018,0.00044734712,0.00032571136,0.005060625,0.7262611,0.000022390066,0.007008261,0.15184978,0.000215947],"about_ca_topic_score_codex":0.00017477515,"about_ca_topic_score_gemma":0.0019102982,"teacher_disagreement_score":0.9487874,"about_ca_system_score_codex":0.00028837036,"about_ca_system_score_gemma":0.0012476535,"threshold_uncertainty_score":0.99940926},"labels":[],"label_agreement":null},{"id":"W567485519","doi":"10.26190/unsworks/1146","title":"Indigenous Resiliency Project Participatory Action Research Component: A report on the Research Training and Development Workshop, Townsville, February 2008","year":2008,"lang":"en","type":"article","venue":"The Sydney eScholarship Repository (The University of Sydney)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"University of New South Wales","keywords":"Participatory action research; Training (meteorology); Indigenous; Component (thermodynamics); Action research; Citizen journalism; Participatory development; Action (physics); Political science; Sociology; Geography; Pedagogy; Anthropology","score_opus":0.605556168354662,"score_gpt":0.4775737241269402,"score_spread":0.12798244422772176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W567485519","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98374754,0.00030048893,0.000057984245,0.0029511715,0.00028609353,0.0011327795,0.0000020598839,0.000038815095,0.011483063],"genre_scores_gemma":[0.99135303,0.00021048923,0.0001779538,0.0001233218,0.00010536675,0.000015464928,0.000004040758,0.00001614379,0.007994214],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.98641664,0.0062591056,0.0007424947,0.00072784413,0.005144756,0.00070916],"domain_scores_gemma":[0.99111265,0.0052456735,0.00045404048,0.0016064555,0.001375302,0.00020589087],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.041128635,0.00021691619,0.0003291001,0.0006286182,0.009279341,0.00022613394,0.0018939816,0.00017615074,0.0001627987],"category_scores_gemma":[0.0029016784,0.00012368518,0.00011763822,0.0017667364,0.0020759082,0.0005933841,0.0005666681,0.0019478825,0.00015444748],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026510737,0.0016874119,0.147481,0.00011277157,0.0006107068,0.0017683904,0.7074914,0.0011091441,0.0119235115,0.0037415654,0.066018485,0.055404525],"study_design_scores_gemma":[0.00093022326,0.00047398152,0.67834795,0.00031639816,0.000043525946,0.000769822,0.179855,0.0005621123,0.0052931397,0.0012578444,0.13172178,0.00042824243],"about_ca_topic_score_codex":0.000609287,"about_ca_topic_score_gemma":0.0002281337,"teacher_disagreement_score":0.5308669,"about_ca_system_score_codex":0.00041702038,"about_ca_system_score_gemma":0.0026355437,"threshold_uncertainty_score":0.9920104},"labels":[],"label_agreement":null},{"id":"W578061300","doi":"10.71781/6140","title":"Expérimentation d'un modèle d'évaluation permettant de juger du développement d'une compétence d'investigation scientifique en laboratoire","year":2008,"lang":"fr","type":"dissertation","venue":"Open MIND","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Philosophy; Humanities","score_opus":0.1784869827260185,"score_gpt":0.4448372580652635,"score_spread":0.26635027533924494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W578061300","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96547145,0.0003410296,0.012380194,0.008064824,0.0024114298,0.0029409446,0.00012256968,0.000009658211,0.00825789],"genre_scores_gemma":[0.76966745,0.0015887351,0.20270357,0.00073662575,0.00035741914,0.00062602473,0.0044920873,0.00008097224,0.019747099],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9888905,0.0023232172,0.0022206558,0.0017583609,0.0040704175,0.00073683076],"domain_scores_gemma":[0.9935349,0.000750511,0.00175629,0.00092886953,0.0025974626,0.00043194805],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.013014526,0.0007041943,0.0007752215,0.0006705094,0.0018698426,0.0020439378,0.0019590496,0.0005140311,0.014740425],"category_scores_gemma":[0.001155714,0.0006801758,0.00020226186,0.0027662043,0.00034252217,0.0027114109,0.0002980084,0.00052373076,0.0036882618],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026772427,0.00068834354,0.030522168,0.00007290429,0.00015939535,0.000041412855,0.17762408,0.019414319,0.13137561,0.0015346162,0.0031114211,0.63518804],"study_design_scores_gemma":[0.0029133724,0.0003514282,0.21224459,0.0009820104,0.00026308146,0.00005877444,0.038558763,0.28745306,0.42509237,0.0038648637,0.026758429,0.0014592457],"about_ca_topic_score_codex":0.000774082,"about_ca_topic_score_gemma":0.0013917446,"teacher_disagreement_score":0.63372874,"about_ca_system_score_codex":0.0011779662,"about_ca_system_score_gemma":0.0062958323,"threshold_uncertainty_score":0.99956495},"labels":[],"label_agreement":null},{"id":"W581397735","doi":"","title":"U.S., CANADA AGREE TO PARTNER ON STUDY","year":2003,"lang":"en","type":"article","venue":"Great Lakes Seaway Log","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Subtitle; Geography; Political science; Oceanography; Geology; Computer science","score_opus":0.20057989266996934,"score_gpt":0.4448254922174971,"score_spread":0.24424559954752778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W581397735","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7234037,0.000015033895,0.00011645363,0.002261015,0.00065713073,0.0005259809,0.000015893176,0.000025098067,0.27297968],"genre_scores_gemma":[0.96255744,0.0000013954188,0.00010044558,0.0037640668,0.000057476303,0.00004165416,0.0000025269328,0.000008602786,0.033466388],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99628955,0.00031487294,0.00041476972,0.00046759107,0.0021917871,0.0003214338],"domain_scores_gemma":[0.99823844,0.00040020252,0.00008142017,0.0007704936,0.0002675485,0.00024188765],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002169119,0.00016037382,0.00023415672,0.00014630408,0.00021289788,0.00014884346,0.00042663192,0.000034786797,0.0046952153],"category_scores_gemma":[0.0008356959,0.000106562315,0.00004714494,0.00065747875,0.0000214412,0.00012227046,0.00004022434,0.00011235864,0.0014713996],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006356199,0.00033605506,0.58928263,0.0000025001477,0.000043708347,0.0000657211,0.00094378716,0.0049853586,0.000050414765,0.012469889,0.35494974,0.036806628],"study_design_scores_gemma":[0.00061799947,0.0004876455,0.20330815,0.0000061120163,0.00001143411,0.0000042264337,0.0019619954,0.00022708857,0.00036187825,0.0007406286,0.79204845,0.00022436213],"about_ca_topic_score_codex":0.032035515,"about_ca_topic_score_gemma":0.7905251,"teacher_disagreement_score":0.75848955,"about_ca_system_score_codex":0.00016301962,"about_ca_system_score_gemma":0.0009417992,"threshold_uncertainty_score":0.9993061},"labels":[],"label_agreement":null},{"id":"W587230877","doi":"","title":"Process evaluation of two remedial programs for alcohol-impaired drivers","year":2013,"lang":"en","type":"article","venue":"International Conference on Alcohol, Drugs and Traffic Safety (T2013), 20th, 2013, Brisbane, Queensland, Australia","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Remedial education; Process (computing); Delphi method; Data collection; Population; Program evaluation; Best practice; Conviction; Computer science; Process management; Engineering; Psychology; Medicine; Political science; Environmental health","score_opus":0.2778358304943045,"score_gpt":0.4823371950430692,"score_spread":0.20450136454876472,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W587230877","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97631115,0.00003320098,0.00048806999,0.011805035,0.0018269706,0.002801027,0.0001804428,0.000080473714,0.0064736297],"genre_scores_gemma":[0.9917106,0.00012222346,0.0008176521,0.00019228413,0.0003174385,0.0004585857,0.00045718148,0.000032151605,0.0058918875],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99193084,0.000409218,0.0016381907,0.0010559942,0.0043635317,0.0006022463],"domain_scores_gemma":[0.9926059,0.00053069857,0.0010550799,0.0005880134,0.0048662852,0.00035400668],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0053214883,0.0005070985,0.00068561843,0.0005183784,0.00028970407,0.00051216787,0.000977466,0.00024951404,0.008323178],"category_scores_gemma":[0.0005394704,0.00040050142,0.00028679072,0.0004877639,0.00037765512,0.0011317161,0.00007945091,0.00034165586,0.00069172186],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015741576,0.0018231088,0.11808705,0.00013434267,0.0011001303,0.000007403637,0.007517602,0.028479319,0.0011797295,0.037841666,0.0985145,0.703741],"study_design_scores_gemma":[0.021688573,0.0013391601,0.25100106,0.00043251034,0.00046034966,0.00004652392,0.00659708,0.6607035,0.0007588004,0.03284996,0.022414545,0.0017079449],"about_ca_topic_score_codex":0.0008577157,"about_ca_topic_score_gemma":0.0015337466,"teacher_disagreement_score":0.70203304,"about_ca_system_score_codex":0.00017578721,"about_ca_system_score_gemma":0.00062049157,"threshold_uncertainty_score":0.9998447},"labels":[],"label_agreement":null},{"id":"W59313340","doi":"10.21225/d5ms3r","title":"Looking Forward by Looking Back: Determining the Value of External Program Reviews","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of University Continuing Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Value (mathematics); Unit (ring theory); Subject (documents); Sociology; Management; Public relations; Computer science; Psychology; Mathematics education; Library science; Political science; Economics","score_opus":0.038595136186109255,"score_gpt":0.37067106145530143,"score_spread":0.33207592526919216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W59313340","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9928292,0.0002227484,0.0013409583,0.0007855963,0.0013659383,0.00020539059,0.000003199132,0.0000022308363,0.0032447227],"genre_scores_gemma":[0.99411756,0.000030903004,0.0037732746,0.00014049467,0.0001513598,3.0698533e-7,0.0000016006346,0.0000044315666,0.0017800649],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985617,0.00023741582,0.00048156624,0.000115459356,0.00044048345,0.0001633822],"domain_scores_gemma":[0.99736834,0.00027330656,0.0009910167,0.0002293362,0.0008959239,0.00024206768],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043193907,0.0000793996,0.00020317135,0.0003448193,0.00018950018,0.00017066376,0.00068939704,0.00005041297,0.00042793277],"category_scores_gemma":[0.0012134489,0.00005925056,0.00012459052,0.00034964478,0.000100698424,0.00056776253,0.000017809167,0.0002916054,0.000016012718],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008142408,0.00002896701,0.1492209,0.0000065537456,0.000006981691,0.0000012688027,0.0040369495,0.000019091676,0.0010911389,0.0005591703,0.0115768965,0.83344394],"study_design_scores_gemma":[0.0005056052,0.00013598801,0.12304208,0.00042946445,0.00007292588,0.000035399775,0.008934822,0.000839193,0.0006563012,0.000508219,0.8646735,0.00016652963],"about_ca_topic_score_codex":0.00053969724,"about_ca_topic_score_gemma":0.00478122,"teacher_disagreement_score":0.8530966,"about_ca_system_score_codex":0.00011381532,"about_ca_system_score_gemma":0.0015748261,"threshold_uncertainty_score":0.46855637},"labels":[],"label_agreement":null},{"id":"W59738575","doi":"10.1596/11062","title":"The Canadian Monitoring and Evaluation System","year":2011,"lang":"en","type":"book","venue":"World Bank, Washington, DC eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Transparency (behavior); Accountability; Government (linguistics); Politics; Public administration; Public sector; Monitoring and evaluation; Political science; Biology and political orientation; Public relations; Business","score_opus":0.16788815080340883,"score_gpt":0.4016711389104887,"score_spread":0.2337829881070799,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W59738575","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021894586,0.0010684332,0.000008291635,0.00037438315,0.0036462175,0.0010864281,0.000020227011,0.00007759399,0.991529],"genre_scores_gemma":[0.2506297,0.000022567941,0.00012093052,0.00008903771,0.0008150239,0.00012848871,0.000016035343,0.000048917573,0.7481293],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99271613,0.00058343995,0.0012270584,0.0008349288,0.004019524,0.00061893574],"domain_scores_gemma":[0.99489933,0.0011737477,0.0008352869,0.0013452171,0.0013181432,0.0004282988],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.017332252,0.0004559485,0.0005086795,0.0009158149,0.0021405178,0.0017991144,0.001322802,0.00029855437,0.0004380676],"category_scores_gemma":[0.00042838816,0.00030489702,0.00016879634,0.00019132742,0.00025070683,0.00025442452,0.00019673424,0.0007903092,0.00067598536],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048795016,0.000011254526,0.00443124,0.00010159637,0.00021721196,0.000018901837,0.005483028,0.00006726931,0.00001947223,0.1707456,0.12350315,0.6953525],"study_design_scores_gemma":[0.00034459966,0.000033083154,0.005526686,0.00044460926,0.0001432829,0.000011341805,0.0005264147,0.0015523123,0.00009913253,0.020613778,0.97024536,0.0004594004],"about_ca_topic_score_codex":0.009647109,"about_ca_topic_score_gemma":0.49415192,"teacher_disagreement_score":0.8467422,"about_ca_system_score_codex":0.0019430715,"about_ca_system_score_gemma":0.0054413374,"threshold_uncertainty_score":0.99994034},"labels":[],"label_agreement":null},{"id":"W60770971","doi":"","title":"Les Preoccupations Ethiques D'enseignants Du Reseau Collegial Francophone Au Quebec","year":2009,"lang":"fr","type":"article","venue":"Canadian Journal of Education / Revue canadienne de l éducation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Focus group; French; Sociology; Humanities; Pedagogy; Political science; Library science; Psychology; Art; Anthropology","score_opus":0.20256929696402975,"score_gpt":0.4346695623345884,"score_spread":0.23210026537055867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W60770971","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.839665,0.0031751,0.0011896028,0.11514767,0.02710948,0.0004551043,0.00009083745,0.000009080903,0.013158128],"genre_scores_gemma":[0.94533145,0.00028271557,0.0017136375,0.0020542862,0.0043528024,0.00002341743,0.00006190851,0.000027195863,0.046152584],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99537516,0.0009545245,0.0016695645,0.00043652861,0.00050603965,0.0010581851],"domain_scores_gemma":[0.9893404,0.0005887089,0.0014214424,0.0006601041,0.0051668407,0.0028224646],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0065833605,0.00032766658,0.00050164474,0.0018765935,0.0010640325,0.000581262,0.0009215171,0.00040426356,0.0046928655],"category_scores_gemma":[0.0075184824,0.00035538065,0.00024109993,0.002086346,0.00028850662,0.001499793,0.000010383758,0.0007298937,0.00017578944],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00005564683,0.00035667565,0.027367733,0.00007589384,0.00006322984,0.00003723609,0.20865908,0.001169379,0.00015801188,0.024942968,0.31279802,0.4243161],"study_design_scores_gemma":[0.00046016226,0.00040691346,0.395612,0.0007558973,0.00008824715,0.00050314056,0.07578234,0.0008794105,0.00010978515,0.00928339,0.5157303,0.00038839332],"about_ca_topic_score_codex":0.5726433,"about_ca_topic_score_gemma":0.9837007,"teacher_disagreement_score":0.4239277,"about_ca_system_score_codex":0.020249238,"about_ca_system_score_gemma":0.17125657,"threshold_uncertainty_score":0.9998898},"labels":[],"label_agreement":null},{"id":"W607935940","doi":"10.4135/9781452226606","title":"The SAGE International Handbook of Educational Evaluation","year":2009,"lang":"en","type":"book","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":85,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"SAGE; Library science; Computer science; Physics","score_opus":0.21475580779562672,"score_gpt":0.543232841427736,"score_spread":0.3284770336321092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W607935940","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00001797467,0.0013628553,0.0006596689,0.008638293,0.0011935382,0.0004052056,0.000014437371,0.0000064348824,0.9877016],"genre_scores_gemma":[0.0010879777,0.00046347873,0.0005140004,0.00049798295,0.0004963367,0.000033209704,0.0001470873,0.000007675144,0.99675226],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9926509,0.00019503632,0.0010108707,0.00032519147,0.005692712,0.00012525567],"domain_scores_gemma":[0.9938693,0.0026698026,0.0008070961,0.00061843905,0.0019841336,0.000051212788],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008255592,0.00015474555,0.00021469584,0.0002556118,0.00018686306,0.00024565592,0.0011301563,0.00012764636,0.049919277],"category_scores_gemma":[0.0018228344,0.00008728382,0.0001748091,0.00013248541,0.00012280347,0.00022762505,0.00007917855,0.00017861079,0.0012152303],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001121746,0.000025144487,0.000122874,0.0000010378825,0.000028457878,3.7279108e-8,0.00007855583,0.00012875718,0.0000059459567,0.04419667,0.5682376,0.3871637],"study_design_scores_gemma":[0.00021395035,0.000034163135,0.0023963985,0.000057120258,0.00002345257,0.0000014837666,0.000041211308,0.0061190813,0.000032818753,0.30209023,0.6888984,0.00009168573],"about_ca_topic_score_codex":0.0000032033051,"about_ca_topic_score_gemma":0.0001072415,"teacher_disagreement_score":0.387072,"about_ca_system_score_codex":0.00030125986,"about_ca_system_score_gemma":0.0037953244,"threshold_uncertainty_score":0.99956244},"labels":[],"label_agreement":null},{"id":"W616581969","doi":"10.11575/prism/10194","title":"Making Collaboration Work: A Case Study of Two Canadian National Parks","year":2008,"lang":"en","type":"article","venue":"Open MIND","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Work (physics); Geography; Environmental resource management; Political science; Engineering; Environmental science","score_opus":0.5354925262363226,"score_gpt":0.5833124188932027,"score_spread":0.047819892656880136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W616581969","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9476478,0.0000061344545,0.000033458473,0.00030923705,0.00012264373,0.00044420877,0.000013271235,3.9157095e-7,0.051422827],"genre_scores_gemma":[0.9959852,5.325289e-7,0.0019358621,0.00009404561,0.000029344475,0.000018655574,0.000004475584,0.0000027853932,0.0019290716],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99800026,0.00016677461,0.00041363112,0.00021596786,0.0010918459,0.00011151715],"domain_scores_gemma":[0.998512,0.00018997578,0.00018515746,0.00021019593,0.0008234584,0.00007917913],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0027674004,0.00005889994,0.00012510383,0.00022969919,0.00030517596,0.00021650255,0.0003511309,0.000023780904,0.008011751],"category_scores_gemma":[0.0003140239,0.00004799916,0.000015349524,0.0010366676,0.000027409573,0.0004881447,0.000064410815,0.000053901033,0.00030483448],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009650411,0.00062061683,0.6494428,9.279254e-7,0.00005348344,0.0010680805,0.071689956,0.015114692,0.00003336551,0.0001937618,0.016889883,0.24479596],"study_design_scores_gemma":[0.010897039,0.0012530093,0.32265538,0.00008090694,0.000074853175,0.0020249065,0.31799003,0.056830015,0.0006836532,0.0013790494,0.28507346,0.0010576809],"about_ca_topic_score_codex":0.013107123,"about_ca_topic_score_gemma":0.5568521,"teacher_disagreement_score":0.543745,"about_ca_system_score_codex":0.00010433361,"about_ca_system_score_gemma":0.0018161056,"threshold_uncertainty_score":0.9934647},"labels":[],"label_agreement":null},{"id":"W631960472","doi":"","title":"Aboriginal Public Servants: Leadership in the British Columbia Public Service","year":2014,"lang":"en","type":"dissertation","venue":"Library and Archives Canada (Government of Canada)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Public service; Public administration; Political science; Geography; Management","score_opus":0.06589868156811936,"score_gpt":0.2796605144948504,"score_spread":0.21376183292673107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W631960472","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47762173,0.00039454346,0.000011242826,0.03957432,0.0009550738,0.00044813682,0.00022910931,0.000010830781,0.480755],"genre_scores_gemma":[0.9187337,0.00019952063,0.000106883286,0.012582343,0.000100884055,0.000037780428,0.00017025975,0.000021670452,0.06804695],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99030405,0.0004715502,0.0007856726,0.0004777103,0.007479509,0.0004814797],"domain_scores_gemma":[0.9975694,0.001154593,0.0005477909,0.00047584658,0.000009452867,0.00024295041],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00033037906,0.00021133116,0.00041716662,0.000054878416,0.00055139663,0.0019098265,0.0013225281,0.00007961796,0.00080980436],"category_scores_gemma":[0.00004557154,0.00021511933,0.000046463858,0.0005764916,0.00005258022,0.0010918179,0.000041591964,0.00039937333,5.1904735e-8],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034321565,0.00022025291,0.6378602,0.0011149397,0.00016334835,0.0001619203,0.0019712842,0.000057748315,0.00034148907,0.04451845,0.12214267,0.1911045],"study_design_scores_gemma":[0.00041158102,0.00004768948,0.5473149,0.00022410679,0.000014941663,0.000008749686,0.03822643,0.0018293366,0.00009147973,0.002781039,0.40873528,0.00031448927],"about_ca_topic_score_codex":0.07987811,"about_ca_topic_score_gemma":0.9927096,"teacher_disagreement_score":0.9128314,"about_ca_system_score_codex":0.000015160206,"about_ca_system_score_gemma":0.0074660084,"threshold_uncertainty_score":0.9991263},"labels":[],"label_agreement":null},{"id":"W632514109","doi":"10.9707/1944-5660.1247","title":"Network Evaluation in Practice: Approaches and Applications","year":2015,"lang":"en","type":"article","venue":"The Foundation Review","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact","funders":"","keywords":"Mechanism (biology); Knowledge management; Computer science; Data science; Management science; Engineering; Epistemology","score_opus":0.6045855432101019,"score_gpt":0.5680346387676503,"score_spread":0.03655090444245168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W632514109","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033413845,0.27362236,0.05758004,0.25074363,0.00086064736,0.013622013,0.0000032156213,0.00009794482,0.40012875],"genre_scores_gemma":[0.86661315,0.07225309,0.010646572,0.039282084,0.0013664623,0.0062996754,0.00023476542,0.00003867159,0.0032655061],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9966429,0.0011372634,0.00053359894,0.00021514857,0.0013685783,0.000102543396],"domain_scores_gemma":[0.9978431,0.00076443324,0.0003234767,0.00044231044,0.00057545915,0.000051239767],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03420313,0.00007006434,0.00015181793,0.000050309907,0.00012211328,0.00016098042,0.00024403461,0.000022186598,0.00038614956],"category_scores_gemma":[0.0029961322,0.000040732302,0.00002097052,0.00094288524,0.000053103595,0.0005895734,0.000055446868,0.00009294105,0.0007835948],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006282285,0.000029670222,0.001589715,0.000025541634,0.0000050382746,4.5966356e-8,0.00026142556,0.0020491781,2.449117e-7,0.03096732,0.008916279,0.9561493],"study_design_scores_gemma":[0.0002581744,0.000020219693,0.0050866175,0.000114361224,0.000062996514,0.000006938739,0.0005709871,0.02216042,3.313646e-7,0.05358176,0.91806513,0.000072086434],"about_ca_topic_score_codex":0.000009037808,"about_ca_topic_score_gemma":0.000040537914,"teacher_disagreement_score":0.95607716,"about_ca_system_score_codex":0.00007297,"about_ca_system_score_gemma":0.0002921124,"threshold_uncertainty_score":0.9999944},"labels":[],"label_agreement":null},{"id":"W63457028","doi":"10.55016/ojs/ajer.v52i1.55109","title":"Setting Cut-Scores for Complex Performance Assessments: A Critical Examination of the Analytic Judgment Method","year":2006,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Evaluation methods; Applied psychology; Statistics; Social psychology; Mathematics education; Mathematics; Reliability engineering; Engineering","score_opus":0.43426259510920384,"score_gpt":0.6329415287968805,"score_spread":0.19867893368767664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W63457028","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91407824,0.00011877621,0.0049212156,0.041796178,0.0006453939,0.0005120147,0.000013322139,5.4848306e-7,0.037914317],"genre_scores_gemma":[0.978582,0.00001136498,0.010656178,0.00013108623,0.00033841992,0.000030237306,0.000007970259,0.000007938954,0.010234777],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9937112,0.0010245191,0.0011939913,0.00021358488,0.0035606017,0.00029613252],"domain_scores_gemma":[0.93839556,0.056062713,0.00055140693,0.00031880272,0.004586258,0.0000852685],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017037563,0.00009782846,0.00024115738,0.0005349007,0.00042107012,0.00017873218,0.00088998064,0.000046870722,0.0051707136],"category_scores_gemma":[0.023923228,0.000060002712,0.00017283836,0.0010023932,0.0002077231,0.0005761043,0.00010242865,0.00028439736,0.000036193567],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048014868,0.0025096468,0.5383035,0.0002672179,0.00020435643,2.8947736e-7,0.0018886864,0.014561439,0.009808253,0.21953969,0.14407903,0.06835776],"study_design_scores_gemma":[0.0005157322,0.0003542245,0.8788296,0.000114750794,0.00003730941,0.000024421079,0.0009158705,0.09362834,0.0017244646,0.012792557,0.010972159,0.00009059073],"about_ca_topic_score_codex":0.00011597481,"about_ca_topic_score_gemma":0.0002696537,"teacher_disagreement_score":0.3405261,"about_ca_system_score_codex":0.00024026116,"about_ca_system_score_gemma":0.0016806574,"threshold_uncertainty_score":0.9957387},"labels":[],"label_agreement":null},{"id":"W641559493","doi":"","title":"Capturing 'what works' in complex process evaluation research: the use of calendar instruments","year":2011,"lang":"en","type":"article","venue":"University of Huddersfield Repository (University of Huddersfield)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Timeline; Recall; Population; Public health; Population health; Consistency (knowledge bases); Computer science; Process (computing); Fidelity; Data science; Psychology; Medicine; Geography; Artificial intelligence; Cognitive psychology; Environmental health","score_opus":0.6765651216540648,"score_gpt":0.43652542976479247,"score_spread":0.24003969188927232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W641559493","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8910934,0.00027154482,0.0012296928,0.0012962921,0.00039596483,0.0008393709,0.000011098265,0.000021571743,0.104841106],"genre_scores_gemma":[0.9979774,0.00026382148,0.0010998616,0.000029329021,0.000012499573,1.5336624e-7,0.0000037922982,0.0000051592574,0.00060798036],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9959037,0.0008689668,0.00042290014,0.0004174402,0.0021078433,0.00027919177],"domain_scores_gemma":[0.9965017,0.0007127221,0.000591365,0.000728092,0.0013722047,0.000093939896],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0028652307,0.00014299808,0.00036865476,0.000596424,0.0004826447,0.00004567215,0.0012202559,0.00020589093,0.027160943],"category_scores_gemma":[0.00024969145,0.00013922033,0.00018499649,0.0008975438,0.00082268077,0.0024008718,0.00029452093,0.00042273008,0.0000107105425],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0029259264,0.00167309,0.13896525,0.00030598763,0.0005577507,0.00015748084,0.36137825,0.00739733,0.0035451392,0.0015250216,0.34058517,0.14098361],"study_design_scores_gemma":[0.001160068,0.00018861816,0.006473211,0.00025378968,0.00006536629,0.0000047256785,0.9804778,0.008684837,0.0013805123,0.0009099739,0.00025733176,0.00014373875],"about_ca_topic_score_codex":0.0038563777,"about_ca_topic_score_gemma":0.002437523,"teacher_disagreement_score":0.61909956,"about_ca_system_score_codex":0.000005396333,"about_ca_system_score_gemma":0.00042602044,"threshold_uncertainty_score":0.97372836},"labels":[],"label_agreement":null},{"id":"W643949957","doi":"","title":"Crossing the bridge: self-evaluations and the Pacific Bridge program","year":2011,"lang":"en","type":"article","venue":"Ritsumeikan Academic Repository (R-Cube) (Ritsumeikan University)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Bridge (graph theory); Engineering; Forensic engineering","score_opus":0.14676556402759666,"score_gpt":0.39736018844963444,"score_spread":0.2505946244220378,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W643949957","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8096933,0.001952023,0.0030540726,0.0052791787,0.0018836727,0.0036872567,0.000043158358,0.0008658347,0.17354152],"genre_scores_gemma":[0.9750667,0.00059879606,0.0010227566,0.00038172255,0.000314804,0.00003383125,0.000010913393,0.000039229857,0.022531236],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99195176,0.0024646192,0.0012104119,0.0011417187,0.0024552038,0.00077627075],"domain_scores_gemma":[0.9943863,0.0019496051,0.00089980767,0.0015567761,0.00083833013,0.00036915945],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.008977738,0.0005006836,0.0006021538,0.00060164335,0.0042282594,0.0010450125,0.002504852,0.0004072702,0.00021801091],"category_scores_gemma":[0.00076070265,0.000316244,0.0003708018,0.0022708522,0.0023740798,0.001630802,0.00066238054,0.0015101944,0.00023094793],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002134826,0.0010997837,0.3137407,0.00011916709,0.0011959694,0.00023807674,0.10185191,0.00023027464,0.0009207263,0.2600018,0.03647839,0.28198835],"study_design_scores_gemma":[0.0052108387,0.0002628404,0.5518756,0.00012908637,0.0007679077,0.00042836368,0.009182664,0.017150104,0.00073168747,0.010890738,0.40235102,0.0010191314],"about_ca_topic_score_codex":0.00020299881,"about_ca_topic_score_gemma":0.00005420603,"teacher_disagreement_score":0.36587265,"about_ca_system_score_codex":0.00028044902,"about_ca_system_score_gemma":0.0008459649,"threshold_uncertainty_score":0.999992},"labels":[],"label_agreement":null},{"id":"W6893283241","doi":"10.5281/zenodo.14772813","title":"Précis des meilleures pratiques pour l'évaluation à distance","year":2021,"lang":"fr","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Context (archaeology); Work (physics); Subject (documents); Term (time)","score_opus":0.20104670471638336,"score_gpt":0.41574869616728694,"score_spread":0.21470199145090357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6893283241","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07960097,0.011859354,0.14342453,0.041031778,0.0018430953,0.001267612,0.0008030282,0.0009768569,0.7191928],"genre_scores_gemma":[0.8097102,0.005216684,0.012103592,0.0013643532,0.0008473598,3.3260338e-7,0.0024418312,0.001723901,0.16659173],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99316347,0.0026802525,0.0007885321,0.0008210143,0.0019754265,0.0005712976],"domain_scores_gemma":[0.9935309,0.0002609947,0.0003305823,0.0008063612,0.0047697434,0.00030141504],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0055669406,0.00025287073,0.00029027788,0.00027902817,0.0037952238,0.0033447635,0.0012369972,0.00014481893,0.16941296],"category_scores_gemma":[0.0070676208,0.00025558984,0.00013319153,0.0017178453,0.0004932352,0.001334254,0.0010929513,0.00039911867,0.026980527],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004767683,0.00033474,0.000049924245,0.00009089541,0.00005460627,0.000024430026,0.0059697004,0.0006130823,0.0026744858,0.034146946,0.31527525,0.6407183],"study_design_scores_gemma":[0.00065154524,0.0002180325,0.0033168849,0.00014744613,0.000037461014,0.00016138612,0.003972044,0.011081303,0.0030258012,0.011338896,0.9657616,0.00028760737],"about_ca_topic_score_codex":0.000027840004,"about_ca_topic_score_gemma":0.0000167704,"teacher_disagreement_score":0.7301092,"about_ca_system_score_codex":0.00043964654,"about_ca_system_score_gemma":0.00013525388,"threshold_uncertainty_score":0.9999896},"labels":[],"label_agreement":null},{"id":"W6901890659","doi":"10.6084/m9.figshare.20438457","title":"Additional file 5 of Selecting implementation models, theories, and frameworks in which to integrate intersectional approaches","year":2022,"lang":"en","type":"article","venue":"Figshare","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Université Laval; University of Calgary; University of Ottawa; McGill University; University of Waterloo; University of British Columbia; Public Health Ontario; York University; McMaster University; University of Manitoba; Ottawa Hospital","funders":"","keywords":"Selection (genetic algorithm); Domain (mathematical analysis); Key (lock); Set (abstract data type); Focus (optics); Black box","score_opus":0.2642392038506342,"score_gpt":0.43271699290784366,"score_spread":0.16847778905720945,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6901890659","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010263516,0.000006807304,0.00007585967,0.00020857948,0.000028363711,0.00016464968,0.99453545,0.000008921192,0.003944993],"genre_scores_gemma":[0.39041874,1.3550385e-7,0.0014551545,0.00024447194,0.000033568653,0.001667007,0.60592204,0.000005243348,0.00025364684],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984724,0.00014863428,0.00031366863,0.00022822677,0.0007303506,0.00010674726],"domain_scores_gemma":[0.9973994,0.0020720777,0.00015319033,0.000104804705,0.00023406443,0.000036474354],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00047196198,0.000065786524,0.00009901897,0.00023486608,0.0001478176,0.00006547883,0.000181533,0.000034035278,0.9942122],"category_scores_gemma":[0.0028276148,0.000058343172,0.00002324108,0.0009520774,0.0000040309405,0.0002757967,0.00020280397,0.00028186582,0.000106967345],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013191961,0.000017385255,0.000047728656,0.0000034786924,0.0000036331417,1.6890465e-7,0.0017945789,0.01259867,9.898497e-7,0.00036895977,0.9711974,0.013953812],"study_design_scores_gemma":[0.0002618362,0.00019496815,0.009388477,0.00026771895,0.0000019372887,0.000010203055,0.04036194,0.34099647,0.000027094658,0.025085147,0.5832084,0.00019583869],"about_ca_topic_score_codex":0.000011870555,"about_ca_topic_score_gemma":0.00040747752,"teacher_disagreement_score":0.9941053,"about_ca_system_score_codex":0.00008217548,"about_ca_system_score_gemma":0.00024509625,"threshold_uncertainty_score":0.33851233},"labels":[],"label_agreement":null},{"id":"W6912846365","doi":"10.5281/zenodo.820609","title":"Evaluation Framework For Cic'S Settlement Programs","year":2004,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Settlement (finance); Service provider; Logic model; Service (business); Process (computing); Stakeholder; Negotiation; Service delivery framework","score_opus":0.2897132460148641,"score_gpt":0.45864748009886297,"score_spread":0.16893423408399888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6912846365","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.060855698,0.0003136122,0.76820034,0.01767563,0.0011112496,0.0063619404,0.0004740674,0.0012798302,0.14372762],"genre_scores_gemma":[0.98110586,0.000042880292,0.014682895,0.00060288527,0.00034468123,0.0000015380523,0.0019283737,0.00067267293,0.0006182002],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99519366,0.00050867733,0.00052763766,0.00054943195,0.0028429742,0.00037760314],"domain_scores_gemma":[0.9954503,0.00011541348,0.00024166353,0.0006714893,0.00334572,0.00017539482],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.011926362,0.00014107795,0.00016015812,0.00028642724,0.0021155684,0.0016885968,0.001207076,0.00007838667,0.020005792],"category_scores_gemma":[0.0053287926,0.00012280306,0.00009379802,0.00093973964,0.00010832202,0.0004709017,0.00046189368,0.00019040053,0.009120032],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005350195,0.00024293666,0.000016165195,0.000011390512,0.00003677284,7.987434e-7,0.0018582839,0.0019103247,0.0003305438,0.06362906,0.04436295,0.88754725],"study_design_scores_gemma":[0.0011230576,0.00047612193,0.0008086908,0.000027671853,0.000028884939,0.000012634973,0.0010914997,0.0039925375,0.00039919,0.094034985,0.8978397,0.00016499778],"about_ca_topic_score_codex":0.0000044886315,"about_ca_topic_score_gemma":0.0000010755671,"teacher_disagreement_score":0.9202502,"about_ca_system_score_codex":0.00040571246,"about_ca_system_score_gemma":0.00003617003,"threshold_uncertainty_score":0.99934775},"labels":[],"label_agreement":null},{"id":"W6920814135","doi":"10.6084/m9.figshare.12858753.v1","title":"Additional file 3 of Indicators to evaluate organisational knowledge brokers: a scoping review","year":2020,"lang":"en","type":"article","venue":"Figshare","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec en Abitibi-Témiscamingue","funders":"","keywords":"Table (database); Expert opinion; Key (lock); Expert system; File format; Outcome (game theory)","score_opus":0.38561513714032464,"score_gpt":0.5148580927939743,"score_spread":0.12924295565364968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6920814135","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000063223765,0.0003665089,0.0000031725772,0.001483631,0.000019584708,0.00044132478,0.98620284,0.000021962891,0.011454631],"genre_scores_gemma":[0.0006621977,0.000008833123,0.0013942168,0.007394592,0.00017515014,0.0009503841,0.9887257,0.000010890969,0.0006780344],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.997501,0.00013016738,0.00054494047,0.000295095,0.0014053793,0.0001234277],"domain_scores_gemma":[0.9958556,0.002747577,0.0003084899,0.00021605914,0.0006772608,0.00019498545],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00032890803,0.00009578061,0.00022634659,0.00013351151,0.000076654316,0.000049844406,0.00045178877,0.000034907116,0.9997243],"category_scores_gemma":[0.042478193,0.00007757888,0.00008697896,0.0013701345,0.0000075236385,0.00022246645,0.00017182915,0.00008138349,0.086401545],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000022183472,0.0000121250605,0.00000336523,0.00030417164,0.000004457499,2.8413285e-7,0.00020851487,0.000019452327,0.0000019367596,0.0000034339516,0.9936907,0.0057492973],"study_design_scores_gemma":[0.0000870202,0.000056220128,0.0012355528,0.053402983,0.000003690494,8.960215e-7,0.000064362175,0.0009940413,0.000045908153,0.000025893432,0.9439835,0.00009996682],"about_ca_topic_score_codex":1.3458805e-7,"about_ca_topic_score_gemma":0.000003390735,"teacher_disagreement_score":0.91332275,"about_ca_system_score_codex":0.00003231674,"about_ca_system_score_gemma":0.0013447932,"threshold_uncertainty_score":0.96558744},"labels":[],"label_agreement":null},{"id":"W6920858877","doi":"10.6084/m9.figshare.20438457.v1","title":"Additional file 5 of Selecting implementation models, theories, and frameworks in which to integrate intersectional approaches","year":2022,"lang":"en","type":"article","venue":"Figshare","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Université Laval; University of Calgary; University of Ottawa; McGill University; University of Waterloo; University of British Columbia; Public Health Ontario; York University; McMaster University; University of Manitoba; Ottawa Hospital","funders":"","keywords":"Selection (genetic algorithm); Domain (mathematical analysis); Key (lock); Set (abstract data type); Focus (optics); Black box","score_opus":0.2642392038506342,"score_gpt":0.43271699290784366,"score_spread":0.16847778905720945,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6920858877","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010263516,0.000006807304,0.00007585967,0.00020857948,0.000028363711,0.00016464968,0.99453545,0.000008921192,0.003944993],"genre_scores_gemma":[0.39041874,1.3550385e-7,0.0014551545,0.00024447194,0.000033568653,0.001667007,0.60592204,0.000005243348,0.00025364684],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984724,0.00014863428,0.00031366863,0.00022822677,0.0007303506,0.00010674726],"domain_scores_gemma":[0.9973994,0.0020720777,0.00015319033,0.000104804705,0.00023406443,0.000036474354],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00047196198,0.000065786524,0.00009901897,0.00023486608,0.0001478176,0.00006547883,0.000181533,0.000034035278,0.9942122],"category_scores_gemma":[0.0028276148,0.000058343172,0.00002324108,0.0009520774,0.0000040309405,0.0002757967,0.00020280397,0.00028186582,0.000106967345],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013191961,0.000017385255,0.000047728656,0.0000034786924,0.0000036331417,1.6890465e-7,0.0017945789,0.01259867,9.898497e-7,0.00036895977,0.9711974,0.013953812],"study_design_scores_gemma":[0.0002618362,0.00019496815,0.009388477,0.00026771895,0.0000019372887,0.000010203055,0.04036194,0.34099647,0.000027094658,0.025085147,0.5832084,0.00019583869],"about_ca_topic_score_codex":0.000011870555,"about_ca_topic_score_gemma":0.00040747752,"teacher_disagreement_score":0.9941053,"about_ca_system_score_codex":0.00008217548,"about_ca_system_score_gemma":0.00024509625,"threshold_uncertainty_score":0.33851233},"labels":[],"label_agreement":null},{"id":"W6921045321","doi":"10.6084/m9.figshare.20438451","title":"Additional file 3 of Selecting implementation models, theories, and frameworks in which to integrate intersectional approaches","year":2022,"lang":"en","type":"article","venue":"Figshare","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Université Laval; University of Calgary; University of Ottawa; McGill University; University of Waterloo; University of British Columbia; Public Health Ontario; York University; McMaster University; University of Manitoba; Ottawa Hospital","funders":"","keywords":"Selection (genetic algorithm); Domain (mathematical analysis); Key (lock); Focus (optics); Set (abstract data type); Black box","score_opus":0.26438409862835766,"score_gpt":0.4325963555282932,"score_spread":0.16821225689993552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6921045321","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010250969,0.00000678352,0.00007553724,0.0002076248,0.000028586514,0.00016436829,0.9945253,0.000008899022,0.003957808],"genre_scores_gemma":[0.3877711,1.3593043e-7,0.0014581546,0.00024480774,0.00003400821,0.0016721315,0.6085528,0.000005260089,0.0002615673],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99847263,0.00014852881,0.0003135666,0.00022817479,0.000730353,0.0001067378],"domain_scores_gemma":[0.9973981,0.0020709238,0.00015318622,0.000104778366,0.00023658943,0.000036472255],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00047134762,0.000065775464,0.00009897869,0.00023476656,0.00014773745,0.00006547294,0.00018146799,0.00003403076,0.99430984],"category_scores_gemma":[0.002856065,0.000058331032,0.000023236154,0.00095189246,0.000004030199,0.00027575693,0.00020271663,0.0002818415,0.00010992859],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001324852,0.000017357404,0.000047738056,0.0000035015264,0.0000036293336,1.6815625e-7,0.001791898,0.0126071535,9.967366e-7,0.00035547174,0.97122985,0.013928992],"study_design_scores_gemma":[0.00025660326,0.00018954305,0.008968301,0.00026036642,0.0000018751853,0.000009850701,0.039238494,0.33372682,0.000026778773,0.024356695,0.5927737,0.00019098543],"about_ca_topic_score_codex":0.000011869057,"about_ca_topic_score_gemma":0.0004043681,"teacher_disagreement_score":0.99419993,"about_ca_system_score_codex":0.00008247412,"about_ca_system_score_gemma":0.00024574032,"threshold_uncertainty_score":0.3419183},"labels":[],"label_agreement":null},{"id":"W6925988112","doi":"10.20381/ruor-29969","title":"Reducing the Overrepresentation of Indigenous Peoples in Canadian Prisons: Bail and the Promise of Gladue Courts","year":2023,"lang":"en","type":"other","venue":"uO Research (University of Ottawa)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Indigenous; Economic Justice; Christian ministry; Criminal justice; Circumstantial evidence; Psychological intervention","score_opus":0.16396686104940814,"score_gpt":0.45237896778634523,"score_spread":0.28841210673693707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6925988112","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5111692,0.0005304535,0.00005463757,0.009226335,0.00023568838,0.0033226889,0.00026668896,0.000028155753,0.47516614],"genre_scores_gemma":[0.7665042,0.0017050998,0.00018416056,0.000011821564,0.000032930202,0.000003842022,0.000010794778,0.000052481657,0.23149462],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9964686,0.0008445704,0.00026062204,0.00025722818,0.0019101949,0.00025878887],"domain_scores_gemma":[0.99649614,0.0021066216,0.00037564192,0.0005403929,0.0003888705,0.000092313254],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0103118345,0.00008054536,0.00029740535,0.001306892,0.00021499408,0.00003288227,0.0008813674,0.00011032537,0.0012402186],"category_scores_gemma":[0.0016706771,0.00005462178,0.000063911335,0.0010988022,0.0007068208,0.00012696847,0.00018844222,0.00026925563,0.000025057236],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009468259,0.00013087719,0.61400855,0.00030258243,0.00019267271,0.000028664748,0.086316995,0.0004145372,0.00007285836,0.017943578,0.2413698,0.039124183],"study_design_scores_gemma":[0.0022490544,0.00015255038,0.7713655,0.00046411462,0.000032284857,0.0000026186233,0.08605108,0.0045050704,0.000055978457,0.0018221798,0.13313198,0.00016756437],"about_ca_topic_score_codex":0.4611152,"about_ca_topic_score_gemma":0.9354775,"teacher_disagreement_score":0.47436228,"about_ca_system_score_codex":0.000114540824,"about_ca_system_score_gemma":0.0019614722,"threshold_uncertainty_score":0.9996728},"labels":[],"label_agreement":null},{"id":"W6939717960","doi":"10.6084/m9.figshare.20438448","title":"Additional file 2 of Selecting implementation models, theories, and frameworks in which to integrate intersectional approaches","year":2022,"lang":"en","type":"article","venue":"Figshare","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Université Laval; University of Calgary; University of Ottawa; McGill University; University of Waterloo; University of British Columbia; Public Health Ontario; York University; McMaster University; University of Manitoba; Ottawa Hospital","funders":"","keywords":"Selection (genetic algorithm); Domain (mathematical analysis); Key (lock); Focus (optics); Black box","score_opus":0.2609385194743372,"score_gpt":0.4324750522526223,"score_spread":0.17153653277828507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6939717960","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001011052,0.0000068561008,0.00007353214,0.00020756978,0.000028484177,0.00016410746,0.9944761,0.000008909568,0.004023392],"genre_scores_gemma":[0.38127512,1.3765003e-7,0.0014449145,0.00024526333,0.000034149187,0.0016732436,0.61506426,0.000005258623,0.00025766718],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998473,0.00014862156,0.0003135663,0.00022810505,0.00073002494,0.00010670716],"domain_scores_gemma":[0.9974113,0.002060127,0.00015336699,0.000104731706,0.0002340058,0.00003646849],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004690211,0.00006576404,0.00009899253,0.00023469291,0.00014776079,0.00006547923,0.00018148197,0.000034033837,0.9943439],"category_scores_gemma":[0.0028228967,0.000058327016,0.000023233197,0.0009515141,0.0000040298587,0.00027573213,0.00020283443,0.0002818348,0.000107600215],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013069116,0.000017320415,0.000046076195,0.0000034658954,0.000003624071,1.7025766e-7,0.0017891992,0.01263332,9.580896e-7,0.00036307477,0.971058,0.01407172],"study_design_scores_gemma":[0.0002533902,0.00018877132,0.008829422,0.00025629162,0.0000018747568,0.000009908837,0.03880996,0.32936993,0.000025905003,0.024337785,0.5977273,0.00018949743],"about_ca_topic_score_codex":0.000011853129,"about_ca_topic_score_gemma":0.00040399662,"teacher_disagreement_score":0.9942363,"about_ca_system_score_codex":0.0000821729,"about_ca_system_score_gemma":0.0002445269,"threshold_uncertainty_score":0.3379475},"labels":[],"label_agreement":null},{"id":"W6958146995","doi":"10.6084/m9.figshare.20438448.v1","title":"Additional file 2 of Selecting implementation models, theories, and frameworks in which to integrate intersectional approaches","year":2022,"lang":"en","type":"article","venue":"Figshare","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Université Laval; University of Calgary; University of Ottawa; McGill University; University of Waterloo; University of British Columbia; Public Health Ontario; York University; McMaster University; University of Manitoba; Ottawa Hospital","funders":"","keywords":"Selection (genetic algorithm); Domain (mathematical analysis); Key (lock); Focus (optics); Black box","score_opus":0.2609385194743372,"score_gpt":0.4324750522526223,"score_spread":0.17153653277828507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958146995","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001011052,0.0000068561008,0.00007353214,0.00020756978,0.000028484177,0.00016410746,0.9944761,0.000008909568,0.004023392],"genre_scores_gemma":[0.38127512,1.3765003e-7,0.0014449145,0.00024526333,0.000034149187,0.0016732436,0.61506426,0.000005258623,0.00025766718],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998473,0.00014862156,0.0003135663,0.00022810505,0.00073002494,0.00010670716],"domain_scores_gemma":[0.9974113,0.002060127,0.00015336699,0.000104731706,0.0002340058,0.00003646849],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004690211,0.00006576404,0.00009899253,0.00023469291,0.00014776079,0.00006547923,0.00018148197,0.000034033837,0.9943439],"category_scores_gemma":[0.0028228967,0.000058327016,0.000023233197,0.0009515141,0.0000040298587,0.00027573213,0.00020283443,0.0002818348,0.000107600215],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013069116,0.000017320415,0.000046076195,0.0000034658954,0.000003624071,1.7025766e-7,0.0017891992,0.01263332,9.580896e-7,0.00036307477,0.971058,0.01407172],"study_design_scores_gemma":[0.0002533902,0.00018877132,0.008829422,0.00025629162,0.0000018747568,0.000009908837,0.03880996,0.32936993,0.000025905003,0.024337785,0.5977273,0.00018949743],"about_ca_topic_score_codex":0.000011853129,"about_ca_topic_score_gemma":0.00040399662,"teacher_disagreement_score":0.9942363,"about_ca_system_score_codex":0.0000821729,"about_ca_system_score_gemma":0.0002445269,"threshold_uncertainty_score":0.3379475},"labels":[],"label_agreement":null},{"id":"W6958276614","doi":"10.6084/m9.figshare.20438451.v1","title":"Additional file 3 of Selecting implementation models, theories, and frameworks in which to integrate intersectional approaches","year":2022,"lang":"en","type":"article","venue":"Figshare","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Université Laval; University of Calgary; University of Ottawa; McGill University; University of Waterloo; University of British Columbia; Public Health Ontario; York University; McMaster University; University of Manitoba; Ottawa Hospital","funders":"","keywords":"Selection (genetic algorithm); Domain (mathematical analysis); Key (lock); Focus (optics); Set (abstract data type); Black box","score_opus":0.26438409862835766,"score_gpt":0.4325963555282932,"score_spread":0.16821225689993552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958276614","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010250969,0.00000678352,0.00007553724,0.0002076248,0.000028586514,0.00016436829,0.9945253,0.000008899022,0.003957808],"genre_scores_gemma":[0.3877711,1.3593043e-7,0.0014581546,0.00024480774,0.00003400821,0.0016721315,0.6085528,0.000005260089,0.0002615673],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99847263,0.00014852881,0.0003135666,0.00022817479,0.000730353,0.0001067378],"domain_scores_gemma":[0.9973981,0.0020709238,0.00015318622,0.000104778366,0.00023658943,0.000036472255],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00047134762,0.000065775464,0.00009897869,0.00023476656,0.00014773745,0.00006547294,0.00018146799,0.00003403076,0.99430984],"category_scores_gemma":[0.002856065,0.000058331032,0.000023236154,0.00095189246,0.000004030199,0.00027575693,0.00020271663,0.0002818415,0.00010992859],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001324852,0.000017357404,0.000047738056,0.0000035015264,0.0000036293336,1.6815625e-7,0.001791898,0.0126071535,9.967366e-7,0.00035547174,0.97122985,0.013928992],"study_design_scores_gemma":[0.00025660326,0.00018954305,0.008968301,0.00026036642,0.0000018751853,0.000009850701,0.039238494,0.33372682,0.000026778773,0.024356695,0.5927737,0.00019098543],"about_ca_topic_score_codex":0.000011869057,"about_ca_topic_score_gemma":0.0004043681,"teacher_disagreement_score":0.99419993,"about_ca_system_score_codex":0.00008247412,"about_ca_system_score_gemma":0.00024574032,"threshold_uncertainty_score":0.3419183},"labels":[],"label_agreement":null},{"id":"W6958347847","doi":"10.6084/m9.figshare.12858750.v1","title":"Additional file 2 of Indicators to evaluate organisational knowledge brokers: a scoping review","year":2020,"lang":"en","type":"article","venue":"Figshare","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec en Abitibi-Témiscamingue","funders":"","keywords":"Key (lock); Data file; File format; Data collection; Government (linguistics)","score_opus":0.38116182835048845,"score_gpt":0.5147565470381018,"score_spread":0.13359471868761336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958347847","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000062269974,0.00037058574,0.0000030810654,0.0014826662,0.000019502251,0.00044041124,0.9860027,0.000021982793,0.0116528515],"genre_scores_gemma":[0.0006387558,0.000008880974,0.0013694771,0.0073495484,0.00017451058,0.0009433891,0.98884284,0.000010799857,0.00066179933],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99750173,0.00013025476,0.0005449402,0.00029499826,0.0014047022,0.00012338969],"domain_scores_gemma":[0.9958799,0.0027313868,0.00030878876,0.0002158914,0.0006691229,0.00019490572],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00032716413,0.00009576275,0.00022638058,0.0001334665,0.000076667326,0.000049849554,0.00045182617,0.000034910507,0.99972606],"category_scores_gemma":[0.041969292,0.000077573146,0.00008696706,0.0013695498,0.000007522956,0.00022244499,0.00017193641,0.00008138142,0.084603205],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002191748,0.000012128596,0.0000032479222,0.00030162686,0.0000044620674,2.8869368e-7,0.0002087163,0.000019547271,0.0000018610094,0.0000035220287,0.9936142,0.0058282274],"study_design_scores_gemma":[0.00008635864,0.000056305747,0.0012221867,0.05283943,0.000003711437,9.0704305e-7,0.00006398094,0.0009851741,0.000044563374,0.000026026599,0.9445716,0.00009971743],"about_ca_topic_score_codex":1.3439404e-7,"about_ca_topic_score_gemma":0.0000033873873,"teacher_disagreement_score":0.91512287,"about_ca_system_score_codex":0.000032189957,"about_ca_system_score_gemma":0.0013376692,"threshold_uncertainty_score":0.96610063},"labels":[],"label_agreement":null},{"id":"W6958620360","doi":"10.6084/m9.figshare.26945109","title":"Additional file 1 of Using mixed methods and partnership to develop a program evaluation toolkit for organizations that provide physical activity programs for persons with disabilities","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; Centre for Interdisciplinary Research in Rehabilitation; University of British Columbia; International Collaboration On Repair Discoveries; BC Wheelchair Sports Association; McGill University; Queen's University","funders":"","keywords":"General partnership; Program evaluation; Data collection; Evaluation methods; Physical activity","score_opus":0.5370612894460969,"score_gpt":0.569802572491087,"score_spread":0.03274128304499013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958620360","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003998616,0.000009990109,0.0027976688,0.00030631354,0.0000272814,0.004289695,0.9882995,0.00006974103,0.00020118723],"genre_scores_gemma":[0.057227794,5.8250347e-8,0.32304695,0.000040743795,0.00015971786,0.045267526,0.5731126,0.00003188091,0.0011127335],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99835527,0.0001642775,0.00017250453,0.0003788974,0.0007568347,0.00017220418],"domain_scores_gemma":[0.9887052,0.009185097,0.00010891357,0.00016578709,0.0017585692,0.00007641672],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007098456,0.000121068646,0.00017800309,0.000102923914,0.00017338405,0.00036475505,0.0001328658,0.000043277305,0.4484044],"category_scores_gemma":[0.029507007,0.00008472555,0.000052322674,0.0010683958,0.000029008823,0.0004930929,0.000053642612,0.00005291086,0.000038055725],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002097341,0.00007819785,0.000016161992,0.00011967729,0.000018067849,3.120784e-8,0.0013915539,0.000096502336,0.000010261486,0.000027451939,0.6622811,0.33594003],"study_design_scores_gemma":[0.00015537735,0.00027471222,0.0016462068,0.0007554019,0.000036198344,0.0000023259365,0.0029400918,0.39091203,0.00039910144,0.00054731005,0.6021882,0.00014302364],"about_ca_topic_score_codex":0.0000010397856,"about_ca_topic_score_gemma":0.000044928358,"teacher_disagreement_score":0.44836634,"about_ca_system_score_codex":0.0000823657,"about_ca_system_score_gemma":0.0013699399,"threshold_uncertainty_score":0.97866786},"labels":[],"label_agreement":null},{"id":"W6958634179","doi":"10.6084/m9.figshare.26945109.v1","title":"Additional file 1 of Using mixed methods and partnership to develop a program evaluation toolkit for organizations that provide physical activity programs for persons with disabilities","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; Centre for Interdisciplinary Research in Rehabilitation; University of British Columbia; International Collaboration On Repair Discoveries; BC Wheelchair Sports Association; McGill University; Queen's University","funders":"","keywords":"General partnership; Program evaluation; Data collection; Evaluation methods; Physical activity","score_opus":0.5370612894460969,"score_gpt":0.569802572491087,"score_spread":0.03274128304499013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958634179","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003998616,0.000009990109,0.0027976688,0.00030631354,0.0000272814,0.004289695,0.9882995,0.00006974103,0.00020118723],"genre_scores_gemma":[0.057227794,5.8250347e-8,0.32304695,0.000040743795,0.00015971786,0.045267526,0.5731126,0.00003188091,0.0011127335],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99835527,0.0001642775,0.00017250453,0.0003788974,0.0007568347,0.00017220418],"domain_scores_gemma":[0.9887052,0.009185097,0.00010891357,0.00016578709,0.0017585692,0.00007641672],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007098456,0.000121068646,0.00017800309,0.000102923914,0.00017338405,0.00036475505,0.0001328658,0.000043277305,0.4484044],"category_scores_gemma":[0.029507007,0.00008472555,0.000052322674,0.0010683958,0.000029008823,0.0004930929,0.000053642612,0.00005291086,0.000038055725],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002097341,0.00007819785,0.000016161992,0.00011967729,0.000018067849,3.120784e-8,0.0013915539,0.000096502336,0.000010261486,0.000027451939,0.6622811,0.33594003],"study_design_scores_gemma":[0.00015537735,0.00027471222,0.0016462068,0.0007554019,0.000036198344,0.0000023259365,0.0029400918,0.39091203,0.00039910144,0.00054731005,0.6021882,0.00014302364],"about_ca_topic_score_codex":0.0000010397856,"about_ca_topic_score_gemma":0.000044928358,"teacher_disagreement_score":0.44836634,"about_ca_system_score_codex":0.0000823657,"about_ca_system_score_gemma":0.0013699399,"threshold_uncertainty_score":0.97866786},"labels":[],"label_agreement":null},{"id":"W6958885519","doi":"10.6084/m9.figshare.26945112","title":"Additional file 2 of Using mixed methods and partnership to develop a program evaluation toolkit for organizations that provide physical activity programs for persons with disabilities","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; Centre for Interdisciplinary Research in Rehabilitation; University of British Columbia; International Collaboration On Repair Discoveries; BC Wheelchair Sports Association; McGill University; Queen's University","funders":"","keywords":"General partnership; Program evaluation; Data collection; Evaluation methods; Physical activity","score_opus":0.5282305939099377,"score_gpt":0.5690837015530448,"score_spread":0.04085310764310712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958885519","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003990368,0.0000101713185,0.002755203,0.00030610574,0.000027530012,0.004299754,0.98833483,0.00006999968,0.00020605067],"genre_scores_gemma":[0.056726605,5.992705e-8,0.31948888,0.000040961342,0.00016267023,0.0447506,0.5776763,0.00003200982,0.001121892],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99835575,0.00016422842,0.00017257343,0.00037864628,0.00075666833,0.00017214821],"domain_scores_gemma":[0.98882294,0.009071,0.00010904982,0.00016550641,0.001755124,0.00007640756],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00070640974,0.0001210345,0.00017804174,0.000102864156,0.00017339532,0.0003654569,0.00013280021,0.000043277527,0.44423518],"category_scores_gemma":[0.029200139,0.00008470098,0.000052313695,0.0010676599,0.000029008466,0.00049339246,0.000053635922,0.000052900054,0.000037695416],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020812045,0.000077950295,0.00001566142,0.00012029158,0.000018016011,3.187223e-8,0.0013885876,0.00009663469,0.00000991711,0.000027799739,0.6580775,0.3401468],"study_design_scores_gemma":[0.00015522235,0.00027282262,0.0016113049,0.0007418851,0.000035828547,0.0000023141388,0.0028930474,0.3864627,0.0003941109,0.0005472983,0.6067417,0.00014175435],"about_ca_topic_score_codex":0.0000010490738,"about_ca_topic_score_gemma":0.00004516411,"teacher_disagreement_score":0.44419748,"about_ca_system_score_codex":0.00008238663,"about_ca_system_score_gemma":0.0013645386,"threshold_uncertainty_score":0.9789773},"labels":[],"label_agreement":null},{"id":"W6959205768","doi":"10.11575/ajer.v47i3.54876","title":"Formative Evaluation Following BEd Program Revisions: Background and Insights","year":2009,"lang":"en","type":"article","venue":"University of Calgary","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Formative assessment; Bachelor; Relevance (law); Program evaluation; Component (thermodynamics); Higher education; Focus group; Value (mathematics)","score_opus":0.14781349155903278,"score_gpt":0.4346430470744631,"score_spread":0.2868295555154303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6959205768","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94935095,0.00029120778,0.0020779793,0.0005174777,0.00007989734,0.00045675176,7.7085247e-7,0.000024474515,0.047200475],"genre_scores_gemma":[0.99336624,0.000069192036,0.006018278,0.000119020144,0.0000067472442,3.1355603e-7,0.000010119964,0.0000013956669,0.00040870497],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99814534,0.00020589393,0.00021087668,0.00018150888,0.0011634355,0.000092955524],"domain_scores_gemma":[0.99900573,0.0002062992,0.00016218005,0.00020267017,0.00035483087,0.000068303525],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018390417,0.00006859941,0.000162294,0.00018546484,0.00021287083,0.00004747119,0.0001991432,0.000048093458,0.0005546388],"category_scores_gemma":[0.00017154915,0.000058249996,0.00007726909,0.0003510988,0.00005420714,0.000855732,0.00004919497,0.000069804744,0.00004010977],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044538858,0.000092084265,0.0012693941,0.0000035049534,0.000016983826,0.00000312318,0.0053657154,0.000024055831,0.00014772441,0.003716084,0.0012449102,0.98807186],"study_design_scores_gemma":[0.0048355944,0.0015158916,0.5310178,0.00020856655,0.00021945755,0.000006051414,0.030617097,0.28757104,0.00029635473,0.055188753,0.088062815,0.0004605939],"about_ca_topic_score_codex":0.000011250764,"about_ca_topic_score_gemma":0.000021810105,"teacher_disagreement_score":0.9876113,"about_ca_system_score_codex":0.000049841867,"about_ca_system_score_gemma":0.00012712892,"threshold_uncertainty_score":0.6072906},"labels":[],"label_agreement":null},{"id":"W6962970895","doi":"10.17635/lancaster/thesis/2316","title":"Examining the impact of evaluation professionalization in Canada on the positioning, practice and employability of evaluators","year":2024,"lang":"en","type":"article","venue":"Lancaster EPrints (Lancaster University)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Professionalization; Credential; Employability; Construct (python library); Field (mathematics); Focus group; Professional development; Body of knowledge; Qualitative research","score_opus":0.16603117289651922,"score_gpt":0.4376524789578774,"score_spread":0.27162130606135815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6962970895","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9862916,0.000041456784,0.0002446595,0.0010135146,0.00015138178,0.00042259146,0.000012393935,0.0000037006605,0.011818697],"genre_scores_gemma":[0.9993121,0.0000068582262,0.00004307921,0.00009603163,0.000017094571,0.0000030209492,0.0000043852315,0.000004876401,0.0005125712],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99666,0.0012562444,0.00037750724,0.00028787774,0.0012928612,0.0001255308],"domain_scores_gemma":[0.99650234,0.002265337,0.0003132578,0.00041097644,0.00047285267,0.000035235116],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00539912,0.00010446036,0.00016483005,0.0002326434,0.00008529517,0.00005655323,0.00025473518,0.000034832028,0.0016198646],"category_scores_gemma":[0.00083146204,0.000055638564,0.000044368353,0.0009201831,0.00007374369,0.00041329284,0.00012373457,0.00016732853,0.000019034269],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014795625,0.00004712988,0.97855,0.00001888861,0.000052449443,0.000006209954,0.0031515234,0.00051126385,0.0001261681,0.0020488435,0.00035757278,0.014981966],"study_design_scores_gemma":[0.00028061547,0.00008018105,0.9492942,0.00013876363,0.000029251465,0.0000057762095,0.004370288,0.04456152,0.00010666643,0.00049648754,0.0005747231,0.00006149379],"about_ca_topic_score_codex":0.028918685,"about_ca_topic_score_gemma":0.04559742,"teacher_disagreement_score":0.044050258,"about_ca_system_score_codex":0.00042766225,"about_ca_system_score_gemma":0.0013955187,"threshold_uncertainty_score":0.9992928},"labels":[],"label_agreement":null},{"id":"W6976693566","doi":"10.6084/m9.figshare.12858753","title":"Additional file 3 of Indicators to evaluate organisational knowledge brokers: a scoping review","year":2020,"lang":"en","type":"article","venue":"Figshare","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec en Abitibi-Témiscamingue","funders":"","keywords":"Table (database); Expert opinion; Key (lock); Expert system; File format; Outcome (game theory)","score_opus":0.38561513714032464,"score_gpt":0.5148580927939743,"score_spread":0.12924295565364968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6976693566","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000063223765,0.0003665089,0.0000031725772,0.001483631,0.000019584708,0.00044132478,0.98620284,0.000021962891,0.011454631],"genre_scores_gemma":[0.0006621977,0.000008833123,0.0013942168,0.007394592,0.00017515014,0.0009503841,0.9887257,0.000010890969,0.0006780344],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.997501,0.00013016738,0.00054494047,0.000295095,0.0014053793,0.0001234277],"domain_scores_gemma":[0.9958556,0.002747577,0.0003084899,0.00021605914,0.0006772608,0.00019498545],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00032890803,0.00009578061,0.00022634659,0.00013351151,0.000076654316,0.000049844406,0.00045178877,0.000034907116,0.9997243],"category_scores_gemma":[0.042478193,0.00007757888,0.00008697896,0.0013701345,0.0000075236385,0.00022246645,0.00017182915,0.00008138349,0.086401545],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000022183472,0.0000121250605,0.00000336523,0.00030417164,0.000004457499,2.8413285e-7,0.00020851487,0.000019452327,0.0000019367596,0.0000034339516,0.9936907,0.0057492973],"study_design_scores_gemma":[0.0000870202,0.000056220128,0.0012355528,0.053402983,0.000003690494,8.960215e-7,0.000064362175,0.0009940413,0.000045908153,0.000025893432,0.9439835,0.00009996682],"about_ca_topic_score_codex":1.3458805e-7,"about_ca_topic_score_gemma":0.000003390735,"teacher_disagreement_score":0.91332275,"about_ca_system_score_codex":0.00003231674,"about_ca_system_score_gemma":0.0013447932,"threshold_uncertainty_score":0.96558744},"labels":[],"label_agreement":null},{"id":"W6976910564","doi":"10.6084/m9.figshare.26945112.v1","title":"Additional file 2 of Using mixed methods and partnership to develop a program evaluation toolkit for organizations that provide physical activity programs for persons with disabilities","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; Centre for Interdisciplinary Research in Rehabilitation; University of British Columbia; International Collaboration On Repair Discoveries; BC Wheelchair Sports Association; McGill University; Queen's University","funders":"","keywords":"General partnership; Program evaluation; Data collection; Evaluation methods; Physical activity","score_opus":0.5282305939099377,"score_gpt":0.5690837015530448,"score_spread":0.04085310764310712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6976910564","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003990368,0.0000101713185,0.002755203,0.00030610574,0.000027530012,0.004299754,0.98833483,0.00006999968,0.00020605067],"genre_scores_gemma":[0.056726605,5.992705e-8,0.31948888,0.000040961342,0.00016267023,0.0447506,0.5776763,0.00003200982,0.001121892],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99835575,0.00016422842,0.00017257343,0.00037864628,0.00075666833,0.00017214821],"domain_scores_gemma":[0.98882294,0.009071,0.00010904982,0.00016550641,0.001755124,0.00007640756],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00070640974,0.0001210345,0.00017804174,0.000102864156,0.00017339532,0.0003654569,0.00013280021,0.000043277527,0.44423518],"category_scores_gemma":[0.029200139,0.00008470098,0.000052313695,0.0010676599,0.000029008466,0.00049339246,0.000053635922,0.000052900054,0.000037695416],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020812045,0.000077950295,0.00001566142,0.00012029158,0.000018016011,3.187223e-8,0.0013885876,0.00009663469,0.00000991711,0.000027799739,0.6580775,0.3401468],"study_design_scores_gemma":[0.00015522235,0.00027282262,0.0016113049,0.0007418851,0.000035828547,0.0000023141388,0.0028930474,0.3864627,0.0003941109,0.0005472983,0.6067417,0.00014175435],"about_ca_topic_score_codex":0.0000010490738,"about_ca_topic_score_gemma":0.00004516411,"teacher_disagreement_score":0.44419748,"about_ca_system_score_codex":0.00008238663,"about_ca_system_score_gemma":0.0013645386,"threshold_uncertainty_score":0.9789773},"labels":[],"label_agreement":null},{"id":"W6977686472","doi":"10.7939/r3-sev5-xq22","title":"The Needs of Evaluation in the Field of Early Childhood Development from the Early Learning and Childcare Educators' Perspective","year":2023,"lang":"en","type":"dissertation","venue":"University of Alberta Library","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Early childhood; Government (linguistics); Field (mathematics); Perspective (graphical); Early childhood education; Capacity building; Set (abstract data type)","score_opus":0.026013891443511024,"score_gpt":0.3374393334091061,"score_spread":0.3114254419655951,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6977686472","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9802228,0.0003841807,0.0000015378122,0.00256953,0.00017439567,0.0003764694,0.000004439806,0.000004241159,0.016262377],"genre_scores_gemma":[0.9942351,0.00021778788,0.00004678413,0.000052087053,0.000027209333,0.000001485143,0.00010209109,0.000007919907,0.005309521],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9976993,0.00052347383,0.0003538777,0.00018851632,0.0011314275,0.000103370665],"domain_scores_gemma":[0.99322563,0.0056528407,0.0005562088,0.000290399,0.00025077793,0.000024119105],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013088686,0.00011994212,0.00022018107,0.00024881557,0.0003053592,0.00007002903,0.0007296551,0.00011077705,0.0004241556],"category_scores_gemma":[0.0007883208,0.00007042732,0.0000909703,0.0007955,0.00008466811,0.00038846539,0.00010364695,0.00030800598,0.0000126767845],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013466856,0.000050665367,0.18149458,0.000007468011,0.00009742507,2.64042e-7,0.7922465,0.000034378245,0.00000496007,0.001649563,0.0019132105,0.022366296],"study_design_scores_gemma":[0.00018782052,0.00006466137,0.61747134,0.000080839636,0.000031962474,8.645161e-8,0.3794903,0.000048436017,0.00008210447,0.0011616434,0.0013296262,0.00005123294],"about_ca_topic_score_codex":0.0049424274,"about_ca_topic_score_gemma":0.005038498,"teacher_disagreement_score":0.4359767,"about_ca_system_score_codex":0.000021934691,"about_ca_system_score_gemma":0.0009398455,"threshold_uncertainty_score":0.7471505},"labels":[],"label_agreement":null},{"id":"W6980006803","doi":"","title":"Application of the theory-driven approach to evaluation in program planning","year":2001,"lang":"en","type":"other","venue":"Library and Archives Canada (Government of Canada)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Practicum; Logic model; Plan (archaeology); Program evaluation; Program Design Language; Development plan","score_opus":0.03700642599479141,"score_gpt":0.3069049126885599,"score_spread":0.2698984866937685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6980006803","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002066127,0.00015246359,0.0013904513,0.0008890015,0.0001254971,0.0010950525,0.000066814144,0.000006444583,0.99420816],"genre_scores_gemma":[0.8043763,0.00003362092,0.003496356,0.0007451157,0.000075102136,0.00018931033,0.000019022684,0.00006026042,0.19100487],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9941686,0.00028218003,0.00042910973,0.00028970517,0.0046730386,0.00015740443],"domain_scores_gemma":[0.9988033,0.00026404837,0.0004398667,0.00040060582,0.0000020674333,0.00009010426],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018986249,0.00014255657,0.00025228434,0.00008730563,0.00005545163,0.000023038472,0.00052760256,0.000040675455,0.00021979987],"category_scores_gemma":[0.000024493012,0.00009728968,0.000027242813,0.00034325552,0.00005460307,0.00010813888,0.0001379586,0.00011218583,1.0531614e-8],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023147021,0.00020059424,0.24539125,0.00016776053,0.00008658603,0.0000020931727,0.00065474486,0.017463446,0.0006298771,0.116954304,0.04438795,0.57382995],"study_design_scores_gemma":[0.0007140734,0.00009106125,0.22195758,0.00039391205,0.000044366843,0.0000023296557,0.006873664,0.14580938,0.0015498458,0.0073429462,0.6148318,0.00038903859],"about_ca_topic_score_codex":0.0020560578,"about_ca_topic_score_gemma":0.025305707,"teacher_disagreement_score":0.8032033,"about_ca_system_score_codex":0.000011920615,"about_ca_system_score_gemma":0.0016435928,"threshold_uncertainty_score":0.9924799},"labels":[],"label_agreement":null},{"id":"W6980621700","doi":"","title":"Collaboration with Mother Nature: Canadian land artist Greg Blair will alter BSC campus; Land art installation schedule","year":2005,"lang":"en","type":"other","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Schedule; Work (physics)","score_opus":0.023541571162222632,"score_gpt":0.37195631546214375,"score_spread":0.34841474429992114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6980621700","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018872765,0.00022789236,0.001084716,0.0052085225,0.00048767345,0.0006582251,0.0001278646,0.0000923732,0.99022543],"genre_scores_gemma":[0.07090171,0.00005199537,0.0025990412,0.002719155,0.000583927,0.000029656907,0.00028391252,0.00013985073,0.92269075],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99701774,0.00012543183,0.00043088253,0.0005616582,0.0015497269,0.00031453866],"domain_scores_gemma":[0.99829715,0.00007323768,0.00038337684,0.0006073268,0.00038360365,0.00025530084],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008947841,0.0002998323,0.00033184688,0.0007654211,0.00014225538,0.0005161396,0.0003110458,0.0004892478,0.0765569],"category_scores_gemma":[0.00008865641,0.00019487794,0.000046332207,0.0008119826,0.00007567813,0.00051920296,0.000022974464,0.0003083218,0.002971546],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021656968,0.000027781893,0.0550528,0.000007141188,0.000049015878,0.0000044368776,0.00012733869,0.0007145673,0.000004193738,0.0011691871,0.9375935,0.005228354],"study_design_scores_gemma":[0.00063829345,0.00006461351,0.008836351,0.00005587819,0.000018939849,0.000006014641,0.000092627066,0.0034538608,0.000018227724,0.0001292418,0.986373,0.00031297115],"about_ca_topic_score_codex":0.008659379,"about_ca_topic_score_gemma":0.9321728,"teacher_disagreement_score":0.9235134,"about_ca_system_score_codex":0.00021099111,"about_ca_system_score_gemma":0.001304001,"threshold_uncertainty_score":0.99794203},"labels":[],"label_agreement":null},{"id":"W6990363428","doi":"","title":"Developing the Program Evaluation Framework for Investment Agriculture Foundation of British Columbia","year":2022,"lang":"en","type":"dissertation","venue":"UVic’s Research and Learning Repository (University of Victoria)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Summative assessment; Formative assessment; Program evaluation; Interview; Foundation (evidence); Agriculture; Monitoring and evaluation; Investment (military); Public sector; Private sector","score_opus":0.13275316867782788,"score_gpt":0.4431621648321757,"score_spread":0.3104089961543478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6990363428","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9821054,0.0008422653,0.0007416753,0.00032775386,0.0015246588,0.0037217396,0.000021183572,0.00003898332,0.010676345],"genre_scores_gemma":[0.85694796,0.00068803335,0.012212587,0.000026627014,0.00049411063,0.00023969598,0.0016075501,0.00003807889,0.12774536],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99370646,0.0014168527,0.000404883,0.00047722636,0.003757139,0.00023745526],"domain_scores_gemma":[0.9932821,0.0017918121,0.0007568417,0.00029808615,0.0037910957,0.00008010889],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.009252885,0.00010190085,0.0003030422,0.00018008385,0.0021518497,0.0004973376,0.000613002,0.00021773345,0.00087598973],"category_scores_gemma":[0.0018888382,0.00011924628,0.000120511206,0.0009464785,0.00014648335,0.00028080662,0.00012691361,0.00087883306,0.0000046914083],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010656111,0.0008533804,0.04508676,0.0012913165,0.00078381505,0.0000150972755,0.05415212,0.0018195021,0.002072022,0.010796846,0.057984773,0.82407874],"study_design_scores_gemma":[0.0010479956,0.0018195831,0.2555944,0.00053826737,0.00014866311,0.0000075046228,0.14340454,0.006944683,0.000073784046,0.027159296,0.562917,0.00034424732],"about_ca_topic_score_codex":0.003927782,"about_ca_topic_score_gemma":0.0128316125,"teacher_disagreement_score":0.8237345,"about_ca_system_score_codex":0.00032774179,"about_ca_system_score_gemma":0.0012515846,"threshold_uncertainty_score":0.99914724},"labels":[],"label_agreement":null},{"id":"W6990448042","doi":"","title":"The development of a Temporal Logic Model","year":2001,"lang":"en","type":"dissertation","venue":"The Atrium (University of Guelph)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"International Development Research Centre","keywords":"Temporal logic; Logic model; Interim; Process (computing); Temporal logic of actions; Perspective (graphical); Development (topology); Dynamic logic (digital electronics)","score_opus":0.13856264670504342,"score_gpt":0.38686058084231223,"score_spread":0.2482979341372688,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6990448042","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9048914,0.0003996605,0.006928856,0.0021602218,0.0005194242,0.0005169425,0.000020333931,0.000023268947,0.084539935],"genre_scores_gemma":[0.903635,0.00014066299,0.0023806526,0.000022666887,0.000017915325,4.5447945e-7,0.00006212319,0.0000058776473,0.09373464],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9973956,0.00015039969,0.00045265714,0.00022616395,0.0016122817,0.0001629184],"domain_scores_gemma":[0.99725753,0.00041112772,0.0009448877,0.0005891288,0.00075333926,0.000044003704],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034870105,0.00013730727,0.00029013056,0.00017480628,0.0006558242,0.0000340048,0.001636159,0.000121238365,0.0005492621],"category_scores_gemma":[0.0001352414,0.000083114384,0.00018504217,0.00055093004,0.00013664899,0.0001612608,0.000120166704,0.0001880366,0.00013187969],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0040707993,0.00070428965,0.008367193,0.00030386046,0.00096641574,0.000014471592,0.20580596,0.02538416,0.020698788,0.041046083,0.078513004,0.61412495],"study_design_scores_gemma":[0.0017683479,0.00024149498,0.38456646,0.00016886281,0.00033301266,0.000003983485,0.3128485,0.11899214,0.0007004776,0.0774883,0.10211294,0.00077548303],"about_ca_topic_score_codex":0.000075233336,"about_ca_topic_score_gemma":0.003143533,"teacher_disagreement_score":0.6133495,"about_ca_system_score_codex":0.000058557318,"about_ca_system_score_gemma":0.0009540502,"threshold_uncertainty_score":0.6014035},"labels":[],"label_agreement":null},{"id":"W6990861157","doi":"","title":"Enhancing Organizational Capacity for Program Evaluation : The Case of the Neighbourhood Small Grants Program","year":2015,"lang":"en","type":"other","venue":"cIRcle (University of British Columbia)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nucleofection; Gestational period; Hyporeflexia; TSG101; Diafiltration; Fusible alloy; Proteogenomics; Demotion","score_opus":0.09923960213469714,"score_gpt":0.3416589294761918,"score_spread":0.24241932734149468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6990861157","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8350712,0.00060395675,0.0038430125,0.0008635813,0.0021630116,0.020337615,0.0036312803,0.00030355668,0.1331828],"genre_scores_gemma":[0.9328216,0.000031908392,0.007756175,0.000060141443,0.00016905834,0.000048908252,0.0001561076,0.0000969995,0.058859147],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99727494,0.0003765521,0.00033035866,0.0004213684,0.0013948543,0.00020194492],"domain_scores_gemma":[0.9957839,0.00021398427,0.0008907541,0.00061778416,0.002413037,0.00008053252],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0037679577,0.00007673375,0.00033663432,0.00008743452,0.00034975444,0.00019710274,0.0008792178,0.00019448475,0.0021592856],"category_scores_gemma":[0.0008497095,0.00012814243,0.00017644926,0.00093438016,0.0003800608,0.00014272104,0.00017216672,0.0001540401,0.000017823726],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000049364057,0.00023794278,0.0017323241,0.000053803542,0.000060023678,0.0000052965206,0.0003641615,0.000019607673,0.000008315416,0.000008283037,0.07792545,0.91957986],"study_design_scores_gemma":[0.004984793,0.00070373964,0.74452585,0.00087093946,0.000797747,0.0004159177,0.010447716,0.0204082,0.0000058937044,0.0075425343,0.20855291,0.00074373075],"about_ca_topic_score_codex":0.02913943,"about_ca_topic_score_gemma":0.7879437,"teacher_disagreement_score":0.9188361,"about_ca_system_score_codex":0.00010198567,"about_ca_system_score_gemma":0.0010401282,"threshold_uncertainty_score":0.9987529},"labels":[],"label_agreement":null},{"id":"W6999380743","doi":"","title":"Challenges in impact evaluation of development interventions: randomized experiments and complexity","year":2011,"lang":"en","type":"book-chapter","venue":"Data Archiving and Networked Services (DANS)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Law Foundation of Nova Scotia","funders":"","keywords":"Impact evaluation; Evaluation methods; Process (computing); Control (management); Key (lock)","score_opus":0.6836757005384365,"score_gpt":0.5204478704930091,"score_spread":0.1632278300454274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6999380743","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32781532,0.08610708,0.0025153628,0.00035049886,0.0010304648,0.0050221984,0.0007323637,0.00009019004,0.5763365],"genre_scores_gemma":[0.9762996,0.015448502,0.0025726738,0.00005849564,0.00011053977,0.00009365611,0.0017549376,0.000042730986,0.0036188762],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9951913,0.00080634176,0.0014633688,0.0008027804,0.0015145454,0.00022169047],"domain_scores_gemma":[0.99676263,0.0009153723,0.0009209788,0.0010656951,0.00022328056,0.00011203859],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019080624,0.0003366753,0.0009772329,0.0004382812,0.0001333638,0.00010593383,0.001032798,0.000114609,0.0006678312],"category_scores_gemma":[0.00010679589,0.00023829773,0.00012428757,0.000070120506,0.00024614198,0.00057523017,0.0010350554,0.00022440165,0.00001678609],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0044518495,0.00018338693,0.003406048,0.0005721022,0.000587622,0.0000024305937,0.026619691,0.00034531267,0.000012099894,0.011382844,0.00013861487,0.952298],"study_design_scores_gemma":[0.054750975,0.0002639183,0.19051239,0.010118847,0.00074082165,0.000024367826,0.0038594129,0.48310754,0.000023363431,0.24428312,0.01095331,0.0013619476],"about_ca_topic_score_codex":0.00018215066,"about_ca_topic_score_gemma":0.004033999,"teacher_disagreement_score":0.950936,"about_ca_system_score_codex":0.00005727478,"about_ca_system_score_gemma":0.00019062849,"threshold_uncertainty_score":0.9717499},"labels":[],"label_agreement":null},{"id":"W7006808003","doi":"","title":"What Can Systems Thinkers Learn From an Evaluation Mindset? | Cameron D Norman + Tara Campbell | Systems Thinking Ontario 20240212","year":2024,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mindset; Conversation; Systems thinking; Function (biology); Field (mathematics); Work (physics); Session (web analytics); Variety (cybernetics)","score_opus":0.04030312769892575,"score_gpt":0.31085100277445826,"score_spread":0.2705478750755325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7006808003","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015109475,0.003357574,0.0000023227126,0.00029556657,0.008317232,0.0018397542,0.0003868955,0.00021517157,0.98407453],"genre_scores_gemma":[0.007076929,0.0002682065,0.0001993563,0.00038577573,0.0006272605,0.00010722448,0.0014175563,0.0001859397,0.9897317],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99001676,0.00082417345,0.0022396678,0.0008057673,0.0055811787,0.0005324316],"domain_scores_gemma":[0.9948719,0.0003712564,0.002093905,0.001346125,0.0010106236,0.00030620254],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.005726339,0.0006956219,0.0009926038,0.00045579026,0.00020897678,0.002537013,0.0012521734,0.00078009133,0.3425603],"category_scores_gemma":[0.00025961842,0.0005819444,0.0002708362,0.00005967973,0.00014972268,0.000010026744,0.00020112596,0.000814495,0.04098291],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051106083,0.000043818833,0.000048238584,0.00023050512,0.00016306751,0.000012393938,0.0067721726,0.016934961,2.2369677e-7,0.0000439649,0.9730881,0.0026114872],"study_design_scores_gemma":[0.0005952808,0.00022044011,0.000043699758,0.0012784387,0.00028012754,0.00003788209,0.011372292,0.008690003,0.0000014386409,0.0000874315,0.9767737,0.00061928557],"about_ca_topic_score_codex":0.38511294,"about_ca_topic_score_gemma":0.36064428,"teacher_disagreement_score":0.3015774,"about_ca_system_score_codex":0.00077789044,"about_ca_system_score_gemma":0.00069680746,"threshold_uncertainty_score":0.9996632},"labels":[],"label_agreement":null},{"id":"W7009757821","doi":"","title":"Exploring, Understanding, and Determining the Quality of Plan Monitoring and Evaluation in Ontario","year":2021,"lang":"en","type":"dissertation","venue":"UWSpace (University of Waterloo)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Regional Municipality of Waterloo","funders":"","keywords":"Plan (archaeology); Quality (philosophy); Stakeholder; Government (linguistics); Context (archaeology); Monitoring and evaluation; Stakeholder engagement; Resource (disambiguation); Audit; Strategic planning","score_opus":0.4994839631211118,"score_gpt":0.41814183919995573,"score_spread":0.08134212392115608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7009757821","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9985993,0.000072731746,0.0000059326617,0.0001505707,0.00027744504,0.00019961307,0.000003793249,0.000003559155,0.00068703404],"genre_scores_gemma":[0.9809132,0.00014739456,0.00020949791,0.0000021177154,0.000009571462,9.60647e-7,0.00004066161,0.000004604711,0.018671952],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9977619,0.00031300186,0.0002960051,0.0002976908,0.0012170504,0.00011434353],"domain_scores_gemma":[0.9985463,0.00035684308,0.0004770224,0.00024114063,0.00033904167,0.00003964455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037320615,0.00011665601,0.0003250884,0.0002883691,0.00016318593,0.000057539444,0.0002132292,0.00008976178,0.00021802199],"category_scores_gemma":[0.00015766415,0.00009988713,0.000051984818,0.0002046621,0.000072872004,0.00048326785,0.00007043233,0.00019902962,0.0000013829579],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000082391154,0.000024460718,0.61293817,0.000051368985,0.00002551078,0.0000012504808,0.37753072,0.000074766445,0.00028199906,0.00021440134,0.000017901648,0.008757045],"study_design_scores_gemma":[0.00042893612,0.00003276678,0.61012214,0.00011787231,0.000029024903,1.860083e-7,0.38831317,0.00030160166,0.00017377024,0.00038698455,0.00002509791,0.000068457535],"about_ca_topic_score_codex":0.12392166,"about_ca_topic_score_gemma":0.8457583,"teacher_disagreement_score":0.7218366,"about_ca_system_score_codex":0.00021882806,"about_ca_system_score_gemma":0.00030878774,"threshold_uncertainty_score":0.88191223},"labels":[],"label_agreement":null},{"id":"W7013214153","doi":"","title":"9781000862577.pdf","year":2023,"lang":"en","type":"other","venue":"OAPEN (The OAPEN Foundation)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Audit; Discipline; Field (mathematics); Performance audit","score_opus":0.19467835210603698,"score_gpt":0.4914896753800274,"score_spread":0.2968113232739904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7013214153","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000029485385,0.000002260637,0.0007845349,0.0050049652,0.0030659286,0.0008075008,3.144806e-8,0.00045594166,0.9898493],"genre_scores_gemma":[0.0009904015,0.00021172555,0.00037104133,0.0012049109,0.0009558502,0.00017738044,0.00013466814,0.0005468021,0.9954072],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9940767,0.00042587798,0.0009291162,0.0008244339,0.0033141586,0.00042965732],"domain_scores_gemma":[0.9955071,0.0013480041,0.00092957844,0.0017750144,0.0003003002,0.00013995597],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0046728817,0.00040004737,0.0005149985,0.0006090452,0.00043551528,0.0010898461,0.002107568,0.00022532283,0.97792],"category_scores_gemma":[0.0010915839,0.00025234674,0.00024865853,0.0014703242,0.000206147,0.00046102362,0.0003505676,0.00039224935,0.997096],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000066866833,0.000023834624,0.0005976311,0.0000049131067,0.000059287395,0.0000026298965,0.00009133737,0.000027196822,0.0000033161596,0.0020767397,0.06316729,0.93393916],"study_design_scores_gemma":[0.00032829196,0.00003472695,0.003560441,0.00005933242,0.000048190766,0.000005342028,0.00023450662,0.0007541306,0.0000068623062,0.0046828613,0.98995084,0.00033446148],"about_ca_topic_score_codex":0.0002887435,"about_ca_topic_score_gemma":0.0027024054,"teacher_disagreement_score":0.93360466,"about_ca_system_score_codex":0.00015119313,"about_ca_system_score_gemma":0.00053358456,"threshold_uncertainty_score":0.99999285},"labels":[],"label_agreement":null},{"id":"W7017813798","doi":"","title":"Call for candidates to serve on technical evaluation standing committee","year":2011,"lang":"en","type":"article","venue":"NPARC","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Work (physics); Key (lock); Set (abstract data type); Government (linguistics)","score_opus":0.4095398986294603,"score_gpt":0.51388646688431,"score_spread":0.10434656825484967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7017813798","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6001434,0.000011591809,0.0305196,0.006030597,0.0007862031,0.0020721701,0.00006374032,0.00009021364,0.36028254],"genre_scores_gemma":[0.9859552,0.0000015323509,0.011522419,0.0010753503,0.000061528895,0.00019959538,0.000009822557,0.000007568215,0.0011669901],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974419,0.00013837886,0.00038112368,0.0002960039,0.0015478849,0.00019471884],"domain_scores_gemma":[0.9983043,0.00054784777,0.00010488265,0.00040924866,0.0005221422,0.00011159973],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0070054745,0.00009116744,0.00014908402,0.00018916062,0.00015868203,0.00008452638,0.00037804566,0.000053081014,0.0050623287],"category_scores_gemma":[0.001416456,0.000064927786,0.00005950587,0.00032784502,0.000023640176,0.00016762958,0.000055151682,0.00007768901,0.0005511798],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000903604,0.00040575804,0.058238942,0.00001510797,0.00003769244,0.0000019050493,0.0055807293,0.0005925508,0.020826092,0.06876191,0.4878442,0.3567915],"study_design_scores_gemma":[0.0034710316,0.0029292705,0.2324121,0.00011709833,0.000093312294,0.0000061041706,0.0016218404,0.12661733,0.035067014,0.43936396,0.15753572,0.0007652417],"about_ca_topic_score_codex":0.000012573241,"about_ca_topic_score_gemma":0.0002746479,"teacher_disagreement_score":0.38581184,"about_ca_system_score_codex":0.00013791854,"about_ca_system_score_gemma":0.00014178005,"threshold_uncertainty_score":0.99584717},"labels":[],"label_agreement":null},{"id":"W7019046283","doi":"","title":"Evaluation of educational personnel","year":2021,"lang":"en","type":"book","venue":"State Library's electronic repository (State Library of Massachusetts)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Harvard Graduate School of Education; Killam Trusts; Dartmouth College","keywords":"Data collection; Program evaluation; Research methodology; Work (physics)","score_opus":0.0457833517174659,"score_gpt":0.33906735071569427,"score_spread":0.2932839989982284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7019046283","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031499323,0.012074023,0.000069981186,0.00468879,0.0016009817,0.0015366176,0.0006422432,0.00013218723,0.9477559],"genre_scores_gemma":[0.04422163,0.0016745471,0.0008707478,0.00035774143,0.00053049915,0.00011327994,0.0019910058,0.00021391133,0.95002663],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.982196,0.0026652531,0.00352804,0.0016429168,0.009005411,0.0009623954],"domain_scores_gemma":[0.9903951,0.0021880975,0.0036859917,0.0021982726,0.0011984304,0.00033407996],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004604776,0.00085986557,0.0015833923,0.0012749583,0.00029909535,0.0006226739,0.0023011582,0.00043233158,0.022730347],"category_scores_gemma":[0.00038111123,0.0007787478,0.00085248315,0.0011952001,0.00045998025,0.005688972,0.00054911943,0.0011454424,0.00016648964],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005270842,0.0007731091,0.010520362,0.0005218857,0.0017062001,0.000027344418,0.0042912746,0.0041655423,0.00081375096,0.024784336,0.921503,0.030366097],"study_design_scores_gemma":[0.0023258834,0.00082633813,0.006130092,0.00067962945,0.0007413258,0.000072776944,0.0006093752,0.006801684,0.01435298,0.46539637,0.50063163,0.001431933],"about_ca_topic_score_codex":0.000011084025,"about_ca_topic_score_gemma":0.000007857568,"teacher_disagreement_score":0.44061202,"about_ca_system_score_codex":0.0003927289,"about_ca_system_score_gemma":0.036656063,"threshold_uncertainty_score":0.99946636},"labels":[],"label_agreement":null},{"id":"W7027719792","doi":"","title":"Defining Quality Planning Outcome Criteria for the City of Calgary","year":2018,"lang":"en","type":"other","venue":"eScholarship@McGill (McGill)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Outcome (game theory); Quality (philosophy); MEDLINE; Data collection; Context (archaeology)","score_opus":0.28979941587665287,"score_gpt":0.4957604781630863,"score_spread":0.20596106228643346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7027719792","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030436499,0.0005411805,0.00016731834,0.000120388664,0.0034874978,0.0013873371,0.0020694102,0.00022815594,0.9615622],"genre_scores_gemma":[0.45296863,0.00008510152,0.014518755,0.0019631826,0.000334703,0.00034527652,0.00016116371,0.00060643966,0.52901673],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99266624,0.0009559026,0.0020820627,0.0010472301,0.0026520288,0.0005965327],"domain_scores_gemma":[0.99119663,0.004127623,0.001977409,0.0017523328,0.0007389274,0.00020708368],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.016990785,0.0005547346,0.0010854857,0.0005314277,0.0009488649,0.00019114054,0.0019498916,0.00055828696,0.014122375],"category_scores_gemma":[0.007769825,0.0003718328,0.0005271738,0.00068435,0.00028595957,0.000412307,0.00048389452,0.0006022433,0.0009420826],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007032685,0.0004924067,0.038363446,0.0006429258,0.0009593902,0.000014029338,0.00008424495,0.000055929497,0.0020338227,0.5072054,0.026355833,0.42308927],"study_design_scores_gemma":[0.00088323996,0.000152456,0.009838447,0.0002303604,0.0001062113,0.000005239737,0.00020960558,0.00035216904,0.0009516207,0.01687156,0.9698354,0.0005637085],"about_ca_topic_score_codex":0.00044858363,"about_ca_topic_score_gemma":0.00065371074,"teacher_disagreement_score":0.94347954,"about_ca_system_score_codex":0.00019760603,"about_ca_system_score_gemma":0.00011519146,"threshold_uncertainty_score":0.99987334},"labels":[],"label_agreement":null},{"id":"W7029244281","doi":"","title":"Institutional evaluation in Québec : an interpretation of organizational response to policy approaches in the context of Marianopolis College","year":2006,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Interpretation (philosophy); Context (archaeology)","score_opus":0.09906475015931117,"score_gpt":0.3926011583333659,"score_spread":0.29353640817405474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7029244281","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96974665,0.000050537037,0.000003558728,0.00041412807,0.00030831288,0.0014782264,0.0011784208,0.0000138258465,0.026806356],"genre_scores_gemma":[0.99645346,0.000006743059,0.0003854032,0.00035659966,0.000033358694,0.0002414002,0.0012969137,0.00003472405,0.0011913701],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9888904,0.0035108952,0.002323012,0.0007811643,0.004182001,0.0003125316],"domain_scores_gemma":[0.99420327,0.0017533178,0.0011449333,0.0007613648,0.002029836,0.00010725797],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0182241,0.0003792209,0.0006584862,0.0032631345,0.00032656675,0.00007897967,0.0012089902,0.00038582183,0.0005236114],"category_scores_gemma":[0.013430776,0.0003115688,0.00015371991,0.0048770974,0.00011590715,0.0011421615,0.00008152414,0.0005312279,0.00006034862],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0068063075,0.0018344383,0.0066923886,0.00015650893,0.00008769885,0.000009158138,0.0030668015,0.030496838,0.016886944,0.63565326,0.000051349136,0.29825827],"study_design_scores_gemma":[0.006342245,0.0011471952,0.76316744,0.0008765402,0.00019068744,0.000024878043,0.040246777,0.033071995,0.02569601,0.11464666,0.013134377,0.0014552141],"about_ca_topic_score_codex":0.009671332,"about_ca_topic_score_gemma":0.21764053,"teacher_disagreement_score":0.75647503,"about_ca_system_score_codex":0.0016252489,"about_ca_system_score_gemma":0.003113175,"threshold_uncertainty_score":0.99993366},"labels":[],"label_agreement":null},{"id":"W7029980422","doi":"","title":"LEARNING ORIENTED EVALUATION OF RECONSTRUCTION PROJECTS","year":2015,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Agency (philosophy); International development; Evaluation methods; Program evaluation; Logical framework; Development (topology)","score_opus":0.5283726822471702,"score_gpt":0.5490025448266078,"score_spread":0.020629862579437663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7029980422","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8718682,0.00001618891,0.0021102675,0.00020446006,0.00045279987,0.00018575959,2.7682017e-7,0.000020695168,0.12514138],"genre_scores_gemma":[0.9952681,0.000002344144,0.0021384044,0.00002618126,0.000033755867,0.000011980602,0.000003055086,0.0000023125654,0.0025138787],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959444,0.00048647795,0.00040725546,0.0001683825,0.0029160227,0.00007748132],"domain_scores_gemma":[0.9963426,0.00013596001,0.00024192635,0.00018519211,0.003039373,0.000054929365],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016497957,0.00004707626,0.000101983096,0.00015174731,0.000044396307,0.000035496625,0.00010649789,0.000031323183,0.0021980344],"category_scores_gemma":[0.00485785,0.000031841577,0.000029025097,0.0006263631,0.00003210511,0.00041511588,0.000025860341,0.0000610682,0.00025524953],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024278454,0.00003058911,0.10879211,0.0000011937329,0.0000064470387,5.0097285e-8,0.0017489657,0.010347776,0.00030491262,0.0015933132,0.0019720178,0.87517834],"study_design_scores_gemma":[0.0012816252,0.00028557758,0.021708589,0.000011324296,0.000022185313,0.000008535099,0.020065347,0.9379533,0.0036710438,0.007897202,0.007004026,0.00009126765],"about_ca_topic_score_codex":0.000025325913,"about_ca_topic_score_gemma":0.000025288566,"teacher_disagreement_score":0.9276055,"about_ca_system_score_codex":0.00007029068,"about_ca_system_score_gemma":0.0006095521,"threshold_uncertainty_score":0.9987141},"labels":[],"label_agreement":null},{"id":"W7038543484","doi":"","title":"Joint External Evaluation of the Health Sector in Tanzania:1999-2006","year":2007,"lang":"en","type":"other","venue":"IHI Repository","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Private sector; Health sector; Government (linguistics); Public sector; Declaration; Christian ministry; Joint (building); Government sector; Strategic planning","score_opus":0.19087307184741675,"score_gpt":0.47423233727418923,"score_spread":0.2833592654267725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7038543484","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013896015,0.0049347356,0.0005464859,0.00035795692,0.0048425086,0.0011301476,0.000021283517,0.000036803427,0.97423404],"genre_scores_gemma":[0.2874645,0.00006925731,0.0006571429,0.0007457645,0.0010546056,0.00008324976,0.0000057575376,0.00013803763,0.7097817],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99199307,0.0010842746,0.0011806866,0.00042019124,0.005094736,0.00022703105],"domain_scores_gemma":[0.99699515,0.00015888276,0.0014852667,0.00094324554,0.00034562696,0.00007184907],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.012436093,0.00018320877,0.00041445147,0.0006912037,0.00007958141,0.00006430848,0.0005782569,0.00019160927,0.004539354],"category_scores_gemma":[0.00031485598,0.000115043345,0.00015992376,0.0006500135,0.00008937879,0.00007426509,0.00008842094,0.00028144225,0.00011890992],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033603075,0.00023500744,0.051053632,0.00006710903,0.00003876726,0.0000049112405,0.0011762099,0.00081720937,0.0008433262,0.00044595762,0.8634121,0.081872195],"study_design_scores_gemma":[0.0016443213,0.00019493776,0.49243334,0.0013016571,0.000057866717,0.000037128728,0.00046330248,0.008665145,0.0018781915,0.0017727244,0.4911139,0.0004374852],"about_ca_topic_score_codex":0.0011018568,"about_ca_topic_score_gemma":0.0015082572,"teacher_disagreement_score":0.44137973,"about_ca_system_score_codex":0.00041156754,"about_ca_system_score_gemma":0.0015840319,"threshold_uncertainty_score":0.9963706},"labels":[],"label_agreement":null},{"id":"W7093678278","doi":"","title":"9781000862577.pdf","year":2023,"lang":"en","type":"other","venue":"OAPEN (The OAPEN Foundation)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Audit; Discipline; Field (mathematics); Performance audit","score_opus":0.19467835210603698,"score_gpt":0.4914896753800274,"score_spread":0.2968113232739904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7093678278","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000029485385,0.000002260637,0.0007845349,0.0050049652,0.0030659286,0.0008075008,3.144806e-8,0.00045594166,0.9898493],"genre_scores_gemma":[0.0009904015,0.00021172555,0.00037104133,0.0012049109,0.0009558502,0.00017738044,0.00013466814,0.0005468021,0.9954072],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9940767,0.00042587798,0.0009291162,0.0008244339,0.0033141586,0.00042965732],"domain_scores_gemma":[0.9955071,0.0013480041,0.00092957844,0.0017750144,0.0003003002,0.00013995597],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0046728817,0.00040004737,0.0005149985,0.0006090452,0.00043551528,0.0010898461,0.002107568,0.00022532283,0.97792],"category_scores_gemma":[0.0010915839,0.00025234674,0.00024865853,0.0014703242,0.000206147,0.00046102362,0.0003505676,0.00039224935,0.997096],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000066866833,0.000023834624,0.0005976311,0.0000049131067,0.000059287395,0.0000026298965,0.00009133737,0.000027196822,0.0000033161596,0.0020767397,0.06316729,0.93393916],"study_design_scores_gemma":[0.00032829196,0.00003472695,0.003560441,0.00005933242,0.000048190766,0.000005342028,0.00023450662,0.0007541306,0.0000068623062,0.0046828613,0.98995084,0.00033446148],"about_ca_topic_score_codex":0.0002887435,"about_ca_topic_score_gemma":0.0027024054,"teacher_disagreement_score":0.93360466,"about_ca_system_score_codex":0.00015119313,"about_ca_system_score_gemma":0.00053358456,"threshold_uncertainty_score":0.99999285},"labels":[],"label_agreement":null},{"id":"W7095416598","doi":"","title":"200 Promenade du Portage","year":2013,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Corporate governance; Training manual; Continuing education; Program evaluation; Humanitarian aid","score_opus":0.19540565360148232,"score_gpt":0.4911614278935469,"score_spread":0.29575577429206457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7095416598","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5232814,0.000007875743,0.0016624546,0.00943479,0.00019438985,0.00020995582,6.241946e-7,0.000035824236,0.46517268],"genre_scores_gemma":[0.8911075,0.0000048714946,0.0009996992,0.0018932064,0.000058098743,0.00003443858,0.0000014114017,0.0000026783293,0.10589808],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99830925,0.00004474258,0.0003108939,0.00017503022,0.0010255176,0.00013456514],"domain_scores_gemma":[0.99915016,0.00014076917,0.00007183772,0.00030188594,0.00024985592,0.00008549526],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0014659245,0.000055057873,0.00008558678,0.00008884408,0.00007461593,0.00023264076,0.0002848974,0.000023373643,0.2063398],"category_scores_gemma":[0.00024281676,0.000031170406,0.000034057764,0.0002706646,0.000022254277,0.0005588608,0.00004252573,0.000043511234,0.0270439],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002050073,0.00006534533,0.12254937,0.0000012075309,0.0000062875774,0.0000013061878,0.00043511388,0.000056646404,0.0007885523,0.01721097,0.7844401,0.07444305],"study_design_scores_gemma":[0.00034285526,0.0000734657,0.5807014,0.000002539152,0.0000024924748,0.0000049653418,0.0015419769,0.027606674,0.00095643784,0.022559341,0.36604732,0.00016052346],"about_ca_topic_score_codex":0.000064435364,"about_ca_topic_score_gemma":0.000035679677,"teacher_disagreement_score":0.45815206,"about_ca_system_score_codex":0.000014056362,"about_ca_system_score_gemma":0.000076403965,"threshold_uncertainty_score":0.97371364},"labels":[],"label_agreement":null},{"id":"W7095642491","doi":"","title":"A Programme Evaluation","year":2003,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Outreach; Sign (mathematics); Maturity (psychological); Quality (philosophy); Order (exchange); Quarter (Canadian coin)","score_opus":0.5754246966741686,"score_gpt":0.5959343108301943,"score_spread":0.0205096141560257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7095642491","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14365996,0.000041169904,0.009676112,0.0012317222,0.00033561114,0.00035222122,2.662468e-7,0.00003517298,0.84466773],"genre_scores_gemma":[0.98401916,0.0000017030422,0.004566868,0.0004818548,0.000016056474,0.000046750953,0.0000013810003,0.0000022515924,0.010863968],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99684966,0.0003146832,0.0002801996,0.00018582559,0.0022320868,0.0001375468],"domain_scores_gemma":[0.99878275,0.00020180337,0.000068399604,0.00029330642,0.0005928155,0.00006093841],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.013875443,0.000046770023,0.000067258625,0.000095715266,0.00007463412,0.00016127888,0.00014411304,0.000022572733,0.03742069],"category_scores_gemma":[0.0030315456,0.000028708248,0.000037640755,0.00048456356,0.000017257767,0.00024347048,0.000009717981,0.000035542114,0.0028786103],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000033528197,0.00007556929,0.037241634,5.505285e-7,0.000005066059,2.1782286e-7,0.00030942724,0.00030643566,0.00012057384,0.16749871,0.01535025,0.7790882],"study_design_scores_gemma":[0.0007877762,0.00008229836,0.028841631,0.0000018981916,0.000010304698,0.000005327382,0.0017465675,0.05846166,0.0013393328,0.15046696,0.7581251,0.00013111823],"about_ca_topic_score_codex":0.0000037972993,"about_ca_topic_score_gemma":0.000039501632,"teacher_disagreement_score":0.8403592,"about_ca_system_score_codex":0.000035528887,"about_ca_system_score_gemma":0.00027238333,"threshold_uncertainty_score":0.99789774},"labels":[],"label_agreement":null},{"id":"W7095718531","doi":"","title":"Canadian Evaluation Society Member Services Committee","year":2006,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Work (physics); Legislation; Agency (philosophy)","score_opus":0.16513206292997412,"score_gpt":0.47803072799845464,"score_spread":0.3128986650684805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7095718531","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3905315,0.000057859208,0.00035747598,0.009128864,0.0003346411,0.00024664184,0.000007745745,0.000032973257,0.5993023],"genre_scores_gemma":[0.97648096,0.0000028212132,0.0013241419,0.0031790244,0.00012032876,0.000019371591,0.00003761804,0.000004639333,0.018831115],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968887,0.00013919323,0.00037940027,0.00024437523,0.0021331108,0.00021520938],"domain_scores_gemma":[0.9985001,0.00017104446,0.00009727526,0.0003786311,0.00074353704,0.00010942201],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.005942044,0.00008553417,0.0001060135,0.00011085636,0.00026126753,0.0003031868,0.00034965086,0.0000599549,0.034610208],"category_scores_gemma":[0.000035469562,0.000059634607,0.0000874185,0.00048381544,0.000021254978,0.00044571,0.00002925931,0.00006571079,0.0018202333],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003039724,0.000045735902,0.3906456,0.0000046831456,0.000015522746,5.05888e-7,0.0007807178,0.005832749,0.0002114833,0.00854736,0.5435482,0.05036441],"study_design_scores_gemma":[0.0003462235,0.000012469878,0.27331668,0.0000033208403,0.000013155869,0.0000013427364,0.0014737112,0.3117198,0.00017887176,0.025333835,0.38747218,0.00012840264],"about_ca_topic_score_codex":0.17721696,"about_ca_topic_score_gemma":0.79887366,"teacher_disagreement_score":0.6216567,"about_ca_system_score_codex":0.00022907252,"about_ca_system_score_gemma":0.00061826804,"threshold_uncertainty_score":0.998957},"labels":[],"label_agreement":null},{"id":"W7096536052","doi":"","title":"Chapter 23 SCIENCE AND TECHNOLOGY EVALUATION PRACTICES IN THE GOVERNMENT OF CANADA","year":2015,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Treasury; Government (linguistics); Audit; Portfolio; Function (biology); Monitoring and evaluation; Set (abstract data type); Perspective (graphical)","score_opus":0.38072300625942684,"score_gpt":0.5261213813158717,"score_spread":0.14539837505644487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7096536052","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8425577,0.000049528793,0.000031765947,0.025571385,0.00010204537,0.00018838175,7.453111e-7,0.0000019707597,0.13149647],"genre_scores_gemma":[0.99903667,0.0000046187415,0.00025450994,0.00041867522,0.0000051440807,0.000010456875,7.817111e-8,6.6893284e-7,0.0002691797],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9925814,0.00008192109,0.00024044758,0.00015887353,0.006846155,0.00009115329],"domain_scores_gemma":[0.99822354,0.00027704693,0.00027508062,0.00025192686,0.00094141194,0.00003096438],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.025699088,0.000034536813,0.00006089692,0.00009684518,0.000057436733,0.000054873715,0.00038149033,0.000013888011,0.00018454406],"category_scores_gemma":[0.008820422,0.000017658866,0.0000032346052,0.0008437494,0.00014595997,0.0003639586,0.000069302325,0.000045100245,0.0000039654246],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041433796,0.00010964757,0.43528244,0.0000035282933,0.000005459104,0.0000020436996,0.004575479,0.0006550895,0.0020763362,0.16818707,0.0115043875,0.3775571],"study_design_scores_gemma":[0.0014745159,0.0003223114,0.4134622,0.000016192154,0.00001764941,0.000021211701,0.12792057,0.31485847,0.0068568685,0.048101086,0.086743645,0.00020531779],"about_ca_topic_score_codex":0.007542141,"about_ca_topic_score_gemma":0.22730584,"teacher_disagreement_score":0.37735176,"about_ca_system_score_codex":0.0001540019,"about_ca_system_score_gemma":0.0020510904,"threshold_uncertainty_score":0.9995287},"labels":[],"label_agreement":null},{"id":"W7097534327","doi":"","title":"THINGS TO CONSIDER WHEN SELECTING AN EXTERNAL EVALUATOR","year":2014,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Order (exchange); Service provider; Service (business); Christian ministry; Best practice; Field (mathematics)","score_opus":0.23041667915819927,"score_gpt":0.5285214318426604,"score_spread":0.2981047526844611,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7097534327","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7802977,0.000006703815,0.12854142,0.004844579,0.00043366593,0.0001993333,4.9510015e-7,0.00008238294,0.08559373],"genre_scores_gemma":[0.928742,3.3770556e-7,0.04652016,0.015145066,0.00017324994,0.000010978736,5.57911e-7,0.000007231418,0.009400407],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99668425,0.00035311814,0.00044670957,0.0003771937,0.0019181576,0.00022059081],"domain_scores_gemma":[0.9979238,0.00071900425,0.000112065725,0.00045326506,0.0005683361,0.00022352592],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.011058042,0.000097026415,0.00015637995,0.00016454015,0.00019953157,0.00045918138,0.00043310653,0.000037755508,0.017723558],"category_scores_gemma":[0.002602396,0.00006434834,0.00004268402,0.00026436674,0.000019960618,0.0008776503,0.00008358263,0.00009775286,0.003203199],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050628245,0.00011054969,0.11755138,0.0000035289906,0.000015006397,0.0000012189196,0.012870171,0.0016145629,0.012608234,0.03385177,0.073531196,0.74779177],"study_design_scores_gemma":[0.0010899539,0.0007175842,0.085705176,0.000029973438,0.000018908482,0.000025952068,0.0033016277,0.49752405,0.009840991,0.17303911,0.22816247,0.0005442103],"about_ca_topic_score_codex":0.00006902907,"about_ca_topic_score_gemma":0.00014182272,"teacher_disagreement_score":0.7472475,"about_ca_system_score_codex":0.000034032582,"about_ca_system_score_gemma":0.00014378833,"threshold_uncertainty_score":0.9975729},"labels":[],"label_agreement":null},{"id":"W7097735947","doi":"","title":"Some Thoughts about the Evolution of Evaluators ’ Methodological Identity Presented at the Canadian Evaluation Society","year":2006,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Identity (music); TRACE (psycholinguistics); Generative grammar; Character (mathematics); Work (physics); Portrait","score_opus":0.41657650733531787,"score_gpt":0.5515349013725962,"score_spread":0.13495839403727833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7097735947","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9503591,0.001365241,0.008017292,0.015345674,0.0011323852,0.0014434318,0.000023359593,0.000032583714,0.022280917],"genre_scores_gemma":[0.98984766,0.000020757941,0.0008576031,0.0005001501,0.00044717162,0.00006983662,0.000016291826,0.0000053572517,0.008235167],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9903103,0.0031056355,0.00080991804,0.00037936357,0.0050873677,0.00030742734],"domain_scores_gemma":[0.99505806,0.0021655143,0.0005276292,0.00078019087,0.0013852925,0.00008329157],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.04909318,0.00013508816,0.00020922103,0.000109693494,0.001140077,0.00023067038,0.00084745674,0.00012335277,0.0031289204],"category_scores_gemma":[0.002964184,0.00005759697,0.00026758353,0.0010323917,0.00035976613,0.0006994226,0.00015472417,0.00017407381,0.00026685736],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007694919,0.00019283517,0.3006949,0.000011463703,0.00014041307,5.899992e-7,0.002282766,0.053146772,0.0029125316,0.229204,0.3920016,0.019335147],"study_design_scores_gemma":[0.0003366912,0.000028896942,0.6627228,0.000003873796,0.000060399132,0.0000022456043,0.0012322601,0.17053714,0.00079864514,0.15376987,0.01041717,0.00008998511],"about_ca_topic_score_codex":0.09164134,"about_ca_topic_score_gemma":0.65580875,"teacher_disagreement_score":0.5641674,"about_ca_system_score_codex":0.0011514855,"about_ca_system_score_gemma":0.0014323571,"threshold_uncertainty_score":0.99778235},"labels":[],"label_agreement":null},{"id":"W7097840005","doi":"","title":"The Innovation Journal: The Public Sector Innovation Journal, Vol. 10(2), article 22. What do lawyers think about judicial evaluation? Responses to the Nova Scotia Judicial Development Project 1","year":2010,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nova scotia; Judicial independence; Judicial review; Independence (probability theory); Judicial discretion; Judicial activism; Judicial opinion; Public sector","score_opus":0.23668501687766938,"score_gpt":0.48374553129316805,"score_spread":0.24706051441549867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7097840005","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88605493,0.00019738081,0.0028544373,0.09600086,0.010356119,0.0015617739,0.0000026452683,0.00004452974,0.0029273499],"genre_scores_gemma":[0.98571473,0.00009111227,0.0014835029,0.007672449,0.0022305015,0.00007846172,0.000009322618,0.000027822549,0.0026920761],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98749185,0.001727893,0.002525825,0.0004804472,0.0071149343,0.000659045],"domain_scores_gemma":[0.97765464,0.0022965162,0.0015028889,0.0010028151,0.017422087,0.0001210317],"candidate_categories":["metaresearch","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.084790684,0.00029651867,0.00026458802,0.001189956,0.004337505,0.012062988,0.0019635095,0.00014718654,0.009358079],"category_scores_gemma":[0.030485114,0.00012761234,0.000102078084,0.00886877,0.00028706426,0.0033323234,0.00025667073,0.0011853575,0.0012965187],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034351664,0.000120724035,0.00610049,0.0000015826255,0.00010153976,0.0000014490106,0.008253937,0.00023639631,0.0022069002,0.022762766,0.43262914,0.5272415],"study_design_scores_gemma":[0.0012368629,0.00023361904,0.09437307,0.00005539623,0.00004603075,0.00012011518,0.019706916,0.0065414566,0.0021196073,0.017559897,0.8576342,0.0003728269],"about_ca_topic_score_codex":0.000035331075,"about_ca_topic_score_gemma":0.0030208693,"teacher_disagreement_score":0.5268687,"about_ca_system_score_codex":0.00031891366,"about_ca_system_score_gemma":0.006243459,"threshold_uncertainty_score":0.9994811},"labels":[],"label_agreement":null},{"id":"W7098019678","doi":"","title":"Performance Evaluation","year":2012,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Work (physics); Agency (philosophy); Government (linguistics); Standardization; Process (computing)","score_opus":0.46589102026953044,"score_gpt":0.5723225181133982,"score_spread":0.10643149784386774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7098019678","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6389908,0.000037805905,0.0005264459,0.00042111473,0.00046521975,0.00009881362,2.319527e-7,0.00001799776,0.35944158],"genre_scores_gemma":[0.9907111,0.00000788495,0.00093411125,0.0005200183,0.00016599218,0.000022701832,0.0000025870474,0.0000027916842,0.007632835],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9968592,0.00014249867,0.00029298064,0.00011935119,0.002393479,0.00019247341],"domain_scores_gemma":[0.99892056,0.00018284532,0.00008066036,0.00031847917,0.0004073065,0.000090126014],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.013159265,0.000055057313,0.00007327874,0.00011478869,0.00010594206,0.00006699357,0.00020858538,0.000025732508,0.036837086],"category_scores_gemma":[0.00053861644,0.000034128563,0.000032224933,0.00038201315,0.000018493,0.0011571951,0.000035712877,0.000044520613,0.008809759],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003222326,0.000030915748,0.5027491,3.951899e-7,0.0000020616285,7.1950557e-9,0.00032792464,0.00022693018,0.00010085273,0.002206806,0.010288876,0.48406294],"study_design_scores_gemma":[0.00019750478,0.000022161421,0.7565195,0.0000014103338,0.0000059111426,0.0000018855636,0.00033758793,0.1538475,0.000869799,0.00047892856,0.087645486,0.000072322066],"about_ca_topic_score_codex":0.0000022326408,"about_ca_topic_score_gemma":0.0000032604844,"teacher_disagreement_score":0.4839906,"about_ca_system_score_codex":0.00004391667,"about_ca_system_score_gemma":0.00008795635,"threshold_uncertainty_score":0.991962},"labels":[],"label_agreement":null},{"id":"W7098439777","doi":"","title":"Toward a Livable Region? An Evaluation of Business Parks in Greater Vancouver ii","year":2004,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Metropolitan area; Space (punctuation); Urban planning; Land use; Industrial park; Central business district; Business development; Land-use planning; City region","score_opus":0.3652001363785243,"score_gpt":0.4789006881012861,"score_spread":0.11370055172276183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7098439777","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9638918,0.000021411237,0.005144282,0.0011102371,0.00037581436,0.000305166,8.5722894e-7,0.000016117934,0.029134294],"genre_scores_gemma":[0.9967412,0.000008798428,0.0013101664,0.00028735894,0.00003360675,0.000030482213,0.0000033653077,0.0000050306794,0.0015800449],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9964334,0.00020094262,0.00059427327,0.00031063758,0.0023013619,0.0001594165],"domain_scores_gemma":[0.99772555,0.00006257016,0.00017561772,0.00046554997,0.0015160223,0.000054669254],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0061022844,0.00009476739,0.0001956138,0.00031414992,0.00006289665,0.00004606995,0.00030254855,0.00006302727,0.003511892],"category_scores_gemma":[0.00045286948,0.00006316247,0.000037485468,0.0010745525,0.000042081978,0.0009381771,0.00006326277,0.00006126602,0.00007587035],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027820762,0.0014294046,0.20357493,0.000027922062,0.000030946576,0.000010703218,0.019715672,0.50164264,0.00066935725,0.007388784,0.01930426,0.24592716],"study_design_scores_gemma":[0.004651965,0.00032031984,0.80980724,0.0000691597,0.00003324348,0.0000068489267,0.004492802,0.08331702,0.0030677647,0.091559395,0.0023758765,0.00029838225],"about_ca_topic_score_codex":0.00037249277,"about_ca_topic_score_gemma":0.0034448372,"teacher_disagreement_score":0.6062323,"about_ca_system_score_codex":0.00012739592,"about_ca_system_score_gemma":0.0005422708,"threshold_uncertainty_score":0.99739903},"labels":[],"label_agreement":null},{"id":"W7100710741","doi":"","title":"Applied Measurement and Evaluation","year":2013,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mandate; Context (archaeology); Dissemination; Visitor pattern; Feature (linguistics); Quality (philosophy)","score_opus":0.5034063699606537,"score_gpt":0.5200830058869607,"score_spread":0.01667663592630697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7100710741","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46633384,0.00005851094,0.004543543,0.0038995366,0.00015187879,0.00069288566,1.8746621e-7,0.00002619497,0.5242934],"genre_scores_gemma":[0.9970328,0.0000039399724,0.0011323275,0.0006812242,0.000024029157,0.000102913684,6.693772e-7,0.0000018946974,0.0010201825],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.996364,0.00007631361,0.00025053276,0.00018222255,0.0030424893,0.00008446666],"domain_scores_gemma":[0.99870694,0.00008987687,0.000060887785,0.00021111184,0.00087405794,0.000057149453],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.007992229,0.00004876649,0.00007056353,0.0000802466,0.00007385922,0.00021929093,0.00011077017,0.000019449077,0.024567032],"category_scores_gemma":[0.00031274,0.00002951013,0.000013360592,0.00016525807,0.000019915473,0.00025370414,0.000032373177,0.00002892748,0.0029229643],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000022236031,0.000019586587,0.0058507593,8.4956406e-7,0.000004925794,1.25927535e-8,0.0002464531,0.00010563083,0.003134025,0.008470767,0.027779615,0.95438516],"study_design_scores_gemma":[0.0008611035,0.000045748777,0.69906473,0.0000031828076,0.000012943285,0.0000010500675,0.0018466733,0.16205409,0.0018575204,0.10720349,0.026896812,0.00015265244],"about_ca_topic_score_codex":0.000020388854,"about_ca_topic_score_gemma":0.000033164808,"teacher_disagreement_score":0.9542325,"about_ca_system_score_codex":0.000038178303,"about_ca_system_score_gemma":0.000086677006,"threshold_uncertainty_score":0.9978534},"labels":[],"label_agreement":null},{"id":"W7100962767","doi":"","title":":: Acknowledgements and Evaluation Team:: Executive Summary","year":2003,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Executive summary; Foundation (evidence); Publication; Event (particle physics); Scholarship","score_opus":0.2111751000185925,"score_gpt":0.5048663994860585,"score_spread":0.29369129946746597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7100962767","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.122484095,0.00018210842,0.0014902458,0.00024003859,0.00055373326,0.00032152745,0.0000013552709,0.000017624741,0.87470925],"genre_scores_gemma":[0.896214,0.000050018247,0.0019107285,0.0006149698,0.000042546457,0.000041491858,0.0000049609266,0.0000052548653,0.101116],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972912,0.00039967755,0.00031987522,0.00028531346,0.001571272,0.00013266152],"domain_scores_gemma":[0.99812704,0.0003052579,0.000088668305,0.00026563625,0.0011386857,0.00007468191],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008118075,0.00007974061,0.00010818865,0.00014601248,0.00013610684,0.00014331107,0.00013583679,0.000034134282,0.031945027],"category_scores_gemma":[0.0026834793,0.00005374314,0.00002726065,0.00035403465,0.000041673848,0.00042367438,0.00004049911,0.000052074574,0.0029866744],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012110254,0.000093701514,0.109299846,0.0000024330113,0.000019612433,2.44117e-7,0.0009922215,0.00008135256,0.00020937237,0.009073133,0.72166175,0.15855421],"study_design_scores_gemma":[0.0014848094,0.00011253049,0.08078761,0.000011946123,0.000030094321,0.000002732932,0.0043034917,0.03802159,0.002085569,0.06399187,0.80893546,0.00023229196],"about_ca_topic_score_codex":0.0000011837235,"about_ca_topic_score_gemma":0.00004445905,"teacher_disagreement_score":0.7737299,"about_ca_system_score_codex":0.000047076737,"about_ca_system_score_gemma":0.00018447013,"threshold_uncertainty_score":0.9977896},"labels":[],"label_agreement":null},{"id":"W7114892371","doi":"10.2139/ssrn.5792462","title":"Transformation-Focused Evaluation as a Catalyst for Human and Planetary Regeneration","year":2025,"lang":"","type":"preprint","venue":"SSRN Electronic Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Futures contract; Mainstream; Human health; Existentialism; Planetary boundaries; Evaluation methods","score_opus":0.09211849296807614,"score_gpt":0.44224642417701787,"score_spread":0.3501279312089417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7114892371","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.57769704,0.019073237,0.3409542,0.029227072,0.0047787065,0.010784513,0.0003916062,0.00008797171,0.017005613],"genre_scores_gemma":[0.97391236,0.014034396,0.00052089646,0.00034932367,0.0010214859,0.000379734,0.0013125696,0.000028363364,0.008440853],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9890182,0.0011837225,0.002734585,0.0010545462,0.0037049805,0.0023039733],"domain_scores_gemma":[0.9942978,0.00063838006,0.0017012843,0.0007232525,0.002401216,0.00023805827],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.046431012,0.0006452022,0.0008381322,0.0012037744,0.002315613,0.0013052444,0.000922251,0.0005685472,0.0008157132],"category_scores_gemma":[0.00075641327,0.0005690069,0.00043960795,0.0005935694,0.00013376694,0.0013408251,0.0001294158,0.0032901359,0.000075145894],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045875163,0.00013193414,0.00045948257,0.00012805595,0.0007069315,4.891818e-7,0.004474944,0.017500568,0.00046051046,0.16433544,0.00040498946,0.8109379],"study_design_scores_gemma":[0.004990285,0.00120597,0.00092979654,0.00027050753,0.0009865622,0.00018177825,0.0057769865,0.21743989,0.00049223227,0.7557138,0.011338511,0.0006736653],"about_ca_topic_score_codex":0.00034765102,"about_ca_topic_score_gemma":0.009138966,"teacher_disagreement_score":0.8102642,"about_ca_system_score_codex":0.0026914445,"about_ca_system_score_gemma":0.030347876,"threshold_uncertainty_score":0.9997315},"labels":[],"label_agreement":null},{"id":"W7115164373","doi":"10.5281/zenodo.17929417","title":"Partnering for Impact: A Blueprint for Knowledge Translation Initiatives in the Canadian Sport Sector","year":2023,"lang":"","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Blueprint; Knowledge translation; General partnership; Action (physics); Knowledge economy; Best practice; Resource (disambiguation)","score_opus":0.4162401245155329,"score_gpt":0.4646433333149629,"score_spread":0.04840320879943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7115164373","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55377465,0.00075245625,0.03160731,0.028523523,0.0021793249,0.022047881,0.006141255,0.0012508122,0.35372275],"genre_scores_gemma":[0.9961691,0.00014737189,0.00021512568,0.00019039234,0.00027593106,0.0000028058685,0.0018150571,0.00059949304,0.0005847427],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9959837,0.00058257225,0.00085615827,0.0007186861,0.0009818753,0.0008770104],"domain_scores_gemma":[0.99654335,0.00069335697,0.00025521166,0.00064307195,0.0015261978,0.00033882345],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.012461822,0.0002648837,0.0003132282,0.0012326504,0.0046404293,0.0025351618,0.0017577785,0.00014074882,0.009737487],"category_scores_gemma":[0.002583369,0.0002163643,0.0002165039,0.0029261701,0.00019441663,0.0008285071,0.00027677487,0.00034443536,0.004768481],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00063480507,0.00045534954,0.00049194973,0.00034636955,0.0001641322,0.000014338578,0.13284846,0.0069477116,0.0008390943,0.023388676,0.111595444,0.72227365],"study_design_scores_gemma":[0.0013444718,0.00051072665,0.02553737,0.00006706406,0.000023964152,0.00001352101,0.0071565625,0.09970665,0.000082655584,0.001202208,0.86408275,0.00027207658],"about_ca_topic_score_codex":0.00077487674,"about_ca_topic_score_gemma":0.0030802442,"teacher_disagreement_score":0.7524873,"about_ca_system_score_codex":0.00059917924,"about_ca_system_score_gemma":0.00020855389,"threshold_uncertainty_score":0.9985003},"labels":[],"label_agreement":null},{"id":"W7115169282","doi":"10.5281/zenodo.17929415","title":"Partnering for Impact: A Blueprint for Knowledge Translation Initiatives in the Canadian Sport Sector","year":2023,"lang":"","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Blueprint; Knowledge translation; General partnership; Action (physics); Knowledge economy; Best practice; Resource (disambiguation)","score_opus":0.4162401245155329,"score_gpt":0.4646433333149629,"score_spread":0.04840320879943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7115169282","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55377465,0.00075245625,0.03160731,0.028523523,0.0021793249,0.022047881,0.006141255,0.0012508122,0.35372275],"genre_scores_gemma":[0.9961691,0.00014737189,0.00021512568,0.00019039234,0.00027593106,0.0000028058685,0.0018150571,0.00059949304,0.0005847427],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9959837,0.00058257225,0.00085615827,0.0007186861,0.0009818753,0.0008770104],"domain_scores_gemma":[0.99654335,0.00069335697,0.00025521166,0.00064307195,0.0015261978,0.00033882345],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.012461822,0.0002648837,0.0003132282,0.0012326504,0.0046404293,0.0025351618,0.0017577785,0.00014074882,0.009737487],"category_scores_gemma":[0.002583369,0.0002163643,0.0002165039,0.0029261701,0.00019441663,0.0008285071,0.00027677487,0.00034443536,0.004768481],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00063480507,0.00045534954,0.00049194973,0.00034636955,0.0001641322,0.000014338578,0.13284846,0.0069477116,0.0008390943,0.023388676,0.111595444,0.72227365],"study_design_scores_gemma":[0.0013444718,0.00051072665,0.02553737,0.00006706406,0.000023964152,0.00001352101,0.0071565625,0.09970665,0.000082655584,0.001202208,0.86408275,0.00027207658],"about_ca_topic_score_codex":0.00077487674,"about_ca_topic_score_gemma":0.0030802442,"teacher_disagreement_score":0.7524873,"about_ca_system_score_codex":0.00059917924,"about_ca_system_score_gemma":0.00020855389,"threshold_uncertainty_score":0.9985003},"labels":[],"label_agreement":null},{"id":"W7117297943","doi":"10.13140/rg.2.2.32771.57121","title":"Assessing Performance: Evaluation Practices and Perspectives in Canada’s Voluntary Sector. Toronto: Canadian Centre for Philanthropy","year":2015,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Voluntary sector; Work (physics); Agency (philosophy); Quality (philosophy)","score_opus":0.4423259293112935,"score_gpt":0.5129239008530999,"score_spread":0.07059797154180641,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117297943","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9567889,0.000644856,0.00005075707,0.009017165,0.0005320979,0.0005515338,0.000012292156,0.000008650451,0.032393724],"genre_scores_gemma":[0.9978073,0.00006689165,0.0010097015,0.0003669055,0.00011245836,0.000027307622,0.000018581899,0.000007771309,0.00058303494],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99701726,0.00024120999,0.0004092159,0.00040288936,0.0016089826,0.00032042566],"domain_scores_gemma":[0.9976613,0.00046616202,0.00030476652,0.0002412591,0.0010078754,0.00031862126],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0063953493,0.00012989134,0.00019008596,0.00013942485,0.00019654988,0.00036936247,0.0002109822,0.00004710655,0.0027246447],"category_scores_gemma":[0.0019486251,0.00009997195,0.000020368258,0.00021102543,0.000035388934,0.0028232413,0.000029141887,0.00008797767,0.000010890629],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00004314932,0.000031406984,0.8660559,0.000007540587,0.000015612291,0.0000015887956,0.009238797,0.0010552247,0.000016713064,0.00039511983,0.022338329,0.10080062],"study_design_scores_gemma":[0.000800025,0.00004766258,0.46301234,0.000014230952,0.000014243235,0.000004008745,0.20412296,0.3142077,0.000035785197,0.0002517841,0.017334856,0.0001544123],"about_ca_topic_score_codex":0.9938186,"about_ca_topic_score_gemma":0.9999449,"teacher_disagreement_score":0.40304357,"about_ca_system_score_codex":0.003996921,"about_ca_system_score_gemma":0.01972288,"threshold_uncertainty_score":0.99982655},"labels":[],"label_agreement":null},{"id":"W7132878271","doi":"","title":"A Context Evaluation of the OISE Psychology Clinic Adult Psychotherapy Service","year":2022,"lang":"","type":"dissertation","venue":"TSpace","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"De Veber","funders":"","keywords":"Context (archaeology); Service (business); Interpersonal communication; Process (computing); Product (mathematics); Program evaluation","score_opus":0.2890708003664671,"score_gpt":0.6233763669138624,"score_spread":0.33430556654739535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7132878271","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8808079,0.002867442,0.00016419523,0.026040748,0.013312459,0.0036204604,0.00005807994,0.000031369753,0.07309739],"genre_scores_gemma":[0.93175244,0.0032805465,0.00015311646,0.016351806,0.0002182021,0.0008196724,0.00023030957,0.00008152238,0.047112364],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.98146206,0.005344642,0.0025995953,0.0013935759,0.008687328,0.00051278993],"domain_scores_gemma":[0.9840509,0.0012277121,0.0041344906,0.0027906047,0.0076418687,0.00015440758],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.019783817,0.00060200226,0.0009761203,0.000532765,0.0008170131,0.00015366662,0.002798977,0.00050862104,0.25017154],"category_scores_gemma":[0.0012169477,0.0004393143,0.0006442277,0.0035970032,0.00018260349,0.00031677002,0.000088877845,0.0011287164,0.0015628253],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0037377533,0.0018937822,0.008303018,0.00021897933,0.00058274425,0.0000010034389,0.23351523,0.0023908361,0.0037693176,0.0025785754,0.050443474,0.69256526],"study_design_scores_gemma":[0.020660968,0.00216448,0.21436127,0.000841967,0.0019205656,0.000023784703,0.38092235,0.10824314,0.0019098265,0.02710779,0.23982109,0.0020227728],"about_ca_topic_score_codex":0.0005524878,"about_ca_topic_score_gemma":0.008189709,"teacher_disagreement_score":0.6905425,"about_ca_system_score_codex":0.00025242157,"about_ca_system_score_gemma":0.0041727284,"threshold_uncertainty_score":0.99980587},"labels":[],"label_agreement":null},{"id":"W7132882714","doi":"","title":"The evaluation of evaluation, a critical perspective on management aspects of teacher evaluation in Ontario&apos;s school systems","year":2001,"lang":"en","type":"dissertation","venue":"TSpace","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Perspective (graphical); Program evaluation","score_opus":0.27447840324464695,"score_gpt":0.5908843459904497,"score_spread":0.31640594274580275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7132882714","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37832007,0.0015217053,0.00003138498,0.00075500197,0.0016014613,0.0040412773,0.000003604725,0.000012877341,0.6137126],"genre_scores_gemma":[0.9724795,0.000081103986,0.000059655733,0.000024853007,0.00009773614,0.0010614961,0.00013914636,0.000029389803,0.026027106],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9745966,0.003979742,0.0018944843,0.0009469407,0.018186657,0.0003955495],"domain_scores_gemma":[0.9829657,0.001382191,0.0013700409,0.0012742765,0.012895897,0.00011185955],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.056759816,0.00038709035,0.00065541296,0.0010258013,0.00023358989,0.00023941965,0.0006732611,0.00030269285,0.008027431],"category_scores_gemma":[0.011643569,0.00028076695,0.0002103835,0.0012906705,0.00011028611,0.00032502477,0.000048124697,0.0006181334,0.00020448334],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028328414,0.0028522713,0.010171278,0.0003462307,0.0010191237,0.000008902111,0.11573609,0.1761425,0.00039321318,0.5026758,0.014549533,0.17327222],"study_design_scores_gemma":[0.0040209205,0.000524052,0.34204325,0.0010665011,0.0014703565,0.0000037744805,0.3013628,0.24327007,0.00028449137,0.1028694,0.00254042,0.0005439305],"about_ca_topic_score_codex":0.0131795425,"about_ca_topic_score_gemma":0.18476003,"teacher_disagreement_score":0.5941594,"about_ca_system_score_codex":0.0048905862,"about_ca_system_score_gemma":0.0051606284,"threshold_uncertainty_score":0.9999645},"labels":[],"label_agreement":null},{"id":"W7132906485","doi":"","title":"The Promise of Responsible Research Assessment","year":2025,"lang":"en","type":"dissertation","venue":"Trepo - Institutional Repository of Tampere University","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Alberta; VSNU Vereniging van Universiteiten; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Research England; Koninklijke Nederlandse Akademie van Wetenschappen; Newcastle University","keywords":"Cynicism; Doctoral studies; Accountability","score_opus":0.21297730603368187,"score_gpt":0.5109170586383193,"score_spread":0.2979397526046374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7132906485","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5277931,0.00017471121,0.00004083559,0.00039385984,0.0013052388,0.00045359775,0.00004476083,0.000014074248,0.46977982],"genre_scores_gemma":[0.702052,0.00014405586,0.0005785083,0.0000053801473,0.000047654616,0.000004479211,0.0000857036,0.000004457466,0.29707778],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9932078,0.0010679492,0.00091882463,0.00051133335,0.004069343,0.00022476229],"domain_scores_gemma":[0.9906064,0.002633602,0.0008746661,0.0009325795,0.0048655635,0.000087162654],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.006489284,0.0001774548,0.0004020743,0.0008241046,0.002075326,0.0000978689,0.0013638447,0.00023909073,0.00018093786],"category_scores_gemma":[0.0019430165,0.00013090721,0.00027970033,0.0012650783,0.00061134854,0.0003509006,0.00018148369,0.0005545073,0.000015537142],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.007424146,0.0014971192,0.021064365,0.00068373705,0.000848955,0.00021746867,0.005495317,0.0048495447,0.02722349,0.8481024,0.04476355,0.03782992],"study_design_scores_gemma":[0.0017485927,0.0005202106,0.25019184,0.0010719404,0.00022222426,0.00002369211,0.031876102,0.002495258,0.026886262,0.01272712,0.6717308,0.0005059551],"about_ca_topic_score_codex":0.00031239612,"about_ca_topic_score_gemma":0.00068914844,"teacher_disagreement_score":0.83537525,"about_ca_system_score_codex":0.00056566804,"about_ca_system_score_gemma":0.0149390595,"threshold_uncertainty_score":0.9992238},"labels":[],"label_agreement":null},{"id":"W7132960077","doi":"","title":"Developing and testing a unified school improvement-school effectiveness framework for evaluating complex school improvement initiatives","year":2004,"lang":"","type":"dissertation","venue":"TSpace","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Program evaluation; Evaluation methods; Order (exchange); Performance improvement; Data collection","score_opus":0.2790289764938705,"score_gpt":0.5500012925354159,"score_spread":0.27097231604154537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7132960077","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77887243,0.00066509505,0.203812,0.0009433895,0.0020131676,0.010542355,0.00007356471,0.00017227347,0.002905722],"genre_scores_gemma":[0.80353844,0.00023429169,0.18964171,0.0012560721,0.00055756996,0.0028630546,0.00045538775,0.00017501594,0.001278427],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98678994,0.0011155176,0.0032390605,0.0029228788,0.004264188,0.001668385],"domain_scores_gemma":[0.9779032,0.010492273,0.0037489082,0.0012745276,0.0054353094,0.0011457986],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.015283013,0.0016308617,0.0019415579,0.0011555157,0.0028830653,0.0024827651,0.0013423384,0.0009272037,0.003103535],"category_scores_gemma":[0.048330642,0.0015377769,0.00040482325,0.0025286006,0.0002550998,0.0018099616,0.00049423525,0.0017940337,0.00036916864],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00602695,0.0011639072,0.046713244,0.010781234,0.0023802263,0.000020846084,0.031037731,0.007968052,0.30877385,0.039080024,0.00022433285,0.5458296],"study_design_scores_gemma":[0.015003294,0.008644605,0.5579131,0.01462973,0.0010423282,0.0000129233595,0.14913629,0.08203596,0.036472183,0.13014281,0.00047783498,0.004488934],"about_ca_topic_score_codex":0.0003477683,"about_ca_topic_score_gemma":0.0001254553,"teacher_disagreement_score":0.5413407,"about_ca_system_score_codex":0.0027051666,"about_ca_system_score_gemma":0.012982277,"threshold_uncertainty_score":0.99964386},"labels":[],"label_agreement":null},{"id":"W7132990817","doi":"","title":"Policy in praxis: A case study of implementing Making Services Work for People","year":2007,"lang":"","type":"dissertation","venue":"TSpace","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Process (computing); Action (physics); Qualitative research; Salient; Conceptual framework; Narrative; Information system; Work (physics); Process theory","score_opus":0.17004411377904483,"score_gpt":0.6138466684139,"score_spread":0.4438025546348552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7132990817","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9910719,0.00021406458,0.0005253284,0.00020285085,0.0005249271,0.0037294538,0.000012242524,0.000018850911,0.003700398],"genre_scores_gemma":[0.99425495,0.0000316246,0.0014893541,0.00011633601,0.00021735654,0.0003113131,0.00006363119,0.000045232217,0.0034701917],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9927311,0.00039802736,0.0025886637,0.0009971714,0.0023718774,0.00091314415],"domain_scores_gemma":[0.99333113,0.0017874349,0.0027463576,0.0008398953,0.0011713089,0.00012384196],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.012147461,0.00050673774,0.0010529864,0.0023343184,0.0005637267,0.0003817601,0.0007983328,0.00026879253,0.0009675547],"category_scores_gemma":[0.0005996315,0.00047454727,0.00021715413,0.00504685,0.000024507426,0.0004878047,0.00020316518,0.00038052458,0.000029599109],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00055785256,0.0010399208,0.28427932,0.00071193714,0.000098677214,0.00008708567,0.6441459,0.0013397216,0.00005645114,0.00015898424,0.000051184667,0.06747295],"study_design_scores_gemma":[0.0025208003,0.0007060178,0.078975484,0.000636044,0.00011628693,0.000034523204,0.90651923,0.009169604,0.00009322786,0.00016721827,0.00064462854,0.0004169252],"about_ca_topic_score_codex":0.014105688,"about_ca_topic_score_gemma":0.28750804,"teacher_disagreement_score":0.27340236,"about_ca_system_score_codex":0.0002198841,"about_ca_system_score_gemma":0.0010857021,"threshold_uncertainty_score":0.9999457},"labels":[],"label_agreement":null},{"id":"W7135164826","doi":"","title":"Creating Systemic Design-Informed Impact Evaluation Frameworks: A case study with the Gord Downie & Chanie Wenjack Fund","year":2023,"lang":"en","type":"article","venue":"OCAD University Open Research Repository (OCAD University)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario College of Art and Design","funders":"","keywords":"Process (computing); Logic model; Presentation (obstetrics); Data collection; Theory of change; Program evaluation; Work (physics); Outcome (game theory)","score_opus":0.479073209453154,"score_gpt":0.534147963771449,"score_spread":0.055074754318295005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7135164826","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7808116,0.000017125107,0.0015790118,0.0004844997,0.00012922025,0.0035947429,0.000011781629,0.0000880597,0.21328399],"genre_scores_gemma":[0.9337345,0.000033078522,0.00015431755,0.000023726401,0.00007015898,0.000007235754,0.000011386149,0.000018813438,0.06594678],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9867052,0.006094723,0.00042117067,0.0009650551,0.004985371,0.00082848826],"domain_scores_gemma":[0.9907633,0.003761041,0.00046682378,0.0014928182,0.0030920468,0.00042395826],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.020527923,0.00031591937,0.00045701774,0.0015409269,0.005071839,0.001560528,0.0030871131,0.00026339488,0.000053414566],"category_scores_gemma":[0.00068691105,0.00022291893,0.00016449603,0.007452995,0.0004299944,0.002863865,0.001019758,0.0012264738,0.00036926096],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.011522165,0.0018557478,0.23985827,0.00013819087,0.0026082152,0.0443011,0.096867144,0.15494083,0.0014933661,0.38949263,0.02546737,0.031454984],"study_design_scores_gemma":[0.0069606025,0.003914343,0.03275728,0.00028801552,0.00039671027,0.0011259151,0.8090807,0.121774815,0.00013707734,0.00015540732,0.02260731,0.0008018128],"about_ca_topic_score_codex":0.0041001537,"about_ca_topic_score_gemma":0.0029506409,"teacher_disagreement_score":0.7122136,"about_ca_system_score_codex":0.002167329,"about_ca_system_score_gemma":0.0041320585,"threshold_uncertainty_score":0.99947596},"labels":[],"label_agreement":null},{"id":"W7143940589","doi":"10.14988/0002000880","title":"日本における「プログラム評価」の可能性 : 行政学からの省察と展望","year":2025,"lang":"ja","type":"article","venue":"Institutional Repositories DataBase (IRDB)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Image (mathematics); Quarter (Canadian coin)","score_opus":0.08598722940476389,"score_gpt":0.445323062331165,"score_spread":0.3593358329264011,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7143940589","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16485731,0.011333798,0.04276784,0.024059322,0.08556964,0.002504691,0.0043310076,0.000562109,0.6640143],"genre_scores_gemma":[0.9386306,0.00073232775,0.0038787054,0.002718028,0.0021992808,0.00015133565,0.00093691895,0.000026601636,0.050726194],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9903819,0.0005055691,0.0021816646,0.0015854333,0.004519229,0.00082619494],"domain_scores_gemma":[0.99309874,0.0014705809,0.0006400285,0.0023252598,0.0020504002,0.0004150215],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.004070707,0.00065634074,0.0007529868,0.00083594624,0.0025663248,0.0016878512,0.0018055864,0.00035133644,0.003261234],"category_scores_gemma":[0.00427972,0.0005735295,0.00037414866,0.0028813835,0.0011654355,0.0032762215,0.0010952924,0.000809248,0.002734438],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00073560385,0.0011472425,0.03545111,0.00030300775,0.00052209484,0.00039482,0.0011333774,0.002635918,0.0044802506,0.65593415,0.27007562,0.027186794],"study_design_scores_gemma":[0.0014652,0.00012864039,0.018516699,0.00082441204,0.00019004542,0.00009347797,0.0010507683,0.0066819484,0.0047306386,0.0028277657,0.96283734,0.0006530414],"about_ca_topic_score_codex":0.00063398044,"about_ca_topic_score_gemma":0.00036674037,"teacher_disagreement_score":0.7737733,"about_ca_system_score_codex":0.00086031144,"about_ca_system_score_gemma":0.0070926496,"threshold_uncertainty_score":0.99967164},"labels":[],"label_agreement":null},{"id":"W749362337","doi":"10.46743/2160-3715/2013.1538","title":"Baby Steps: A Book Review of Dorothy Valcarcel Craig’s Action Research Essentials","year":2015,"lang":"en","type":"review","venue":"The Qualitative Report","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Reading (process); Action (physics); Action research; Psychology; Resource (disambiguation); Epistemology; Engineering ethics; Sociology; Pedagogy; Computer science; Linguistics; Philosophy; Engineering","score_opus":0.9093686151238525,"score_gpt":0.794629451071062,"score_spread":0.1147391640527905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W749362337","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000016026548,0.9539593,0.00031846156,0.0015082584,0.0005692322,0.0028050255,0.00005900412,0.000024550482,0.040754564],"genre_scores_gemma":[0.0000021245376,0.94461995,0.00017541273,0.0004103895,0.00023984954,0.00054941274,0.000113171634,0.000038595455,0.05385106],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9541698,0.027511843,0.005510318,0.0010511102,0.011237117,0.00051978324],"domain_scores_gemma":[0.97221833,0.012275168,0.0051370193,0.00271656,0.007453187,0.00019971225],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.22792546,0.00043201784,0.0030590026,0.0006489265,0.00028661135,0.0001551581,0.0015838039,0.00023200133,0.0055169687],"category_scores_gemma":[0.022290658,0.00022007454,0.0009566335,0.002665171,0.0006462857,0.0004972603,0.00041173433,0.0008900945,0.0016625283],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011058707,0.0000659304,5.57576e-7,0.019742047,0.00017192146,0.000018868295,0.0039184387,4.5831496e-7,5.5607325e-7,0.00072128896,0.4579667,0.5173822],"study_design_scores_gemma":[0.00009331716,0.00014637745,0.0000021238477,0.03430211,0.00033147505,0.0001464191,0.0050543672,0.0000043160685,0.0000034090097,0.004536345,0.9551472,0.00023255036],"about_ca_topic_score_codex":0.00007059196,"about_ca_topic_score_gemma":0.000010857912,"teacher_disagreement_score":0.5171496,"about_ca_system_score_codex":0.00039527414,"about_ca_system_score_gemma":0.005145578,"threshold_uncertainty_score":0.9991148},"labels":[],"label_agreement":null},{"id":"W753671048","doi":"10.1007/978-94-6209-986-9_11","title":"The ‘Ayes’ have it?","year":2015,"lang":"en","type":"book-chapter","venue":"SensePublishers eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Nipissing University","funders":"","keywords":"Classroom management; Democracy; Mathematics education; Pedagogy; Sociology; Political science; Psychology; Law; Politics","score_opus":0.34306142865695644,"score_gpt":0.46514221903928576,"score_spread":0.12208079038232933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W753671048","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00001626561,0.0003492252,0.0000613843,0.0061132344,0.0025842793,0.00045968688,0.000027194224,0.00007762451,0.9903111],"genre_scores_gemma":[0.0019446611,0.000022659731,0.00011785148,0.0021599478,0.00062537397,0.000016098042,0.00002565996,0.00006112619,0.99502665],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9920767,0.00017531363,0.0012168497,0.0007800341,0.005216045,0.0005350612],"domain_scores_gemma":[0.9931861,0.001368837,0.0008312214,0.0019302354,0.0022988247,0.00038477365],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.010730789,0.0004556002,0.00051944307,0.0003524184,0.0005732811,0.0030647814,0.0016330157,0.00045437354,0.0038558813],"category_scores_gemma":[0.0013548477,0.00026505179,0.00035117802,0.00004806476,0.0004899966,0.00040813797,0.00035204893,0.0008134205,0.002895984],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022417282,0.0000026584694,0.000008651914,0.0000015724762,0.000044280245,0.000009510236,0.00049286406,0.000010602818,0.0000011806977,0.09221697,0.7900304,0.11715889],"study_design_scores_gemma":[0.00025585733,0.00006118326,0.00001232687,0.000024464442,0.0000261811,0.000013252124,0.00078782486,0.00034993957,0.0000036904808,0.20514008,0.79304427,0.00028091692],"about_ca_topic_score_codex":0.00002009499,"about_ca_topic_score_gemma":0.00067965395,"teacher_disagreement_score":0.11687797,"about_ca_system_score_codex":0.00024886575,"about_ca_system_score_gemma":0.0015890928,"threshold_uncertainty_score":0.99998015},"labels":[],"label_agreement":null},{"id":"W767205952","doi":"10.26522/tl.v1i2.103","title":"Developing a Diagnostic Assessment Model","year":2003,"lang":"en","type":"article","venue":"Teaching and Learning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mathematics education; Standardized test; Quality (philosophy); Scale (ratio); Educational assessment; Test (biology); Psychology; Medical education; Medicine; Geography","score_opus":0.19914859019680595,"score_gpt":0.4974074992217229,"score_spread":0.2982589090249169,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W767205952","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5611188,0.000075990814,0.3795793,0.000791137,0.000090985755,0.00006573346,1.9021724e-7,0.000051860872,0.058225997],"genre_scores_gemma":[0.930953,0.00001907628,0.064418584,0.00042900554,0.00001738462,0.000009587435,0.0000013742199,0.0000072556318,0.0041446923],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99730587,0.001181702,0.00031254717,0.0002780372,0.000727639,0.0001942338],"domain_scores_gemma":[0.99666005,0.0029179452,0.0001226163,0.00015564772,0.00007100287,0.00007275099],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013327661,0.00009791617,0.0001483655,0.00013145625,0.0009669183,0.00028634685,0.00012925072,0.000036166966,0.00019419742],"category_scores_gemma":[0.011088105,0.00007378886,0.000031686835,0.00013220301,0.00002391541,0.00025999328,0.00004296107,0.0007393508,0.00006455511],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000035139647,0.000041196967,0.19169424,0.000010052943,0.000017419883,0.0000037375726,0.008768833,0.18116395,0.00022499308,0.28265476,0.000649574,0.33476773],"study_design_scores_gemma":[0.0004694557,0.000069944865,0.041323315,0.000053570267,0.000012575095,0.000016269332,0.0059360783,0.828692,0.000031504693,0.025420964,0.097692534,0.0002817433],"about_ca_topic_score_codex":0.000010786565,"about_ca_topic_score_gemma":0.0000055460423,"teacher_disagreement_score":0.6475281,"about_ca_system_score_codex":0.000052919753,"about_ca_system_score_gemma":0.00021257343,"threshold_uncertainty_score":0.9972419},"labels":[],"label_agreement":null},{"id":"W78612901","doi":"10.3138/cjpe.0017.008","title":"Defining the Benefits, Outputs, and Knowledge Elements of Program Evaluation","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Promotion (chess); Process (computing); Program evaluation; Process management; Knowledge management; Raising (metalworking); Evaluation methods; Participatory evaluation; Management science; Business; Computer science; Public relations; Political science; Engineering; Public administration","score_opus":0.346987607917928,"score_gpt":0.5305338923085439,"score_spread":0.18354628439061588,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W78612901","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94770753,0.024931505,0.000561145,0.0018539011,0.0018482679,0.0067156157,0.000019136412,0.000018117227,0.016344769],"genre_scores_gemma":[0.9930192,0.00005444529,0.0064223777,0.000073009214,0.00006763705,0.0002640497,0.000014027944,0.00001153107,0.00007372675],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9936026,0.00156633,0.0014093552,0.0002461287,0.0028498932,0.00032572413],"domain_scores_gemma":[0.9922829,0.0004021617,0.0012240364,0.00034914925,0.0053987796,0.00034292968],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.04448366,0.00015779128,0.00027928167,0.00058184995,0.0003407967,0.000375414,0.0004045528,0.00008772751,0.0011496536],"category_scores_gemma":[0.00643301,0.000104826984,0.00011863988,0.0009913787,0.00015424803,0.0005308649,0.000016667096,0.0002205635,0.000033273467],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007350692,0.00007023135,0.045613274,0.0000058373125,0.00003566897,3.3829792e-7,0.0013801428,0.0008310687,0.000006568809,0.008150543,0.0009284835,0.9429705],"study_design_scores_gemma":[0.0051182224,0.0026864705,0.42422885,0.00029336545,0.0008486578,0.000114211405,0.008548507,0.20863533,0.0006921472,0.029311545,0.31903172,0.0004909678],"about_ca_topic_score_codex":0.0001407305,"about_ca_topic_score_gemma":0.010888319,"teacher_disagreement_score":0.94247955,"about_ca_system_score_codex":0.00029775812,"about_ca_system_score_gemma":0.006744636,"threshold_uncertainty_score":0.9997634},"labels":[],"label_agreement":null},{"id":"W82003583","doi":"10.1007/978-1-4419-7430-3_6","title":"Ways to Improve Political Decision-Making: Negotiating Errors to be Avoided","year":2010,"lang":"en","type":"book-chapter","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Fantasy; Nothing; Aesthetics; Politics; Negotiation; Dystopia; Art; Sociology; History; Media studies; Literature; Political science; Epistemology; Law; Social science; Philosophy","score_opus":0.18896515795234944,"score_gpt":0.47262563368859,"score_spread":0.28366047573624054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W82003583","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014058888,0.000010450886,0.09507017,0.008146829,0.0030380774,0.00090941606,0.000076331475,0.00010251175,0.89124036],"genre_scores_gemma":[0.16603078,0.0000040848095,0.11948859,0.03652714,0.0012153324,0.000070834634,0.000018843031,0.0001274761,0.6765169],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99156916,0.000037716258,0.0016973679,0.0012920841,0.004623059,0.00078064034],"domain_scores_gemma":[0.9915789,0.0040871673,0.00038216825,0.0016723267,0.0013115336,0.0009679227],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.004230231,0.0005305477,0.0007626555,0.0010068191,0.00036654223,0.00078552606,0.0015090377,0.0005811808,0.03498958],"category_scores_gemma":[0.007433907,0.00038048532,0.00030928056,0.00024923985,0.00008681189,0.0003021114,0.0008116031,0.0009133446,0.01225231],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044108558,0.000019389985,0.000054205597,0.000003328069,0.000018060666,0.000007310143,0.00033047338,0.00017441975,0.0002624782,0.8974357,0.02690435,0.07474615],"study_design_scores_gemma":[0.00021727524,0.00026612912,0.00029333023,0.00009647384,0.00002651906,0.000008404493,0.00041174536,0.002225387,0.0001497325,0.27088633,0.7247869,0.00063178735],"about_ca_topic_score_codex":0.00004184366,"about_ca_topic_score_gemma":0.00054662616,"teacher_disagreement_score":0.69788253,"about_ca_system_score_codex":0.00022401616,"about_ca_system_score_gemma":0.0006956319,"threshold_uncertainty_score":0.9998647},"labels":[],"label_agreement":null},{"id":"W832038935","doi":"10.1016/j.prps.2015.05.004","title":"L’évaluation du risque de récidive et l’intervention basée sur les données probantes : les conditions nécessaires à l’implantation de méthodes structurées d’évaluation et d’intervention efficaces","year":2015,"lang":"fr","type":"article","venue":"Pratiques Psychologiques","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Political science; Humanities; Art","score_opus":0.44596282953268196,"score_gpt":0.5048219533974774,"score_spread":0.058859123864795415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W832038935","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7904826,0.0041586165,0.1771364,0.020750409,0.0013571718,0.0013437542,0.00025385464,0.00038118617,0.004135999],"genre_scores_gemma":[0.9469727,0.009473053,0.03947862,0.0008901639,0.00035972026,0.00058616826,0.0009096655,0.000060832495,0.0012690288],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.976433,0.017603006,0.0021826094,0.0011450776,0.0019134313,0.0007228971],"domain_scores_gemma":[0.99099916,0.003237923,0.001875897,0.00064373546,0.002934936,0.00030834333],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0382063,0.0006813159,0.0006921246,0.0007402347,0.0006332515,0.0016275026,0.00083029416,0.0007830865,0.0019990525],"category_scores_gemma":[0.009159346,0.00061193545,0.0004614447,0.0006410837,0.00054378284,0.0039421637,0.00018730924,0.0009154963,0.00016125522],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00083417323,0.0029994599,0.29057935,0.0006506204,0.00042366568,0.000032391552,0.066984035,0.023987267,0.0051759714,0.09486225,0.023166379,0.4903044],"study_design_scores_gemma":[0.0036181707,0.0026040182,0.58705664,0.0020038902,0.00038631278,0.00017312272,0.0246836,0.10987073,0.013484635,0.24826595,0.00683697,0.0010159428],"about_ca_topic_score_codex":0.0039032164,"about_ca_topic_score_gemma":0.014930856,"teacher_disagreement_score":0.48928848,"about_ca_system_score_codex":0.00079499267,"about_ca_system_score_gemma":0.0014917213,"threshold_uncertainty_score":0.9996332},"labels":[],"label_agreement":null},{"id":"W895784969","doi":"","title":"Argumentation: Cognition and Community : Proceedings of the 9th International Conference of the Ontario Society for the Study of Argumentation","year":2011,"lang":"en","type":"article","venue":"Lund University Publications (Lund University)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Argumentation theory; Epistemology; Cognition; Sociology; Political science; Social science; Psychology; Philosophy","score_opus":0.28768836865895303,"score_gpt":0.3612836366599489,"score_spread":0.07359526800099586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W895784969","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78860027,0.0000015330098,0.0011665173,0.0009934045,0.0001898381,0.0008077058,0.000051742645,0.000007366003,0.20818165],"genre_scores_gemma":[0.9284309,0.000010956323,0.00048662082,0.000031077245,0.0000052217574,0.0000014201719,0.000008553907,0.0000022660918,0.07102298],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9988199,0.00013773778,0.00024471196,0.00015565469,0.00056474603,0.00007727937],"domain_scores_gemma":[0.9967026,0.00039455274,0.0006657709,0.0003062017,0.0019010773,0.000029811557],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010465595,0.00007748459,0.00011840411,0.00017765418,0.0010005214,0.000049907125,0.0011707968,0.00004245991,0.000301948],"category_scores_gemma":[0.00010825914,0.00005195571,0.00012730548,0.0010096299,0.0003583913,0.0008706656,0.00033296895,0.00017493815,6.207515e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016236276,0.0012254905,0.22489415,0.00001934037,0.00034713856,3.5562984e-8,0.09247668,0.000040714618,0.00065402215,0.6773774,0.0015890284,0.0012136379],"study_design_scores_gemma":[0.0020124568,0.00021634446,0.48441198,0.000022670874,0.00035870765,0.0000012376366,0.369599,0.001250789,0.000778684,0.0022954203,0.13895334,0.00009935845],"about_ca_topic_score_codex":0.0020659338,"about_ca_topic_score_gemma":0.013637993,"teacher_disagreement_score":0.67508197,"about_ca_system_score_codex":0.00014875963,"about_ca_system_score_gemma":0.00027423233,"threshold_uncertainty_score":0.7695303},"labels":[],"label_agreement":null},{"id":"W89579817","doi":"10.1007/978-3-319-07794-9_19","title":"Reflections on Validation Practices in the Social, Behavioral, and Health Sciences","year":2014,"lang":"en","type":"book-chapter","venue":"Social indicators research series","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Construct (python library); Construct validity; External validity; Plan (archaeology); Model validation; Psychology; Behavioural sciences; Theoretical definition; Management science; Data science; Computer science; Social psychology; Psychometrics; Epistemology; Engineering; Clinical psychology; Geography; Psychotherapist","score_opus":0.8097883839940646,"score_gpt":0.7184328754582148,"score_spread":0.09135550853584984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W89579817","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02016335,0.00024902448,0.000011898022,0.13010865,0.0003292449,0.0012121762,0.000051254985,0.000041150637,0.8478332],"genre_scores_gemma":[0.8788792,0.0015170088,0.00011118047,0.001468202,0.0010536222,0.00018855352,0.000056280416,0.000035495505,0.11669044],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99113214,0.0016628054,0.000683939,0.00062696164,0.005450088,0.00044408048],"domain_scores_gemma":[0.9967416,0.001394329,0.0011351472,0.00028506992,0.00036034707,0.000083517356],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.03785495,0.00019960485,0.000367204,0.0016725581,0.005140331,0.0013420219,0.000945124,0.0002754457,0.00072449003],"category_scores_gemma":[0.0009403979,0.00013252792,0.00008670805,0.0010773465,0.002033894,0.0005685362,0.00017911749,0.0012305051,0.00020009786],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003405818,0.00006920793,0.00086646626,0.000019102059,0.00001194783,0.0000016426261,0.022576272,0.0000012695308,0.0000044208427,0.88169044,0.049658924,0.04506622],"study_design_scores_gemma":[0.00018775566,0.0011443598,0.011012731,0.000056527282,0.000010213326,0.0000032734054,0.025596846,0.0000053834747,0.00001538724,0.14595793,0.81577796,0.00023162145],"about_ca_topic_score_codex":0.00028075234,"about_ca_topic_score_gemma":0.0020400963,"teacher_disagreement_score":0.85871583,"about_ca_system_score_codex":0.0002668991,"about_ca_system_score_gemma":0.0016269146,"threshold_uncertainty_score":0.9996947},"labels":[],"label_agreement":null},{"id":"W943891908","doi":"10.15453/0191-5096.3140","title":"From \"Poor\" to \"Not Poor\": Improved Understandings and the Advantage of the Qualitative Approach","year":2006,"lang":"en","type":"article","venue":"The Journal of Sociology & Social Welfare","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Georgian College","funders":"","keywords":"Poverty; Qualitative research; Intervention (counseling); Sociology; Qualitative property; Capability approach; Poor people; Economic growth; Social psychology; Psychology; Social science; Economics; Computer science","score_opus":0.12665438065047874,"score_gpt":0.47232921151050555,"score_spread":0.3456748308600268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W943891908","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8318289,0.00019396654,0.0017961629,0.16329665,0.00028652532,0.00024846417,0.000039367776,0.0000035979679,0.0023063454],"genre_scores_gemma":[0.9971055,0.00001858813,0.00022191364,0.0020279044,0.0002989361,0.0000037109435,0.0000015012462,0.0000067219266,0.00031526544],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9955527,0.002455306,0.00080240844,0.00013153441,0.0008778814,0.000180153],"domain_scores_gemma":[0.99557364,0.0026278133,0.001142874,0.0001805449,0.0004396415,0.000035483234],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011254731,0.00012152674,0.0004190421,0.00005677631,0.0009044486,0.000047394107,0.0008310767,0.00011075334,0.00015093597],"category_scores_gemma":[0.0006467699,0.00004768944,0.00021507534,0.00024310648,0.0016765695,0.00014785265,0.00016188805,0.0004034118,0.0000042280653],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026523124,0.0001385416,0.0035427772,0.000008453891,0.0003539017,8.5666704e-7,0.68606824,0.0002550467,0.005455842,0.28334793,0.015083635,0.0030924592],"study_design_scores_gemma":[0.0023324548,0.00017331564,0.051358275,0.000008340589,0.000138417,0.0000075203393,0.70197433,0.00036984915,0.00025456704,0.23989439,0.0033777235,0.0001108012],"about_ca_topic_score_codex":0.00020492754,"about_ca_topic_score_gemma":0.000067855166,"teacher_disagreement_score":0.16527654,"about_ca_system_score_codex":0.00008905369,"about_ca_system_score_gemma":0.000132544,"threshold_uncertainty_score":0.6956379},"labels":[],"label_agreement":null},{"id":"W96280461","doi":"10.5206/cie-eci.v31i2.9033","title":"Observation on the INES Symposium","year":2012,"lang":"en","type":"article","venue":"Comparative and International Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computational biology; Biology","score_opus":0.6271436652804296,"score_gpt":0.5893932556006383,"score_spread":0.037750409679791375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W96280461","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8913089,0.00016874679,0.00041685594,0.026290955,0.0023993533,0.00014334216,0.0000027474846,0.000008851562,0.07926025],"genre_scores_gemma":[0.97529405,0.000029463241,0.00016329758,0.0029657471,0.00045771006,0.000052246753,0.000022613656,0.0000020734858,0.02101277],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9989128,0.00011981065,0.0002318901,0.00012510526,0.00053047633,0.0000799171],"domain_scores_gemma":[0.9985637,0.0005260364,0.00014129751,0.0001534955,0.00056961924,0.000045822817],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011589075,0.00006792425,0.00007023592,0.00010552048,0.000151479,0.00016438932,0.00021640811,0.000019130717,0.0012057967],"category_scores_gemma":[0.0003508549,0.00003841179,0.000024111625,0.00018237403,0.000042941476,0.00069493055,0.00003039294,0.00006813553,0.000492773],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035391473,0.0003598874,0.25963867,0.0000013214534,0.000025798792,1.0308746e-8,0.008059309,0.00011631414,0.0010683275,0.46319816,0.23774953,0.029747289],"study_design_scores_gemma":[0.00008630403,0.000033448632,0.54333943,0.000010530616,0.000003774951,0.0000016325489,0.0032338111,0.00446117,0.000905382,0.010170347,0.43768406,0.00007010524],"about_ca_topic_score_codex":0.000007338282,"about_ca_topic_score_gemma":0.0000044984986,"teacher_disagreement_score":0.4530278,"about_ca_system_score_codex":0.00004339258,"about_ca_system_score_gemma":0.00009362172,"threshold_uncertainty_score":0.9997072},"labels":[],"label_agreement":null},{"id":"W968281521","doi":"","title":"Aligning Assessments as a Process in Program Evaluation","year":2015,"lang":"en","type":"article","venue":"Scholarship@Western (Western University)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Process (computing); Computer science; Process management; Engineering; Programming language","score_opus":0.5823857445871686,"score_gpt":0.5805798605105934,"score_spread":0.001805884076575226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W968281521","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99112123,0.00003744565,0.00033248865,0.00037760005,0.00039382424,0.0013581024,0.0000047354306,0.00012523838,0.006249305],"genre_scores_gemma":[0.99584776,0.0000068581867,0.00017223762,0.00031411662,0.00006194226,0.00003092692,0.000028750059,0.000021924749,0.0035154962],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99268556,0.001194121,0.0006395258,0.0008393407,0.004142196,0.0004992511],"domain_scores_gemma":[0.9966583,0.00022316308,0.00044637866,0.0007028441,0.0015660799,0.00040321468],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009736111,0.0002825407,0.00037087238,0.0012042625,0.00017493873,0.00085286243,0.0012983336,0.00018683249,0.0002211133],"category_scores_gemma":[0.00085462467,0.0002685759,0.00009872745,0.0022096494,0.00008560193,0.0045426544,0.00028141955,0.00045778687,0.0011860937],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001265518,0.00023130816,0.9751466,0.000007839444,0.000016985854,0.000049132606,0.0013865975,0.0011876832,0.000032543598,0.00006051354,0.0000029495397,0.021751288],"study_design_scores_gemma":[0.0035290758,0.0006217778,0.9780658,0.00013710208,0.00005798297,0.000022017604,0.007027238,0.00038055217,0.00048384367,0.0041071787,0.005120243,0.00044717727],"about_ca_topic_score_codex":0.000006605778,"about_ca_topic_score_gemma":0.0014207087,"teacher_disagreement_score":0.02130411,"about_ca_system_score_codex":0.0006462508,"about_ca_system_score_gemma":0.0014127578,"threshold_uncertainty_score":0.99997663},"labels":[],"label_agreement":null},{"id":"W990536225","doi":"","title":"Implementation: the forgotten dimension of agreement making in Australia and Canada","year":2002,"lang":"en","type":"article","venue":"Griffith Research Online (Griffith University, Queensland, Australia)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":45,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Dimension (graph theory); Agreement; Project commissioning; Publishing; Political science; Law; Mathematics; Linguistics; Philosophy","score_opus":0.4738910935098254,"score_gpt":0.5321541552245432,"score_spread":0.058263061714717845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W990536225","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98705953,0.00004721624,0.00002750049,0.011169681,0.0001761474,0.0006598292,0.00019594068,0.000009449652,0.00065472035],"genre_scores_gemma":[0.98512274,0.00015774656,0.00042951666,0.00010901185,0.00008408699,0.0000032246146,0.000036986836,0.000009377819,0.01404733],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9934416,0.0009278767,0.0007400269,0.0005966178,0.0035630814,0.0007307975],"domain_scores_gemma":[0.9970639,0.00090341957,0.00030854542,0.0006491863,0.00086841494,0.00020657928],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0041614897,0.00022929146,0.0003760608,0.00068228174,0.00043191496,0.00012403751,0.00094394333,0.00011061659,0.0032861794],"category_scores_gemma":[0.00021690763,0.00016457542,0.00007391138,0.0015780749,0.000330807,0.00035534264,0.00045718573,0.00066014606,0.000046436217],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014552176,0.00022082655,0.8927889,0.000041703966,0.00006104338,0.0001204374,0.0014867771,0.00073916215,0.00019988323,0.0022810118,0.092860304,0.009054444],"study_design_scores_gemma":[0.0020339673,0.00028933783,0.92087924,0.00008404039,0.000023614772,0.0000148510335,0.014168887,0.0021465106,0.00013033913,0.00039345835,0.0595866,0.00024915938],"about_ca_topic_score_codex":0.3961685,"about_ca_topic_score_gemma":0.9305618,"teacher_disagreement_score":0.53439325,"about_ca_system_score_codex":0.000404078,"about_ca_system_score_gemma":0.00039275206,"threshold_uncertainty_score":0.99762493},"labels":[],"label_agreement":null},{"id":"W998744973","doi":"","title":"The Politics of Poverty: Shifting the Policy Discourse","year":2013,"lang":"en","type":"article","venue":"Social alternatives","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Poverty; Culture of poverty; Blame; Politics; Development economics; Action (physics); Political science; Sociology; Economic growth; Political economy; Basic needs; Economics; Law; Social psychology","score_opus":0.15781532465964193,"score_gpt":0.5307752226929845,"score_spread":0.37295989803334256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W998744973","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8199717,0.0000976807,0.00038055592,0.1251523,0.00037701527,0.00023926077,0.000012618036,0.000012302237,0.053756613],"genre_scores_gemma":[0.9896778,0.000028924973,0.00005088435,0.0011198133,0.0006731998,0.000017736456,6.35398e-7,0.0000048508405,0.008426145],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978595,0.00028016584,0.00036304112,0.0001211604,0.0011705189,0.00020563832],"domain_scores_gemma":[0.9977735,0.0013292528,0.00030474752,0.00021938903,0.0003386127,0.000034478584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016535335,0.000073560186,0.000113263624,0.00005339542,0.00086889404,0.00027087642,0.0007491444,0.000021109528,0.0003565061],"category_scores_gemma":[0.001231808,0.000030959396,0.00009329034,0.00032643724,0.00039727316,0.00029184352,0.00013262375,0.00010397082,0.00017488681],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004013497,0.0000349128,0.017012455,0.0000015613766,0.000041427265,1.2877584e-7,0.025098104,0.000017743028,0.00019492222,0.7946777,0.011257795,0.15165927],"study_design_scores_gemma":[0.00026099072,0.000044879856,0.3079302,0.0000072435537,0.000008053849,5.391286e-7,0.045071196,0.0025610821,0.00067380344,0.6068714,0.03646016,0.000110416586],"about_ca_topic_score_codex":0.0005079045,"about_ca_topic_score_gemma":0.00006813294,"teacher_disagreement_score":0.29091775,"about_ca_system_score_codex":0.000036883703,"about_ca_system_score_gemma":0.0001984472,"threshold_uncertainty_score":0.6682918},"labels":[],"label_agreement":null}]}